EUVIMEDSkopri EUVIMED
Open access · CC BY 4.0

A Unified Framework for Classification and Segmentation of Ambiguous Dual-Type Lesions in Colonoscopic Images

Siqi Chen, Kun Jiang, Ruishi Lin, Xiufeng Su, Liyong Ma iD

Bioengineering · 2026-06-11 · 13 (6) · 679

DOI: 10.3390/bioengineering13060679 ↗

At a glance

Journal article in Bioengineering, published online on 2026-06-11. Written by Siqi Chen and 4 co-authors. Institution: Department of Control Science and Engineering, Harbin Institute of Technology, Harbin 150001, China. 47 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Key R&D Program of China, National Key R&D Program of China.

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Accurate analysis of lesions in colonoscopic images is essential for computer-aided diagnosis. However, most existing methods are designed for single-lesion segmentation and assume a predefined lesion category, limiting their applicability in real-world scenarios where multiple lesion types exhibit similar visual characteristics. To address this issue, we propose a unified framework for the joint classification and segmentation of dual-type lesions in colonoscopic images, enabling simultaneous identification and localization of submucosal lesions and polyps/adenomas. The proposed method integrates joint supervision, context-aware feature enhancement, and ambiguity-aware optimization to improve consistency between semantic recognition and spatial delineation. In particular, a soft-label supervision strategy is introduced to alleviate semantic ambiguity, while an imbalance-aware loss design enhances segmentation accuracy and reduces false negative predictions. Extensive experiments on both private and public datasets demonstrate that the proposed method achieves superior performance compared with representative CNN- and transformer-based approaches. Notably, the method shows clear advantages in segmentation accuracy, localization precision, and robustness under challenging conditions. Ablation studies further confirm the effectiveness of each component in the proposed framework. These results indicate that the proposed approach provides an effective solution for dual-type lesion analysis and has the potential to assist clinical decision-making in gastrointestinal endoscopy.

Subjects

Author keywords

colonoscopic imagescomputer-aided diagnosisdeep learningdual-type lesionsjoint classification and segmentationsemantic ambiguity

Authors and institutions

  • Department of Control Science and Engineering, Harbin Institute of Technology, Harbin 150001, China.
  • Suzhou Research Institute, Harbin Institute of Technology, Suzhou 215104, China.
  • Weihai Municipal Hospital, Cheeloo College of Medicine, Shandong University, Weihai 264299, China.
  • School of Information Science and Engineering, Harbin Institute of Technology, Weihai 264209, China.

ORCID profiles: Liyong Ma

Funding

  • National Key R&D Program of China
  • National Key R&D Program of China

Cite

APA

Chen, S., Jiang, K., Lin, R., Su, X., & Ma, L. (2026). A Unified Framework for Classification and Segmentation of Ambiguous Dual-Type Lesions in Colonoscopic Images. Bioengineering, 13(6), 679. https://doi.org/10.3390/bioengineering13060679

Vancouver

Chen S, Jiang K, Lin R, Su X, Ma L. A Unified Framework for Classification and Segmentation of Ambiguous Dual-Type Lesions in Colonoscopic Images. Bioengineering. 2026;13(6):679. doi:10.3390/bioengineering13060679

BibTeX
@article{Chen2026,
  author = {Chen, Siqi and Jiang, Kun and Lin, Ruishi and Su, Xiufeng and Ma, Liyong},
  title = {A Unified Framework for Classification and Segmentation of Ambiguous Dual-Type Lesions in Colonoscopic Images},
  journal = {Bioengineering},
  year = {2026},
  volume = {13},
  number = {6},
  pages = {679},
  doi = {10.3390/bioengineering13060679}
}
Start for free →