兰州大学机构库
Evaluation of Breast Cancer Tumor-Infiltrating Lymphocytes on Ultrasound Images Based on a Novel Multi-Cascade Residual U-Shaped Network
Wu, Ruichao1; Jia, Yingying2,3,4; Li, Nana2,3,4; Lu, Xiangyu1; Yao, Zihuan1; Ma, Yide1; Nie, Fang2,3,4
2023-11
Online publication date2023-09
Source PublicationULTRASOUND IN MEDICINE AND BIOLOGY   Impact Factor & Quartile
ISSN0301-5629 ; 1879-291X
Volume49Issue:11Pages:2398-2406
page numbers9
AbstractObjective: Breast cancer has become the leading cancer of the 21st century. Tumor-infiltrating lymphocytes (TILs) have emerged as effective biomarkers for predicting treatment response and prognosis in breast cancer. The work described here was aimed at designing a novel deep learning network to assess the levels of TILs in breast ultra-sound images.Methods: We propose the Multi-Cascade Residual U-Shaped Network (MCRUNet), which incorporates a gray feature enhancement (GFE) module for image reconstruction and normalization to achieve data synergy. Addition-ally, multiple residual U-shaped (RSU) modules are cascaded as the backbone network to maximize the fusion of global and local features, with a focus on the tumor's location and surrounding regions. The development of MCRUNet is based on data from two hospitals and uses a publicly available ultrasound data set for transfer learning.Results: MCRUNet exhibits excellent performance in assessing TILs levels, achieving an area under the receiver operating characteristic curve of 0.8931, an accuracy of 85.71%, a sensitivity of 83.33%, a specificity of 88.64% and an F1 score of 86.54% in the test group. It outperforms six state-of-the-art networks in terms of performance.Conclusion: The MCRUNet network based on breast ultrasound images of breast cancer patients holds promise for non-invasively predicting TILs levels and aiding personalized treatment decisions.
KeywordTumor -infiltrating lymphocytes Deep learning Breast cancer Ultrasound
PublisherELSEVIER SCIENCE INC
DOI10.1016/j.ultrasmedbio.2023.08.003
Indexed BySCIE
Language英语
WOS Research AreaAcoustics ; Radiology, Nuclear Medicine & Medical Imaging
WOS SubjectAcoustics ; Radiology, Nuclear Medicine & Medical Imaging
WOS IDWOS:001076939500001
Original Document TypeArticle
PMID 37634979
Citation statistics
Document Type期刊论文
Identifierhttps://ir.lzu.edu.cn/handle/262010/569335
Collection兰州大学
Corresponding AuthorMa, Yide
Affiliation
1.Lanzhou Univ, Sch Informat Sci & Engn, Lanzhou, Peoples R China;
2.Lanzhou Univ, Hosp 2, Ultrasound Med Ctr, Lanzhou, Peoples R China;
3.Gansu Prov Med Engn Res Ctr Intelligence Ultrasoun, Lanzhou, Peoples R China;
4.Gansu Prov Clin Res Ctr Ultrasonog, Lanzhou, Peoples R China
Recommended Citation
GB/T 7714
Wu, Ruichao,Jia, Yingying,Li, Nana,et al. Evaluation of Breast Cancer Tumor-Infiltrating Lymphocytes on Ultrasound Images Based on a Novel Multi-Cascade Residual U-Shaped Network[J]. ULTRASOUND IN MEDICINE AND BIOLOGY,2023,49(11):2398-2406.
APA Wu, Ruichao.,Jia, Yingying.,Li, Nana.,Lu, Xiangyu.,Yao, Zihuan.,...&Nie, Fang.(2023).Evaluation of Breast Cancer Tumor-Infiltrating Lymphocytes on Ultrasound Images Based on a Novel Multi-Cascade Residual U-Shaped Network.ULTRASOUND IN MEDICINE AND BIOLOGY,49(11),2398-2406.
MLA Wu, Ruichao,et al."Evaluation of Breast Cancer Tumor-Infiltrating Lymphocytes on Ultrasound Images Based on a Novel Multi-Cascade Residual U-Shaped Network".ULTRASOUND IN MEDICINE AND BIOLOGY 49.11(2023):2398-2406.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Altmetrics Score
Google Scholar
Similar articles in Google Scholar
[Wu, Ruichao]'s Articles
[Jia, Yingying]'s Articles
[Li, Nana]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wu, Ruichao]'s Articles
[Jia, Yingying]'s Articles
[Li, Nana]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wu, Ruichao]'s Articles
[Jia, Yingying]'s Articles
[Li, Nana]'s Articles
Terms of Use
No data!
Social Bookmark/Share
No comment.
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.