Ultrasound Detection of Subquadricipital Recess Distension

TL;DR

This study develops and compares two computer-aided ultrasound image analysis methods for detecting and assessing subquadricipital recess distension in hemophilia patients, aiming to improve diagnosis accuracy.

Contribution

It introduces two novel automated approaches for detecting and evaluating knee recess distension in ultrasound images, filling a gap in computer-aided diagnosis tools for hemophilia.

Findings

Object detection approach achieved 0.74 balanced accuracy and 0.66 mean IoU.

Multi-task approach achieved 0.78 balanced accuracy, slightly lower IoU.

Both methods show promise for supporting clinical diagnosis.

Abstract

Joint bleeding is a common condition for people with hemophilia and, if untreated, can result in hemophilic arthropathy. Ultrasound imaging has recently emerged as an effective tool to diagnose joint recess distension caused by joint bleeding. However, no computer-aided diagnosis tool exists to support the practitioner in the diagnosis process. This paper addresses the problem of automatically detecting the recess and assessing whether it is distended in knee ultrasound images collected in patients with hemophilia. After framing the problem, we propose two different approaches: the first one adopts a one-stage object detection algorithm, while the second one is a multi-task approach with a classification and a detection branch. The experimental evaluation, conducted with $483$ annotated images, shows that the solution based on object detection alone has a balanced accuracy score of $0.74$ with a mean IoU value of $0.66$, while the multi-task approach has a higher balanced accuracy value ($0.78$) at the cost of a slightly lower mean IoU value.