App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 10

Medical image generation via progressive mask fusion and segmentation-guided diffusion models

Cao Lu1
He Xiquan1
Mai Chaoyun1
Xie Hao1
Liao Junhong2
Rao Mintong1
1. School of Electronic and Information Engineering, Wuyi University, Jiangmen Guangdong 529000, China
2. Department of Respiratory and Critical Care Medicine, Jiangmen People's Hospital, Jiangmen Guangdong 529000, China
DOI: 10.19734/j.issn.1001-3695.2025.12.0540

Abstract

To address the shortage of high-quality annotated data for medical image segmentation and the structural discontinuities and boundary artifacts that existing diffusion-model conditioning methods often introduce, this work proposes med-controlnet, a medical image generation model based on progressive mask Fusion and segmentation guidance.the method builds a progressive mask Fusion module that adaptively adjusts the feature receptive field and enables progressive Fusion by emphasizing global anatomical coherence in the early stage and refining lesion textures in the later stage. in parallel, the method designs a segmentation guidance module that leverages a frozen pretrained teacher segmentation network to introduce both shape and semantic priors. this module constrains lesion morphology and aligns deep semantic representations through prediction loss and feature normalization.experimental results show that the model generates images with better image-quality metrics, including fid and lpips, and that the high-fidelity generated samples significantly improve the dice coefficient of downstream segmentation models. these findings demonstrate that the proposed model produces medical images with both high fidelity and diversity, restores the complex boundary transitions found in real pathological tissues more effectively, and provides a more semantically consistent data augmentation solution for alleviating annotated-data scarcity in medical image segmentation tasks.

Foundation Support

广东普通高校重点领域专项(2025ZDZX1040)
湖南省自科基金资助项目(2023JJ50393)
江门市省科技创新战略专项项目计划(江科[2023]72号)
江门市基础理论科研科技计划项目(2023JC010039)
江门市医疗卫生科技计划项目(江科[2025]88号)
五邑大学大学生创新创业训练计划项目(X202511349050)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.12.0540
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 10

Publish History

[2026-07-03] Accepted Paper

Cite This Article

曹路, 何锡权, 麦超云, 等. 基于渐进式掩码融合与分割引导的医学图像生成扩散模型 [J]. 计算机应用研究, 2026, 43 (10). (2026-07-30). https://doi.org/10.19734/j.issn.1001-3695.2025.12.0540. (Cao Lu, He Xiquan, Mai Chaoyun, et al. Medical image generation via progressive mask fusion and segmentation-guided diffusion models [J]. Application Research of Computers, 2026, 43 (10). (2026-07-30). https://doi.org/10.19734/j.issn.1001-3695.2025.12.0540. )

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)