SP-Det: Self-Prompted Dual-Text Fusion for Generalized Multi-Label Lesion Detection
This addresses the labor-intensive and impractical reliance on expert-annotated prompts in clinical applications for multi-label lesion detection, representing a novel method for a known bottleneck.
The paper tackled the problem of automated lesion detection in chest X-rays by proposing SP-Det, a self-prompted framework that eliminates the need for manual annotations, resulting in outperforming state-of-the-art methods on two datasets.
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.