Gastrointestinal (GI) cancers are a leading cause of cancer-related mortality worldwide. Accurate identification of lymphatic spread is essential for staging, prognosis, and treatment planning. The first metastatic lymph nodes vary depending on the primary tumor site, representing the initial echelon of nodal involvement. This pictorial essay reviews the lymphatic drainage patterns of major gastrointestinal cancers-including esophageal, gastric, pancreatic, hepatobiliary, and colorectal tumors-highlighting key nodal stations commonly involved in metastatic spread emphasizing their diagnostic and clinical relevance. By integrating multimodality imaging findings, we highlight key lymph node groups involved in metastasis, discuss their anatomical significance, and illustrate their appearance on computed tomography (CT) and magnetic resonance imaging (MRI). Understanding these patterns is critical for optimizing oncologic management.

To develop and validate computed tomography (CT)-based intratumoral and peritumoral radiomics signatures for preoperative prediction of lymph node metastasis (LNM) in patients with ovarian cancer (OC).

Patients with pathological diagnosis of OC were retrospectively included. Intratumoral and peritumoral radiomics features were extracted from contrast-enhanced CT images. Intratumoral and peritumoral radiomics features were extracted from contrast-enhanced CT images. Intratumoral, peritumoral, and combined radiomics signatures were constructed, and their radiomics scores were calculated. Univariate and multivariate logistic regression analyses were performed to identify predictors of clinical outcomes. A radiomics nomogram was developed by incorporating the combined radiomics signature with clinical risk factors. The prediction efficiency of the various models was evaluated using the accuracy value, the area under the receiver-operating characteristic curve (AUC) and decision curve analysis (DCA).

Two hundred and seventy-three patients with OC were enrolled and randomly divided into a training cohort (n=190) and a test cohort (n=83) in a 7:3 ratio. The intratumoral, peritumoral, and combined radiomics signatures were constructed using 18, 11, and 17 radiomics features, respectively. The combined radiomics signature showed the best prediction ability, with accuracy of 0.783 and an AUC of 0.860 (95% confidence interval 0.779-0.941). The DCA results showed that the combined radiomics signature had better clinical application than the clinical model and the radiomics nomogram.

A CT-based combined radiomics signature incorporating intratumoral and peritumoral radiomics features can predict LNM in patients with OC before surgery.

To develop and validate a radiomics signature, utilizing baseline and restaging CT, for preoperatively predicting progression-free survival (PFS) after neoadjuvant chemotherapy (NAC) in locally advanced gastric cancer (LAGC).

A total of 316 patients with LAGC who received NAC followed by gastrectomy were retrospectively included in this single-center study; these patients were split into two cohorts, one for training (n = 243) and the other for validation (n = 73), based on the different districts of our hospital. A total of 1316 radiomics features were extracted from the volume of interest of the gastric-cancer lesion on venous phase CT images. Four radiomics signatures were built for predicting PFS based on baseline CT (Pre-Rad), restaging CT (Post-Rad), delta radiomics (Delta-Rad) and multi-time radiomics (PrePost-Rad), respectively. Then the PrePost-Rad was combined with clinical factors to establish a nomogram (Rad-clinical model). Kaplan-Meier survival curves with log-rank tests were used to assess the prognostic usefulness of the Rad-clinical model.

All baseline characteristics were not statistically different between the two cohorts. The PrePost-Rad achieved improved predictive value by a C-index of 0.724 (95% CI: 0.639-0.809) in the validation cohort [Pre-Rad: 0.715 (0.632-0.798); Post-Rad: 0.632 (0.538-0.725), Delta-Rad: 0.549 (0.447-0.651)]. In terms of clinical benefit, calibration capability, and prediction efficacy, the Rad-clinical model performed well for PFS prediction, with a C-index of 0.754 (95% CI: 0.707-0.800) and 0.719 (95% CI: 0.639-0.800) in the training and validation cohorts, respectively, superior to the clinical model (cN stage and CA199) but comparable to the PrePost-Rad. Moreover, the Rad-clinical model could accurately classify gastric-cancer patients after NAC into three PFS risk groups in both training and validation cohorts. The risk stratification also performed well in most subgroups (good responders, poor responders, ypTNM Ⅱ, and ypTNM Ⅲ/Ⅳ).

The Rad-clinical model integrating longitudinal radiomics score and clinical factors performed well in preoperatively predicting PFS of LAGC patients after NAC and surgery.

Gallbladder cancer (GBC) is a highly aggressive malignancy with dismal prognosis. GBC is characterized by marked geographic predilection. GBC has distinct morphological types that pose unique challenges in diagnosis and differentiation from benign lesions. There are no specific clinical or serological markers of GBC. Imaging plays a key role not only in diagnosis and staging but also in prognostication. Ultrasound (US) is the initial test of choice that allows risk stratification in wall thickening and polypoidal type of gallbladder lesions. US findings guide further investigations and management. Computed tomography (CT) is the test of choice for staging GBC as it allows comprehensive evaluation of the gallbladder lesion, liver involvement, lymph nodes, peritoneum, and other distant sites for potential metastases. Magnetic resonance imaging (MRI) and magnetic resonance cholangiopancreatography allow better delineation of the biliary system involvement. Contrast-enhanced US and advanced MRI techniques including diffusion-weighted imaging and dynamic contrast-enhanced MRI are used as problem-solving tools in cases where distinction from benign lesion is challenging at US and CT. Positron emission tomography is also used in selected cases for accurate staging of the disease. In this review, we provide an up-to-date insight into the role of imaging in diagnosis, staging, and prognostication of GBC.

The standard therapy for locally unresectable advanced non-small cell lung cancer (NSCLC) is comprised of chemoradiotherapy (CRT) before immunotherapy (IO) consolidation. However, how to predict treatment outcomes and recognize patients that will benefit from IO remain unclear. This study aimed to identify prognostic biomarkers by integrating computed tomography (CT)-based radiomics and genomics. Specifically, our research involved 165 patients suffering from unresectable Stage III NSCLC. Cohort 1 (IO following CRT) was divided into D1 (n = 74), D2 (n = 32), and D3 (n = 26) sets, and the remaining 33 patients treated with CRT alone were grouped in D4. According to the CT images of primary tumor regions, radiomic features were analyzed through the least absolute shrinkage and selection operator (LASSO) regression. The Rad-score was figured out to forecast the progression-free survival (PFS). According to the Rad-score, patients were divided into high and low risk groups. Next-generation sequencing was implemented on peripheral blood and tumor tissue samples in the D3 and D4 cohorts. The maximum somatic allele frequency (MSAF) about circulating tumor DNA levels was assessed. Mismatch repair and switching/sucrose non-fermenting signaling pathways were significantly enriched in the low-risk group compared to the high-risk group (p < 0.05). Moreover, patients with MSAF ≥ 1% and those showing a decrease in MSAF after treatment significantly benefited from IO. This study developed a radiomics model predicting PFS after CRT and IO in Stage III NSCLC and constructed a radio-genomic map to identify underlying biomarkers, supplying valuable insights for cancer biology.

