# CarveMix: A Simple Data Augmentation Method for Brain Lesion Segmentation

arXiv: https://arxiv.org/abs/2108.06883 · HTML: https://mlsanity.com/paper/2108.06883/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 64 references that are in the map.
- First posted on arXiv 16 Aug 2021.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation](https://mlsanity.com/paper/2012.07177/) (2020)
- [Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation](https://mlsanity.com/paper/1603.05959/) (2016)
- [Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation](https://mlsanity.com/paper/1908.10454/) (2019)
- [Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection](https://mlsanity.com/paper/1708.01642/) (2017)
- [Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentation](https://mlsanity.com/paper/1808.01200/) (2018)
- [Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity](https://mlsanity.com/paper/2102.03065/) (2021)
- [Modeling Visual Context is Key to Augmenting Object Detection Datasets](https://mlsanity.com/paper/1807.07428/) (2018)
- [InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting](https://mlsanity.com/paper/1908.07801/) (2019)
- [Detecting Outliers with Foreign Patch Interpolation](https://mlsanity.com/paper/2011.04197/) (2020)
- [Analyzing Overfitting under Class Imbalance in Neural Networks for Image Segmentation](https://mlsanity.com/paper/2102.10365/) (2021)
- [Smoothness and Stability in GANs](https://mlsanity.com/paper/2002.04185/) (2020)
- [Semi-supervised Task-driven Data Augmentation for Medical Image Segmentation](https://mlsanity.com/paper/2007.05363/) (2020)
- [Enhancing MR Image Segmentation with Realistic Adversarial Data Augmentation](https://mlsanity.com/paper/2108.03429/) (2021)
- [A Contrast-Adaptive Method for Simultaneous Whole-Brain and Lesion Segmentation in Multiple Sclerosis](https://mlsanity.com/paper/2005.05135/) (2020)
- [ROAM: Random Layer Mixup for Semi-Supervised Learning in Medical Imaging](https://mlsanity.com/paper/2003.09439/) (2020)

