Computer vision assisted deep transfer learning model for accurate grading of renal cell carcinoma from kidney histopathology images

Abstract

Renal cell carcinomas (RCCs) are the seventh most widespread histological cancer. Around 40% of patients die in RCC due to the disease development. Thus, this tumour is the most lethal malignant urological tumour. The histopathologic classification of RCC is vital for the prognosis, diagnosis, and patient management. Classification and detection of intricate RCC histologic patterns on surgical and biopsy surgery slides under a microscope endures a comprehensively specified, time-consuming task and error-prone for pathologists. A wholly automatic and accurate technique of grading kidney tumours from histopathology images (HIs) is in great demand for recognizing harmful cancers. The correct classification of RCC stage and grade is vital for managing medical management, prognosis, and molecular-based treatments. Many preceding works concentrate on machine learning (ML) and deep learning (DL) methods for the RCC classification. The application of DL to study the histopathological images of kidneys, breasts, etc., and other organs contains several tasks like classification of cancer subtypes and grading. This study presents a Computer Vision Assisted Deep Transfer Learning Model for the Accurate Grading of the RCC (CVDTLM-AGRCC) technique. The CVDTLM-AGRCC technique enables the detection and classification of RCC from kidney histopathology images. Initially, the CVDTLM-AGRCC technique applies the image pre-processing stage using a Gaussian filter (GF) to prevent and eliminate the noise. Furthermore, the fusion of ShuffeNetV2-1.0-SE and CapsNet models is employed for the feature extraction. Moreover, the CVDTLM-AGRCC method uses a hybrid of convolutional neural networks and bidirectional long short-term memory (CNN-BiLSTM) techniques for the RCC classification. Finally, the crayfish optimization algorithm (COA) is used for the hyperparameter tuning of the CNN-BiLSTM method. The efficiency of the CVDTLM-AGRCC approach is examined under the KMC dataset. The comparison study of the CVDTLM-AGRCC approach portrayed a superior accuracy value of 93.89% over existing techniques.

Ähnliche Arbeiten