To develop a model based on intra- and peritumoral radiomics features derived from B-mode ultrasound (BMUS), strain elastography (SE), and shear wave elastography (SWE) for cervical lymph node metastasis (LNM) prediction in papillary thyroid cancer (PTC) and to determine the optimal peritumoral size.

PTC Patients were enrolled from two medical centers. Radiomics features were extracted from intratumoral and four peritumoral regions with widths of 0.5-2.0 mm on tri-modality ultrasound (US) images. Boruta algorithm and XGBoost classifier were used for features selection and radiomics signature (RS) construction, respectively. A hybrid model combining the optimal RS with the highest AUC and clinical characteristics as well as a clinical model were built via multivariate logistic regression analysis. The performance of the established models was evaluated by discrimination, calibration, and clinical utility. DeLong's test was used for performance comparison. The diagnostic augmentation of two radiologists with hybrid model's assistance was also evaluated.

A total of 660 patients (mean age, 41 years ± 12 [SD]; 506 women) were divided into training, internal test and external test cohorts. The multi-modality RS1.0 mm yielded the optimal AUCs of 0.862, 0.798 and 0.789 across the three cohorts, outperforming other single-modality RSs and intratumoral RS. The AUCs of the hybrid model integrating multi-modality RS1.0 mm, age, gender, tumor size and microcalcification were 0.883, 0.873 and 0.841, respectively, which were significantly superior to other RSs and clinical model (all p < 0.05). The hybrid model assisted to significantly improve the sensitivities of junior and senior radiologists by 19.7% and 18.3%, respectively (all p < 0.05).

The intra-peritumoral radiomics model based on tri-modality US imaging holds promise for improving risk stratification and guiding treatment strategies in PTC.

Retrospectively registered.

The present study aimed to develop a nomogram model for predicting overall survival (OS) in esophageal squamous cell carcinoma (ESCC) patients.

A total of 205 patients with ESCC were enrolled and randomly divided into a training cohort (n = 153) and a test cohort (n = 52) at a ratio of 7:3. Multivariate Cox regression was used to construct the radiomics model based on CT data. The mutation signature was constructed based on whole genome sequencing data and found to be significantly associated with the prognosis of patients with ESCC. A nomogram model combining the Rad-score and mutation signature was constructed. An integrated nomogram model combining the Rad-score, mutation signature, and clinical factors was constructed.

A total of 8 CT features were selected for multivariate Cox regression analysis to determine whether the Rad-score was significantly correlated with OS. The area under the curve (AUC) of the radiomics model was 0.834 (95% CI, 0.767-0.900) for the training cohort and 0.733 (95% CI, 0.574-0.892) for the test cohort. The Rad-score, S3, and S6 were used to construct an integrated RM nomogram. The predictive performance of the RM nomogram model was better than that of the radiomics model, with an AUC of 0. 830 (95% CI, 0.761-0.899) in the training cohort and 0.793 (95% CI, 0.653-0.934) in the test cohort. The Rad-score, TNM stage, lymph node metastasis status, S3, and S6 were used to construct an integrated RMC nomogram. The predictive performance of the RMC nomogram model was better than that of the radiomics model and RM nomogram model, with an AUC of 0. 862 (95% CI, 0.795-0.928) in the training cohort and 0. 837 (95% CI, 0.705-0.969) in the test cohort.

An integrated nomogram model combining the Rad-score, mutation signature, and clinical factors can better predict the prognosis of patients with ESCC.

Lymph node metastasis (LNM) in patients with intrahepatic cholangiocarcinoma (iCCA) affects treatment strategies and prognosis. However, preoperative imaging is not reliable enough for identifying LNM.

To develop and validate a radiomics nomogram based on dynamic contrast enhanced (DCE)-MR images for identifying LNM and prognosis in iCCA.

Retrospective.

Two hundred four patients with pathologically proven iCCA who underwent curative-intent resection and lymphadenectomy (training cohort: N = 107, internal test cohort: N = 46, and external test cohort: N = 51).

T1- and T2-weighted imaging, diffusion-weighted imaging and DCE imaging at 1.5 T or 3.0 T.

Radiomics features were extracted from intra- and peri-tumoral regions on preoperative DCE-MR images. Imaging features were evaluated by three radiologists, and significant variables in univariable and multivariable regression analysis were included in clinical model. The best-performing radiomics signature and clinical characteristics (intrahepatic duct dilatation, MRI-reported LNM) were combined to build a nomogram. Patients were divided into high-risk and low-risk groups based on their nomogram scores (cutoff = 0.341). Patients were followed up for 1-102 months (median 12) after surgery, the overall survival (OS) and recurrence-free survival (RFS) were calculated.

Receiver operating characteristic (ROC) curve, calibration, decision curve, Delong test, Kaplan-Meier curves, log rank test. Two tailed P < 0.05 was considered statistically significant.

The nomogram incorporating intra- and peri-tumoral radiomics features, intrahepatic duct dilatation and MRI-reported LNM obtained the best discrimination for LNM, with areas under the ROC curves of 0.946, 0.913, and 0.859 in the training, internal, and external test cohorts. In the entire cohort, high-risk patients had significantly lower RFS and OS than low-risk patients. High-risk of LNM was an independent factor of unfavorable OS and RFS.

The nomogram integrating intra- and peri-tumoral radiomics signatures has potential to identify LNM and prognosis in iCCA.

3 TECHNICAL EFFICACY: Stage 2.

To construct a 2.5-dimensional (2.5D) CT radiomics-based deep learning (DL) model to predict early postoperative recurrence of hepatocellular carcinoma (HCC).

We retrospectively analyzed the data of patients who underwent HCC resection at 2 centers. The 232 patients from center 1 were randomly divided into the training (162 patients) and internal validation cohorts (70 patients); 91 patients from center 2 formed the external validation cohort. We developed a 2.5D DL model based on a central 2D image with the maximum tumor cross-section and adjacent slices. Multiple views (transverse, sagittal, and coronal) and phases (arterial, plain, and portal) were incorporated. Multi-instance learning techniques were applied to the extracted data; the resulting comprehensive feature set was modeled using Logistic Regression, RandomForest, ExtraTrees, XGBoost, and LightGBM, with 5-fold cross validation and hyperparameter optimization with Grid-search. Receiver operating characteristic curves, calibration curves, DeLong test, and decision curve analysis were used to evaluate model performance.

The 2.5D DL model performed well in the training (AUC: 0.920), internal validation (AUC: 0.825), and external validation cohorts (AUC: 0.795). The 3D DL model performed well in the training cohort and poorly in the internal and external validation cohorts (AUCs: 0.751, 0.666, and 0.567, respectively), indicating overfitting. The combined model (2.5D DL+clinical) performed well in all cohorts (AUCs: 0.921, 0.835, 0.804). The Hosmer-Lemeshow test, DeLong test, and decision curve analysis confirmed the superiority of the combined model over the other signatures.

