Recurrent Visual Feature Extraction and Stereo Attentions for CT Report Generation

TL;DR

This paper introduces a novel CT report generation method using recurrent visual feature extraction and stereo attentions, leveraging a vision Transformer and hierarchical modeling to improve accuracy over existing approaches.

Contribution

It proposes a new hierarchical feature modeling approach with recurrent visual extraction and stereo attentions, explicitly capturing inter-slice transformations for better report generation.

Findings

Outperforms baseline models on M3D-Cap dataset

Achieves state-of-the-art results in CT report generation

Demonstrates effectiveness of hierarchical visual feature modeling

Abstract

Generating reports for computed tomography (CT) images is a challenging task, while similar to existing studies for medical image report generation, yet has its unique characteristics, such as spatial encoding of multiple images, alignment between image volume and texts, etc. Existing solutions typically use general 2D or 3D image processing techniques to extract features from a CT volume, where they firstly compress the volume and then divide the compressed CT slices into patches for visual encoding. These approaches do not explicitly account for the transformations among CT slices, nor do they effectively integrate multi-level image features, particularly those containing specific organ lesions, to instruct CT report generation (CTRG). In considering the strong correlation among consecutive slices in CT scans, in this paper, we propose a large language model (LLM) based CTRG method with recurrent visual feature extraction and stereo attentions for hierarchical feature modeling. Specifically, we use a vision Transformer to recurrently process each slice in a CT volume, and employ a set of attentions over the encoded slices from different perspectives to selectively obtain important visual information and align them with textual features, so as to better instruct an LLM for CTRG. Experiment results and further analysis on the benchmark M3D-Cap dataset show that our method outperforms strong baseline models and achieves state-of-the-art results, demonstrating its validity and effectiveness.