Multi-scale context U-net for breast cancer postoperative radiotherapy in patients with brachial plexus

Sep 30, 2026

Purpose proposes a Multi-Scale Context U-net (MSC-U-net) for precise, automated segmentation of the brachial plexus in breast cancer patients after postoperative radiotherapy. Methods include training on 389 postoperative radiotherapy cases and testing on 55, with evaluation using Dice Similarity Coefficient (DSC) and HD95. Comparison and ablation experiments assess robustness, and clinical practicability is reviewed in a clinical setting. Results report DSC 79.16 ± 0.05% and HD95 6.95 ± 0.76 mm, with superior performance over classical networks. Conclusions show reduced manual effort and human-factor-driven accuracy issues, supporting efficient, accurate automation for radiotherapy planning and future organ segmentation research.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Abstract

Purpose

Methods

Results

Conclusions

Innovation

Non-Local Block and SE Block reconsideration

Nearest neighbor interpolation upsampling

Improved automatic segmentation accuracy

Keywords

Background

Xie etal. BMC Medical Imaging (2026) 26:8 [https://doi.org/10.1186/s12880-025-02078-1](https://doi.org/10.1186/s12880-025-02078-1) BMC Medical Imaging RESEARCH Open Access Multi-scale context U-net for breast cancer postoperative radiotherapy in patients with brachial plexus Hui Xie 1,2, Zijie Chen3, Jianfang Zhang4 and Tao Tan 1* Abstract Purpose In this study, we propose a Multi-Scale Context U-net (MSC-U-net) network model for the precise and automated segmentation of the brachial plexus in patients who have undergone postoperative radiotherapy for breast cancer. Methods A total of 389 patients who underwent postoperative radiotherapy for breast cancer were included in the training set, while 55 patients were included in the test set. The network model proposed in this study was optimized and trained to achieve the most accurate segmentation results. The performance of the model was evaluated using the Dice Similarity Coefficient (DSC) and the 95% Hausdorff distance (HD95) . To further validate the effectiveness of the segmentation, comparison and ablation experiments were conducted. Subsequently, the clinical practicability was assessed within a clinical setting. Results MSC-U-net achieved precise segmentation results with DSC and HD95 values of 79.16 ± 0. 05% and 6.95 ± 0.76 mm, respectively, in the test set. In comparison experiments with four other classical networks, the model showed significant statistical differences (p < 0. 05) in performance. Ablation experiments further confirmed that the MSC-U-net network model achieved the best segmentation performance (p < 0. 05) . The radiation oncologists’subjective evaluations also demonstrated the clinical applicability of the MSC-U-net network model. There was no statistically significant difference between manual segmentation and model segmentation in terms of segmentation accuracy and radiation dose (p >0. 05) . The above results demonstrate the superior performance of the MSC-U-net network model in medical image segmentation, and also indicate its effectiveness in clinical applications. Conclusions In the context of segmenting the brachial plexus in localization CT images of breast cancer patients after postoperative radiotherapy, MSC-U-net has demonstrated exceptional performance, significantly minimizing the manual segmentation accuracy issues caused by human factors. This network exhibits high efficiency in automatic segmentation and a high level of accuracy. Notably, the MSC-U-net network holds significant importance in the advancement of radiotherapy automation, and it also offers valuable insights for future research in the field of automatic organ segmentation. *Correspondence: Tao Tan [taotanjs@gmail.com](taotanjs@gmail.com) Full list of author information is available at the end of the article © The Author(s) 2025. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit [http://creati](http://creati)[vecommons.org/l](vecommons.org/l)icenses/by-nc-nd/4.0/. Innovation (1) The structure of Non-Local Block and SE Block is reconsidered, and

FAQs

What problem does MSC-U-net address in this study?

It targets precise and automated segmentation of the brachial plexus in localization CT images for breast cancer patients who have undergone postoperative radiotherapy.

How were the model results evaluated?

Performance was measured using Dice Similarity Coefficient (DSC) and the 95% Hausdorff distance (HD95), with additional comparison and ablation experiments.

How did automatic segmentation compare with manual segmentation?

No statistically significant differences were found between manual and model segmentation regarding segmentation accuracy and radiation dose (p > 0.05).

Sep 30, 2026

Uploaded by 4398046744996