Topicwise Separable Sentence Retrieval for Medical Report Generation

TL;DR

This paper introduces Teaser, a novel retrieval-based method for medical report generation that effectively captures both common and rare topics, improving report quality and reliability, especially for critical rare findings.

Contribution

The paper proposes Topicwise Separable Sentence Retrieval with Topic Contrastive Loss and an Abstractor module, enhancing rare topic representation and query-topic alignment in medical report generation.

Findings

Outperforms state-of-the-art models on MIMIC-CXR and IU X-ray datasets.

Effectively captures rare and critical medical report topics.

Improves query-topic correspondence and report completeness.

Abstract

Automated radiology reporting holds immense clinical potential in alleviating the burdensome workload of radiologists and mitigating diagnostic bias. Recently, retrieval-based report generation methods have garnered increasing attention due to their inherent advantages in terms of the quality and consistency of generated reports. However, due to the long-tail distribution of the training data, these models tend to learn frequently occurring sentences and topics, overlooking the rare topics. Regrettably, in many cases, the descriptions of rare topics often indicate critical findings that should be mentioned in the report. To address this problem, we introduce a Topicwise Separable Sentence Retrieval (Teaser) for medical report generation. To ensure comprehensive learning of both common and rare topics, we categorize queries into common and rare types to learn differentiated topics, and then propose Topic Contrastive Loss to effectively align topics and queries in the latent space. Moreover, we integrate an Abstractor module following the extraction of visual features, which aids the topic decoder in gaining a deeper understanding of the visual observational intent. Experiments on the MIMIC-CXR and IU X-ray datasets demonstrate that Teaser surpasses state-of-the-art models, while also validating its capability to effectively represent rare topics and establish more dependable correspondences between queries and topics.