Computer-aided diagnosis system for the classification of multi-class kidney abnormalities in the noisy ultrasound images

•A computer-aided diagnosis (CAD) system for the classification of kidney ultrasound images in the noisy environment is proposed.•The presented CAD system consists of despeckling and classification module, which will be useful in noise reduction and precise classification.•The noisy ultrasound images are despeckled using deep RLN which helps to drastically improve the performance of the CAD system in the classification process.•The proposed approach resulted in maximum classification accuracy in testing with the noisy ultrasound images when compared to the state-of-the-art approaches.•The presented CAD system will also reduce the burden of experienced radiologists and nephrologists in their diagnostic procedures Background and Objective: The primary causes of kidney failure are chronic and polycystic kidney diseases. Cyst, stone, and tumor development lead to chronic kidney diseases that commonly impair kidney functions. The kidney diseases are asymptomatic and do not show any significant symptoms at its initial stage. Therefore, diagnosing the kidney diseases at their earlier stage is required to prevent the loss of kidney function and kidney failure. Methods: This paper proposes a computer-aided diagnosis (CAD) system for detecting multi-class kidney abnormalities from ultrasound images. The presented CAD system uses a pre-trained ResNet-101 model for extracting the features and support vector machine (SVM) classifier for the classification purpose. Ultrasound images usually gets affected by speckle noise that degrades the image quality and performance of the CAD system. Hence, it is necessary to remove speckle noise from the ultrasound images. Therefore, a CAD based system is proposed with the despeckling module using a deep residual learning network (RLN) to reduce speckle noise. Pre-processing of ultrasound images using deep RLN helps to drastically improve the classification performance of the CAD system. The proposed CAD system achieved better prediction results when compared to the existing state-of-the-art methods. Results: To validate the proposed CAD system performance, the experiments have been carried out in the noisy kidney ultrasound images. The designed system framework achieved the maximum classification accuracy when compared to the existing approaches. The SVM classifier is selected for the CAD system based on performance comparison with various classifiers like K-nearest neighbour, tree, discriminant, Naive Bayes, and linear. Conclusion