Enhancing Diabetic Foot Ulcer Assessment Through Fine-Tuned Vision-Language Models

Reza Basiri; Asad Ghaffar; Donya Ghiasi; Meaka Tesfaye Mekonnen; Milos R. Popovic; Shehroz S. Khan

doi:10.1007/978-981-95-0568-5_9

Conference paper, 2025

Enhancing Diabetic Foot Ulcer Assessment Through Fine-Tuned Vision-Language Models

Reza Basiri, Asad Ghaffar, Donya Ghiasi, Meaka Tesfaye Mekonnen, Milos R. Popovic, Shehroz S. Khan

IJCAI 2025 workshops, Communications in Computer and Information Science (Springer), 117-131. DOI 10.1007/978-981-95-0568-5_9

In brief

General-purpose vision-language models can describe a photograph, but not the way a wound-care clinician would. This work fine-tunes vision-language models on diabetic foot ulcer images so they assess and describe wounds in clinical terms, moving from the off-the-shelf approach of UlcerGPT to models adapted to the domain.

Key findings

Domain fine-tuning of vision-language models for wound assessment
Builds on UlcerGPT's multimodal image transcription
Presented at the International Joint Conference on Artificial Intelligence (IJCAI) 2025

Read at the publisher

Themes

Keywords

Cite

Basiri, R., Ghaffar, A., Ghiasi, D., Mekonnen, M. T., Popovic, M. R., & Khan, S. S. (2025). Enhancing Diabetic Foot Ulcer Assessment Through Fine-Tuned Vision-Language Models. IJCAI 2025 workshops, Communications in Computer and Information Science (Springer), 117-131. https://doi.org/10.1007/978-981-95-0568-5_9

BibTeX

@inproceedings{basiri2025enhancing,
  title = {{Enhancing Diabetic Foot Ulcer Assessment Through Fine-Tuned Vision-Language Models}},
  author = {Reza Basiri and Asad Ghaffar and Donya Ghiasi and Meaka Tesfaye Mekonnen and Milos R. Popovic and Shehroz S. Khan},
  booktitle = {IJCAI 2025 workshops, Communications in Computer and Information Science (Springer)},
  year = {2025},
  pages = {117--131},
  doi = {10.1007/978-981-95-0568-5_9}
}

Enhancing Diabetic Foot Ulcer Assessment Through Fine-Tuned Vision-Language Models

In brief

Key findings

Related work

Temporal machine learning framework for diabetic foot ulcer healing trajectory prediction

Multimodal Artificial Intelligence System to Enhance the Classification and Analysis of Diabetic Foot Ulcer Healing Conditions

Applications of Generative AI in Diabetic Foot Ulcer Treatment