Filters








717 Hits in 4.6 sec

Ensembles of Multiple Models and Architectures for Robust Brain Tumour Segmentation [article]

Konstantinos Kamnitsas, Wenjia Bai, Enzo Ferrante, Steven McDonagh, Matthew Sinclair, Nick Pawlowski, Martin Rajchl, Matthew Lee, Bernhard Kainz, Daniel Rueckert, Ben Glocker
2017 arXiv   pre-print
This paper explores Ensembles of Multiple Models and Architectures (EMMA) for robust performance through aggregation of predictions from a wide range of methods.  ...  The approach reduces the influence of the meta-parameters of individual models and the risk of overfitting the configuration to a particular database.  ...  We gratefully acknowledge the support of NVIDIA with the donation of GPUs for our research.  ... 
arXiv:1711.01468v1 fatcat:4xpgd3qrdzbllhgkown3pgbi2u

Brain Tumour Image Segmentation Using Deep Networks

Mahnoor Ali, Syed Omer Gilani, Asim Waris, Kashan Zafar, Mohsin Jamil
2020 IEEE Access  
Automated segmentation of brain tumour from multimodal MR images is pivotal for the analysis and monitoring of disease progression.  ...  Extensively used for biomedical image segmentation, Convolutional Neural Networks have significantly improved the state-of-the-art accuracy on the task of brain tumour segmentation.  ...  In this work, we utilise multiple 3D CNN models for brain tumour segmentation from multimodal MRI scans and ensemble their probability maps for more stable predictions.  ... 
doi:10.1109/access.2020.3018160 fatcat:veahn632a5allkot6qxc4e72uu

Automatic Brain Tumour Segmentation and Biophysics-Guided Survival Prediction [article]

Shuo Wang, Chengliang Dai, Yuanhan Mo, Elsa Angelini, Yike Guo, Wenjia Bai
2019 arXiv   pre-print
In this paper, we compare severalstate-of-the-art convolutional neural network models for brain tumourimage segmentation.  ...  Accurate segmentation of gliomas and theirsub-regions on multi-parametric magnetic resonance images (mpMRI)is of great clinical importance, which defines tumour size, shape andappearance and provides abundant  ...  Acknowledgement This work was supported by the SmartHeart EPSRC Programme Grant (EP/P001009/1) and the NIHR Imperial Biomedical Research Centre (BRC) .  ... 
arXiv:1911.08483v1 fatcat:3oj7hzkdyfe3vfdxknszj3lnuq

Object Detection Improves Tumour Segmentation in MR Images of Rare Brain Tumours

Hamza Chegraoui, Cathy Philippe, Volodia Dangouloff-Ros, Antoine Grigis, Raphael Calmon, Nathalie Boddaert, Frédérique Frouin, Jacques Grill, Vincent Frouin
2021 Cancers  
Presently, numerous deep learning segmentation architectures have been shown to perform well on the specific tumour type they are trained on (e.g., glioblastoma in brain hemispheres).  ...  Our strategy allowed us to achieve robust segmentation inference on a rare tumour located in an unseen tumour context region during training.  ...  Combination Strategies To obtain a robust segmentation of brain tumours, we combined proven object-detection models and segmentation models.  ... 
doi:10.3390/cancers13236113 pmid:34885222 fatcat:pjuonkkpyfgh5olfmltjctqbcu

Vox2Vox: 3D-GAN for Brain Tumour Segmentation [article]

Marco Domenico Cirillo and David Abramian and Anders Eklund
2020 arXiv   pre-print
Hence, using the data provided by the BraTS Challenge 2020, we propose a 3D volume-to-volume Generative Adversarial Network for segmentation of brain tumours.  ...  scores and 6.44mm, 24.36mm, and 18.95mm for Hausdorff distance 95 percentile for the BraTS testing set after ensembling 10 Vox2Vox models obtained with a 10-fold cross-validation.  ...  Acknowledgement This study was supported by LiU Cancer, VINNOVA Analytic Imaging Diagnostics Arena (AIDA), and the ITEA3 / VINNOVA funded project Intelligence based iMprovement of Personalized treatment  ... 
arXiv:2003.13653v3 fatcat:l7r32mkujvc2voxct5fxeypfji

Automated Brain Tumour Segmentation Using Deep Fully Residual Convolutional Neural Networks [article]

Indrajit Mazumdar
2020 arXiv   pre-print
We obtained Dice scores of 0.79 for enhancing tumour, 0.90 for whole tumour, and 0.82 for tumour core on the BraTS 2018 validation set.  ...  Automated brain tumour segmentation has the potential of making a massive improvement in disease diagnosis, surgery, monitoring and surveillance. However, this task is extremely challenging.  ...  Ensembles of Multiple Models and Architectures (EMMA) [12] is an ensemble of widely varying CNN models that include two variations of DeepMedic model [11, 13] , three variations of 3D FCN model [14  ... 
arXiv:1908.04250v3 fatcat:on5kbtg7vvbolpjmsqyef3uuoe

