Cross-device cross-anatomy adaptation network for ultrasound video analysis

Conference item

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.

Authors: Chen, Q; Liu, Y; Hu, Y; Self, A; Papageorghiou, A

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Springer
• Host title: Medical Ultrasound, and Preterm, Perinatal and Paediatric Image Analysis
• Pages: 42-51
• Series: Lecture Notes in Computer Science
• Series number: 12437
• Publication date: 2020-10-01
• Acceptance date: 2020-07-28
• Event title: ASMUS: International Workshop on Advances in Simplifying Medical Ultrasound 2020
• Event location: Lima, Peru
• Event website: https://sites.google.com/view/asmus2020
• Event start date: 2020-10-04
• Event end date: 2020-10-04
• DOI: 10.1007/978-3-030-60334-2_5
• EISSN: 1611-3349
• ISSN: 0302-9743
• EISBN: 9783030603342
• ISBN: 9783030603335
• Language: English
• Keywords: FFR