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

Felix Meissen, Philip Müller, Georgios Kaissis, Daniel Rueckert

Keywords: Metric, Pathology Detection, Object Detection

TL;DR: A novel detection metric for pathologies in medical images that better reflects the clinical needs for this task.

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](https://github.com/FeliMe/RoDeO) and published RoDeO as pip package ($rodeometric$).

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2303.01920/code)