Instruction-Guided Lesion Segmentation for Chest X-rays with Automatically Generated Large-Scale Dataset
This addresses the problem of practical use in medical imaging by enabling diverse lesion segmentation with simple instructions, though it is incremental as it builds on existing vision-language models.
The paper tackles the limited applicability of chest X-ray lesion segmentation models by introducing instruction-guided lesion segmentation (ILS) and constructing MIMIC-ILS, a large-scale dataset with 1.1M instruction-answer pairs from 192K images, and ROSALIA, a fine-tuned model that achieves high segmentation and textual accuracy.
The applicability of current lesion segmentation models for chest X-rays (CXRs) has been limited both by a small number of target labels and the reliance on long, detailed expert-level text inputs, creating a barrier to practical use. To address these limitations, we introduce a new paradigm: instruction-guided lesion segmentation (ILS), which is designed to segment diverse lesion types based on simple, user-friendly instructions. Under this paradigm, we construct MIMIC-ILS, the first large-scale instruction-answer dataset for CXR lesion segmentation, using our fully automated multimodal pipeline that generates annotations from chest X-ray images and their corresponding reports. MIMIC-ILS contains 1.1M instruction-answer pairs derived from 192K images and 91K unique segmentation masks, covering seven major lesion types. To empirically demonstrate its utility, we introduce ROSALIA, a vision-language model fine-tuned on MIMIC-ILS. ROSALIA can segment diverse lesions and provide textual explanations in response to user instructions. The model achieves high segmentation and textual accuracy in our newly proposed task, highlighting the effectiveness of our pipeline and the value of MIMIC-ILS as a foundational resource for pixel-level CXR lesion grounding.