Contrastive Language Prompting to Ease False Positives in Medical Anomaly Detection

TL;DR

This paper introduces CLAP, a contrastive language prompting method that reduces false positives in medical anomaly detection by leveraging positive and negative text prompts to improve CLIP's performance in medical imaging.

Contribution

The paper proposes a simple yet effective contrastive language prompting technique that attenuates attention on normal regions, improving anomaly detection accuracy in medical images.

Findings

CLAP improves anomaly detection performance on BMAD and other biomedical benchmarks.

Using negative prompts reduces false positives in medical image analysis.

Extensive experiments validate the effectiveness of the proposed method.

Abstract

A pre-trained visual-language model, contrastive language-image pre-training (CLIP), successfully accomplishes various downstream tasks with text prompts, such as finding images or localizing regions within the image. Despite CLIP's strong multi-modal data capabilities, it remains limited in specialized environments, such as medical applications. For this purpose, many CLIP variants-i.e., BioMedCLIP, and MedCLIP-SAMv2-have emerged, but false positives related to normal regions persist. Thus, we aim to present a simple yet important goal of reducing false positives in medical anomaly detection. We introduce a Contrastive LAnguage Prompting (CLAP) method that leverages both positive and negative text prompts. This straightforward approach identifies potential lesion regions by visual attention to the positive prompts in the given image. To reduce false positives, we attenuate attention on normal regions using negative prompts. Extensive experiments with the BMAD dataset, including six biomedical benchmarks, demonstrate that CLAP method enhances anomaly detection performance. Our future plans include developing an automated fine prompting method for more practical usage.