mlsanityData to 7 Oct 2026

Towards Robust General Medical Image Segmentation

arXiv 2107.04263 ↗First posted 9 Jul 2021cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 35 of its 39 references that are in the map. First posted on arXiv 9 Jul 2021.

Builds on

35 of 39 references.

References · 35

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  7. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  8. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  9. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  10. 2016Universal adversarial perturbationscited by 774
  11. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  12. 2019Adversarial Training for Free!cited by 638
23 more
  1. 2019UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentationcited by 583
  2. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  3. 2019On Evaluating Adversarial Robustnesscited by 442
  4. 2019A large annotated medical image dataset for the development and evaluation of segmentation algorithmscited by 371
  5. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
  6. 2018nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentationcited by 291
  7. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  8. 2019Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systemscited by 151
  9. 2017On the Robustness of Semantic Segmentation Models to Adversarial Attackscited by 126
  10. 2020nnU-Net for Brain Tumor Segmentationcited by 103
  11. 2018Curriculum Adversarial Trainingcited by 89
  12. 2020Smooth Adversarial Trainingcited by 89
  13. 2019Towards Adversarially Robust Object Detectioncited by 55
  14. 2017Houdini: Fooling Deep Structured Prediction Modelscited by 50
  15. 2019C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentationcited by 49
  16. 2019V-NAS: Neural Architecture Search for Volumetric Medical Image Segmentationcited by 27
  17. 2019Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentationcited by 26
  18. 2018Defending Against Universal Perturbations With Shared Adversarial Trainingcited by 25
  19. 2019One Network to Segment Them All: A General, Lightweight System for Accurate 3D Medical Image Segmentationcited by 24
  20. 2019NoduleNet: Decoupled False Positive Reductionfor Pulmonary Nodule Detection and Segmentationcited by 21
  21. 2017A 3D Coarse-to-Fine Framework for Volumetric Medical Image Segmentationcited by 20
  22. 2020Improving the affordability of robustness training for DNNscited by 8
  23. 2020Volumetric Medical Image Segmentation: A 3D Deep Coarse-to-fine Framework and Its Adversarial Examplescited by 5

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 3; 2023: 4; 2024: 4; 2025: 2.

14 papers.

Sort:

By area:

  1. 2022SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustnesscited by 74
  2. 2023Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challengescited by 16
  3. 2023Frequency Domain Adversarial Training for Robust Volumetric Medical Segmentationcited by 6
  4. 2022Robust Prototypical Few-Shot Organ Segmentation with Regularized Neural-ODEscited by 5
  5. 2022Adaptive Adversarial Training to Improve Adversarial Robustness of DNNs for Medical Image Segmentation and Detectioncited by 4
  6. 2023Certification of Deep Learning Models for Medical Image Segmentationcited by 4
  7. 2024On Evaluating Adversarial Robustness of Volumetric Medical Segmentation Modelscited by 2
  8. 2021Medical Aegis: Robust adversarial protectors for medical imagescited by 1
  9. 2023JoB-VS: Joint Brain-Vessel Segmentation in TOF-MRA Imagescited by 1
  10. 2024Mitigating False Predictions In Unreasonable Body Regionscited by 1
  11. 2024Integrating uncertainty quantification into randomized smoothing based robustness guaranteescited by 1
  12. 2025GLoG-CSUnet: Enhancing Vision Transformers with Adaptable Radiomic Features for Medical Image Segmentationcited by 1
2 more
  1. 2025Synthetic Data-Driven Multi-Architecture Framework for Automated Polyp Segmentation Through Integrated Detection and Mask Generationcited by 1
  2. 2024The Limits of Perception: Analyzing Inconsistencies in Saliency Maps in XAIcited by 0