Robustness Testing of Black-Box Models Against CT Degradation Through Test-Time Augmentation

TL;DR

This paper introduces a framework for testing the robustness of black-box deep learning models in medical imaging against CT image quality degradation, emphasizing the impact of model architecture and data preprocessing.

Contribution

It presents a novel test-time augmentation method enabling independent robustness evaluation using only a few local cases, addressing model sustainability amidst imaging protocol shifts.

Findings

Model architecture and preprocessing significantly influence robustness.

The framework effectively simulates CT artifacts and degradation.

It helps assess model performance under future image quality changes.

Abstract

Deep learning models for medical image segmentation and object detection are becoming increasingly available as clinical products. However, as details are rarely provided about the training data, models may unexpectedly fail when cases differ from those in the training distribution. An approach allowing potential users to independently test the robustness of a model, treating it as a black box and using only a few cases from their own site, is key for adoption. To address this, a method to test the robustness of these models against CT image quality variation is presented. In this work we present this framework by demonstrating that given the same training data, the model architecture and data pre processing greatly affect the robustness of several frequently used segmentation and object detection methods to simulated CT imaging artifacts and degradation. Our framework also addresses the concern about the sustainability of deep learning models in clinical use, by considering future shifts in image quality due to scanner deterioration or imaging protocol changes which are not reflected in a limited local test dataset.