SP-Det: Self-Prompted Dual-Text Fusion for Generalized Multi-Label Lesion Detection

TL;DR

SP-Det introduces a self-prompted, expert-free framework for multi-label lesion detection in chest X-rays, utilizing dual-text prompts and feature enhancement to improve accuracy without manual annotations.

Contribution

It presents a novel self-prompted detection method with dual-text prompt generation and bidirectional feature enhancement, eliminating the need for expert annotations in lesion detection.

Findings

Outperforms state-of-the-art detection methods on chest X-ray datasets.

Eliminates dependency on expert-annotated prompts.

Improves feature representation and detection accuracy.

Abstract

Automated lesion detection in chest X-rays has demonstrated significant potential for improving clinical diagnosis by precisely localizing pathological abnormalities. While recent promptable detection frameworks have achieved remarkable accuracy in target localization, existing methods typically rely on manual annotations as prompts, which are labor-intensive and impractical for clinical applications. To address this limitation, we propose SP-Det, a novel self-prompted detection framework that automatically generates rich textual context to guide multi-label lesion detection without requiring expert annotations. Specifically, we introduce an expert-free dual-text prompt generator (DTPG) that leverages two complementary textual modalities: semantic context prompts that capture global pathological patterns and disease beacon prompts that focus on disease-specific manifestations. Moreover, we devise a bidirectional feature enhancer (BFE) that synergistically integrates comprehensive diagnostic context with disease-specific embeddings to significantly improve feature representation and detection accuracy. Extensive experiments on two chest X-ray datasets with diverse thoracic disease categories demonstrate that our SP-Det framework outperforms state-of-the-art detection methods while completely eliminating the dependency on expert-annotated prompts compared to existing promptable architectures.