KUB-UNet: Segmentation of Organs of Urinary System from a KUB X-ray Image

Purpose: The alarming increase in diseases of urinary system is a cause of concern for the populace and health experts. The traditional techniques used for the diagnosis of these diseases are inconvenient for patients, require high cost, and additional waiting time for generating the reports. The objective of this research is to utilize the proven potential of Artificial Intelligence for organ segmentation. Correct identification and segmentation of the region of interest in a medical image are important to enhance the accuracy of disease diagnosis. Also, it improves the reliability of the system by ensuring the extraction of features only from the region of interest. Method: A lot of research works are proposed in the literature for the segmentation of organs using MRI, CT scans, and ultrasound images. But, the segmentation of kidneys, ureters, and bladder from KUB X-ray images is found under explored. Also, there is a lack of validated datasets comprising KUB X-ray images. These challenges motivated the authors to tie up with the team of radiologists and gather the anonymous and validated dataset that can be used to automate the diagnosis of diseases of the urinary system. Further, they proposed a KUB-UNet model for semantic segmentation of the urinary system. Results: The proposed KUB-UNet model reported the highest accuracy of 99.18% for segmentation of organs of urinary system. Conclusion: The comparative analysis of its performance with state-of-the-art models and validation of results by radiology experts prove its reliability, robustness, and supremacy. This segmentation phase may prove useful in extracting the features only from the region of interest and improve the accuracy diagnosis. (c) 2022 Elsevier B.V. All rights reserved.

Automated summary

The increase in diseases of urinary system is a cause of concern. This research utilizes Artificial Intelligence for organ segmentation to enhance disease diagnosis. The authors collaborated with radiologists to gather a validated dataset and proposed a KUB-UNet model for semantic segmentation of the urinary system. The model demonstrates superior performance and reliability.