The combined model integrating 2.5D DL and clinical features accurately predicts early postoperative HCC recurrence.

Radiomics, which involves the conversion of digital images into high-dimensional data, has been used in oncological studies since 2012. We analyzed the publications that had been conducted on this subject using bibliometric and visual methods to expound the hotpots and future trends regarding radiomics in evaluating lymph node status in oncology.

Documents published between 2012 and 2023, updated to August 1, 2024, were searched using the Scopus database. VOSviewer, R Package, and Microsoft Excel were used for visualization.

A total of 898 original articles and reviews written in English and be related to radiomics for evaluating lymph node status in oncology, published between 2015 and 2023, were retrieved. A significant increase in the number of publications was observed, with an annual growth rate of 100.77%. The publications predominantly originated from three countries, with China leading in the number of publications and citations. Fudan University was the most contributing affiliation, followed by Sun Yat-sen University and Southern Medical University, all of which were from China. Tian J. from the Chinese Academy of Sciences contributed the most within 5885 authors. In addition, Frontiers in Oncology had the most publications and transcended other journals in recent 4 years. Moreover, the keywords co-occurrence suggested that the interplay of "radiomics" and "lymph node metastasis," as well as "major clinical study" were the predominant topics, furthermore, the focused topics shifted from revealing the diagnosis of cancers to exploring the deep learning-based prediction of lymph node metastasis, suggesting the combination of artificial intelligence research would develop in the future.

The present bibliometric and visual analysis described an approximately continuous trend of increasing publications related to radiomics in evaluating lymph node status in oncology and revealed that it could serve as an efficient tool for personalized diagnosis and treatment guidance in clinical patients, and combined artificial intelligence should be further considered in the future.

Pulmonary embolism (PE) is life-threatening and requires timely and accurate diagnosis, yet current imaging methods, like computed tomography pulmonary angiography, present limitations, particularly for patients with contraindications to iodinated contrast agents. We aimed to develop a quantitative texture analysis pipeline using machine learning (ML) based on non-contrast thoracic computed tomography (CT) scans to discover intensity and textural features correlated with regional lung perfusion (Q) physiology and pathology and synthesize voxel-wise Q surrogates to assist in PE diagnosis.

We retrospectively collected 99mTc-labeled macroaggregated albumin Q-SPECT/CT scans from patients suspected of PE, including an internal dataset of 76 patients (64 for training, 12 for testing) and an external testing dataset of 49 patients. Quantitative CT features were extracted from segmented lung subregions and underwent a two-stage feature selection pipeline. The prior-knowledge-driven preselection stage screened for robust and non-redundant perfusion-correlated features, while the data-driven selection stage further filtered features by fitting ML models for classification. The final classification model, trained with the highest-performing PE-associated feature combination, was evaluated in the testing cohorts based on the Area Under the Curve (AUC) for subregion-level predictability. The voxel-wise Q surrogate was then synthesized using the final selected feature maps (FMs) and model score maps (MSMs) to investigate spatial distributions. The Spearman correlation coefficient (SCC) and Dice similarity coefficient (DSC) were used to assess the spatial consistency between FMs or MSMs and Q-SPECT scans.

The optimal model performance achieved an AUC of 0.863 during internal testing and 0.828 on the external testing cohort. The model identified a combination containing 14 intensity and textural features that were non-redundant, robust, and capable of distinguishing between high- and low-functional lung regions. Spatial consistency assessment in the internal testing cohort showed moderate-to-high agreement between MSMs and reference Q-SPECT scans, with median SCC of 0.66, median DSCs of 0.86 and 0.64 for high- and low-functional regions, respectively.

This study validated the feasibility of using quantitative texture analysis and a data-driven ML pipeline to generate voxel-wise lung perfusion surrogates, providing a radiation-free, widely accessible alternative to functional lung imaging in managing pulmonary vascular diseases.

Not applicable.

Accurate assessment of N staging in patients with non-small cell lung cancer (NSCLC) is critical for the development of effective treatment plans, the optimization of therapeutic strategies, and the enhancement of patient survival rates. This study proposes a hybrid model based on 3D convolutional neural networks (CNNs) and transformers for predicting the N-staging and survival rates of NSCLC patients within the NSCLC radiogenomics and Nsclc-radiomics datasets. The model achieved accuracies of 0.805, 0.828, and 0.819 for the training, validation, and testing sets, respectively. By leveraging the strengths of CNNs in local feature extraction and the superior performance of transformers in global information modeling, the model significantly enhances predictive accuracy and efficacy. A comparative analysis with traditional CNN and transformer architectures demonstrates that the CNN-transformer hybrid model outperforms N-staging predictions. Furthermore, this study extracts the one-year survival rate as a feature and employs the Lasso-Cox model for survival predictions at various time intervals (1, 3, 5, and 7 years), with all survival prediction p-values being less than 0.05, illustrating the time-dependent nature of survival analysis. The application of time-dependent ROC curves further validates the model's accuracy and reliability for survival predictions. Overall, this research provides innovative methodologies and new insights for the early diagnosis and prognostic evaluation of NSCLC.

To extract texture features from vocal cord leukoplakia (VCL) images and establish a VCL risk stratification prediction model using machine learning (ML) techniques.

A total of 462 patients with pathologically confirmed VCL were retrospectively collected and divided into low-risk and high-risk groups. We use a 5-fold cross validation method to ensure the generalization ability of the model built using the included dataset and avoid overfitting. Totally 504 texture features were extracted from each laryngoscope image. After feature selection, 10 ML classifiers were utilized to construct the model. The SHapley Additive exPlanations (SHAP) was employed for feature analysis. To evaluate the model, accuracy, sensitivity, specificity, and the area under the receiver operating characteristic (ROC) curve (AUC) were utilized. In addition, the model was transformed into an online application for public use and further tested in an independent dataset with 52 cases of VCL.

A total of 12 features were finally selected, random forest (RF) achieved the best model performance, the mean accuracy, sensitivity, specificity, and AUC of the 5-fold cross validation were 92.2 ± 4.1%, 95.6 ± 4.0%, 85.8 ± 5.8%, and 90.7 ± 4.9%, respectively. The result is much higher than the clinicians (AUC between 63.1% and 75.2%). The SHAP algorithm ranks the importance of 12 texture features to the model. The test results of the additional independent datasets were 92.3%, 95.7%, 90.0%, and 93.3%, respectively.

The proposed VCL risk stratification prediction model, which has been developed into a public online prediction platform, may be applied in practical clinical work.

