Published online Sep 6, 2024. doi: 10.12998/wjcc.v12.i25.5673
Revised: May 28, 2024
Accepted: June 19, 2024
Published online: September 6, 2024
Processing time: 134 Days and 7 Hours
Due to frequent and high-risk sports activities, the elbow joint is susceptible to injury, especially to cartilage tissue, which can cause pain, limited movement and even loss of joint function.
To evaluate magnetic resonance imaging (MRI) multisequence imaging for improving the diagnostic accuracy of adult elbow cartilage injury.
A total of 60 patients diagnosed with elbow cartilage injury in our hospital from January 2020 to December 2021 were enrolled in this retrospective study. We analyzed the accuracy of conventional MRI sequences (T1-weighted imaging, T2-weighted imaging, proton density weighted imaging, and T2 star weighted image) and Three-Dimensional Coronary Imaging by Spiral Scanning (3D-CISS) in the diagnosis of elbow cartilage injury. Arthroscopy was used as the gold standard to evaluate the diagnostic effect of single and combination sequences in different injury degrees and the consistency with arthroscopy.
The diagnostic accuracy of 3D-CISS sequence was 89.34% ± 4.98%, the sensitivity was 90%, and the specificity was 88.33%, which showed the best performance among all sequences (P < 0.05). The combined application of the whole sequence had the highest accuracy in all sequence combinations, the accuracy of mild injury was 91.30%, the accuracy of moderate injury was 96.15%, and the accuracy of severe injury was 93.33% (P < 0.05). Compared with arthroscopy, the combination of all MRI sequences had the highest consistency of 91.67%, and the kappa value reached 0.890 (P < 0.001).
Combination of 3D-CISS and each sequence had significant advantages in improving MRI diagnostic accuracy of elbow cartilage injuries in adults. Multisequence MRI is recommended to ensure the best diagnosis and treatment.
Core Tip: Combination of three-dimensional hydrography sequence and each sequence had significant advantages in improving magnetic resonance imaging (MRI) diagnostic accuracy of elbow cartilage injuries in adults. Multisequence MRI is recommended in clinical practice to ensure the best diagnosis and treatment.
- Citation: Ding WW, Ding L, Li L, Zhang P, Gong R, Li J, Xu MY, Ding F, Chen B. Clinical study on improving the diagnostic accuracy of adult elbow joint cartilage injury by multisequence magnetic resonance imaging. World J Clin Cases 2024; 12(25): 5673-5680
- URL: https://www.wjgnet.com/2307-8960/full/v12/i25/5673.htm
- DOI: https://dx.doi.org/10.12998/wjcc.v12.i25.5673
Due to frequent and high-risk sports activities, the elbow joint is susceptible to injury, especially to cartilage tissue, which can cause pain, limited movement and even loss of joint function[1]. Cartilage injury of the elbow joint is common, and its diagnosis and treatment are important for restoring joint function and preventing chronic changes[2]. However, due to the absence of blood vessels and nerves and the weak regenerative ability of cartilage itself, the possibility of self-repair is limited after damage; therefore, early diagnosis and accurate assessment of the degree of cartilage damage have become the key factors for good therapeutic effects[3,4].
Traditional imaging methods, such as X-ray examination, are limited by their resolution and have many limitations in the diagnosis of cartilage injury[5]. Although X-ray examination can visualize well fractures and positional abnormalities, it is often unable to provide sufficient diagnostic information because of its insufficient ability to detect subtle changes in early cartilage damage[6]. With the continuous development of medical technology, magnetic resonance imaging (MRI), as a nonradioactive and high-resolution imaging technique, has become the preferred method for clinical evaluation of cartilage injury[7]. MRI can provide detailed images of articular cartilage and surrounding soft tissue structures, and has shown obvious advantages especially in the evaluation of cartilage tissue hierarchy and pathological changes[8].
