App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 8

ICFDRL-SLS: invariant causal flow deep reinforcement learning for semi-supervised layer segmentation

Zha Zian1
Dong Xinghua1
Zhu Junhui1
Xiang Dehui2
Gao Enting1
1. School of Electronic and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, Jiangsu, China
2. School of Electronic and Information Engineering, Soochow University, Suzhou 215006, Jiangsu, China
DOI: 10.19734/j.issn.1001-3695.2025.10.0487

Abstract

Accurate segmentation of scalp tissue layers in High-resolution magnetic resonance (HR-MR) images offers a promising assesment tool for the grading diagnosis of androgenetic alopecia (AGA) . However, due to the inherent complexity of medical images and the scarcity of high-quality annotated data, existing methods often struggle to achieve precise layer segmentation and lack sufficient interpretability. To address these challenges, this paper proposes an Invariant Causal Flow Deep Reinforcement Learning framework for Semi-Supervised Layer Segmentation (ICFDRL-SLS) . The proposed method introduces a Layer Structure Encoder (LSE) to robustly extract cross-region layer structure features, and employs a deep reinforcement learning policy to construct an invariant causal flow that attenuates confounding factors that degrade segmentation performance. Extensive experiments conducted on a private scalp HR-MR dataset and the public multiple sclerosis retinal OCT (MS-OCT) dataset demonstrate the effectiveness of this approach. Under 5%, 10%, and 30% labeled data settings on the scalp HR-MR dataset, ICFDRL-SLS achieves average Dice improvements of 2.25%, 1.57% and 2.81% over state-of-the-art methods. On the MS-OCT dataset, using a single labeled image and a 5% labeled data setting yields average Dice improvements of 2.14% and 1.70%, respectively. The results verify the effectiveness and robustness of ICFDRL-SLS for thin-layer structure segmentation in low-annotation scenarios.

Foundation Support

国家自然科学基金资助项目(62371328,62273247,61971298,61771326,81871352)
国家重点研发计划颠覆性技术创新项目(2023YFF1500804)
2024年度江苏省先进机器人技术重点实验室开放课题(KJS2446)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.10.0487
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 8

Publish History

[2026-04-09] Accepted Paper

Cite This Article

查子安, 董兴华, 朱军辉, 等. ICFDRL-SLS:基于因果不变流的深度强化学习半监督层分割方法 [J]. 计算机应用研究, 2026, 43 (8). (2026-04-30). https://doi.org/10.19734/j.issn.1001-3695.2025.10.0487. (Zha Zian, Dong Xinghua, Zhu Junhui, et al. ICFDRL-SLS: invariant causal flow deep reinforcement learning for semi-supervised layer segmentation [J]. Application Research of Computers, 2026, 43 (8). (2026-04-30). https://doi.org/10.19734/j.issn.1001-3695.2025.10.0487. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)