Contrastive Language Prompting to Ease False Positives in Medical Anomaly Detection

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Park, YeongHyeon, Kim, Myung Jin, Kim, Hyeong Seok
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913692028764160
author Park, YeongHyeon
Kim, Myung Jin
Kim, Hyeong Seok
author_facet Park, YeongHyeon
Kim, Myung Jin
Kim, Hyeong Seok
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_07546
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Contrastive Language Prompting to Ease False Positives in Medical Anomaly Detection
Park, YeongHyeon
Kim, Myung Jin
Kim, Hyeong Seok
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
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.
title Contrastive Language Prompting to Ease False Positives in Medical Anomaly Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2411.07546