In recent years, multisequence MRI has been increasingly used in clinical practice, especially in the diagnosis of joint diseases, and plays an irreplaceable role[9]. Multisequence MRI can identify and evaluate the lesions of cartilage and surrounding tissues more comprehensively and accurately by combining sequences with different imaging parameters[10]. For example, T1-weighted imaging (T1WI) is well suited for displaying anatomical structures, while T2-weighted imaging (T2WI) has excellent sensitivity for fluid and edema[11]. Proton density weighted imaging (PDWI) is particularly useful in identifying soft tissue structures, while T2*-weighted imaging (T2*WI) is particularly sensitive in detecting subchondral bone abnormalities and early degenerative transformation of articular cartilage[12]. Three-dimensional water imaging sequence (3D-CISS) can provide high resolution, which has unique advantages for identifying anatomical and pathological changes of cartilage, and is an important tool for the diagnosis of cartilage diseases[13].
At present, although a single MRI sequence can provide a lot of effective information, the complexity of joint diseases often requires the combination of multiple sequences to obtain the best imaging effect. Different MRI sequences can reveal different aspects of tissue conditions, such as cartilage stability, degree of hydration, or changes in subchondral bone. Therefore, using specific sequence combinations, damage to cartilage can be detected, qualitatively and quanti
This study aimed to provide data for improving the diagnostic accuracy of elbow cartilage injury by evaluating and comparing the performance of different MRI sequences and their combinations. By investigating the diagnostic efficacy of multisequence combination in comparison with arthroscopy (as the gold standard), and analyzing its accuracy for the diagnosis of different degrees of injury, this study provides guidance for how to rationally use MRI sequence combi
This was a retrospective clinical study, and the cases were selected from the patient records of our hospital between January 2020 and December 2021. The total number of cases was 60, including 35 male and 25 female patients. The age distribution ranged from 18 to 65 years, with a mean of 38.4 years. The common characteristics of the selected patients were that they were all diagnosed with elbow cartilage injury by preliminary clinical diagnosis, and they had not received surgical treatment for elbow cartilage injury.
Inclusion criteria: Adults aged 18–65 years; symptoms of elbow pain and limited movement; and physical examination suggested that cartilage might be damaged, consistent with the preliminary clinical diagnosis of cartilage injury of the elbow joint. Consent was obtained and all study procedures including conventional MRI and multisequence MRI imaging techniques were completed.
Exclusion criteria: Age < 18 or > 65 years; pregnant or lactating women; history of elbow surgery or other traumatic event; severe systemic disease, such as diabetes or cardiovascular disease, or any other health condition that may affect MRI imaging; contraindications to MRI, such as implantation of metal objects in the body; patients unable to cooperate with the completion of the imaging procedure; patients who did not consent to participate in the study or were unable to provide informed consent.
In all the patients involved in this study, MRI was performed in multiple different planes, including horizontal, coronal/oblique coronal, and sagittal. All scans were performed using a Siemens MAGNETOM Avanto 1.5T magnetic resonance device. The examination sequences included T1WI, T2WI, PDWI, T2*WI and 3D-CISS. The detailed scanning parameter settings are shown in Table 1.
TR (ms) | TE (ms) | Matrix of images | Slice thickness (mm) | Layer spacing (mm) | Scan duration (min) | |
T1WI | 550 | 15 | 256×256 | 5 | 0.6 | 6 |
T2WI | 4000 | 102 | 256×256 | 4 | 0.5 | 7 |
PDWI | 3000 | 30 | 256×256 | 3 | 0.4 | 7 |
T2*WI | 560 | 15 | 256×256 | 3 | 0.6 | 6 |
3D-CISS | 700 | 12 | 512×512 | 1.5 | 0.3 | 5 |
For arthroscopy, patients received brachial plexus block. The patient was positioned to ensure that the affected limb was properly spread while preparing for intra-articular manipulation. After adequate disinfection, a small incision was made and the arthroscopic probe was inserted. Using a special needle tube of the arthroscope, the joint was punctured through a small incision to obtain a clear view. The pathological changes in the joint cavity were recorded in detail during arthroscopic observation. After completion, the exudate in the joint cavity was thoroughly cleaned, the instrument was withdrawn, and the wound was carefully sutured.
