# Brain Tumor Segmentation using an Ensemble of 3D U-Nets and Overall Survival Prediction using Radiomic Features

arXiv: https://arxiv.org/abs/1812.01049 · HTML: https://mlsanity.com/paper/1812.01049/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2018.

## Built on by (most cited first, 30 of 33)

- [Are we using appropriate segmentation metrics? Identifying correlates of human expert perception for CNN training beyond rolling the DICE coefficient](https://mlsanity.com/paper/2103.06205/) (2021)
- [Mediastinal lymph nodes segmentation using 3D convolutional neural network ensembles and anatomical priors guiding](https://mlsanity.com/paper/2102.06515/) (2021)
- [Orthogonal Ensemble Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/2105.10827/) (2021)
- [QUBIQ: Uncertainty Quantification for Biomedical Image Segmentation Challenge](https://mlsanity.com/paper/2405.18435/) (2024)
- [Point-Unet: A Context-aware Point-based Neural Network for Volumetric Segmentation](https://mlsanity.com/paper/2203.08964/) (2022)
- [AeroPath: An airway segmentation benchmark dataset with challenging pathology](https://mlsanity.com/paper/2311.01138/) (2023)
- [Meningioma segmentation in T1-weighted MRI leveraging global context and attention mechanisms](https://mlsanity.com/paper/2101.07715/) (2021)
- [3D AGSE-VNet: An Automatic Brain Tumor MRI Data Segmentation Framework](https://mlsanity.com/paper/2107.12046/) (2021)
- [Improving Across-Dataset Brain Tissue Segmentation Using Transformer](https://mlsanity.com/paper/2201.08741/) (2022)
- [Automatic Segmentation of Head and Neck Tumor: How Powerful Transformers Are?](https://mlsanity.com/paper/2201.06251/) (2022)
- [Glioblastoma Multiforme Prognosis: MRI Missing Modality Generation, Segmentation and Radiogenomic Survival Prediction](https://mlsanity.com/paper/2104.01149/) (2021)
- [Cherry-Picking Gradients: Learning Low-Rank Embeddings of Visual Data via Differentiable Cross-Approximation](https://mlsanity.com/paper/2105.14250/) (2021)
- [ME-Net: Multi-Encoder Net Framework for Brain Tumor Segmentation](https://mlsanity.com/paper/2203.11213/) (2022)
- [3DConvCaps: 3DUnet with Convolutional Capsule Encoder for Medical Image Segmentation](https://mlsanity.com/paper/2205.09299/) (2022)
- [Artificial Intelligence in Tumor Subregion Analysis Based on Medical Imaging: A Review](https://mlsanity.com/paper/2103.13588/) (2021)
- [Multi-modal Brain Tumor Segmentation via Missing Modality Synthesis and Modality-level Attention Fusion](https://mlsanity.com/paper/2203.04586/) (2022)
- [MMMNA-Net for Overall Survival Time Prediction of Brain Tumor Patients](https://mlsanity.com/paper/2206.06267/) (2022)
- [Integrating Edges into U-Net Models with Explainable Activation Maps for Brain Tumor Segmentation using MR Images](https://mlsanity.com/paper/2401.01303/) (2024)
- [A Survey and Analysis on Automated Glioma Brain Tumor Segmentation and Overall Patient Survival Prediction](https://mlsanity.com/paper/2101.10599/) (2021)
- [EXACT-Net:EHR-guided lung tumor auto-segmentation for non-small cell lung cancer radiotherapy](https://mlsanity.com/paper/2402.14099/) (2024)
- [M-Net: MRI Brain Tumor Sequential Segmentation Network via Mesh-Cast](https://mlsanity.com/paper/2507.20582/) (2025)
- [Analysis of MRI Biomarkers for Brain Cancer Survival Prediction](https://mlsanity.com/paper/2109.02785/) (2021)
- [Super Images -- A New 2D Perspective on 3D Medical Imaging Analysis](https://mlsanity.com/paper/2205.02847/) (2022)
- [Future Artificial Intelligence tools and perspectives in medicine](https://mlsanity.com/paper/2206.03289/) (2022)
- [CNN-based fully automatic wrist cartilage volume quantification in MR Image](https://mlsanity.com/paper/2206.11127/) (2022)
- [Comparative Analysis of State-of-the-Art Deep Learning Models for Detecting COVID-19 Lung Infection from Chest X-Ray Images](https://mlsanity.com/paper/2208.01637/) (2022)
- [Ensemble uncertainty as a criterion for dataset expansion in distinct bone segmentation from upper-body CT images](https://mlsanity.com/paper/2208.09216/) (2022)
- [Medical Image Analysis using Deep Relational Learning](https://mlsanity.com/paper/2303.16099/) (2023)
- [Diagnosis and Prognosis of Head and Neck Cancer Patients using Artificial Intelligence](https://mlsanity.com/paper/2306.00034/) (2023)
- [Image Synthesis-based Late Stage Cancer Augmentation and Semi-Supervised Segmentation for MRI Rectal Cancer Staging](https://mlsanity.com/paper/2312.04779/) (2023)

## Abstract (arXiv)

Accurate segmentation of different sub-regions of gliomas including peritumoral edema, necrotic core, enhancing and non-enhancing tumor core from multimodal MRI scans has important clinical relevance in diagnosis, prognosis and treatment of brain tumors. However, due to the highly heterogeneous appearance and shape, segmentation of the sub-regions is very challenging. Recent development using deep learning models has proved its effectiveness in the past several brain segmentation challenges as well as other semantic and medical image segmentation problems. Most models in brain tumor segmentation use a 2D/3D patch to predict the class label for the center voxel and variant patch sizes and scales are used to improve the model performance. However, it has low computation efficiency and also has limited receptive field. U-Net is a widely used network structure for end-to-end segmentation and can be used on the entire image or extracted patches to provide classification labels over the entire input voxels so that it is more efficient and expect to yield better performance with larger input size. Furthermore, instead of picking the best network structure, an ensemble of multiple models, trained on different dataset or different hyper-parameters, can generally improve the segmentation performance. In this study we propose to use an ensemble of 3D U-Nets with different hyper-parameters for brain tumor segmentation. Preliminary results showed effectiveness of this model. In addition, we developed a linear model for survival prediction using extracted imaging and non-imaging features, which, despite the simplicity, can effectively reduce overfitting and regression errors.