基于深度学习的三维超声先天性子宫异常智能诊断
Deep Learning-based Intelligent Diagnosis of Congenital Uterine Anomalies in 3D Ultrasound
- Medical Ultrasound Image Computing (MUSIC) Lab, Shenzhen University（深圳大学医学超声图像计算实验室）
- Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences（中国科学院香港创新研究院人工智能与机器人创新中心）
- Affiliated Hospital of Youjiang Medical College for Nationalities（右江民族医学院附属医院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出CUA-Net，一种基于3D ResNet-18的深度学习框架，无需冠状面重建即可自动分类先天性子宫异常，在内部和外部测试集上均取得高准确率，性能优于初级超声医师，与高级医师相当。
AI中文摘要：
目的：开发一种名为CUA-Net的智能框架，用于在无需冠状面重建的情况下对先天性子宫异常（CUA）进行自动分类，并评估其临床适用性。方法：CUA-Net基于3D ResNet-18构建，配备动态数据重采样策略以缓解数据不平衡问题，以及硬样本挖掘技术，通过损失调整充分学习困难病例。我们进一步提出了自监督重建以全面探索体数据，以及在线数据增强以修正错误预测并增强模型的泛化能力。我们在测试集中将CUA-Net与不同的深度学习方法以及初级/高级超声医师进行了比较。评估指标包括准确率、精确率、召回率、F1分数、micro-AUC和macro-AUC。结果：所提出的CUA-Net在内部和外部测试集中均表现出令人满意的性能。在内部队列中，模型达到了93.88%的准确率、87.01%的精确率、95.92%的召回率、88.09%的F1分数，以及0.9982的micro-AUC和0.9997的macro-AUC。在外部队列中，模型保持了良好性能，准确率为91.52%，精确率为83.27%，召回率为88.63%，F1分数为81.49%，micro-AUC为0.9945，macro-AUC为0.9990。我们的CUA-Net在所有性能指标上均优于初级超声医师，并在大多数指标上达到了与高级超声医师相当的性能。结论：CUA-Net在分类常见CUA类别方面表现出良好的准确性和泛化能力，同时在识别较少见异常方面显示出初步潜力。这些能力可能有助于优化临床工作流程并支持更标准化的诊断。
英文摘要：
Objective: To develop an intelligent framework, termed CUA-Net, for the automated classification of congenital uterine anomalies (CUA) without requiring coronal plane reconstruction, and to evaluate its clinical applicability. Methods: CUA-Net was built on 3D ResNet-18, equipped with a dynamic data resampling strategy to mitigate the data imbalance issue and a hard sample mining technique to fully learn from the difficult cases by loss adjustment. We further proposed the self-supervised reconstruction to comprehensively explore the volumes and the online data augmentation to refine the wrong predictions and enhance the model's generalization. We compared the CUA-Net with different deep-learning methods and junior/senior sonographers in the testing set. The evaluation metrics included accuracy, precision, recall, F1-score, micro-AUC, and macro-AUC. Results: The proposed CUA-Net exhibited satisfactory performance in both internal and external test sets. In the internal cohort, the model achieved accuracy of 93.88%, precision of 87.01%, recall of 95.92%, F1-score of 88.09%, and micro-AUC of 0.9982 and macro-AUC of 0.9997. In the external set, it maintained good performance with accuracy of 91.52%, precision of 83.27%, recall of 88.63%, F1-score of 81.49%, micro-AUC of 0.9945 and macro-AUC of 0.9990. Our CUA-Net outperformed the junior sonographers across all performance indicators and achieved performance comparable to that of the senior sonographers across most metrics. Conclusion: The CUA-Net demonstrates favorable accuracy and generalizability in classifying common CUA categories, while showing preliminary potential for recognizing less prevalent anomalies. These capabilities may help optimize clinical workflows and support more standardized diagnosis.
