Deep Learning-Assisted Ultrasonic Diagnosis and Localization of Testicular Appendix Torsion

Ying Jiang

Status: Not yet enrolling

Conditions: Testicular Appendix Torsion; Epididymitis; Testicular Torsion

Study type: Observational

Funder types: Other

Identifiers

NCT07301086

CHZhejiangjiangying

Details and patient eligibility

About

Ultrasound data were both retrospectively and prospectively 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, ConvNeXtV2 was used as the classification network and YOLOv12 was adopted as the detection network.The retrospective dataset from the primary center was split into training, validation, and test subsets, on which the model was trained, validated, and tested respectively; additional validation was conducted on both retrospective and prospective datasets from the primary center and sub-centers.Meanwhile, four physicians were assigned to interpret the ultrasound data from the retrospective and prospective datasets from the primary center and sub-centers using two diagnostic methods-independent diagnosis and artificial intelligence (AI)-assisted diagnosis-and the diagnostic accuracy of these two approaches was further compared.By collecting and learning the treatment methods of patients in the primary center training set, predicting the treatment methods of patients in the sub-center datasets, and comparing the proportion of surgeries predicted by AI with the actual proportion of surgeries, the efficacy of the model was verified.

Full description

Ultrasound data were both retrospectively and prospectively 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, ConvNeXtV2 was used as the classification network and YOLOv12 was adopted as the detection network.The retrospective dataset from the primary center was split into training, validation, and test subsets, on which the model was trained, validated, and tested respectively; additional validation was conducted on both retrospective and prospective datasets from the primary center and sub-centers.Meanwhile, four physicians were assigned to interpret the ultrasound data from the retrospective and prospective datasets from the primary center and sub-centers using two diagnostic methods-independent diagnosis and artificial intelligence (AI)-assisted diagnosis-and the diagnostic accuracy of these two approaches was further compared.By collecting and learning the treatment methods of patients in the primary center training set, predicting the treatment methods of patients in the sub-center datasets, and comparing the proportion of surgeries predicted by AI with the actual proportion of surgeries, the efficacy of the model was verified.

Enrollment: 2,000 estimated patients

Sex: Male

Ages: 1 minute to 18 years old

Volunteers: Accepts Healthy Volunteers

Inclusion criteria

1. Age ≤ 18 years old
2. Underwent ultrasound examination due to acute scrotal pain (≤ 24 hours)
3. Patients clinically diagnosed with testicular appendage torsion (TAT)

Exclusion criteria

1. Poor ultrasound image quality (failure to identify testicular structures)
2. Incomplete clinical data (failure to confirm the diagnosis of testicular appendage torsion [TAT])

Trial design

2,000 participants in 4 patient groups

Testicular Appendix Torsion Group

Description:

Patients diagnosed with testicular appendage torsion

Testicular Torsion Group

Description:

Patients diagnosed with testicular torsion

Epididymitis Group

Description:

Patients diagnosed with epididymitis

Normal Group

Description:

Patients with no testicular appendage torsion,testicular torsion,epididymitis,and the scrotum is normal