mlsanityData to 7 Oct 2026

Learn to Ignore: Domain Adaptation for Multi-Site MRI Analysis

arXiv 2110.06803 ↗First posted 13 Oct 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

The limited availability of large image datasets, mainly due to data privacy and differences in acquisition protocols or hardware, is a significant issue in the development of accurate and generalizable machine learning methods in medicine. This is especially the case for Magnetic Resonance (MR) images, where different MR scanners introduce a bias that limits the performance of a machine learning model. We present a novel method that learns to ignore the scanner-related features present in MR images, by introducing specific additional constraints on the latent space. We focus on a real-world classification scenario, where only a small dataset provides images of all classes. Our method textitLearn to Ignore (L2I) outperforms state-of-the-art domain adaptation methods on a multi-site MR dataset for a classification task between multiple sclerosis patients and healthy controls.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 28 of its 52 references that are in the map. First posted on arXiv 13 Oct 2021.

Builds on

28 of 52 references.

References · 28

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  4. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  5. 2020Supervised Contrastive Learningcited by 2,803
  6. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  7. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  8. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  9. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 405
  10. 2021Domain Adaptation for Medical Image Analysis: A Surveycited by 351
  11. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 322
  12. 2020Contrastive learning of global and local features for medical image segmentation with limited annotationscited by 309
16 more
  1. 2015Simultaneous Deep Transfer Across Domains and Taskscited by 205
  2. 2017Generate To Adapt: Aligning Domains using Generative Adversarial Networkscited by 183
  3. 2019Automated brain extraction of multi-sequence MRI using artificial neural networkscited by 133
  4. 2016Unsupervised domain adaptation in brain lesion segmentation with adversarial networkscited by 125
  5. 2017Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenescited by 105
  6. 2018Unsupervised domain adaptation for medical imaging segmentation with self-ensemblingcited by 94
  7. 2017Deep MR to CT Synthesis using Unpaired Datacited by 86
  8. 2019Disentangled Representation Learning in Cardiac Image Analysiscited by 69
  9. 2019The reliability of a deep learning model in clinical out-of-distribution MRI data: a multicohort studycited by 38
  10. 2020A Learning Strategy for Contrast-agnostic MRI Segmentationcited by 35
  11. 2020Joint Contrastive Learning for Unsupervised Domain Adaptationcited by 25
  12. 2018One-shot domain adaptation in multiple sclerosis lesion segmentation using convolutional neural networkscited by 20
  13. 2017Residual Parameter Transfer for Deep Domain Adaptationcited by 8
  14. 2017Adversarial Transfer Learning for Cross-domain Visual Recognitioncited by 4
  15. 2020Projective Latent Interventions for Understanding and Fine-tuning Classifierscited by 3
  16. 2021Unsupervised Domain Adaptation with Semantic Consistency across Heterogeneous Modalities for MRI Prostate Lesion Segmentationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 0; 2025: 1; 2026: 1.

5 papers.

  1. 2023Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectivescited by 24
  2. 2023CoactSeg: Learning from Heterogeneous Data for New Multiple Sclerosis Lesion Segmentationcited by 9
  3. 2023Reverse Engineering Breast MRIs: Predicting Acquisition Parameters Directly from Imagescited by 7
  4. 2025Learning from Heterogeneous Structural MRI via Collaborative Domain Adaptation for Late-Life Depression Assessmentcited by 0
  5. 2026Self-Supervised Multi-Stage Domain Unlearning for White-Matter Lesion Segmentationcited by 0