Journal
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
Volume 25, Issue 1, Pages 121-130Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JBHI.2020.2986926
Keywords
Image segmentation; Semantics; Feature extraction; Task analysis; Medical diagnostic imaging; Standards; Convolutional neural networks; deep learning; medical image segmentation; deep attention; self-attention
Categories
Funding
- ETS Montreal
Ask authors/readers for more resources
This paper introduces a new architecture that improves the accuracy and reliability of medical image segmentation by capturing richer contextual dependencies through guided self-attention mechanisms. Compared to other state-of-the-art models, our model demonstrates better segmentation performance, showcasing the effectiveness of our approach.
Even though convolutional neural networks (CNNs) are driving progress in medical image segmentation, standard models still have some drawbacks. First, the use of multi-scale approaches, i.e., encoder-decoder architectures, leads to a redundant use of information, where similar low-level features are extracted multiple times at multiple scales. Second, long-range feature dependencies are not efficiently modeled, resulting in non-optimal discriminative feature representations associated with each semantic class. In this paper we attempt to overcome these limitations with the proposed architecture, by capturing richer contextual dependencies based on the use of guided self-attention mechanisms. This approach is able to integrate local features with their corresponding global dependencies, as well as highlight interdependent channel maps in an adaptive manner. Further, the additional loss between different modules guides the attention mechanisms to neglect irrelevant information and focus on more discriminant regions of the image by emphasizing relevant feature associations. We evaluate the proposed model in the context of semantic segmentation on three different datasets: abdominal organs, cardiovascular structures and brain tumors. A series of ablation experiments support the importance of these attention modules in the proposed architecture. In addition, compared to other state-of-the-art segmentation networks our model yields better segmentation performance, increasing the accuracy of the predictions while reducing the standard deviation. This demonstrates the efficiency of our approach to generate precise and reliable automatic segmentations of medical images. Our code is made publicly available at: https://github.com/sinAshish/Multi-Scale-Attention .
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