DIAGNOSIS OF KIDNEY CYST, TUMOR AND STONE FROM CT SCAN IMAGESUSING FEATURE FUSION HYPERGRAPH CONVOLUTIONAL NEURAL NETWORK (F2HCN2)

The development of a computational tool to diagnose kidney disorders in their early stages is necessary due to the rise in chronic kidney diseases (CKDs) and the global shortage of nephrologists. The three common renal disorders covered in this study are kidney stones, cysts, and tumors. Early diagnosis of these diseases from the computed tomography (CT) images is a challenging task. Yet, present graph convolutional neural network (GCNN) approaches have the issue of overdependence on the adjacency matrix. Moreover, compared to deep convolutional neural network (CNN) models, a single modal feature results in low accuracy and robustness. In this paper, we proposed the feature fusion hypergraph CNN (F²HCN²) to accurately diagnose kidney diseases in the early stage based on CT scan images. The discriminative features of the images are extracted using DarkNet19 and residual features are extracted using ResNet50. The extracted features are classified using feature fusion hypergraph CNN. The proposed model is trained with 12,446 CT whole urogram and abdomen images. The hypergraph representation learning is performed to train the network with the fused features. Deep learning metrics including accuracy, F1 score (F1), recall, positive predictive value (PPV), receiver operating characteristic curve, and area under curve (AUC) are used to validate the proposed model. It outperforms compared to other state-of-the-art algorithms with accuracy of 99.71%. The proposed F²HCN² is a robust computer-aided tool for the early diagnosis of kidney diseases. It will assist the radiologist for better prognosis for kidney related abnormalities.