Analysis of Kidney Ultrasound Images Using Deep Learning and Machine Learning Techniques: A Review

Abstract

AbstractUltrasonography is the most accepted and widely used imaging technique due to its non-invasive and radiation-free nature. The heterogeneous structure of kidney makes the disease detection a difficult task. Hence, more efficient models and methods are required to assist radiologists in making precise decisions. Since ultrasound imaging is considered to be the initial step in the diagnosis, more efficient processing techniques are needed in the interpretation of images. The presence of speckle noise is a challenge task in image processing. It diminishes the clarity of the images. In this article, an in-depth review has been performed on various machine learning and deep learning techniques, which are helping to improve the quality of images. The pre-processing, segmentation, feature extraction, and classification are described in detail using kidney cyst, stone, tumor, and normal kidney images. Deep learning techniques are enhancing the quality of the images with better accuracy. The remaining challenges and directions for future research are also explored.KeywordsDeep learningImage processingMachine learningUltrasound (US)Kidney ultrasound imagesSegmentationClassificationNoise removal