Journal
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
Volume 34, Issue 9, Pages 7283-7299Publisher
ELSEVIER
DOI: 10.1016/j.jksuci.2021.10.002
Keywords
Breast lesion segmentation; Multiscale fusion; Dual attention mechanism; Encoder -decoder architecture
Categories
Ask authors/readers for more resources
Accurate breast lesion segmentation is essential for breast cancer treatment planning. This study proposes a multiscale dual attention-based network (MDA-Net) for concurrent segmentation of breast lesion images. The MDA-Net achieves high performance on various datasets and demonstrates broad applicability in different imaging modalities.
Accurate breast lesion segmentation is a great help in the initial stage of breast cancer treatment plan-ning. Ultrasound is considered the safe and cheapest method for the breast screening process. However, ultrasound images inherently contain speckle noise, unclear boundaries, and complex shapes, making it more challenging for automatic segmentation methods. This work proposes a multiscale dual attention-based network (MDA-Net) for concurrent segmentation of breast lesions images. The multi -scale fusion (MF) block is introduced that addresses the classical fixed receptive field issues, and helps to extract more semantic features and aims to achieve more features diversity. A dual-attention (dA) is also proposed, which is a hybrid of channel-based attention (cA) and lesion attention (lA) blocks that improves the feature representation capability and adaptatively learns a discriminative representation of high-level features. As a result, a combination of two attention blocks helped the proposed network to concentrate on a more relevant field of view of targets. The MDA-Net is extensively tested on both self-collected private datasets and two public UDIAT, BUSIS datasets. Furthermore, our method is also evaluated on MRI datasets to observe the broad applicability of our method in a different imaging modal-ity. The MDA-Net has achieved the DSC of 87.68%, 91.85%, 90.41%, 83.47% on UDIAT, BUSIS, Private, and RIDER breast MRI datasets (p -value < 0.05 with paired t-test). Our MDA-Net implementation code and pretrained models are released at GitHub: https://github.com/ahmedeqbal/MDA-Net. (c) 2021 The Authors. Published by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
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