DeepMedic for Brain Tumor Segmentation

By Konstantinos Kamnitsas, Enzo Ferrante, Sarah Parisot, Christian Ledig, Aditya V. Nori, Antonio Criminisi, Daniel Rueckert, Ben Glocker. BrainLes@MICCAI, 2016

325 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Neurology, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/0824550ffc8417d291f74c36a84b9082e91721aa

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Neurology

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Contrastive learning of global and local features for medical image segmentation with limited annotations (2020, background): “Supervised deep learning provides state-of-the-art medical image segmentation [49, 41, 32, 33], when large labeled datasets are available .”
Autofocus Layer for Semantic Segmentation (2018, methodology): “To demonstrate this, we chose DeepMedic ( Dm ) [9] with residual connections [8] as a starting point.”
MRI Augmentation via Elastic Registration for Brain Lesions Segmentation (2017, methodology): “We wanted to reproduce the architecture and the training procedure as close as possible to the original, so in our experiments we use the architecture from [13], since this paper has more details than more recent [12].”
No New-Net (2018, background): “Kamnitsas et al. later enhanced their architectures with residual connections for BraTS 2016 [11].”
3D Deep Learning on Medical Images: A Review (2020, methodology): “Researchers are working on reaching human-level performance for many tasks (known as Artificial General Intelligence) [24], [42], [98], [99].”
Brain Tumor Segmentation and Radiomics Survival Prediction: Contribution to the BRATS 2017 Challenge (2017, background): “For their submission to the brain tumor segmentation challenge in 2016 [8], they enhanced their architecture through the addition of residual connections, yielding minor improvements.”
Deep learning for segmentation of brain tumors: Impact of cross‐institutional training and testing (2018, background): “Medical Physics, 45 (3), March 2018 1154 AlBadawy et al.”
Ensembles of Multiple Models and Architectures for Robust Brain Tumour Segmentation (2017, methodology): “The ﬁrst is the residual version previously employed in BRATS 2016 [22], depicted in Fig.”
Deep learning based brain tumor segmentation: a survey (2020, methodology): “EMMA ensembles segmentation results from DeepMedic [131], FCN [40] and U-Net [41] and associated the final segmentation with the highest confidence score.”
Key challenges for delivering clinical impact with artificial intelligence (2019, methodology): “…algorithms for interpreting chest radiographs [5 – 9], detecting cancer in mammograms [10, 11], analysing computer tomography scans [12 – 15], identifying brain tumours on magnetic resonance images [16], and predicting development of Alzheimer ’ s disease from positron emission tomography [17].”
Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks (2017, unknown): “3D convolutions require the image patches and/or volumes to be isotropic in 3D (Kamnitsas et al., 2015, 2016b).”