The study evaluated the diagnostic efficacy of different sequences of MRI for elbow cartilage injury using arthroscopy and intraoperative observation as the gold standard. The observation indicators mainly included the display of cartilage injury and the determination of the degree of injury on MR images. This study compared the diagnostic performance of T1WI, T2WI, PDWI, T2*WI and 3D-CISS images and evaluated their accuracy for different grades of cartilage injury when used alone or in combination. The diagnosis of imaging findings was completed by three senior radiologists independently, and consensus was reached through discussion when differences of opinion occurred.
SPSS 22.0 software was used for statistical analysis. Continuous variables were presented as means ± SD, and differences were analyzed by Student's t test. The χ2 test was used for noncontinuous variables to determine the difference between the different series. The consistency between the diagnostic results of each MRI sequence and the gold standard was evaluated by calculating the accuracy. In all statistical tests, a significance level of < 0.05 was set.
There were 35 male patients and 25 female patients. The mean age overall was 38.4 years, and the mean age of men and women was 39.5 and 36.8 years, respectively. The mean body mass index (BMI) indicated a trend toward overweight n, with a mean BMI of 25.3 overall and 26.1 and 24.2 in men and women, respectively. The average duration of pain in all patients was 6.2 mo, and there was no significant difference between genders (P > 0.05). In terms of smoking history, 34.3% of males and 24.0% of females were smokers. In addition, 16.7% of the patients had a history of elbow injury, with 17.1% in men and 16.0% in women, and there was no significant difference in baseline characteristics between men and women (P > 0.05) (Table 2).
Overall (n = 60) | Male (n = 35) | Female (n = 25) | t/χ2 | P value | |
Age (yr) | 38.4 ± 10.2 | 39.5 ± 10.5 | 36.8 ± 9.8 | 1.009 | 0.317 |
Body mass index (kg/m²) | 25.3 ± 4.2 | 26.1 ± 3.9 | 24.2 ± 4.5 | 1.745 | 0.086 |
Duration of pain (mo) | 6.2 ± 3.7 | 5.9 ± 3.3 | 6.6 ± 4.1 | -0.732 | 0.467 |
Smoking (yes) | 18 (30) | 12 (34.3) | 6 (24.0) | 0.327 | 0.567 |
Past history of elbow joint (yes) | 10 (16.7) | 6 (17.1) | 4 (16.0) | 0.014 | 0.906 |
Table 3 shows the performance of different MRI sequences in the diagnosis of cartilage injury in the elbow. 3D-CISS sequence had the best diagnostic accuracy (89.34% ± 4.98%), diagnostic sensitivity (90%), and diagnostic specificity (88.33%). The diagnostic accuracy, sensitivity and specificity of T1WI sequence were 79.67% ± 6.54%, 81.67% and 78.33%, respectively. Other sequences including T2WI, PDWI and T2*WI also showed high diagnostic accuracy (75.00% ± 5.58%, 78.33% ± 5.25%, and 77.96% ± 5.99%, respectively). Positive and negative predictive values corroborated these findings. The positive predictive value of 3D-CISS was 87.10%±5.18 and the negative predictive value was 92.31% ± 4.13%, which was the highest among the five sequences (P < 0.05).
Diagnostic sensitivity (%) | Diagnostic specificity (%) | Accuracy (%) | Positive predictive value (%) | Negative predictive value (%) | |
T1WI | 81.67 [49/60] | 78.33 [47/60] | 79.67 ± 6.54 | 76.47 ± 7.32 | 82.61 ± 5.88 |
T2WI | 83.33 [50/60] | 71.67 [43/60]a | 75.00 ± 5.58a | 68.49 ± 7.25a | 84.75 ± 4.47 |
PDWI | 70.00 [42/60]b | 85 [51/60]a,b | 78.33 ± 5.25 | 82.35 ± 6.65a,b | 74.19 ± 6.01a,b |
T2*WI | 78.33 [47/60]c | 78.33 [47/60]b,c | 77.96 ± 5.99 | 73.53±7.44b,c | 80.77 ± 6.20c |
3D-CISS | 90.00 [54/60]a,b,c,d | 88.33 [53/60]a,b,d | 89.34 ± 4.98a,b,c,d | 87.10 ± 5.18a,b,c,d | 92.31 ± 4.13a,b,c,d |
Figure 1 provides an overview of the accuracy of MRI sequence combinations in the diagnosis of different grades of elbow cartilage injury. The combined accuracy of the whole sequence was the highest in all the combinations (P < 0.05), especially in moderate injury accuracy (96.15%) and in severe injury accuracy (93.33%), which proved the superiority of using multiple sequences. In addition, the combination of PDWI and 3D-CISS also showed high accuracy in the diagnosis of mild and moderate injuries (86.96% and 92.31%, respectively). In contrast, the combination of T1WI and T2WI had the lowest performance for all levels of injury diagnosis (P < 0.05) (Table 4).
