Journal
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2019, PT VI
Volume 11769, Issue -, Pages 13-21Publisher
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-030-32226-7_2
Keywords
Universal lesion detection; Multi-view; Position-aware; Attention
Categories
Funding
- National Natural Science Foundation of China [61876181, 61721004, 61403383, 61625201, 61527804]
- Projects of Chinese Academy of Sciences [QYZDB-SSW-JSC006, 173211KYSB20160008]
Ask authors/readers for more resources
Universal lesion detection (ULD) on computed tomography (CT) images is an important but underdeveloped problem. Recently, deep learning-based approaches have been proposed for ULD, aiming to learn representative features from annotated CT data. However, the hunger for data of deep learning models and the scarcity of medical annotation hinders these approaches to advance further. In this paper, we propose to incorporate domain knowledge in clinical practice into the model design of universal lesion detectors. Specifically, as radiologists tend to inspect multiple windows for an accurate diagnosis, we explicitly model this process and propose a multi-view feature pyramid network (FPN), where multi-view features are extracted from images rendered with varied window widths and window levels; to effectively combine this multi-view information, we further propose a position-aware attention module. With the proposed model design, the data-hunger problem is relieved as the learning task is made easier with the correctly induced clinical practice prior. We show promising results with the proposed model, achieving an absolute gain of 5.65% (in the sensitivity of FPs@4.0) over the previous state-of-the-art on the NIH DeepLesion dataset.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available