基于改进YOLOv8-CBAM-ASFF模型的中风检测算法研究
Research on stroke detection algorithm based on the improved model of YOLOv8-CBAM-ASFF
该研究提出了一种基于改进YOLOv8-CBAM-ASFF模型的中风检测算法,该模型在检测中、大型病灶时提高了敏感性,同时保持了整体mAP水平。
- Weijia Zhang1,2,3,4,
- Luyang Ji1,2,
- Yang Liu1,2,4,
- Dan Qiu2,
- Feiyu Chen2,
- Xue Cheng2,
- Dongqing Sun2,4,
- Nutapong Somjit7,
- Shaomin Cai2,5,
- Jianhao Hu5,6 &
- …
- Jianjun Li1,2
We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.
Abstract
Accurate early diagnosis of stroke is critical for reducing mortality and disability. Leveraging the rapid advances in deep learning, automated stroke detection has become an active research focus. Yet, existing approaches still underperform in detecting small lesions, adapting to complex backgrounds, and operating in real time. Four YOLOv8 variants of different scales were systematically evaluated, and an optimized architecture integrating the Convolutional Block Attention Module (CBAM) and the Adaptive Spatial Feature Fusion (Detect_ASFF) component was proposed. CBAM selectively amplifies salient features while suppressing background noise, whereas Detect_ASFF dynamically reweights multi-scale features, mitigating small-object loss and contextual degradation. Compared with the baseline, the refined model achieved a comparable overall mAP while improving lesion-level sensitivity for medium and large lesions. On a strictly patient-level held-out test set (34 patients, 474 images), the enhanced YOLOv8n reached 74.9% mean average precision at an intersection-over-union threshold of 0.5, where a lesion counts as detected when the predicted box overlaps the annotated lesion by at least 50% (mAP@0.5), and 36.1% when the same measure is averaged over thresholds from 0.5 to 0.95 (mAP@0.5:0.95). It also increased the recall of medium-sized lesions (32–96 px) from 62.5% to 73.5% and of large lesions from 84.9% to 90.3%, at a modest cost of 0.2 additional false positives per image. Owing to its lightweight design, the optimized YOLOv8n is a promising candidate for real-time stroke-lesion detection; this work is presented as a proof of principle, and clinical deployment requires further validation.
Funding
This research received no external funding.
Author information
Authors and Affiliations
School of Mathematical Information, Shaoxing University, Shaoxing, China
Weijia Zhang, Luyang Ji, Yang Liu & Jianjun Li
International Science and Technology Cooperation Base for Integrated Circuit Product Design in Zhejiang Province, Shaoxing University, Shaoxing, China
Weijia Zhang, Luyang Ji, Yang Liu, Dan Qiu, Feiyu Chen, Xue Cheng, Dongqing Sun, Shaomin Cai & Jianjun Li
Department of AOP Physics, University of Oxford, Oxford, UK
Weijia Zhang
Key Laboratory of Artificial Intelligence Multi-Dimensional Application Research, Shaoxing, China
Weijia Zhang, Yang Liu & Dongqing Sun
School of Medicine, Shaoxing University, Shaoxing, China
Shaomin Cai & Jianhao Hu
Shaoxing City Hospital, Shaoxing, China
Jianhao Hu
School of Electronic and Electrical Engineering, University of Leeds, Leeds, UK
Nutapong Somjit
Authors
- Weijia Zhang
- Luyang Ji
- Yang Liu
- Dan Qiu
- Feiyu Chen
- Xue Cheng
- Dongqing Sun
- Nutapong Somjit
- Shaomin Cai
- Jianhao Hu
- Jianjun Li
Corresponding authors
Correspondence to Shaomin Cai, Jianhao Hu or Jianjun Li.
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
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://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Zhang, W., Ji, L., Liu, Y. et al. Research on stroke detection algorithm based on the improved model of YOLOv8-CBAM-ASFF. Sci Rep (2026). https://doi.org/10.1038/s41598-026-78529-8
Received: 31 July 2025
Accepted: 27 October 2026
Published: 04 November 2026
DOI: https://doi.org/10.1038/s41598-026-78529-8
Keywords
来源:Nature 健康护理主题 · nature.com