Point, Detect, Count: Multi-Task Medical Image Understanding with Instruction-Tuned Vision-Language Models

• URL: http://arxiv.org/abs/2505.16647v1
• Date: Thu, 22 May 2025 13:18:44 GMT
• Title: Point, Detect, Count: Multi-Task Medical Image Understanding with Instruction-Tuned Vision-Language Models
• Authors: Sushant Gautam, Michael A. Riegler, Pål Halvorsen,
• Abstract summary: We investigate fine-tuning Vision-Language Models (VLMs) for multi-task medical image understanding.<n>We reformulate each task into instruction-based prompts suitable for vision-language reasoning.<n>Results show that multi-task training improves robustness and accuracy.
• Score: 3.3091869879941687
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We investigate fine-tuning Vision-Language Models (VLMs) for multi-task medical image understanding, focusing on detection, localization, and counting of findings in medical images. Our objective is to evaluate whether instruction-tuned VLMs can simultaneously improve these tasks, with the goal of enhancing diagnostic accuracy and efficiency. Using MedMultiPoints, a multimodal dataset with annotations from endoscopy (polyps and instruments) and microscopy (sperm cells), we reformulate each task into instruction-based prompts suitable for vision-language reasoning. We fine-tune Qwen2.5-VL-7B-Instruct using Low-Rank Adaptation (LoRA) across multiple task combinations. Results show that multi-task training improves robustness and accuracy. For example, it reduces the Count Mean Absolute Error (MAE) and increases Matching Accuracy in the Counting + Pointing task. However, trade-offs emerge, such as more zero-case point predictions, indicating reduced reliability in edge cases despite overall performance gains. Our study highlights the potential of adapting general-purpose VLMs to specialized medical tasks via prompt-driven fine-tuning. This approach mirrors clinical workflows, where radiologists simultaneously localize, count, and describe findings - demonstrating how VLMs can learn composite diagnostic reasoning patterns. The model produces interpretable, structured outputs, offering a promising step toward explainable and versatile medical AI. Code, model weights, and scripts will be released for reproducibility at https://github.com/simula/PointDetectCount.

Related papers

• ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs [98.27348724529257]
  We introduce ViCrit (Visual Caption Hallucination Critic), an RL proxy task that trains VLMs to localize a subtle, synthetic visual hallucination injected into paragraphs of human-written image captions.<n>Models trained with the ViCrit Task exhibit substantial gains across a variety of vision-language models benchmarks.
  arXiv  Detail & Related papers  (2025-06-11T19:16:54Z)
• UMIT: Unifying Medical Imaging Tasks via Vision-Language Models [17.65946656129399]
  UMIT is a unified multi-modal, multi-task VLM designed specifically for medical imaging tasks.<n>It is able to solve various tasks, including visual question answering, disease detection, and medical report generation.<n>It supports both English and Chinese, expanding its applicability globally.
  arXiv  Detail & Related papers  (2025-03-20T06:43:36Z)
• RadVLM: A Multitask Conversational Vision-Language Model for Radiology [10.522909557551419]
  We present RadVLM, a compact, multitask conversational foundation model for CXR interpretation.<n>Our results show that RadVLM achieves state-of-the-art performance in conversational capabilities and visual grounding.<n>Together, these findings highlight the potential of RadVLM as a clinically relevant AI assistant.
  arXiv  Detail & Related papers  (2025-02-05T16:27:02Z)
• LLaVA-Ultra: Large Chinese Language and Vision Assistant for Ultrasound [7.941670191244354]
  We propose a fine-grained adaptive VLM architecture for Chinese medical visual conversations through parameter-efficient tuning. Specifically, we devise a fusion module with fine-grained vision encoders to achieve enhancement for subtle medical visual semantics. For execution, we leverage a large-scale multimodal Chinese ultrasound dataset obtained from the hospital.
  arXiv  Detail & Related papers  (2024-10-19T11:38:31Z)
• LoGra-Med: Long Context Multi-Graph Alignment for Medical Vision-Language Model [55.80651780294357]
  State-of-the-art medical multi-modal large language models (med-MLLM) leverage instruction-following data in pre-training. LoGra-Med is a new multi-graph alignment algorithm that enforces triplet correlations across image modalities, conversation-based descriptions, and extended captions. Our results show LoGra-Med matches LLAVA-Med performance on 600K image-text pairs for Medical VQA and significantly outperforms it when trained on 10% of the data.
  arXiv  Detail & Related papers  (2024-10-03T15:52:03Z)
• Dr-LLaVA: Visual Instruction Tuning with Symbolic Clinical Grounding [53.629132242389716]
  Vision-Language Models (VLM) can support clinicians by analyzing medical images and engaging in natural language interactions. VLMs often exhibit "hallucinogenic" behavior, generating textual outputs not grounded in contextual multimodal information. We propose a new alignment algorithm that uses symbolic representations of clinical reasoning to ground VLMs in medical knowledge.
  arXiv  Detail & Related papers  (2024-05-29T23:19:28Z)
• Medical Vision-Language Pre-Training for Brain Abnormalities [96.1408455065347]
  We show how to automatically collect medical image-text aligned data for pretraining from public resources such as PubMed. In particular, we present a pipeline that streamlines the pre-training process by initially collecting a large brain image-text dataset. We also investigate the unique challenge of mapping subfigures to subcaptions in the medical domain.
  arXiv  Detail & Related papers  (2024-04-27T05:03:42Z)
• MedFLIP: Medical Vision-and-Language Self-supervised Fast Pre-Training with Masked Autoencoder [26.830574964308962]
  We introduce MedFLIP, a Fast Language-Image Pre-training method for Medical analysis. We explore MAEs for zero-shot learning with crossed domains, which enhances the model's ability to learn from limited data. Lastly, we validate using language will improve the zero-shot performance for the medical image analysis.
  arXiv  Detail & Related papers  (2024-03-07T16:11:43Z)
• LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching [59.01894976615714]
  We introduce LVM-Med, the first family of deep networks trained on large-scale medical datasets. We have collected approximately 1.3 million medical images from 55 publicly available datasets. LVM-Med empirically outperforms a number of state-of-the-art supervised, self-supervised, and foundation models.
  arXiv  Detail & Related papers  (2023-06-20T22:21:34Z)
• Vision-Language Modelling For Radiological Imaging and Reports In The Low Data Regime [70.04389979779195]
  This paper explores training medical vision-language models (VLMs) where the visual and language inputs are embedded into a common space. We explore several candidate methods to improve low-data performance, including adapting generic pre-trained models to novel image and text domains. Using text-to-image retrieval as a benchmark, we evaluate the performance of these methods with variable sized training datasets of paired chest X-rays and radiological reports.
  arXiv  Detail & Related papers  (2023-03-30T18:20:00Z)
• Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing [53.89917396428747]
  Self-supervised learning in vision-language processing exploits semantic alignment between imaging and text modalities. We explicitly account for prior images and reports when available during both training and fine-tuning. Our approach, named BioViL-T, uses a CNN-Transformer hybrid multi-image encoder trained jointly with a text model.
  arXiv  Detail & Related papers  (2023-01-11T16:35:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.