# Brain tumor segmentation with self-ensembled, deeply-supervised 3D U-net neural networks: a BraTS 2020 challenge solution

arXiv: https://arxiv.org/abs/2011.01045 · HTML: https://mlsanity.com/paper/2011.01045/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Oct 2020.

## Built on by (most cited first, 20 of 20)

- [Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation](https://mlsanity.com/paper/2102.04525/) (2021)
- [BiTr-Unet: a CNN-Transformer Combined Network for MRI Brain Tumor Segmentation](https://mlsanity.com/paper/2109.12271/) (2021)
- [The Segment Anything foundation model achieves favorable brain tumor autosegmentation accuracy on MRI to support radiotherapy treatment planning](https://mlsanity.com/paper/2304.07875/) (2023)
- [Cross-dimensional transfer learning in medical image segmentation with deep learning](https://mlsanity.com/paper/2307.15872/) (2023)
- [Quantifying U-Net Uncertainty in Multi-Parametric MRI-based Glioma Segmentation by Spherical Image Projection](https://mlsanity.com/paper/2210.06512/) (2022)
- [Improving the Segmentation of Pediatric Low-Grade Gliomas through Multitask Learning](https://mlsanity.com/paper/2111.14959/) (2021)
- [A Neural Ordinary Differential Equation Model for Visualizing Deep Neural Network Behaviors in Multi-Parametric MRI based Glioma Segmentation](https://mlsanity.com/paper/2203.00628/) (2022)
- [Optimizing Prediction of MGMT Promoter Methylation from MRI Scans using Adversarial Learning](https://mlsanity.com/paper/2201.04416/) (2022)
- [Deep Superpixel Generation and Clustering for Weakly Supervised Segmentation of Brain Tumors in MR Images](https://mlsanity.com/paper/2209.09930/) (2022)
- [DIGEST: Deeply supervIsed knowledGE tranSfer neTwork learning for brain tumor segmentation with incomplete multi-modal MRI scans](https://mlsanity.com/paper/2211.07993/) (2022)
- [Towards SAMBA: Segment Anything Model for Brain Tumor Segmentation in Sub-Sharan African Populations](https://mlsanity.com/paper/2312.11775/) (2023)
- [Advancing Brain Tumor Segmentation via Attention-based 3D U-Net Architecture and Digital Image Processing](https://mlsanity.com/paper/2510.19109/) (2025)
- [A Novel SLCA-UNet Architecture for Automatic MRI Brain Tumor Segmentation](https://mlsanity.com/paper/2307.08048/) (2023)
- [SEDNet: Shallow Encoder-Decoder Network for Brain Tumor Segmentation](https://mlsanity.com/paper/2401.13403/) (2024)
- [UPMAD-Net: A Brain Tumor Segmentation Network with Uncertainty Guidance and Adaptive Multimodal Feature Fusion](https://mlsanity.com/paper/2505.03494/) (2025)
- [Demystifying Deep Learning-based Brain Tumor Segmentation with 3D UNets and Explainable AI (XAI): A Comparative Analysis](https://mlsanity.com/paper/2510.07785/) (2025)
- [MedGEN-Bench: A Contextually Entangled Benchmark for Open-ended Multimodal Medical Generation](https://mlsanity.com/paper/2511.13135/) (2025)
- [Attention-gated U-Net model for semantic segmentation of brain tumors and feature extraction for survival prognosis](https://mlsanity.com/paper/2602.15067/) (2026)
- [DALight-3D: A Lightweight 3D U-Net for Brain Tumor Segmentation from Multi-Modal MRI](https://mlsanity.com/paper/2605.04518/) (2026)
- [Degradation-Aware Blur-Segmentation of Brain Tumor](https://mlsanity.com/paper/2605.15671/) (2026)

## Abstract (arXiv)

Brain tumor segmentation is a critical task for patient's disease management. In order to automate and standardize this task, we trained multiple U-net like neural networks, mainly with deep supervision and stochastic weight averaging, on the Multimodal Brain Tumor Segmentation Challenge (BraTS) 2020 training dataset. Two independent ensembles of models from two different training pipelines were trained, and each produced a brain tumor segmentation map. These two labelmaps per patient were then merged, taking into account the performance of each ensemble for specific tumor subregions. Our performance on the online validation dataset with test time augmentation were as follows: Dice of 0.81, 0.91 and 0.85; Hausdorff (95%) of 20.6, 4,3, 5.7 mm for the enhancing tumor, whole tumor and tumor core, respectively. Similarly, our solution achieved a Dice of 0.79, 0.89 and 0.84, as well as Hausdorff (95%) of 20.4, 6.7 and 19.5mm on the final test dataset, ranking us among the top ten teams. More complicated training schemes and neural network architectures were investigated without significant performance gain at the cost of greatly increased training time. Overall, our approach yielded good and balanced performance for each tumor subregion. Our solution is open sourced at https://github.com/lescientifik/open_brats2020.