## Built on by (most cited first, 30 of 30)

- [A Foundation Model for Brain Lesion Segmentation with Mixture of Modality Experts](https://mlsanity.com/paper/2405.10246/) (2024)
- [MAPPING: Model Average with Post-processing for Stroke Lesion Segmentation](https://mlsanity.com/paper/2211.15486/) (2022)
- [Brain Lesion Synthesis via Progressive Adversarial Variational Auto-Encoder](https://mlsanity.com/paper/2208.03203/) (2022)
- [Augmenting Medical Imaging: A Comprehensive Catalogue of 65 Techniques for Enhanced Data Analysis](https://mlsanity.com/paper/2303.01178/) (2023)
- [LesionMix: A Lesion-Level Data Augmentation Method for Medical Image Segmentation](https://mlsanity.com/paper/2308.09026/) (2023)
- [Brain-Aware Replacements for Supervised Contrastive Learning in Detection of Alzheimer's Disease](https://mlsanity.com/paper/2207.04574/) (2022)
- [Data efficient deep learning for medical image analysis: A survey](https://mlsanity.com/paper/2310.06557/) (2023)
- [Subject-Specific Lesion Generation and Pseudo-Healthy Synthesis for Multiple Sclerosis Brain Images](https://mlsanity.com/paper/2208.02135/) (2022)
- [One-Shot Segmentation of Novel White Matter Tracts via Extensive Data Augmentation](https://mlsanity.com/paper/2303.06852/) (2023)
- [Synthetic Data for Robust Stroke Segmentation](https://mlsanity.com/paper/2404.01946/) (2024)
- [ARHNet: Adaptive Region Harmonization for Lesion-aware Augmentation to Improve Segmentation Performance](https://mlsanity.com/paper/2307.01220/) (2023)
- [Local Gamma Augmentation for Ischemic Stroke Lesion Segmentation on MRI](https://mlsanity.com/paper/2401.06893/) (2024)
- [Adaptive Sensitivity Analysis for Robust Augmentation against Natural Corruptions in Image Segmentation](https://mlsanity.com/paper/2406.01425/) (2024)
- [Labeled-to-Unlabeled Distribution Alignment for Partially-Supervised Multi-Organ Medical Image Segmentation](https://mlsanity.com/paper/2409.03228/) (2024)
- [SegHeD+: Segmentation of Heterogeneous Data for Multiple Sclerosis Lesions with Anatomical Constraints and Lesion-aware Augmentation](https://mlsanity.com/paper/2412.10946/) (2024)
- [USegMix: Unsupervised Segment Mix for Efficient Data Augmentation in Pathology Images](https://mlsanity.com/paper/2502.16160/) (2025)
- [Benchmarking and Explaining Deep Learning Cortical Lesion MRI Segmentation in Multiple Sclerosis](https://mlsanity.com/paper/2507.12092/) (2025)
- [MSRepaint: Multiple Sclerosis Repaint with Conditional Denoising Diffusion Implicit Model for Bidirectional Lesion Filling and Synthesis](https://mlsanity.com/paper/2510.02063/) (2025)
- [Cut to the Mix: Simple Data Augmentation Outperforms Elaborate Ones in Limited Organ Segmentation Datasets](https://mlsanity.com/paper/2602.03555/) (2026)
- [Advanced Tumor Segmentation in PET/CT Imaging: A Training Strategy Study with nnU-Net for AutoPET III](https://mlsanity.com/paper/2605.08161/) (2026)
- [Learning Transferable Object-Centric Diffeomorphic Transformations for Data Augmentation in Medical Image Segmentation](https://mlsanity.com/paper/2307.13645/) (2023)
- [CONSULT: Contrastive Self-Supervised Learning for Few-shot Tumor Detection](https://mlsanity.com/paper/2410.11307/) (2024)
- [Enhancing Medical Image Analysis through Geometric and Photometric transformations](https://mlsanity.com/paper/2501.13643/) (2025)
- [Multi-modal Liver Segmentation and Fibrosis Staging Using Real-world MRI Images](https://mlsanity.com/paper/2509.26061/) (2025)
- [From Healthy Scans to Annotated Tumors: A Tumor Fabrication Framework for 3D Brain MRI Synthesis](https://mlsanity.com/paper/2511.18654/) (2025)
- [Data-Efficient Meningioma Segmentation via Implicit Spatiotemporal Mixing and Sim2Real Semantic Injection](https://mlsanity.com/paper/2601.17031/) (2026)
- [Decomposing Subject-Driven Image Generation via Intermediate Structural Prediction](https://mlsanity.com/paper/2605.20807/) (2026)
- [OTLesMix: Wasserstein Barycenter and Optimal Transport Map for Synthetic Lesion Generation with Diverse Shapes and Locations](https://mlsanity.com/paper/2608.06264/) (2026)
- [Native-Space 3D CarveMix for Multi-Site T1w Stroke Segmentation](https://mlsanity.com/paper/2608.23882/) (2026)
- [CarveMix-RC: Addressing Rare-Class Imbalance Through Lesion-Aware Synthetic Augmentation for Brain Metastasis Segmentation](https://mlsanity.com/paper/2609.35195/) (2026)

## Abstract (arXiv)

Brain lesion segmentation provides a valuable tool for clinical diagnosis, and convolutional neural networks (CNNs) have achieved unprecedented success in the task. Data augmentation is a widely used strategy that improves the training of CNNs, and the design of the augmentation method for brain lesion segmentation is still an open problem. In this work, we propose a simple data augmentation approach, dubbed as CarveMix, for CNN-based brain lesion segmentation. Like other "mix"-based methods, such as Mixup and CutMix, CarveMix stochastically combines two existing labeled images to generate new labeled samples. Yet, unlike these augmentation strategies based on image combination, CarveMix is lesion-aware, where the combination is performed with an attention on the lesions and a proper annotation is created for the generated image. Specifically, from one labeled image we carve a region of interest (ROI) according to the lesion location and geometry, and the size of the ROI is sampled from a probability distribution. The carved ROI then replaces the corresponding voxels in a second labeled image, and the annotation of the second image is replaced accordingly as well. In this way, we generate new labeled images for network training and the lesion information is preserved. To evaluate the proposed method, experiments were performed on two brain lesion datasets. The results show that our method improves the segmentation accuracy compared with other simple data augmentation approaches.