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.
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.
Study Type
OBSERVATIONAL
Enrollment
2,000
Children's Hospital of Zhejiang University School of Medicine
Hangzhou, Zhejiang, China
Accuracy of deep-learning model verify four conditions:testicular appendage torsion;testicular torsion;epididymitis and normal condition
accuracy of deep-learning model verify four conditions:testicular appendage torsion;testicular torsion;epididymitis and normal condition
Time frame: From image input to result generation is expected to be 24 hours
Number of Participants with Acute Scrotal Pain
Time frame: From enrollment begin to the end is expected to be 5 months
The accuracy rate of clinicians in diagnosing and localizing testicular appendix torsion
Time frame: From the begin of Clinicians diagnose and locate to the end is expected to be 15 days
The accuracy rate of the Deep learning model in predicting the treatment modality for testicular appendix torsion,conservative treatment or surgery
Time frame: From the begin of the prediction of treatment for testicular appendix torsion by Deep learning model to the end is expected to be 24 hours
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.