Table 5 presents the agreement between arthroscopic diagnosis and diagnosis with different MRI sequences. Among the 60 patients who underwent arthroscopy, the highest consistency was 91.67% compared with all MRI sequences, and the kappa value was 0.890 (P < 0.001), showing almost perfect consistency. Secondly, compared with 3D-CISS sequence, the consistency reached 86.67%, and the kappa value was 0.840 (P < 0.001), showing a high consistency. The consistency of T1WI, T2WI and PDWI was 70.0%, 75.0% and 80.0%, respectively (P < 0.001), while the consistency of T2*WI and arthroscopy was lower (66.67%, P < 0.001).
No. of joints | No. of agreements | No. of inconsistencies | Kappa value | P value | |
Arthroscopy and T1WI | 60 | 42 (70.00) | 18 (30.00) | 0.650 | < 0.001 |
Arthroscopy and T2WI | 60 | 45 (75.00) | 15 (25.00) | 0.720 | < 0.001 |
Arthroscopy and PDWI | 60 | 48 (80.00) | 12 (20.00) | 0.760 | < 0.001 |
Arthroscopy and T2*WI | 60 | 40 (66.67) | 20 (33.33) | 0.620 | < 0.001 |
Arthroscopy and 3D-CISS | 60 | 52 (86.67) | 8 (13.33) | 0.840 | < 0.001 |
Arthroscopy was combined with all MRI sequences | 60 | 55 (91.67) | 5 (8.33) | 0.890 | < 0.001 |
In elbow injuries, limited by the low resolution of X-ray examination, it is difficult to observe the cartilage and ligaments around the joint in detail, so the possibility of misdiagnosis and missed diagnosis is high. In order to make a better diagnosis and treatment plan, it is necessary to use high-resolution and clear imaging methods[14]. MRI examination has obvious imaging clarity, soft tissue resolution is also high, and allows for multiangle imaging. However, there are a variety of MRI sequences, including T1WI, T2WI, PDWI and T2*WI, which have different principles and different resolutions, so there are also differences in the display of elbow cartilage[15,16]. Cartilage is a complex structure composed of cells, fibers and matrix. In 3D-DESS sequence, synovial fluid shows a high signal, while cartilage shows a medium signal. When the elbow cartilage is injured in children, synovial fluid can enter the cartilage through the tear, and 3D-DESS sequence can clearly show this situation, which is helpful to accurately assess the degree of injury. In contrast, it is difficult for other sequences to clearly show the contrast effect of synovial fluid and cartilage[17,18].
The connective tissue structure of articular cartilage has a layered distribution, including the superficial tangential zone, the middle transition zone, the deep radial zone, and the bottom calcified cartilage layer. The multilevel and high-resolution examination function of MRI is conducive to the accurate classification and diagnosis of elbow cartilage injury[19]. However, because MRI examination involves a variety of sequences, different imaging angles and interference factors lead to differences in the display effects of cartilage, which in turn affects the accuracy of diagnosis[17]. In general, although 2D sequences can reflect the contrast between cartilage and bone, they cannot clearly distinguish the signals of articular cartilage and synovial fluid, and are insufficient sensitive to cartilage defects. 3D-DESS imaging technology can clearly display the signals of fat, cartilage and synovial fluid of the elbow joint, provide high-resolution diagnostic information, and can reconstruct the image in any plane after one scan, thereby improving the diagnostic accuracy. In addition, in the case of poor imaging quality, the use of MRI multicombined imaging technology can provide clearer diagnostic evidence[20].
