Object Detection for Healthcare Data Using Deep Convolutional Neural Networks

Gallstone disease is a prevalent chronic condition impacting individuals worldwide, posing significant challenges to healthcare systems globally. It ranks among the most common ailments encountered by individuals seeking emergency care due to abdominal discomfort. The complexity of gallbladder ultrasound scans arises from numerous factors, including variations in gallbladder anatomy. In this study, we propose a healthcare informatics system aimed at identifying and analyzing gallstones. We conduct a thorough examination of several state-of-the-art object detection algorithms, including Faster Region-based Convolutional Neural Network (Faster RCNN), Mask Region-based Convolutional Neural Network (Mask R-CNN), and Single Shot Detector (SSD) Our approach, which combines elements of Mask R-CNN, SSD, and Faster R-CNN, facilitates the precise detection of gallstones within the gallbladder by leveraging region-based proposals. We specifically focus on training the Mask RCNN model with various backbone networks. Ultrasound images utilized in our experiments were sourced from medical professionals, encompassing diverse demographic characteristics such as gender, age, and urban/rural residence. Our findings demonstrate that the Mask R-CNN model, with a Resnet-101-FPN backbone network, excels in gallstone detection, surpassing alternative techniques in object localization accuracy.