Differentiation of renal angiomyolipoma without visible fat from renal cell carcinoma by machine learning based on whole-tumor computed tomography texture features

Abstract

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.

Radiomics Applications in Renal Tumor Assessment: A Comprehensive Review of the Literature

“…However, up to 5% of AMLs lack macroscopic fat, a condition known as AML without visible fat (AMLwvf), making it challenging to differentiate them from RCC by conventional imaging [36]. Several studies described certain imaging features that are highly suggestive of AMLwvf and analyzed them with radiomics models [20][21][22][23]25,26].…”

“…Other investigations employed similar strategies, although with ML-based TA from CECT images, and they reported higher accuracy (93.9%) and AUC (0.955) [21,24]. Moreover, Cui et al proposed an automatic computer identification system to differentiate AMLwvf from all RCC subtypes from whole-tumor CECT images using an over-sampling technique to increase the sample volume of AMLwvf [23]. They showed that morphological interpretation by radiologists achieved overall lower performance differentiating AMLwvf from all RCC subtypes.…”

Automated Ischemic Stroke Subtyping Based on Machine Learning Approach

“…Even if data preprocessing was carried out with standardization, normalization, and et al, the classifiers, such as linear SVC, Multinomial-Naïve-Bayes and AdaBoost didn't perform better. The RFECV method worked well in other fields, such as image processing, financial data analyzing, and was already used in medical research [25,26]. The classifiers used in the study; except ExtraTrees, RandomForest and the simple deep learning model, didn't work well (with highest accuracy of 0.815) to subtype ischemic stroke (IS) with 8 neurological deficits.…”

Development of a Deep Learning Algorithm for Segmentation of Kidney Tumor Imaging

“…First, it allows one to massively scale the process of kidney segmentation in cross-sectional imaging compared to manual segmentation, which is precursor to any analysis that requires segmented tumor volumes. [11,[20][21][22][23] Perhaps more importantly, it can serve as an important infrastructural component for methods that aim to predict clinical attributes, such as pathologic features, from cross-sectional imaging. [10] The present results represent foundational work for the more ambitious goal of developing deep learning methods to enhance clinical diagnosis from radiologic images.…”