The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)
By Bjoern H Menze, A. Jakab, Stefan Bauer, Jayashree Kalpathy-Cramer, Keyvan Farahani, J. Kirby, Y. Burren, N. Porz, J. Slotboom, Roland Wiest and 58 more. 2015
6,325 citations recorded by the source corpus.
In this paper we report the set-up and results of the Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized in conjunction with the MICCAI 2012 and 2013 conferences. Twenty state-of-the-art tumor segmentation algorithms were applied to a set of 65 multi-contrast MR scans of low- and high-grade glioma patients - manually annotated by up to four raters - and to 65 comparable scans generated using tumor image simulation software. Quantitative evaluations revealed considerable disagreement between the human raters in segmenting various tumor sub-regions (Dice scores in the range 74%-85%), illustrating the difficulty of this task. We found that different algorithms worked best for different sub-regions (reaching performance comparable to human inter-rater variability), but that no single algorithm ranked in the top for all sub-regions simultaneously. Fusing several good algorithms using a hierarchical majority vote yielded segmentations that consistently ranked above all individual algorithms, indicating remaining opportunities for further methodological improvements. The BRATS image data and manual annotations continue to be publicly available through an online evaluation system as an ongoing benchmarking resource.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Neurology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yoshua Bengio
- Dacheng Tao
- Mohit Bansal
- Percy Liang
- Sergey Levine
- Jianfeng Gao
- Quoc V. Le
- Bernt Schiele
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Ming-Hsuan Yang
- Xiaogang Wang
- Trevor Darrell
- Ling Shao
- Bernt Schiele
- Yi Yang
In Neurology
- Mingxia Liu
- Dinggang Shen
- Maciej A. Mazurowski
- Arvid Lundervold
- Ben Glocker
- Sérgio Pereira
- Carlos Alberto Silva
- Victor Alves
Citations in the corpus
- Deep Learning for Medical Image Analysis (2017, methodology): “We evaluated proposed methods on popular benchmark [9] and the outcome results compared with state-of-the art approches.”
- MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation (2019, methodology): “In order to evaluate our proposed architecture with 3D medical images, we used the magnetic resonance images (MRI) from the BraTS17 competition database [44, 45].”
- Unsupervised Medical Image Translation With Adversarial Diffusion Models (2022, neutral): “We demonstrated SynDiff on two multi-contrast brain MRI datasets (IXI, 1 BRATS [61]), and a multi-modal pelvic MRI-CT dataset [62].”
- A Deep Learning Approach for Brain Tumor Classification and Segmentation Using a Multiscale Convolutional Neural Network (2021, methodology): “Havaei et al. [10] trained several CNN neural networks with the BRATS-2013 glioma tumor dataset.”
- HyperDense-Net: A Hyper-Densely Connected CNN for Multi-Modal Image Segmentation (2018, background): “Multi-modal image segmentation in brain-related applications has received a substantial research attention, for instance, brain tumors [3]–[6], brain tissues of both infant [7]– [17] and adult [18], [19], subcortical structures [20], among other problems [21]–[23].”
- Multi-Institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentation (2018, methodology): “The inter-rater agreement for expert neuro-radiologists measured by the DC was reported in the original BraTS benchmark paper [6] equal to 0.”
- How Artificial Intelligence Is Shaping Medical Imaging Technology: A Survey of Innovations and Applications (2023, neutral): “[118]”
- A Review of Deep-Learning-Based Medical Image Segmentation Methods (2021, methodology): “Brain tumor segmentation (BRATS): This data set is a brain tumor segmentation competition data set, which is combined with the MICCAI conference [107].”
- Diffusion Models for Medical Anomaly Detection (2022, methodology): “, the BRATS2020 brain tumor challenge [16,2,3], and the CheXpert dataset [11], and compare our method against standard anomaly detection methods.”
- CaraNet: context axial reverse attention network for segmentation of small medical objects (2021, background): “They all achieved excellent performance on medical image segmentation challenges from different modalities, like BraTS [5,6,7], KiTS19 [8], and COVID19-20 [9,10].”
- A review: Deep learning for medical image segmentation using multi-modality fusion (2019, methodology): “In order to obtain accurate segmentation and compare different stateof-the-art methods, some well-known publicly challenges for segmentation are created, such as Brain Tumour Segmentation (BraTS) [48], Ischemic Stroke Le-”
- Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks (2018, neutral): “Therefore, for most existing medical image segmentation datasets, such as those in Grand challenge 4 , the image numbers are also quite small.”
- CE-Net: Context Encoder Network for 2D Medical Image Segmentation (2019, background): “, [14], [15], [16] and brain segmentation [17], [18], [19], [20], [21], [22] in computed tomography (CT) and magnetic resonance imaging (MRI).”
- A large annotated medical image dataset for the development and evaluation of segmentation algorithms (2019, methodology): “Task01_BrainTumour The brain tumour dataset included in the MSD challenge describes a subset of the data used in the 2016 and 2017 Brain Tumour Image Segmentation (BraTS) challenges [8, 9, 10].”