Patra Arijit, Cai Yifan, Chatelain Pierre, Sharma Harshita, Drukker Lior, Papageorghiou Aris, Noble J Alison
University of Oxford, Oxford OX3 7DQ, United Kingdom.
Med Image Comput Comput Assist Interv. 2019;22(Pt 4):394-402. doi: 10.1007/978-3-030-32251-9_43. Epub 2019 Oct 10.
Recent automated medical image analysis methods have attained state-of-the-art performance but have relied on memory and compute-intensive deep learning models. Reducing model size without significant loss in performance metrics is crucial for time and memory-efficient automated image-based decision-making. Traditional deep learning based image analysis only uses expert knowledge in the form of manual annotations. Recently, there has been interest in introducing other forms of expert knowledge into deep learning architecture design. This is the approach considered in the paper where we propose to combine ultrasound video with point-of-gaze tracked for expert sonographers as they scan to train memory-efficient ultrasound image analysis models. Specifically we develop teacher-student knowledge transfer models for the exemplar task of frame classification for the fetal abdomen, head, and femur. The best performing memory-efficient models attain performance within 5% of conventional models that are 1000× larger in size.
最近的自动化医学图像分析方法已经达到了先进水平，但依赖于内存和计算密集型的深度学习模型。在不显著损失性能指标的情况下减小模型大小，对于基于图像的高效时间和内存自动化决策至关重要。传统的基于深度学习的图像分析仅以手动标注的形式使用专家知识。最近，人们对将其他形式的专家知识引入深度学习架构设计产生了兴趣。本文考虑的就是这种方法，我们建议将超声视频与专家超声医师扫描时的注视点跟踪相结合，以训练内存高效的超声图像分析模型。具体而言，我们针对胎儿腹部、头部和股骨的帧分类示例任务开发了师生知识转移模型。性能最佳的内存高效模型所达到的性能，与大小为其1000倍的传统模型相差不到5%。
