LoRIS - Weakly-Supervised Anomaly Detection for Ultrasound Images
LoRIS is a weakly-supervised anomaly detection method for knee ultrasound images. Trained only on nondistended cases, it uses a location prior to guide reconstruction and detect anomalies. It outperforms unsupervised methods and matches supervised ones—without needing segmentation annotations or images from both classes.
Oct 5, 2024
Ultrasound detection of subquadricipital recess distension
The paper proposes two approaches for automatically detecting joint bleeding in patients with hemophilia using ultrasound imaging. The experimental evaluation shows that the multi-task approach has higher accuracy, but with a slightly lower mean IoU value. The study suggests that computer-aided diagnosis tools can be useful for diagnosing joint bleeding in hemophilia patients.
Feb 1, 2023
GAJA - Guided self-Acquisition of Joint ultrAsound images
Feb 1, 2023
A Computer-Aided Diagnosis Tool for the Detection of Hemarthrosis By Remote Joint Ultrasound in Patients with Hemophilia
Nov 15, 2022