3 Laryngoscope, 134:4329-4337, 2024.

Bone marrow is the leading site for metastasis from neuroblastoma and affects the prognosis of patients with neuroblastoma. However, the accurate diagnosis of bone marrow metastasis is limited by the high spatial and temporal heterogeneity of neuroblastoma. Radiomics analysis has been applied in various cancers to build accurate diagnostic models but has not yet been applied to bone marrow metastasis of neuroblastoma.

We retrospectively collected information from 187 patients pathologically diagnosed with neuroblastoma and divided them into training and validation sets in a ratio of 7:3. A total of 2632 radiomics features were retrieved from venous and arterial phases of contrast-enhanced computed tomography (CT), and nine machine learning approaches were used to build radiomics models, including multilayer perceptron (MLP), extreme gradient boosting, and random forest. We also constructed radiomics-clinical models that combined radiomics features with clinical predictors such as age, gender, ascites, and lymph gland metastasis. The performance of the models was evaluated with receiver operating characteristics (ROC) curves, calibration curves, and risk decile plots.

The MLP radiomics model yielded an area under the ROC curve (AUC) of 0.97 (95% confidence interval [CI]: 0.95-0.99) on the training set and 0.90 (95% CI: 0.82-0.95) on the validation set. The radiomics-clinical model using an MLP yielded an AUC of 0.93 (95% CI: 0.89-0.96) on the training set and 0.91 (95% CI: 0.85-0.97) on the validation set.

MLP-based radiomics and radiomics-clinical models can precisely predict bone marrow metastasis in patients with neuroblastoma.

According to clinical practice guidelines, transarterial chemoembolization (TACE) is the standard treatment modality for patients with intermediate-stage hepatocellular carcinoma (HCC). Early prediction of treatment response can help patients choose a reasonable treatment plan. This study aimed to investigate the value of the radiomic-clinical model in predicting the efficacy of the first TACE treatment for HCC to prolong patient survival.

A total of 164 patients with HCC who underwent the first TACE from January 2017 to September 2021 were analyzed. The tumor response was assessed by modified response evaluation criteria in solid tumors (mRECIST), and the response of the first TACE to each session and its correlation with overall survival were evaluated. The radiomic signatures associated with the treatment response were identified by the least absolute shrinkage and selection operator (LASSO), and four machine learning models were built with different types of regions of interest (ROIs) (tumor and corresponding tissues) and the model with the best performance was selected. The predictive performance was assessed with receiver operating characteristic (ROC) curves and calibration curves.

Of all the models, the random forest (RF) model with peritumor (+10 mm) radiomic signatures had the best performance [area under ROC curve (AUC) = 0.964 in the training cohort, AUC = 0.949 in the validation cohort]. The RF model was used to calculate the radiomic score (Rad-score), and the optimal cutoff value (0.34) was calculated according to the Youden's index. Patients were then divided into a high-risk group (Rad-score > 0.34) and a low-risk group (Rad-score ≤ 0.34), and a nomogram model was successfully established to predict treatment response. The predicted treatment response also allowed for significant discrimination of Kaplan-Meier curves. Multivariate Cox regression identified six independent prognostic factors for overall survival, including male [hazard ratio (HR) = 0.500, 95% confidence interval (CI): 0.260-0.962, P = 0.038], alpha-fetoprotein (HR = 1.003, 95% CI: 1.002-1.004, P < 0.001), alanine aminotransferase (HR = 1.003, 95% CI: 1.001-1.005, P = 0.025), performance status (HR = 2.400, 95% CI: 1.200-4.800, P = 0.013), the number of TACE sessions (HR = 0.870, 95% CI: 0.780-0.970, P = 0.012) and Rad-score (HR = 3.480, 95% CI: 1.416-8.552, P = 0.007).

The radiomic signatures and clinical factors can be well-used to predict the response of HCC patients to the first TACE and may help identify the patients most likely to benefit from TACE.

Biliary tract cancers are malignant neoplasms arising from bile duct epithelial cells. They include cholangiocarcinomas and gallbladder cancer. Gallbladder cancer has a marked geographical preference and is one of the most common cancers in women in northern India. Biliary tract cancers are usually diagnosed at an advanced, unresectable stage. Hence, the prognosis is extremely dismal. The five-year survival rate in advanced gallbladder cancer is < 5%. Hence, early detection and radical surgery are critical to improving biliary tract cancer prognoses. Radiological imaging plays an essential role in diagnosing and managing biliary tract cancers. However, the diagnosis is challenging because the biliary tract is affected by many diseases that may have radiological appearances similar to cancer. Artificial intelligence (AI) can improve radiologists' performance in various tasks. Deep learning (DL)-based approaches are increasingly incorporated into medical imaging to improve diagnostic performance. This paper reviews the AI-based strategies in biliary tract cancers to improve the diagnosis and prognosis.

Enhanced magnetic resonance imaging (MRI) is widely used in the diagnosis, treatment and prognosis of hepatocellular carcinoma (HCC), but it can not effectively reflect the heterogeneity within the tumor and evaluate the effect after treatment. Preoperative imaging analysis of voxel changes can effectively reflect the internal heterogeneity of the tumor and evaluate the progression-free survival (PFS).

To predict the PFS of patients with HCC before operation by building a model with enhanced MRI images.

Delineate the regions of interest (ROI) in arterial phase, portal venous phase and delayed phase of enhanced MRI. After extracting the combinatorial features of ROI, the features are fused to obtain deep learning radiomics (DLR)_Sig. DeLong's test was used to evaluate the diagnostic performance of different typological features. K-M analysis was applied to assess PFS in different risk groups, and the discriminative ability of the model was evaluated using the C-index.

Tumor diameter and diolame were independent factors influencing the prognosis of PFS. Delong's test revealed multi-phase combined radiomic features had significantly greater area under the curve values than did those of the individual phases (P < 0.05).In deep transfer learning (DTL) and DLR, significant differences were observed between the multi-phase and individual phases feature sets (P < 0.05). K-M survival analysis revealed a median survival time of high risk group and low risk group was 12.8 and 14.2 months, respectively, and the predicted probabilities of 6 months, 1 year and 2 years were 92%, 60%, 40% and 98%, 90%,73%, respectively. The C-index was 0.764, indicating relatively good consistency between the predicted and observed results. DTL and DLR have higher predictive value for 2-year PFS in nomogram.

Based on the multi-temporal characteristics of enhanced MRI and the constructed Nomograph, it provides a new strategy for predicting the PFS of transarterial chemoembolization treatment of HCC.

To establish a radiomics-based automatic grading model for knee osteoarthritis (OA) and evaluate the influence of different body positions on the model's effectiveness.

