Show abstract - Show schedule - Proceedings - PDF - Reviews

In clinical practice, regions of interest in medical imaging (MI) often need to be identified through a process of precise image segmentation. For MI segmentation to generalize, we need two components: to identify continuous and local descriptions, but at the same time to develop a holistic representation of the image that captures long-range spatial dependencies. Unfortunately, we demonstrate that the start of the art does not achieve the latter. In particular, it does not provide a modeling that yields a global, contextual model. To improve accuracy, and enable holistic modeling, we introduce a novel deep neural network architecture endowed with spatial recurrence. The implementation relies on gated recurrent units that directionally traverse the feature map, greatly increasing each layers receptive field and explicitly modeling non-adjacent, contextual relationships between pixels. Our method is evaluated in four different segmentations tasks: nuclei segmentation in microscopy images, colorectal polyp segmentation in colonoscopy videos, liver segmentation in abdominal CT scans, and aorta artery segmentation in thoracic CT scans. Our experiments demonstrate an average increase in performance of 4.72 Dice points and 0.68 Hausdorff distance units when compared with commonly used architectures.
Hide abstract

Wednesday 6th July
Poster Session 1.1 - onsite 15:20 - 16:20, virtual 11:00 - 12:00 (UTC+2)
Hide schedule