Unlocking the Potential of Weakly Labeled Data: A Co-Evolutionary Learning Framework for Abnormality Detection and Report Generation
This addresses the challenge of integrating detection and report generation in medical imaging for clinical practice, offering a novel approach but with incremental improvements over existing methods.
The paper tackles the joint problem of anatomical abnormality detection and report generation in chest X-rays by proposing a co-evolutionary framework that leverages both fully and weakly labeled data, achieving state-of-the-art results with improvements such as a 3.2% gain in detection mAP and 2.1% in report generation BLEU-4 scores.
Anatomical abnormality detection and report generation of chest X-ray (CXR) are two essential tasks in clinical practice. The former aims at localizing and characterizing cardiopulmonary radiological findings in CXRs, while the latter summarizes the findings in a detailed report for further diagnosis and treatment. Existing methods often focused on either task separately, ignoring their correlation. This work proposes a co-evolutionary abnormality detection and report generation (CoE-DG) framework. The framework utilizes both fully labeled (with bounding box annotations and clinical reports) and weakly labeled (with reports only) data to achieve mutual promotion between the abnormality detection and report generation tasks. Specifically, we introduce a bi-directional information interaction strategy with generator-guided information propagation (GIP) and detector-guided information propagation (DIP). For semi-supervised abnormality detection, GIP takes the informative feature extracted by the generator as an auxiliary input to the detector and uses the generator's prediction to refine the detector's pseudo labels. We further propose an intra-image-modal self-adaptive non-maximum suppression module (SA-NMS). This module dynamically rectifies pseudo detection labels generated by the teacher detection model with high-confidence predictions by the student.Inversely, for report generation, DIP takes the abnormalities' categories and locations predicted by the detector as input and guidance for the generator to improve the generated reports.