An Artificial Intelligence-Based System for Identifying Ureteral Stricture Regions

This paper proposes a technical system designed to accurately identify the stenotic site in patients with ureteral stricture and guide the surgeon. The objective of this technical solution is to improve surgical efficiency.

The proposed system applies the YOLOv5 algorithm, an artificial intelligence technology, to analyze real-time input images, detect the location of stenosis with high precision, and provide clinical support. The YOLOv5 algorithm was selected to enable rapid and accurate detection of the stenotic area.

The system demonstrated high recognition accuracy, yielding an average final sensitivity of 0.95. Because sensitivity reflects the probability of a true positive result, this finding confirms that the proposed method offered precise guidance for identifying the stenotic site.

The proposed method, which utilizes the YOLOv5 algorithm, can support surgery for patients with ureteral stricture. This system assists surgical procedures by accurately detecting strictures through real-time image analysis. Future research aims to provide both conservative and flexible boundary estimates for determining the stricture location.