Robust Detection Outcome: A Metric for Pathology Detection in Medical Images

Felix Meissen, Philip Müller, Georgios Kaissis, Daniel Rueckert
3/3/2023
cs.CV

Official code: FeliMe/RoDeO (12 stars, MIT, last commit 2023-08-09).

Abstract

Detection of pathologies is a fundamental task in medical imaging and the evaluation of algorithms that can perform this task automatically is crucial. However, current object detection metrics for natural images do not reflect the specific clinical requirements in pathology detection sufficiently. To tackle this problem, we propose Robust Detection Outcome (RoDeO); a novel metric for evaluating algorithms for pathology detection in medical images, especially in chest X-rays. RoDeO evaluates different errors directly and individually, and reflects clinical needs better than current metrics. Extensive evaluation on the ChestX-ray8 dataset shows the superiority of our metrics compared to existing ones. We released the code at https://github.com/FeliMe/RoDeO and published RoDeO as pip package (rodeometric).

View on arXivView PDF

Code Implementations(1)

FeliMe/RoDeOOfficial100%
MIT

Official Repository of "Robust Detection Outcome: A Metric for Pathology Detection in Medical Images"

120PythonMar 2, 20233 years agoMIT

Similar Papers

BMAD: Benchmarks for Medical Anomaly Detection

85% match1 repo1042023

Image-aware Evaluation of Generated Medical Reports

84% match2024

Reg R-CNN: Lesion Detection and Grading under Noisy Labels

83% match1 repo512019

AI-based Anomaly Detection for Clinical-Grade Histopathological Diagnostics

82% match2024

Lung Disease Detection with Vision Transformers: A Comparative Study of Machine Learning Methods

82% match2024

Anatomy-Driven Pathology Detection on Chest X-rays

82% match1 repo72023

Cite this paper

@article{meissen2023robust,
  title  = {Robust Detection Outcome: A Metric for Pathology Detection in Medical Images},
  author = {Felix Meissen and Philip Müller and Georgios Kaissis and Daniel Rueckert},
  year   = {2023},
  eprint = {2303.01920},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2303.01920v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2303.01920.svg)](https://codeofpaper.com/paper/2303.01920)

Discussion