This study aimed to evaluate the clinical application of MRI multisequence imaging in improving the diagnostic accuracy of adult elbow cartilage injury. Table 3 shows that various MRI sequences have shown some diagnostic potential, but the 3D-CISS sequence performs best with high accuracy of 89.34%, high sensitivity of 90%, and high specificity of 88.33%. Analysis of the data in Table 4 shows that the diagnostic accuracy of all grades of elbow cartilage injury was significantly improved by the combined application of the full sequence, which showed > 90% diagnostic accuracy for mild, moderate and severe injuries. The combination of different MRI sequences significantly improved the diagnostic performance, which may be because the different sequences can provide information about different aspects of cartilage tissue, thus complementing and improving the overall diagnostic effect. As the gold standard, the consistency comparison between arthroscopy and MRI sequences also showed the superiority of multisequence combination. It is worth noting that the highest diagnostic agreement was 91.67% when all MRI sequences were combined, and the kappa value was 0.890, which supports the value of comprehensive application of multisequence imaging technology in clinical practice. MRI multisequence imaging shows high sensitivity and specificity in the diagnosis of elbow cartilage injury, and the combined application of 3D-CISS and other sequences such as T1WI and T2WI provides more accurate diagnostic information.
In recent years, advances in medical imaging technology have expanded the diagnostic capabilities for evaluating cartilage injuries in the elbow joint. While this study focused on the diagnostic accuracy of different MRI sequences, it is essential to acknowledge other imaging modalities that have shown promising results.
Cartilage mapping is one such modality that has gained recognition for its ability to provide detailed information about the structural integrity of cartilage. By utilizing specialized imaging techniques, such as T2 mapping or T1rho mapping, cartilage mapping can assess the biochemical composition of the cartilage and detect subtle changes indicative of injury or degeneration. This modality offers a quantitative assessment of cartilage quality and has demonstrated potential in enhancing the diagnostic accuracy of elbow cartilage injuries. Future studies should explore the integration of cartilage mapping techniques in combination with multisequence MRI to improve diagnostic outcomes.
Another emerging technique is volumetric interpolated breath-hold examination (Vibe) MRI. Vibe MRI enables rapid image acquisition with high spatial resolution, making it particularly suitable for assessing dynamic joint structures, including the elbow cartilage. The real-time imaging capability of Vibe MRI allows for the visualization of joint motion and can aid in the detection of subtle abnormalities, such as cartilage defects during different stages of joint movement. Incorporating Vibe MRI into the imaging protocol may provide additional valuable information for diagnosing and characterizing elbow cartilage injuries.
It is worth mentioning that complementary imaging modalities, such as ultrasound and computed tomography arthrography, have demonstrated utility in the evaluation of elbow joint pathologies. Ultrasound offers the advantage of real-time imaging, affordability, and absence of ionizing radiation, making it a valuable tool for initial assessment and follow-up of elbow cartilage injuries. Computed tomography arthrography combines the benefits of computed tomography with the use of contrast agents to enhance visualization of the joint structures, providing detailed information about the cartilage surface and adjacent soft tissues. The integration of these modalities in a multimodal diagnostic approach may enhance the accuracy and comprehensive evaluation of elbow cartilage injuries.
Clinical decision pathways should be adjusted based on the findings of this study and should rely more heavily on multisequence MRI techniques. Such a more comprehensive diagnostic evaluation can help circumvent the limitations that may arise from a single sequence. However, the clinical decision to apply full-sequence imaging requires weighing the potential burden and cost issues associated with additional imaging time. Despite the positive conclusions of this study, there were some limitations. Firstly, the number of samples was limited, which may affect generalization of the statistical results. In addition, the study had a retrospective design and may have been subject to selection bias. Future prospective studies with larger samples should verify the generalizability of these findings.
This study clearly defined the important role of multisequence MRI in the diagnosis of adult elbow cartilage injury. The 3D-CISS sequences in particular showed excellent imaging performance, while the combined application of different sequences further improved the accuracy. The use of multisequence MRI is recommended in the evaluation and diagnosis of cartilage injuries in the elbow to ensure optimal clinical outcomes.
