Comparative Analysis for the Distinction of Chromophobe Renal Cell Carcinoma from Renal Oncocytoma in Computed Tomography Imaging Using Machine Learning Radiomics Analysis

Abstract

Background: ChRCC and RO are two types of rarely occurring renal tumors that are difficult to distinguish from one another based on morphological features alone. They differ in prognosis, with ChRCC capable of progressing and metastasizing, but RO is benign. This means discrimination of the two tumors is of crucial importance. Objectives: The purpose of this research was to develop and comprehensively evaluate predictive models that can discriminate between ChRCC and RO tumors using Computed Tomography (CT) scans and ML-Radiomics texture analysis methods. Methods: Data were obtained from 78 pathologically confirmed renal masses, scanned at two institutions. Data from the two institutions were combined to form a third set resulting in three data cohorts, i.e., cohort 1, 2 and combined. Contrast-enhanced scans were used and the axial cross-sectional slices of each tumor were extracted from the 3D data using a semi-automatic segmentation technique for both 2D and 3D scans. Radiomics features were extracted before and after applying filters and the dimensions of the radiomic features reduced using the least absolute shrinkage and selection operator (LASSO) method. Synthetic minority oversampling technique (SMOTE) was applied to avoid class imbalance. Five ML algorithms were used to train models for predictive classification and evaluated using 5-fold cross-validation. Results: The number of selected features with good model performance was 20, 40 and 6 for cohorts 1, 2 and combined, respectively. The best model performance in cohorts 1, 2 and combined had an excellent Area Under the Curve (AUC) of 1.00 ± 0.000, 1.00 ± 0.000 and 0.87 ± 0.073, respectively. Conclusions: ML-based radiomics signatures are potentially useful for distinguishing ChRCC and RO tumors, with a reliable level of performance for both 2D and 3D scanning.

Characterisation of Intra-tumoural Subregions Heterogeneity and Tumour Grade Prediction using CT Scan Images: An In-depth Radiomics Features Machine Learning Analysis of Clear Cell Renal Cell Carcinoma

“…Moreover, the degree of association between clinical features and the outcome is affected by sample size i.e., statistical significance is likely to increase with increase in sample size [88]. This is clearly portrayed in previous research by Alhussaini et al [48]. Even in our own research cohort 4 data despite being from the same population as cohort 1 data, the age, tumour size, tumour volume and gender are not statistically significant indicating that the sample size might be the likely cause.…”

“…In a previous study [48] it had been shown that a combination of the original feature classes and filter features improved model performance significantly. We therefore extracted the filter classes features in addition to the original features.…”

“…Radiomics eliminates the subjectivity in the extraction of tumour features from medical images as it works as an objective virtual biopsy [47]. There are quite a number of studies that have applied radiomics in the classification of tumour subtypes, grading and even the staging of tumours [48,49].…”

“…Similar to our previous research [48], texture descriptors of the features were computed using the PyRadiomics module in python 3.6. 1.…”

Comprehensive Study on Mineral Processing Methods and Mineral Technical Economics of Manganese Ore in Chongqing Chengkou

“…The presence of noise in the image leads to difficulties in subsequent image processing steps. In general, a filtering process must be applied to the input image to minimize noise and improve image quality . In this experiment, a nonlocal mean filter is used to denoise the original image.…”