2019/02/24 by En-Ming Cui, Enming Cui, Fan Lin +9 · 59 citations
Medicine · #Angiomyolipoma #Artificial intelligence #Computed tomography #Image (mathematics) #Internal medicine #Kidney #MRI in cancer diagnosis #Medicine #Pathology #Radiology #Radiomics and Machine Learning in Medical Imaging #Renal cell carcinoma #Renal cell carcinoma treatment #Texture (cosmology) #Tomography
paper · doi:10.1177/0284185119830282
published in Acta Radiologica 60(11), 1543-1552 (SAGE Publishing)
crossref issued 2019/02/24 · crossref published 2019/02/24 · crossref published-online 2019/02/24 · openalex publication_date 2019/02/24 · crossref created 2019/02/25 · crossref published-print 2019/11/01 · openalex created_date 2025/10/10 · crossref deposited 2026/04/28 · crossref indexed 2026/08/03 · openalex updated_date 2026/08/04
Background Morphological findings showed poor accuracy in differentiating angiomyolipoma without visible fat (AMLwvf) from renal cell carcinoma (RCC). Purpose To determine the performance of a machine learning classifier in differentiating AMLwvf from different subtypes of RCC based on whole-tumor slices of CT images. Material and Methods In this retrospective study, 171 pathologically proven renal masses were collected from a single institution. Texture features were extracted from whole-tumor images in three phases including the pre-contrast (PCP), corticomedullary (CMP), and nephrographic (NP) phases. A support vector machine with the recursive feature elimination method based on fivefold cross-validation (SVM-RFECV) with the synthetic minority oversampling technique (SMOTE) was utilized to establish classifiers for differentiating AMLwvf from all subtypes of RCC (all-RCC), clear cell RCC (ccRCC), and non-ccRCC. The performances of the classifiers based on three-phase and single-phase images were compared with each other and morphological interpretations. Results A machine learning classifier achieved the best performance in differentiating AMLwvf from all-RCC, ccRCC, and non-ccRCC. The performance of the best machine learning classifier for differentiating AMLwvf from all-RCC (area under the curve [AUC] = 0.96) and ccRCC (AUC = 0.97) was higher than that for differentiating AMLwvf from non-ccRCC (AUC = 0.89); morphological interpretations achieved lower performance for differentiating AMLwvf from all-RCC (AUC = 0.67), ccRCC (AUC = 0.68), and non-ccRCC (AUC = 0.64). Conclusion Machine learning can be a useful non-invasive technique for differentiating AMLwvf from all-RCC, ccRCC, and non-ccRCC, and it can be more accurate than morphological interpretation by radiologists.