Read Like a Radiologist: Efficient Vision-Language Model for 3D Medical Imaging Interpretation

TL;DR

This paper introduces MS-VLM, a novel vision-language model that mimics radiologists' sequential slice analysis to improve 3D medical image interpretation, overcoming previous limitations of volumetric representation methods.

Contribution

MS-VLM leverages self-supervised 2D transformers to learn inter-slice dependencies from sequences, enabling flexible volumetric representations from any slice length and multiple imaging planes.

Findings

MS-VLM outperforms existing methods in radiology report generation.

MS-VLM produces more coherent and clinically relevant reports.

The model demonstrates robustness across different 3D imaging modalities.

Abstract

Recent medical vision-language models (VLMs) have shown promise in 2D medical image interpretation. However extending them to 3D medical imaging has been challenging due to computational complexities and data scarcity. Although a few recent VLMs specified for 3D medical imaging have emerged, all are limited to learning volumetric representation of a 3D medical image as a set of sub-volumetric features. Such process introduces overly correlated representations along the z-axis that neglect slice-specific clinical details, particularly for 3D medical images where adjacent slices have low redundancy. To address this limitation, we introduce MS-VLM that mimic radiologists' workflow in 3D medical image interpretation. Specifically, radiologists analyze 3D medical images by examining individual slices sequentially and synthesizing information across slices and views. Likewise, MS-VLM leverages self-supervised 2D transformer encoders to learn a volumetric representation that capture inter-slice dependencies from a sequence of slice-specific features. Unbound by sub-volumetric patchification, MS-VLM is capable of obtaining useful volumetric representations from 3D medical images with any slice length and from multiple images acquired from different planes and phases. We evaluate MS-VLM on publicly available chest CT dataset CT-RATE and in-house rectal MRI dataset. In both scenarios, MS-VLM surpasses existing methods in radiology report generation, producing more coherent and clinically relevant reports. These findings highlight the potential of MS-VLM to advance 3D medical image interpretation and improve the robustness of medical VLMs.