U.S., Dec. 25 -- ClinicalTrials.gov registry received information related to the study (NCT07301086) titled 'Deep Learning-Assisted Ultrasonic Diagnosis and Localization of Testicular Appendix Torsion' on Dec. 09.
Brief Summary: Ultrasound data were retrospectively collected from the primary center and six other sub-centers. Combined with clinical diagnostic outcomes, the data labeling was completed by physicians with extensive clinical experience.
In this study, YOLOv11 was adopted as the detection network, which was integrated with the convolutional attention mechanism (Spatial Convolutional Block Attention Module, namely Spatial CBAM) and the self-attention mechanism (e.g., Attention Convolution Mixer, ACMix). The dataset from the prim...