Plain radiographs of a total of 473 pairs of knee joints from 473 patients (May 2020 to July 2021) were retrospectively analyzed. Each knee joint included anteroposterior (AP) and lateral (LAT) images which were randomly assigned to the training cohort and the testing cohort at a ratio of 7:3. First, an assessment of knee OA severity was done by two independent radiologists with Kallgren-Lawrence grading scale. Then, another two radiologists independently delineated the region of interest for radiomic feature extraction and selection. The radiomic classification features were dimensionally reduced and a machine model was conducted using logistic regression (LR). Finally, the classification efficiency of the model was evaluated using receiver operating characteristic curves and the area under the curve (AUC).

The AUC (macro/micro) of the model using a combination of AP and LAT (AP&LAT) images were 0.772/0.778, 0.818/0.799, and 0.864/0.879, respectively. The radiomic features from the combined images achieved better classification performance than the individual position image (p < 0.05). The overall accuracy of the radiomic model with AP&LAT images was 0.727 compared to 0.712 and 0.417 for radiologists with 4 years and 2 years of musculoskeletal diagnostic experience.

A radiomic model constructed by combining the AP&LAT images of the knee joint can better grade knee OA and assist clinicians in accurate diagnosis and treatment.

A radiomic model based on plain radiographs accurately grades knee OA severity. By utilizing the LR classifier and combining AP&LAT images, it improves accuracy and consistency in grading, aiding clinical decision-making, and treatment planning.

Radiomic model performed more accurately in K/L grading of knee OA than junior radiologists. Radiomic features from the combined images achieved better classification performance than the individual position image. A radiomic model can improve the grading of knee OA and assist in diagnosis and treatment.

Radical surgery, the first-line treatment for patients with hepatocellular cancer (HCC), faces the dilemma of high early recurrence rates and the inability to predict effectively. We aim to develop and validate a multimodal model combining clinical, radiomics, and pathomics features to predict the risk of early recurrence.

We recruited HCC patients who underwent radical surgery and collected their preoperative clinical information, enhanced computed tomography (CT) images, and whole slide images (WSI) of hematoxylin and eosin (H & E) stained biopsy sections. After feature screening analysis, independent clinical, radiomics, and pathomics features closely associated with early recurrence were identified. Next, we built 16 models using four combination data composed of three type features, four machine learning algorithms, and 5-fold cross-validation to assess the performance and predictive power of the comparative models.

Between January 2016 and December 2020, we recruited 107 HCC patients, of whom 45.8% (49/107) experienced early recurrence. After analysis, we identified two clinical features, two radiomics features, and three pathomics features associated with early recurrence. Multimodal machine learning models showed better predictive performance than bimodal models. Moreover, the SVM algorithm showed the best prediction results among the multimodal models. The average area under the curve (AUC), accuracy (ACC), sensitivity, and specificity were 0.863, 0.784, 0.731, and 0.826, respectively. Finally, we constructed a comprehensive nomogram using clinical features, a radiomics score and a pathomics score to provide a reference for predicting the risk of early recurrence.

The multimodal models can be used as a primary tool for oncologists to predict the risk of early recurrence after radical HCC surgery, which will help optimize and personalize treatment strategies.

Despite advances in risk-stratified treatment strategies for children with medulloblastoma (MB), the prognosis for MB with short-term recurrence is extremely poor, and there is still a lack of evaluation of short-term recurrence risk or short-term survival. This study aimed to construct and validate a radiomics model for predicting the outcome of MB based on preoperative multiparametric magnetic resonance images (MRIs) and to provide an objective for clinical decision-making.

The clinical and imaging data of 64 patients with MB admitted to Shenzhen Children's Hospital from December 2012 to December 2021 and confirmed by pathology were retrospectively collected. According to the 18-month progression-free survival, the cases were classified into a good prognosis group and a poor prognosis group, and all cases were divided into training group (70%) and validation group (30%) randomly. Radiomics features were extracted from MRI of each child. The consistency test, t-test, and the least absolute shrinkage and selection operator were used for feature selection. The support vector machine (SVM) and receiver operator characteristic were used to evaluate the distinguishing ability of the selected features to the prognostic groups. RAD score was calculated based on the selected features. The clinical characteristics and RAD score were included in the multivariate logistic regression, and prediction models were constructed by screening out independent influences. The radiomics nomogram was constructed, and its clinical significance was evaluated.

A total of 1930 radiomic features were extracted from the images of each patient, and 11 features were included in the construction of radiomics score after selected. The area under the curve (AUC) values of the SVM model in the training and validation groups were 0.946 and 0.797, respectively. The radiomics nomogram was constructed based on the training cohort, and the AUC values in the training group and the validation group were 0.926 and 0.835, respectively. The results of clinical decision curve analysis showed that a good net benefit could be obtained from the nomogram.

The radiomics nomogram established based on MRI can be used as a noninvasive predictive tool to evaluate the prognosis of children with MB, which is expected to help neurosurgeons better conduct preoperative planning and patient follow-up management.

The purpose of this study was to investigate the prognostic significance of radiomics in conjunction with hematological parameters in relation to the overall survival (OS) of individuals diagnosed with esophageal squamous cell carcinoma (ESCC) following definitive chemoradiotherapy (dCRT).

In this retrospective analysis, a total of 122 patients with locally advanced ESCC were included. These patients were randomly assigned to either the training cohort (n = 85) or the validation cohort (n = 37). In the training group, the least absolute shrinkage and selection operator (LASSO) regression was utilized to choose the best radiomic features for calculating the Rad-score. To develop a nomogram model, both univariate and multivariate analyses were conducted to identify the clinical factors and hematologic parameters that could predict the OS. The performance of the predictive model was evaluated using the C-index, while the accuracy was assessed through the calibration curve.

The Rad-score was calculated by selecting 10 radiomic features through LASSO regression. OS was predicted independently by neutrophil-to-monocyte ratio (NMR) and Rad-score according to the results of multivariate analysis. Patients who had a Rad-score > 0.47 and an NMR > 9.76 were at a significant risk of mortality. A nomogram was constructed using the findings from the multivariate analysis. In the training cohort, the nomogram had a C-index of 0.619, while in the validation cohort, it was 0.573. The model's accuracy was demonstrated by the calibration curve, which was excellent.

A prognostic model utilizing radiomics and hematologic parameters was developed, enabling the prediction of OS in patients with ESCC following dCRT.

Patients with esophageal cancer who underwent definitive chemoradiotherapy may benefit from including CT radiomics in the nomogram model.

• Predicting the prognosis of ESCC patients before treatment is particularly important. • Patients with a Rad-score > 0.47 and neutrophil-to-monocyte ratio > 9.76 had a high risk of mortality. • CT-based radiomics nomogram model could be used to predict the survival of patients.

We aimed to develop a novel preoperative nomogram to predict lymph node metastasis (LNM) in perihilar cholangiocarcinoma (pCCA) patients.