1. | Aarabi B, Neal CJ, Hersh DS, Harrop JS, Fehlings MG, Toups EG, Guest JD, Ugiliweneza B, Akhtar-Danesh N, Kurpad SN, Grossman RG. Mortality in ASIA Impairment Scale grade A to D Patients With Odontoid Fracture and Magnetic Resonance Imaging Evidence of Spinal Cord Injury. Neurotrauma Rep. 2023;4:375-383. [PubMed] [DOI] [Cited in This Article: ] [Cited by in Crossref: 1] [Reference Citation Analysis (0)] |
2. | Arega TW, Bricq S. Automatic Myocardial Scar Segmentation from Multi-sequence Cardiac MRI Using Fully Convolutional Densenet with Inception and Squeeze-Excitation Module. Myocardial Pathology Segmentation Combining Multi-Sequence Cardiac Magnetic Resonance Images, 2020. [Cited in This Article: ] |
3. | Astley JR, Biancardi AM, Hughes PJC, Marshall H, Collier GJ, Chan HF, Saunders LC, Smith LJ, Brook ML, Thompson R, Rowland-Jones S, Skeoch S, Bianchi SM, Hatton MQ, Rahman NM, Ho LP, Brightling CE, Wain LV, Singapuri A, Evans RA, Moss AJ, McCann GP, Neubauer S, Raman B; C-MORE/PHOSP-COVID Collaborative Group, Wild JM, Tahir BA. Implementable Deep Learning for Multi-sequence Proton MRI Lung Segmentation: A Multi-center, Multi-vendor, and Multi-disease Study. J Magn Reson Imaging. 2023;58:1030-1044. [PubMed] [DOI] [Cited in This Article: ] [Cited by in Crossref: 2] [Reference Citation Analysis (0)] |
4. | Chen Y, Staring M, Neve OM, Romeijn SR, Hensen EF, Verbist BM, Wolterink JM, Tao Q. CoNeS: Conditional neural fields with shift modulation for multi-sequence MRI translation. Melba. 2024;2:657-685. [DOI] [Cited in This Article: ] |
5. | Ding W, Li L, Qiu J, Wang S, Huang L, Chen Y, Yang S, Zhuang X. Aligning Multi-Sequence CMR Towards Fully Automated Myocardial Pathology Segmentation. IEEE Trans Med Imaging. 2023;42:3474-3486. [PubMed] [DOI] [Cited in This Article: ] [Reference Citation Analysis (0)] |
6. | Du MS, Xiong XQ, Liu H, Qin X, Hu XF, Chen W. The evaluation of bone marrow edema in sacroiliac joint in patients with ankylosing spondylitis using magnetic resonance imaging Dixon sequence. BMC Musculoskelet Disord. 2021;22:919. [PubMed] [DOI] [Cited in This Article: ] [Cited by in Crossref: 1] [Cited by in F6Publishing: 1] [Article Influence: 0.3] [Reference Citation Analysis (0)] |
7. | Gai D, Liu S, Zhang H, Kuang X, Lu Q, Gong W, Xiang X, Li H. Analysis of MRI Image-Assisted Diagnosis of Osteoarthritis Based on Support Vector Machine Algorithm. j Med Imaging Hlth Inform. 2021;11:144-149. [DOI] [Cited in This Article: ] [Cited by in Crossref: 1] [Cited by in F6Publishing: 1] [Article Influence: 0.3] [Reference Citation Analysis (0)] |
8. | Goodkin O, Prados F, Vos SB, Pemberton H, Collorone S, Hagens MHJ, Cardoso MJ, Yousry TA, Thornton JS, Sudre CH, Barkhof F; MAGNIMS study group. FLAIR-only joint volumetric analysis of brain lesions and atrophy in clinically isolated syndrome (CIS) suggestive of multiple sclerosis. Neuroimage Clin. 2021;29:102542. [PubMed] [DOI] [Cited in This Article: ] [Cited by in Crossref: 4] [Cited by in F6Publishing: 4] [Article Influence: 1.0] [Reference Citation Analysis (0)] |
9. | Janssen I, Sollmann N, Barz M, Baum T, Schaller K, Zimmer C, Ryang YM, Kirschke JS, Meyer B. Occult Disco-Ligamentous Lesions of the Subaxial c-Spine-A Comparison of Preoperative Imaging Findings and Intraoperative Site Inspection. Diagnostics (Basel). 2021;11. [PubMed] [DOI] [Cited in This Article: ] [Cited by in Crossref: 6] [Cited by in F6Publishing: 6] [Article Influence: 2.0] [Reference Citation Analysis (0)] |
