@ARTICLE{Byra_Michał_Few-shot_Early,
 author={Byra, Michał and Rachmadi, Muhammad Febrian and Skibbe, Henrik},
 pages={e153838},
 journal={Bulletin of the Polish Academy of Sciences Technical Sciences},
 howpublished={online},
 year={Early Access},
 abstract={Deep learning methods are gaining momentum in radiology. In this work, we investigate the usefulness of vision-language models (VLMs) and large language models for binary few-shot classification of medical images. We utilize the GPT-4 model to generate text descriptors that encapsulate the shape and texture characteristics of objects in medical images. Subsequently, these GPT-4 generated descriptors, alongside VLMs pre-trained on natural images, are employed to classify chest X-rays and breast ultrasound images. Our results indicate that few-shot classification of medical images using VLMs and GPT-4 generated descriptors is a viable approach. However, accurate classification requires to exclude certain descriptors from the calculations of the classification scores. Moreover, we assess the ability of VLMs to evaluate shape features in breast mass ultrasound images. This is performed by comparing VLM based results generated for shape-related text descriptors with the actual values of the shape features calculated using segmentation masks. We further investigate the degree of variability among the sets of text descriptors produced by GPT-4. Our work provides several important insights about the application of VLMs for medical image analysis.},
 title={Few-shot medical image classification with simple shape and texture text descriptors using vision-language models},
 type={Article},
 URL={http://czasopisma.pan.pl/Content/134335/PDF-MASTER/BPASTS-04440-EA.pdf},
 doi={10.24425/bpasts.2025.153838},
 keywords={medical image classification, vision-language models, large language models, few-shot learning},
}