الفهرس | Only 14 pages are availabe for public view |
Abstract Early assessment of renal cell carcinoma (RCC) is essential to provide the proper management plan. Biopsy remains the gold standard, however, it is unfavorable due its invasiveness, high cost, and adverse events such as bleeding and infection, and it takes around a week for reporting. To account for these limitations, we develop a two-stage classification computer aided diagnostic (CAD) system that has the ability to differentiate benign from malignant renal tumors and classify its sub-types using contrast-enhanced computed tomography (CE-CT). Our study includes renal tumors obtained from 79 biopsy-proven cases of which 70 were diagnosed as malignant tumors (clear cell RCC (ccRCC) = 40 and non-clear cell RCC (nccRCC) = 30) and nine were diagnosed as benign tumors (angiomyolipoma (AML) = 9). The proposed renal cancer CAD (RC-CAD) system mainly consists of three steps: (i) preprocessing of grey images to obtain 3D segmented renal tumor objects; (ii) extracting different discriminating features, namely; texture features, shape features, and functional features from segmented renal tumor objects; and (iii) obtaining the final diagnosis of the renal tumor by applying a two-stage classification process using different machine learning classifiers. In the first stage, the classification performance of the RC-CAD system was evaluated using the individual aforementioned features along with a random forest machine learning classifier. Then, a majority voting criteria was applied on the output class-membership to determine if the renal tumor is benign (AML) or malignant (RCC). |