U-Capkidnets++-: A Novel Hybrid Capsule Networks with Optimized Deep Feed Forward Networks for an Effective Classification of Kidney Tumours Using CT Kidney Images

Abstract

Chronic Kidney Diseases (CKD) has become one among the world wide health crisis and needs the associated efforts to prevent the complete organ damage. A considerable research effort has been put forward onto the effective seperation and classification of kidney tumors from the kidney CT Images. Emerging machine learning along with deep learning algorithms have waved the novel paths of tumor detections. But these methods are proved to be laborious and its success rate is purely depends on the previous experiences. To achieve the better classification and segmentation of tumors, this paper proposes the hybrid ensemble of visual capsule networks in U-NET deep learning architecture and w deep feed-forward extreme learning machines. The proposed framework incorporates the data-preprocessing powerful data augmentation, saliency tumor segmentation (STS) followed by the classification phase. Furthermore, classification levels are constructed based upon the feed forward extreme learning machines (FFELM) to enhance the effectiveness of the suggested model .The extensive experimentation has been conducted to evaluate the efficacy of the recommended structure and matched with the other prevailing hybrid deep learning model. Experimentation demonstrates that the suggested model has showed the superior predominance over the other models and exhibited DICE co-efficient of kidney tumors as high as 0.96 and accuracy of 97.5 %respectively.