Review
Copyright ©The Author(s) 2023.
Artif Intell Gastroenterol. Dec 8, 2023; 4(3): 48-63
Published online Dec 8, 2023. doi: 10.35712/aig.v4.i3.48
Table 1 Studies on differentiation of indeterminate lesions using artificial intelligence
No.
Ref.
Number of patients
Organ of interest
Sub-type of AI
Outcome
1Ippolito et al[12], 2004453Thyroid nodule (benign vs malignant)ANNRefinement of risk stratification of FNAB and clinical data
2Daniels et al[13], 2020121Indeterminant thyroid noduleMLML and ultrasonography can identify genetically high risk lesions
3Becker et al[14], 2018632Breast lesion (benign vs malignant)Generic DLSAids diagnosing cancer on breast ultrasound images with an accuracy comparable to radiologists
4Scott et al[15], 2019125Lung GGO (benign vs malignant)ANNImprove diagnostic ability using CT scan, PET, and clinical data
5Guo et al[16], 202220Indeterminant small lung lesionsDNNDNN based method may detect small lesions < 10 mm at an effective radiation dose < 0.1 mSv.
6Yasaka et al[17], 2018460Liver mass (HCC vs others)CNNHigh diagnostic performance in differentiation of liver masses using dynamic CT
7Moawad et al[18], 202140Adrenal incidentaloma (benign vs malignant)MLMachine learning and CT texture analysis can differentiate between benign and malignant indeterminate adrenal tumors
8Stanzione et al[19], 202155Indeterminant solid adrenal lesionsMLMRI handcrafted radiomics and ML can be used to different adrenal incidentalomas
9Massa'a et al[20], 2022160Indeterminant solid renal mass (benign vs malignant)MLMRI-based radiomics and ML can be useful in differentiation
10Saraiva et al[21], 202285Indeterminant biliary stricturesCNNCNN can accurately differentiate benign strictures from malignant ones