160 pCCA patients were enrolled at Lihuili Hospital from July 2006 to May 2022. A novel nomogram model was established to predict LNM in pCCA patients based on the independent predictive factors selected by the multivariate logistic regression model. The precision of the nomogram model was evaluated through internal and external validation with calibration curve statistics and the concordance index (C-index). Receiver operating characteristic (ROC) curve and decision curve analysis (DCA) were used to evaluate and determine the clinical utility of the nomogram.

Multivariate logistic regression demonstrated that age (OR = 0.963, 95% CI: 0.930-0.996, P = 0.030), CA19-9 level (> 559.8 U/mL vs. ≤559.8 U/mL: OR = 3.162, 95% CI: 1.519-6.582, P = 0.002) and tumour diameter (OR = 1.388, 95% CI: 1.083-1.778, P = 0.010) were independent predictive factors of LNM in pCCA patients. The C-index was 0.763 (95% CI: 0.667-0.860) and 0.677 (95% CI: 0.580-0.773) in training cohort and validation cohort, respectively. ROC curve analysis indicated the comparative stability and adequate discriminative ability of nomogram. The sensitivity and specificity were 0.820 and 0.652 in training cohort and 0.704 and 0.649 in validation cohort, respectively. DCA revealed that the nomogram model could augment net benefits in the prediction of LNM in pCCA patients.

The novel prediction model is useful for predicting LNM in pCCA patients and showed adequate discriminative ability and high predictive accuracy.

Spread Through Air Spaces (STAS) is involved in lung adenocarcinoma (LUAD) recurrence, where cancer cells spread into adjacent lung tissue, impacting surgical planning and prognosis assessment. Radiomics-based models show promise in predicting STAS preoperatively, enhancing surgical precision and prognostic evaluations. The present study performed network meta-analysis to assess the predictive efficacy of imaging models for STAS in LUAD. Data were systematically sourced from PubMed, Embase, Scopus, Wiley and Web of Science, according to the Cochrane Handbook for Systematic Reviews of Interventions) and A Measurement Tool to Assess systematic Reviews 2. Using Stata software v17.0 for meta-analysis, surface under the cumulative ranking area (SUCRA) was applied to identify the most effective diagnostic method. Quality assessments were performed using Cochrane Collaboration's risk-of-bias tool and publication bias was assessed using Deeks' funnel plot. The analysis encompassed 14 articles, involving 3,734 patients, and assessed 17 predictive models for STAS in LUAD. According to comprehensive analysis of SUCRA, the machine learning (ML)_Peri_tumour model had the highest accuracy (56.5), the Features_computed tomography (CT) model had the highest sensitivity (51.9) and the positron emission tomography (pet)_CT model had the highest specificity (53.9). ML_Peri_tumour model had the highest predictive performance. The accuracy was as follows: ML_Peri_tumour vs. Features_CT [relative risk (RR)=1.14; 95% confidence interval (CI), 0.99-1.32]; ML_Peri_tumour vs. ML_Tumour (RR=1.04; 95% CI, 0.83-1.30) and ML_Peri_tumour vs. pet_CT (RR=1.04; 95% CI, 0.84-1.29). Comparative analyses revealed heightened predictive accuracy of the ML_Peri_tumour compared with other models. Nonetheless, the field of radiological feature analysis for STAS prediction remains nascent, necessitating improvements in technical reproducibility and comprehensive model evaluation.

This study aimed to determine the methodological quality and evaluate the diagnostic performance of radiomics features in detecting lymph node metastasis on preoperative images in patients with cholangiocarcinoma and gallbladder cancer.

Publications between January 2005 and October 2022 were considered for inclusion. Databases such as Pubmed/Medline, Scopus, Embase, and Google Scholar were searched for relevant studies. The quality of the methodology of the manuscripts was determined using the Radiomics Quality Score and Quality Assessment of Diagnostic Accuracy Studies 2. Pooled results with corresponding 95% confidence intervals (CIs) were calculated using the DerSimonian-Liard method (random-effect model). Forest plots were used to visually represent the diagnostic profile of radiomics signature in each of the data sets pertaining to each study. Fagan plot was used to determine clinical applicability.

Overall sensitivity was 0.748 (95% CI, 0.703-0.789). Overall specificity was 0.795 (95% CI, 0.742-0.839). The combined negative likelihood ratio was 0.299 (95% CI, 0.266-0.350), and the positive likelihood ratio was 3.545 (95% CI, 2.850-4.409). The combined odds ratio of the studies was 12.184 (95% CI, 8.477-17.514). The overall summary receiver operating characteristics area under the curve was 0.83 (95% CI, 0.80-0.86). Three studies applied nomograms to 8 data sets and achieved a higher pooled sensitivity and specificity (0.85 [0.80-0.89] and 0.85 [0.71-0.93], respectively).

The pooled analysis showed that predictive models fed with radiomics features achieve good sensitivity and specificity in detecting lymph node metastasis in computed tomography and magnetic resonance imaging images. Supplementation of the models with biological correlates increased sensitivity and specificity in all data sets.

It is essential yet highly challenging to preoperatively diagnose variant histologies such as urothelial carcinoma with squamous differentiation (UC w/SD) from pure UC in patients with muscle-invasive bladder carcinoma (MIBC), as their treatment strategy varies significantly. We developed a non-invasive automated machine learning (AutoML) model to preoperatively differentiate UC w/SD from pure UC in patients with MIBC.

A total of 119 MIBC patients who underwent baseline bladder MRI were enrolled in this study, including 38 patients with UC w/SD and 81 patients with pure UC. These patients were randomly assigned to a training set or a test set (3:1). An AutoML model was built from the training set, using 13 selected radiomic features from T2-weighted imaging, semantic features (ADC values), and clinical features (tumor length, tumor stage, lymph node metastasis status), and subsequent ten-fold cross-validation was performed. A test set was used to validate the proposed model. The AUC of the ROC curve was then calculated for the model.

This AutoML model enabled robust differentiation of UC w/SD and pure UC in patients with MIBC in both training set (ten-fold cross-validation AUC = 0.955, 95% confidence interval [CI]: 0.944-0.965) and test set (AUC = 0.932, 95% CI: 0.812-1.000).

The presented AutoML model, that incorporates the radiomic, semantic, and clinical features from baseline MRI, could be useful for preoperative differentiation of UC w/SD and pure UC.

This MRI-based automated machine learning (AutoML) study provides a non-invasive and low-cost preoperative prediction tool to identify the muscle-invasive bladder cancer patients with variant histology, which may serve as a useful tool for clinical decision-making.

• It is important to preoperatively diagnose variant histology from urothelial carcinoma in patients with muscle-invasive bladder carcinoma (MIBC), as their treatment strategy varies significantly. • An automated machine learning (AutoML) model based on baseline bladder MRI can identify the variant histology (squamous differentiation) from urothelial carcinoma preoperatively in patients with MIBC. • The developed AutoML model is a non-invasive and low-cost preoperative prediction tool, which may be useful for clinical decision-making.

