mlsanityData to 7 Oct 2026

Subject-Specific Lesion Generation and Pseudo-Healthy Synthesis for Multiple Sclerosis Brain Images

arXiv 2208.02135 ↗First posted 3 Aug 2022eess.IV cs.CV cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Understanding the intensity characteristics of brain lesions is key for defining image-based biomarkers in neurological studies and for predicting disease burden and outcome. In this work, we present a novel foreground-based generative method for modelling the local lesion characteristics that can both generate synthetic lesions on healthy images and synthesize subject-specific pseudo-healthy images from pathological images. Furthermore, the proposed method can be used as a data augmentation module to generate synthetic images for training brain image segmentation networks. Experiments on multiple sclerosis (MS) brain images acquired on magnetic resonance imaging (MRI) demonstrate that the proposed method can generate highly realistic pseudo-healthy and pseudo-pathological brain images. Data augmentation using the synthetic images improves the brain image segmentation performance compared to traditional data augmentation methods as well as a recent lesion-aware data augmentation technique, CarveMix. The code will be released at https://github.com/dogabasaran/lesion-synthesis.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 14 of its 30 references that are in the map. First posted on arXiv 3 Aug 2022.

Builds on

14 of 30 references.

References · 14

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  3. 2016Least Squares Generative Adversarial Networkscited by 1,000
  4. 2016Generative Adversarial Text to Image Synthesiscited by 735
  5. 2019Disentangled Representation Learning in Cardiac Image Analysiscited by 69
  6. 2019Attention-Guided Generative Adversarial Networks for Unsupervised Image-to-Image Translationcited by 39
  7. 2018An Introduction to Image Synthesis with Generative Adversarial Netscited by 32
  8. 2018An Adversarial Learning Approach to Medical Image Synthesis for Lesion Detectioncited by 30
  9. 2021CarveMix: A Simple Data Augmentation Method for Brain Lesion Segmentationcited by 30
  10. 2019Skin Lesion Synthesis with Generative Adversarial Networkscited by 22
  11. 2021A Structural Causal Model for MR Images of Multiple Sclerosiscited by 21
  12. 2020Pseudo-healthy synthesis with pathology disentanglement and adversarial learningcited by 19
2 more
  1. 2021Free-form tumor synthesis in computed tomography images via richer generative adversarial networkcited by 16
  2. 2019Multiple Sclerosis Lesion Synthesis in MRI using an encoder-decoder U-NETcited by 13

Built on by

Cited by year

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

5 papers.

  1. 2023LesionMix: A Lesion-Level Data Augmentation Method for Medical Image Segmentationcited by 7
  2. 20223D Brain and Heart Volume Generative Models: A Surveycited by 4
  3. 2024SegHeD+: Segmentation of Heterogeneous Data for Multiple Sclerosis Lesions with Anatomical Constraints and Lesion-aware Augmentationcited by 1
  4. 2025MSRepaint: Multiple Sclerosis Repaint with Conditional Denoising Diffusion Implicit Model for Bidirectional Lesion Filling and Synthesiscited by 1
  5. 2025Enhancing Corpus Callosum Segmentation in Fetal MRI via Pathology-Informed Domain Randomizationcited by 0