mlsanityData to 14 Oct 2026

MAPPING: Model Average with Post-processing for Stroke Lesion Segmentation

arXiv 2211.15486 ↗First posted 11 Nov 2022eess.IV cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Accurate stroke lesion segmentation plays a pivotal role in stroke rehabilitation research, to provide lesion shape and size information which can be used for quantification of the extent of the stroke and to assess treatment efficacy. Recently, automatic segmentation algorithms using deep learning techniques have been developed and achieved promising results. In this report, we present our stroke lesion segmentation model based on nnU-Net framework, and apply it to the Anatomical Tracings of Lesions After Stroke (ATLAS v2.0) dataset. Furthermore, we describe an effective post-processing strategy that can improve some segmentation metrics. Our method took the first place in the 2022 MICCAI ATLAS Challenge with an average Dice score of 0.6667, Lesion-wise F1 score of 0.5643, Simple Lesion Count score of 4.5367, and Volume Difference score of 8804.9102. Our code and trained model weights are publicly available at https://github.com/King-HAW/ATLAS-R2-Docker-Submission.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 11 of its 20 references that are in the map. First posted on arXiv 11 Nov 2022.

Builds on

11 of 20 references.

References · 11

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  4. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  5. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
  6. 2022ISLES 2022: A multi-center magnetic resonance imaging stroke lesion segmentation datasetcited by 106
  7. 2017Learning with Average Top-k Losscited by 52
  8. 2021CarveMix: A Simple Data Augmentation Method for Brain Lesion Segmentationcited by 30
  9. 2022Brain Lesion Synthesis via Progressive Adversarial Variational Auto-Encodercited by 8
  10. 2019Automatic Post-Stroke Lesion Segmentation on MR Images using 3D Residual Convolutional Neural Networkcited by 7
  11. 2020Brain Stroke Lesion Segmentation Using Consistent Perception Generative Adversarial Networkcited by 4

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 5; 2025: 1.

9 papers.

  1. 2024Transformers-based architectures for stroke segmentation: A reviewcited by 5
  2. 2024ISLES'24: Final Infarct Prediction with Multimodal Imaging and Clinical Data. Where Do We Stand?cited by 4
  3. 2024Deep models for stroke segmentation: do complex architectures always perform better?cited by 3
  4. 2024Segmenting Small Stroke Lesions with Novel Labeling Strategiescited by 2
  5. 2023ARHNet: Adaptive Region Harmonization for Lesion-aware Augmentation to Improve Segmentation Performancecited by 1
  6. 2023BeSt-LeS: Benchmarking Stroke Lesion Segmentation using Deep Supervisioncited by 1
  7. 2023Fuzzy Information Seeded Region Growing for Automated Lesions After Stroke Segmentation in MR Brain Imagescited by 1
  8. 2024Neuro-TransUNet: Segmentation of stroke lesion in MRI using transformerscited by 0
  9. 2025Stroke Lesion Segmentation using Multi-Stage Cross-Scale Attentioncited by 0