The occurrence of lymph node metastasis (LNM) is one of the critical factors in determining the staging, treatment and prognosis of cervical cancer (CC). Heart rate variability (HRV) is associated with LNM in patients with CC. The purpose of this study was to validate the feasibility of machine learning (ML) models constructed with preoperative HRV as a feature of CC patients in predicting CC LNM.

A total of 292 patients with pathologically confirmed CC admitted to the Department of Gynecological Oncology of the First Affiliated Hospital of Bengbu Medical University from November 2020 to September 2023 were included in the study. The patient' preoperative 5-min electrocardiogram data were collected, and HRV time-domain, frequency-domain and non-linear analyses were subsequently performed, and six ML models were constructed based on 32 parameters. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity.

Among the 6 ML models, the random forest (RF) model showed the best predictive performance, as specified by the following metrics on the test set: AUC (0.852), accuracy (0.744), sensitivity (0.783), and specificity (0.785).

The RF model built with preoperative HRV parameters showed superior performance in CC LNM prediction, but multicenter studies with larger datasets are needed to validate our findings, and the physiopathological mechanisms between HRV and CC LNM need to be further explored.

The prognosis of nasopharyngeal carcinoma (NPC) is challenging due to late-stage identification and frequently undetectable Epstein-Barr virus (EBV) DNA. Incorporating radiomic features, which quantify tumor characteristics from imaging, may enhance prognosis assessment.

To investigate the predictive power of radiomic features on overall survival (OS), progression-free survival (PFS), and distant metastasis-free survival (DMFS) in NPC.

A retrospective analysis of 183 NPC patients treated with chemoradiotherapy from 2010 to 2019 was conducted. All patients were followed for at least three years. The pretreatment CT images with contrast medium, MR images (T1W and T2W), as well as gross tumor volume (GTV) contours, were used to extract radiomic features using PyRadiomics v.2.0. Robust and efficient radiomic features were chosen using the intraclass correlation test and univariate Cox proportional hazard regression analysis. They were then combined with clinical data including age, gender, tumor stage, and EBV DNA level for prognostic evaluation using Cox proportional hazard regression models with recursive feature elimination (RFE) and were optimized using 20 repetitions of a five-fold cross-validation scheme.

Integrating radiomics with clinical data significantly enhanced the predictive power, yielding a C-index of 0.788 ± 0.066 to 0.848 ± 0.079 for the combined model versus 0.745 ± 0.082 to 0.766 ± 0.083 for clinical data alone (p<0.05). Multimodality radiomics combined with clinical data offered the highest performance. Despite the absence of EBV DNA, radiomics integration significantly improved survival predictions (C-index ranging from 0.770 ± 0.070 to 0.831 ± 0.083 in combined model versus 0.727 ± 0.084 to 0.734 ± 0.088 in clinical model, p<0.05).

The combination of multimodality radiomic features from CT and MR images could offer superior predictive performance for OS, PFS, and DMFS compared to relying on conventional clinical data alone.

Cholangiocarcinoma (CCA) is a highly aggressive hepatobiliary malignancy, second only to hepatocellular carcinoma in prevalence. Despite surgical treatment being the recommended method to achieve a cure, it is not viable for patients with advanced CCA. Gene sequencing and artificial intelligence (AI) have recently opened up new possibilities in CCA diagnosis, treatment, and prognosis assessment. Basic research has furthered our understanding of the tumor-immunity microenvironment and revealed targeted molecular mechanisms, resulting in immunotherapy and targeted therapy being increasingly employed in the clinic. Yet, the application of these remedies in CCA is a challenging endeavor due to the varying pathological mechanisms of different CCA types and the lack of expressed immune proteins and molecular targets in some patients. AI in medical imaging has emerged as a powerful tool in this situation, as machine learning and deep learning are able to extract intricate data from CCA lesion images while assisting clinical decision making, and ultimately improving patient prognosis. This review summarized and discussed the current immunotherapy and targeted therapy related to CCA, and the research progress of AI in this field.

To develop a CT-based radiomics model for preoperative prediction of lymph node (LN) metastasis in perihilar cholangiocarcinoma (pCCA).

The study enrolled consecutive pCCA patients from three independent Chinese medical centers. The Boruta algorithm was applied to build the radiomics signature for the primary tumor and LN. The k-means algorithm was employed to cluster the selected LNs based on the radiomics signature LN. Support vector machines were used to construct the prediction models. The diagnostic efficiency was measured by the area under the receiver operating characteristic curve (AUC). The optimal model was evaluated in terms of calibration, clinical usefulness, and prognostic value.

A total of 214 patients were included in the study (mean age: 61.6 years ± 9.4; 130 male). The selected LNs were classified into two clusters, which were significantly correlated with LN metastasis in all cohorts (p < 0.001). The model incorporated the clinical risk factors, radiomics signature primary tumor, and the LN cluster obtained the best discrimination, with AUC values of 0.981 (95% CI: 0.962-1), 0.896 (95% CI: 0.810-0.982), and 0.865 (95% CI: 0.768-0.961) in the training, internal validation, and external validation cohorts, respectively. High-risk patients predicted by the optimal model had shorter overall survival than low-risk patients (median, 13.7 vs. 27.3 months, p < 0.001).

The study proposed a radiomics model with good performance to predict LN metastasis in pCCA. As a noninvasive preoperative prediction tool, this model may help in patient risk stratification and personalized treatment.

A CT-based radiomics model accurately predicts lymph node metastasis in perihilar cholangiocarcinoma patients. This noninvasive preoperative tool can aid in patient risk stratification and personalized treatment, potentially improving patient outcomes.

• The radiomics model based on contrast-enhanced CT is a useful tool for preoperative prediction of lymph node metastasis in perihilar cholangiocarcinoma. • Radiomics features extracted from lymph nodes show great potential for predicting lymph node metastasis. • The study is the first to identify a lymph node phenotype with a high probability of metastasis based on radiomics.

Purpose To develop a model integrating radiomics features from cardiac MR cine images with clinical and standard cardiac MRI predictors to identify patients with hypertrophic cardiomyopathy (HCM) at high risk for heart failure (HF). Materials and Methods In this retrospective study, 516 patients with HCM (median age, 51 years [IQR: 40-62]; 367 [71.1%] men) who underwent cardiac MRI from January 2015 to June 2021 were divided into training and validation sets (7:3 ratio). Radiomics features were extracted from cardiac cine images, and radiomics scores were calculated based on reproducible features using the least absolute shrinkage and selection operator Cox regression. Radiomics scores and clinical and standard cardiac MRI predictors that were significantly associated with HF events in univariable Cox regression analysis were incorporated into a multivariable analysis to construct a combined prediction model. Model performance was validated using time-dependent area under the receiver operating characteristic curve (AUC), and the optimal cutoff value of the combined model was determined for patient risk stratification. Results The radiomics score was the strongest predictor for HF events in both univariable (hazard ratio, 10.37; P < .001) and multivariable (hazard ratio, 10.25; P < .001) analyses. The combined model yielded the highest 1- and 3-year AUCs of 0.81 and 0.80, respectively, in the training set and 0.82 and 0.77 in the validation set. Patients stratified as high risk had more than sixfold increased risk of HF events compared with patients at low risk. Conclusion The combined model with radiomics features and clinical and standard cardiac MRI parameters accurately identified patients with HCM at high risk for HF. Keywords: Cardiomyopathies, Outcomes Analysis, Cardiovascular MRI, Hypertrophic Cardiomyopathy, Radiomics, Heart Failure Supplemental material is available for this article. © RSNA, 2024.

