用合成数据实现心脏超声分割的无数据知识蒸馏，性能接近真实数据训练。
EchoDFKD: Data-Free Knowledge Distillation for Cardiac Ultrasound Segmentation using Synthetic Data
- 仅用合成数据通过知识蒸馏训练分割模型，无需真实标注数据。
- 在心室收缩末期和舒张末期帧识别上达到最新最好结果（SOTA）。
- 适合缺乏标注数据或需降低模型参数量的医疗图像分割场景。
基于大型公开数据集，机器学习在心脏超声视频（即超声心动图）中的应用日益广泛。传统监督任务如射血分数回归正逐步被关注数据分布潜在结构及生成方法的新范式取代。本文提出一种仅通过知识蒸馏训练的模型，可基于真实或合成数据，利用教师模型生成的掩码进行训练。在识别心室收缩末期与舒张末期帧的任务中，该方法达到当前最优（SOTA）表现。仅使用合成数据训练时，模型分割性能接近真实数据训练，且参数量显著减少。与5种主流方法对比，本方法在多数情况下表现更优。此外，我们提出一种新评估方法，不依赖人工标注，而是基于大型辅助模型进行评估，其得分与人工标注一致。该方法利用海量记录的集成知识，克服了人工标注固有的局限性。
原文摘要 · Abstract (English)
The application of machine learning to medical ultrasound videos of the heart, i.e., echocardiography, has recently gained traction with the availability of large public datasets. Traditional supervised tasks, such as ejection fraction regression, are now making way for approaches focusing more on the latent structure of data distributions, as well as generative methods. We propose a model trained exclusively by knowledge distillation, either on real or synthetical data, involving retrieving masks suggested by a teacher model. We achieve state-of-the-art (SOTA) values on the task of identifying end-diastolic and end-systolic frames. By training the model only on synthetic data, it reaches segmentation capabilities close to the performance when trained on real data with a significantly reduced number of weights. A comparison with the 5 main existing methods shows that our method outperforms the others in most cases. We also present a new evaluation method that does not require human annotation and instead relies on a large auxiliary model. We show that this method produces scores consistent with those obtained from human annotations. Relying on the integrated knowledge from a vast amount of records, this method overcomes certain inherent limitations of human annotator labeling. Code: https://github.com/GregoirePetit/EchoDFKD
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。