Joint Dense Residual and Recurrent Attention Network for DCE-MRI Breast Tumor Segmentation.

Publisher: Hindawi Pub. Corp Country of Publication: United States NLM ID: 101279357 Publication Model: eCollection Cited Medium: Internet ISSN: 1687-5273 (Electronic) NLM ISO Abbreviation: Comput Intell Neurosci Subsets: MEDLINE

Original Publication: New York, NY : Hindawi Pub. Corp.

Breast Neoplasms*/diagnostic imaging; Algorithms ; Female ; Humans

Competing Interests: The author declares that there are no conflicts of interest regarding the publication of this paper.
Breast cancer detection largely relies on imaging characteristics and the ability of clinicians to easily and quickly identify potential lesions. Magnetic resonance imaging (MRI) of breast tumors has recently shown great promise for enabling the automatic identification of breast tumors. Nevertheless, state-of-the-art MRI-based algorithms utilizing deep learning techniques are still limited in their ability to accurately separate tumor and healthy tissue. Therefore, in the current work, we propose an automatic and accurate two-stage U-Net-based segmentation framework for breast tumor detection using dynamic contrast-enhanced MRI (DCE-MRI). This framework was evaluated using T2-weighted MRI data from 160 breast tumor cases, and its performance was compared with that of the standard U-Net model. In the first stage of the proposed framework, a refined U-Net model was utilized to automatically delineate a breast region of interest (ROI) from the surrounding healthy tissue. Importantly, this automatic segmentation step reduced the impact of the background chest tissue on breast tumors' identification. For the second stage, we employed an improved U-Net model that combined a dense residual module based on dilated convolution with a recurrent attention module. This model was used to accurately and automatically segment the tumor tissue from healthy tissue in the breast ROI derived in the previous step. Overall, compared to the U-Net model, the proposed technique exhibited increases in the Dice similarity coefficient, Jaccard similarity, positive predictive value, sensitivity, and Hausdorff distance of 3%, 3%, 3%, 2%, and 16.2, respectively. The proposed model may in the future aid in the clinical diagnosis of breast cancer lesions and help guide individualized patient treatment.
(Copyright © 2022 ChuanBo Qin et al.)

Contrast Media Mol Imaging. 2018 Oct 24;2018:5308517. (PMID: 30647551)
Eur J Radiol. 2012 Jul;81(7):1532-8. (PMID: 21570225)
IEEE J Biomed Health Inform. 2022 Jan;26(1):103-114. (PMID: 33945491)
BMC Med Imaging. 2022 Jan 5;22(1):6. (PMID: 34986785)
IEEE J Biomed Health Inform. 2015 Jan;19(1):349-57. (PMID: 25561456)
IEEE Trans Pattern Anal Mach Intell. 2017 Apr;39(4):640-651. (PMID: 27244717)
IEEE Trans Med Imaging. 2013 Apr;32(4):637-48. (PMID: 23008246)
IEEE Trans Med Imaging. 2018 Dec;37(12):2663-2674. (PMID: 29994201)
J Healthc Eng. 2019 Jan 14;2019:8415485. (PMID: 30774849)
Acad Radiol. 2006 Jan;13(1):63-72. (PMID: 16399033)
Artif Intell Med. 2020 Mar;103:101781. (PMID: 32143788)
Med Phys. 2014 Aug;41(8):082303. (PMID: 25086552)
IEEE Trans Med Imaging. 2019 Feb;38(2):435-447. (PMID: 30130181)
Med Phys. 2013 Mar;40(3):032305. (PMID: 23464337)

Date Created: 20220502 Date Completed: 20220503 Latest Revision: 20240827

20250114

PMC9045980

10.1155/2022/3470764

35498198