Deep Learning-Assisted Ultrasonic Diagnosis and Localization of Testicular Appendix Torsion: A Multicenter Retrospective Validation Study
试验速览
- 阶段
- 不适用
- 状态
- 尚未招募
- 发起方
- 入组人数
- 2,000
- 试验地点
- 1
- 主要终点
- Accuracy of deep-learning model verify four conditions:testicular appendage torsion;testicular torsion;epididymitis and normal condition
研究概览
简要总结
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.
详细描述
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.
研究设计
- 研究类型
- Observational
- 观察模型
- Cohort
- 时间视角
- Other
入排标准
- 年龄范围
- 1 Minute 至 18 Years（Child, Adult）
- 性别
- Male
- 接受健康志愿者
- 是
入选标准
- •Age ≤ 18 years old
- •Underwent ultrasound examination due to acute scrotal pain (≤ 24 hours)
- •Patients clinically diagnosed with testicular appendage torsion (TAT)
排除标准
- •Poor ultrasound image quality (failure to identify testicular structures)
- •Incomplete clinical data (failure to confirm the diagnosis of testicular appendage torsion [TAT])
结局指标
主要结局
Accuracy of deep-learning model verify four conditions:testicular appendage torsion;testicular torsion;epididymitis and normal condition
时间窗: From image input to result generation is expected to be 24 hours
accuracy of deep-learning model verify four conditions:testicular appendage torsion;testicular torsion;epididymitis and normal condition
次要结局
- Number of Participants with Acute Scrotal Pain(From enrollment begin to the end is expected to be 5 months)
- The accuracy rate of clinicians in diagnosing and localizing testicular appendix torsion(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(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)
研究者
Ying Jiang
resident physician
The Children's Hospital of Zhejiang University School of Medicine