EUVIMEDEUVIMED entdecken
Crossref

T2ID: Towards trustworthy incomplete modality diagnosis via dual-axis adaptive completion and confidence-aware integration

Jing Li, Qinkai Yu, Feixiang Zhou, Dongbo Zhang, Bo Huang, Yitian Zhao, Deng-Ping Fan, Huazhu Fu, Yalin Zheng, Yanda Meng

Medical Image Analysis · 2027-01 · 115 · 104331

DOI: 10.1016/j.media.2026.104331 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Image Analysis, 2027-01. Verfasst von Jing Li und 9 weiteren Autor:innen. Beteiligte Einrichtung: Guangdong Provincial Key Laboratory of Multimodal Big Data Intelligent Analysis, South China University of Technology, Guangzhou, China; Department o…. Hauptthemen laut MEDLINE: Multimodal Imaging, Magnetic Resonance Imaging, Image Interpretation, Computer-Assisted. Die Arbeit nennt 50 Literaturangaben. Gefördert von: King Abdullah University of Science and Technology, Royal Society.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multimodal medical images provide abundant and complementary diagnostic cues that are often indispensable for accurate clinical decision-making. However, various constraints, such as limited equipment availability, physical limitations of patients, etc. often lead to incomplete modality of medical data acquisition in the real world. This scenario makes it difficult to design robust and trustworthy diagnostic AI models under missing-modality conditions. In addition, for some samples, cross-modal completion may not always be beneficial when the available modality representation can already support a reliable prediction. Blindly completing every missing modality may introduce noisy or mismatched complementary features, increase unnecessary computation, and potentially degrade model performance. To address these limitations, we propose T2ID, a multimodal diagnostic framework, which adaptively completes missing modalities and explicitly models cross-modal interactions while maintaining trustworthiness and robustness against missing modality scenarios. Our framework incorporates two key innovations. Firstly, we design a Dual-axis Adaptive Modality Completion (DAA) module, which integrates vertical and horizontal completion strategies to efficiently estimate whether retrieval-based cross-modal completion is expected to provide reliable complementary evidence for the current sample, or cross-modal retrieval is needed for adaptive modality completion. Secondly, we introduce Dynamic Collaborative Confidence-aware Modality Integration (DCC) module, which estimates both unimodal-confidence and synergistic-confidence to capture synergistic or conflicting interactions across modalities, thereby ensuring trustworthy diagnostic predictions. Extensive experiments on three multimodal medical imaging datasets demonstrate that our T2ID achieves superior performance compared with other state-of-the-art methods under diverse missing-modality scenarios. The implementation code is publicly available at https://github.com/lijing-coder/T2ID.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Multimodal ImagingMagnetic Resonance ImagingImage Interpretation, Computer-AssistedHumansAlgorithms

Stichwörter der Autor:innen

Adaptive modality completionExplicit cross-modal interactionsMissing modality learningRobust and trustworthy diagnosis

Autor:innen und Institutionen

  • Guangdong Provincial Key Laboratory of Multimodal Big Data Intelligent Analysis, South China University of Technology, Guangzhou, China; Department of Computer Science, University of Exeter, Exeter, United Kingdom; Depa…
  • Department of Computer Science, University of Exeter, Exeter, United Kingdom; Liverpool Centre for Cardiovascular Science, University of Liverpool, Liverpool, United Kingdom; Bioengineering Program, Biomedical Sciences…
  • Department of Eye and Vision Sciences, University of Liverpool, Liverpool, United Kingdom; Liverpool Centre for Cardiovascular Science, University of Liverpool, Liverpool, United Kingdom.
  • School of Automation and Electronic Information, Xiangtan University, Xiangtan, China.
  • College of Optoelectronic Engineering, Chongqing University, Chongqing, China.
  • Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, China.

Förderung

  • King Abdullah University of Science and Technology
  • Royal Society

Zitieren

APA

Li, J., Yu, Q., Zhou, F., Zhang, D., Huang, B., Zhao, Y., Fan, D. P., Fu, H., Zheng, Y., & Meng, Y. (2027). T2ID: Towards trustworthy incomplete modality diagnosis via dual-axis adaptive completion and confidence-aware integration. Medical Image Analysis, 115, 104331. https://doi.org/10.1016/j.media.2026.104331

Vancouver

Li J, Yu Q, Zhou F, Zhang D, Huang B, Zhao Y, et al. T2ID: Towards trustworthy incomplete modality diagnosis via dual-axis adaptive completion and confidence-aware integration. Medical Image Analysis. 2027;115:104331. doi:10.1016/j.media.2026.104331

BibTeX
@article{Li2027,
  author = {Li, Jing and Yu, Qinkai and Zhou, Feixiang and Zhang, Dongbo and Huang, Bo and Zhao, Yitian and Fan, Deng-Ping and Fu, Huazhu and Zheng, Yalin and Meng, Yanda},
  title = {T2ID: Towards trustworthy incomplete modality diagnosis via dual-axis adaptive completion and confidence-aware integration},
  journal = {Medical Image Analysis},
  year = {2027},
  volume = {115},
  pages = {104331},
  doi = {10.1016/j.media.2026.104331}
}
Kostenlos starten →