Our study aimed to determine whether radiomics models based on contrast-enhanced computed tomography (CECT) have considerable ability to predict serosal involvement in gallbladder cancer (GBC) patients.

A total of 152 patients diagnosed with GBC were retrospectively enrolled and divided into the serosal involvement group and no serosal involvement group according to paraffin pathology results. The regions of interest (ROIs) in the lesion on all CT images were drawn by two radiologists using ITK-SNAP software (version 3.8.0). A total of 412 features were extracted from the CT images of each patient. The Mann‒Whitney U test was applied to identify features with significant differences between groups. Seven machine learning algorithms and a deep learning model based on fully connected neural networks (f-CNNs) were used for radiomics model construction. The prediction efficacy of the models was evaluated using receiver operating characteristic (ROC) curve analysis.

Through the Mann‒Whitney U test, 75 of the 412 features extracted from the CT images of patients were significantly different between groups (P < 0.05). Among all the algorithms, logistic regression achieved the highest performance with an area under the curve (AUC) of 0.944 (sensitivity 0.889, specificity 0.8); the f-CNN deep learning model had an AUC of 0.916, and the model showed high predictive power for serosal involvement, with a sensitivity of 0.733 and a specificity of 0.801.

Radiomics models based on features derived from CECT showed convincing performances in predicting serosal involvement in GBC.

The aim of this study was to explore the clinical value of a radiomics prediction model based on T2-weighted imaging (T2WI) and clinical indexes in predicting lateral lymph node (LLN) metastasis in rectal cancer patients.

This was a retrospective analysis of 106 rectal cancer patients who had undergone LLN dissection. The clinical risk factors for LLN metastasis were selected by multivariable logistic regression analysis of the clinical indicators of the patients. The LLN radiomics features were extracted from the pelvic T2WI of the patients. The least absolute shrinkage and selection operator algorithm and backward stepwise regression method were adopted for feature selection. Three LLN metastasis prediction models were established through logistic regression analysis based on the clinical risk factors and radiomics features. Model performance was assessed in terms of discriminability and decision curve analysis in the training, verification and test sets.

The model based on the combined T2WI radiomics features and clinical risk factors demonstrated the highest accuracy, surpassing the models based solely on either T2WI radiomics features or clinical risk factors. Specifically, the model achieved an AUC value of 0.836 in the test set. Decision curve analysis revealed that this model had the greatest clinical utility for the vast majority of the threshold probability range from 0.4 to 1.0.

Combining T2WI radiomics features with clinical risk factors holds promise for the noninvasive assessment of the biological characteristics of the LLNs in rectal cancer, potentially aiding in therapeutic decision-making and optimizing patient outcomes.

This study aimed to evaluate the diagnostic performance of machine learning (ML)-based ultrasound (US) radiomics models for risk stratification of gallbladder (GB) masses.

We prospectively examined 640 pathologically confirmed GB masses obtained from 640 patients between August 2019 and October 2022 at four institutions. Radiomics features were extracted from grayscale US images and germane features were selected. Subsequently, 11 ML algorithms were separately used with the selected features to construct optimum US radiomics models for risk stratification of the GB masses. Furthermore, we compared the diagnostic performance of these models with the conventional US and contrast-enhanced US (CEUS) models.

The optimal XGBoost-based US radiomics model for discriminating neoplastic from non-neoplastic GB lesions showed higher diagnostic performance in terms of areas under the curves (AUCs) than the conventional US model (0.822-0.853 vs. 0.642-0.706, p < 0.05) and potentially decreased unnecessary cholecystectomy rate in a speculative comparison with performing cholecystectomy for lesions sized over 10 mm (2.7-13.8% vs. 53.6-64.9%, p < 0.05) in the validation and test sets. The AUCs of the XGBoost-based US radiomics model for discriminating carcinomas from benign GB lesions were higher than the conventional US model (0.904-0.979 vs. 0.706-0.766, p < 0.05). The XGBoost-US radiomics model performed better than the CEUS model in discriminating GB carcinomas (AUC: 0.995 vs. 0.902, p = 0.011).

The proposed ML-based US radiomics models possess the potential capacity for risk stratification of GB masses and may reduce the unnecessary cholecystectomy rate and use of CEUS.

The machine learning-based ultrasound radiomics models have potential for risk stratification of gallbladder masses and may potentially reduce unnecessary cholecystectomies.

• The XGBoost-based US radiomics models are useful for the risk stratification of GB masses. • The XGBoost-based US radiomics model is superior to the conventional US model for discriminating neoplastic from non-neoplastic GB lesions and may potentially decrease unnecessary cholecystectomy rate for lesions sized over 10 mm in comparison with the current consensus guideline. • The XGBoost-based US radiomics model could overmatch CEUS model in discriminating GB carcinomas from benign GB lesions.

Accurate identification of extrahepatic cholangiocarcinoma (ECC) from an image is challenging because of the small size and complex background structure. Therefore, considering the limitation of manual delineation, it's necessary to develop automated identification and segmentation methods for ECC. The aim of this study was to develop a deep learning approach for automatic identification and segmentation of ECC using MRI.

We recruited 137 ECC patients from our hospital as the main dataset (C1) and an additional 40 patients from other hospitals as the external validation set (C2). All patients underwent axial T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), and diffusion-weighted imaging (DWI). Manual delineations were performed and served as the ground truth. Next, we used 3D VB-Net to establish single-mode automatic identification and segmentation models based on T1WI (model 1), T2WI (model 2), and DWI (model 3) in the training cohort (80% of C1), and compared them with the combined model (model 4). Subsequently, the generalization capability of the best models was evaluated using the testing set (20% of C1) and the external validation set (C2). Finally, the performance of the developed models was further evaluated.

Model 3 showed the best identification performance in the training, testing, and external validation cohorts with success rates of 0.980, 0.786, and 0.725, respectively. Furthermore, model 3 yielded an average Dice similarity coefficient (DSC) of 0.922, 0.495, and 0.466 to segment ECC automatically in the training, testing, and external validation cohorts, respectively.

The DWI-based model performed better in automatically identifying and segmenting ECC compared to T1WI and T2WI, which may guide clinical decisions and help determine prognosis.