Medical Ultrasound, and Preterm, Perinatal and Paediatric Image Analysis - First International Workshop, ASMUS 2020, and 5th International Workshop, PIPPI 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 4-8, 2020, Proceedings
Medical Ultrasound, and Preterm, Perinatal and Paediatric Image Analysis - First International Workshop, ASMUS 2020, and 5th International Workshop, PIPPI 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 4-8, 2020, Proceedings
复制标题
医学超声、早产儿、围产期和儿科图像分析 - 第一届国际研讨会，ASMUS 2020，第五届国际研讨会，PIPPI 2020，与 MICCAI 2020 同期举行，秘鲁利马，2020 年 10 月 4-8 日，会议记录
DOI：
10.1007/978-3-030-60334-2_5
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Chen Q
中科院分区：
文献类型：
--
作者：
Chen Q
领域自适应是当前医学图像分析研究的一个活跃领域。本文提出了一种跨设备、跨解剖的胎儿超声视频自动标注网络(CCAN)。在我们的方法中，深度学习模型针对从高端超声机获得的更广泛可用的专家获取和手动标记的徒手超声视频进行训练，以适应使用简化的扫描协议收集有限的和未标记的超声视频的特定场景，该协议适用于使用低成本探头的经验较少的用户。这种无监督的域自适应问题很有趣，因为在数据集之间存在两个域变化：(1)由于使用不同的换能器而导致的跨设备图像外观变化；以及(2)交叉解剖变化，因为简化的扫描协议不一定包含在典型的徒手扫描视频中看到的标准视图。通过引入一种新的结构感知对抗性训练模块来学习跨设备变异，以及一种新的选择性适应模块来适应跨解剖变异域转移。从高端机器临床视频和专家标签的数据集学习，我们在使用非专家和低成本超声探头协议获取的未标记扫描数据上验证了所提出的方法在解剖分类中的有效性。实验结果表明，在仅学习和减少设备间差异的情况下，CCan的平均识别准确率分别比未采用领域自适应的方法和现有的自适应方法分别提高了20.8%和10.0%。当跨设备和跨解剖的差异都减小时，CCAN的平均识别准确率比这些其他最先进的自适应方法提高了20%，具有统计学意义。
Domain adaptation is an active area of current medical image analysis research. In this paper, we present a cross-device and cross-anatomy adaptation network (CCAN) for automatically annotating fetal anomaly ultrasound video. In our approach, deep learning models trained on more widely available expert-acquired and manually-labeled free-hand ultrasound video from a high-end ultrasound machine are adapted to a particular scenario where limited and unlabeled ultrasound videos are collected using a simplified sweep protocol suitable for less-experienced users with a low-cost probe. This unsupervised domain adaptation problem is interesting as there are two domain variations between the datasets: (1) cross-device image appearance variation due to using different transducers; and (2) cross-anatomy variation because the simplified scanning protocol does not necessarily contain standard views seen in typical free-hand scanning video. By introducing a novel structure-aware adversarial training module to learn the cross-device variation, together with a novel selective adaptation module to accommodate cross-anatomy variation domain transfer is achieved. Learning from a dataset of high-end machine clinical video and expert labels, we demonstrate the efficacy of the proposed method in anatomy classification on the unlabeled sweep data acquired using the non-expert and low-cost ultrasound probe protocol. Experimental results show that, when cross-device variations are learned and reduced only, CCAN significantly improves the mean recognition accuracy by 20.8% and 10.0%, compared to a method without domain adaptation and a state-of-the-art adaptation method, respectively. When both the cross-device and cross-anatomy variations are reduced, CCAN improves the mean recognition accuracy by a statistically significant 20% compared with these other state-of-the-art adaptation methods .