Unlocking the Potential of Weakly Labeled Data: A Co-Evolutionary Learning Framework for Abnormality Detection and Report Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Jinghan, Wei, Dong, Xu, Zhe, Lu, Donghuan, Liu, Hong, Wang, Hong, Tsaftaris, Sotirios A., McDonagh, Steven, Zheng, Yefeng, Wang, Liansheng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912160349683712
author Sun, Jinghan
Wei, Dong
Xu, Zhe
Lu, Donghuan
Liu, Hong
Wang, Hong
Tsaftaris, Sotirios A.
McDonagh, Steven
Zheng, Yefeng
Wang, Liansheng
author_facet Sun, Jinghan
Wei, Dong
Xu, Zhe
Lu, Donghuan
Liu, Hong
Wang, Hong
Tsaftaris, Sotirios A.
McDonagh, Steven
Zheng, Yefeng
Wang, Liansheng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_13599
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Unlocking the Potential of Weakly Labeled Data: A Co-Evolutionary Learning Framework for Abnormality Detection and Report Generation
Sun, Jinghan
Wei, Dong
Xu, Zhe
Lu, Donghuan
Liu, Hong
Wang, Hong
Tsaftaris, Sotirios A.
McDonagh, Steven
Zheng, Yefeng
Wang, Liansheng
Computer Vision and Pattern Recognition
Computation and Language
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.
title Unlocking the Potential of Weakly Labeled Data: A Co-Evolutionary Learning Framework for Abnormality Detection and Report Generation
topic Computer Vision and Pattern Recognition
Computation and Language
url https://arxiv.org/abs/2412.13599