10. | Liu N, Liu B. Research on knee sports injury classification based on medical images and Kwon3D software. Rev Bras Med Esporte. 2021;27:456-459. [DOI] [Cited in This Article: ] [Reference Citation Analysis (0)] |
11. | Lv Y, Song Y, Wei YG, Wen RQ, Li L. The Value of CT and MRI in the Diagnosis and Classification of Tibial Plateau Fracture and Its Effect on Clinical Effect. Acta Microsc. 2020;29:1557 Available from: https://openurl.ebsco.com/EPDB%3Agcd%3A14%3A6553982/detailv2?sid=ebsco%3Aplink%3Ascholar&id=ebsco%3Agcd%3A143422100&crl=f. [Cited in This Article: ] |
12. | Mu S, Lu W, Yu G, Zheng L, Qiu J. Deep learning-based grading of white matter hyperintensities enables identification of potential markers in multi-sequence MRI data. Comput Methods Programs Biomed. 2024;243:107904. [PubMed] [DOI] [Cited in This Article: ] [Reference Citation Analysis (0)] |
13. | Pan S, Zhao Y, Wu S. Imaging Examination Techniques. Radiol Infect Inflam Dis. 2022;5:3-22. [DOI] [Cited in This Article: ] |
14. | Rahimpour M, Bertels J, Radwan A, Vandermeulen H, Sunaert S, Vandermeulen D, Maes F, Goffin K, Koole M. Cross-Modal Distillation to Improve MRI-Based Brain Tumor Segmentation With Missing MRI Sequences. IEEE Trans Biomed Eng. 2022;69:2153-2164. [PubMed] [DOI] [Cited in This Article: ] [Cited by in Crossref: 2] [Cited by in F6Publishing: 7] [Article Influence: 2.3] [Reference Citation Analysis (0)] |
15. | Shao J, Zhang Y. Cartilage and Osteochondral Injury. Differ Diag Fract. 2021;. [DOI] [Cited in This Article: ] |
16. | Tang L, Zhang Z, Yang J, Feng Y, Sun S, Liu B, Ma J, Liu J, Shao H. A New Automated Prognostic Prediction Method Based on Multi-Sequence Magnetic Resonance Imaging for Hepatic Resection of Colorectal Cancer Liver Metastases. IEEE J Biomed Health Inform. 2024;28:1528-1539. [PubMed] [DOI] [Cited in This Article: ] [Reference Citation Analysis (0)] |
17. | Wang B, Wang L, Wang Y, Qin F. Clinical Diagnostic Value of Magnetic Resonance Imaging in Knee Joint Sports Injury. j Med Imaging Hlth Inform. 2021;11:453-461. [DOI] [Cited in This Article: ] [Cited by in Crossref: 3] [Cited by in F6Publishing: 3] [Article Influence: 1.0] [Reference Citation Analysis (0)] |
18. | Wang KN, Yang X, Miao J, Li L, Yao J, Zhou P, Xue W, Zhou GQ, Zhuang X, Ni D. AWSnet: An auto-weighted supervision attention network for myocardial scar and edema segmentation in multi-sequence cardiac magnetic resonance images. Med Image Anal. 2022;77:102362. [PubMed] [DOI] [Cited in This Article: ] [Cited by in Crossref: 1] [Reference Citation Analysis (0)] |
19. | Wang T, Wang H, Deng J, Zhang D, Feng J, Chen B. Feature generation and multi-sequence fusion based deep convolutional network for breast tumor diagnosis with missing MR sequences. Biom Signal Process Control. 2023;82:104536. [DOI] [Cited in This Article: ] [Reference Citation Analysis (0)] |
20. |
Zhuang CJ, Chen WZ, Zhang WX, Jiang XM.
Clinical application of magnetic resonance imaging (MRI) in the reconstruction of anterior cruciate ligament tears in the knee joint. Int J Clin Exp Med 2020; |