Towards Robust General Medical Image Segmentation

07/09/2021
by   Laura Daza, et al.
0

The reliability of Deep Learning systems depends on their accuracy but also on their robustness against adversarial perturbations to the input data. Several attacks and defenses have been proposed to improve the performance of Deep Neural Networks under the presence of adversarial noise in the natural image domain. However, robustness in computer-aided diagnosis for volumetric data has only been explored for specific tasks and with limited attacks. We propose a new framework to assess the robustness of general medical image segmentation systems. Our contributions are two-fold: (i) we propose a new benchmark to evaluate robustness in the context of the Medical Segmentation Decathlon (MSD) by extending the recent AutoAttack natural image classification framework to the domain of volumetric data segmentation, and (ii) we present a novel lattice architecture for RObust Generic medical image segmentation (ROG). Our results show that ROG is capable of generalizing across different tasks of the MSD and largely surpasses the state-of-the-art under sophisticated adversarial attacks.

READ FULL TEXT
research
07/14/2023

Frequency Domain Adversarial Training for Robust Volumetric Medical Segmentation

It is imperative to ensure the robustness of deep learning models in cri...
research
05/18/2023

Quantifying the robustness of deep multispectral segmentation models against natural perturbations and data poisoning

In overhead image segmentation tasks, including additional spectral band...
research
07/05/2022

Vector Quantisation for Robust Segmentation

The reliability of segmentation models in the medical domain depends on ...
research
11/10/2021

Trustworthy Medical Segmentation with Uncertainty Estimation

Deep Learning (DL) holds great promise in reshaping the healthcare syste...
research
10/29/2020

Volumetric Medical Image Segmentation: A 3D Deep Coarse-to-fine Framework and Its Adversarial Examples

Although deep neural networks have been a dominant method for many 2D vi...
research
08/01/2019

Robustifying deep networks for image segmentation

Purpose: The purpose of this study is to investigate the robustness of a...
research
07/01/2022

Online Reflective Learning for Robust Medical Image Segmentation

Deep segmentation models often face the failure risks when the testing i...

Please sign up or login with your details

Forgot password? Click here to reset