Orthogonal Ensemble Networks for Biomedical Image Segmentation [article]

Agostina J. Larrazabal, César Martínez, Jose Dolz, Enzo Ferrante
2021 arXiv   pre-print
The experimental results show that our approach produces more robust and well-calibrated ensemble models and can deal with challenging tasks in the context of biomedical image segmentation.  ...  We benchmark the proposed framework in two challenging brain lesion segmentation tasks --brain tumor and white matter hyper-intensity segmentation in MR images.  ...  Acknowledgments The authors gratefully acknowledge NVIDIA Corporation with the donation of the GPUs used for this research, and the support of UNL (CAID-0620190100145LI, CAID-50220140100084LI) and ANPCyT  ... 
arXiv:2105.10827v1 fatcat:tqu2pvifqjdfra4coaovxz5w2e

One Network to Segment Them All: A General, Lightweight System for Accurate 3D Medical Image Segmentation [chapter]

Mathias Perslev, Erik Bjørnager Dam, Akshay Pai, Christian Igel
2019 Lecture Notes in Computer Science  
We propose a simple and thoroughly evaluated deep learning framework for segmentation of arbitrary medical image volumes.  ...  In addition, it ranked 5-th and 6-th in the first and second round of the 2018 Medical Segmentation Decathlon comprising another 10 tasks.  ...  Acknowledgements We would like to thank both Microsoft and NVIDIA for providing computational resources on the Azure platform for this project.  ... 
doi:10.1007/978-3-030-32245-8_4 fatcat:phkiypfqazhx7akmskw7ykjarm

Image classification-based brain tumour tissue segmentation

Salma Al-qazzaz, Xianfang Sun, Hong Yang, Yingxia Yang, Ronghua Xu, Len Nokes, Xin Yang
2020 Multimedia tools and applications  
Brain tumour tissue segmentation is essential for clinical decision making.  ...  In this paper, a classification-based method for automatic brain tumour tissue segmentation is proposed using combined CNNbased and hand-crafted features.  ...  Kamnitsas's method [15] used ensembles of multiple models and architectures, which consists of two deepMedic models, three 3D FCNs, and two 3D versions of the U-Net architecture [10, 33] , where U-Net  ... 
doi:10.1007/s11042-020-09661-4 fatcat:wlsj5gjcyjeixliegi24fky2em

Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation

Konstantinos Kamnitsas, Christian Ledig, Virginia F.J. Newcombe, Joanna P. Simpson, Andrew D. Kane, David K. Menon, Daniel Rueckert, Ben Glocker
2017 Medical Image Analysis  
We propose a dual pathway, 11-layers deep, three-dimensional Convolutional Neural Network for the challenging task of brain lesion segmentation.  ...  Our pipeline is extensively evaluated on three challenging tasks of lesion segmentation in multi-channel MRI patient data with traumatic brain injuries, brain tumors, and ischemic stroke.  ...  We gratefully acknowledge the support of NVIDIA Corporation with the donation of two Titan X GPUs for our research.  ... 
doi:10.1016/j.media.2016.10.004 pmid:27865153 fatcat:nuf3ml26obe4zaghbasznuzuvm

a MODE –Based Ensemble Method for Brain Tumour Diagnosis

kimia rezaei, hamed agahi, azar mahmoodzadeh
2019 IET Image Processing  
In this study, a novel multi-step method, recognising benign and malignant tumour slices in real brain computed tomography (CT) images is proposed.  ...  For the segmentation purpose, support vector machine (SVM) is performed on CT images.  ...  Acknowledgment The authors wish to acknowledge the SICAS Medical Image Repository for providing the original brain tumour images.  ... 
doi:10.1049/iet-ipr.2018.6377 fatcat:5lpl5falhffwbcg4sfp3cy4mhe

Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation [article]

Michael Yeung, Evis Sala, Carola-Bibiane Schönlieb, Leonardo Rundo
2021 arXiv   pre-print
(BUS2017), Brain Tumour Segmentation 2020 (BraTS20) and Kidney Tumour Segmentation 2019 (KiTS19).  ...  Loss functions used in the training of deep learning algorithms differ in their robustness to class imbalance, with direct consequences for model convergence.  ...  Automatic methods of tumour delineation aim to address these issues, and public datasets, such as the Kidney Tumour Segmentation 19 (KiTS19) dataset for kidney tumour CT [26] and Brain Tumour Segmentation  ... 
arXiv:2102.04525v4 fatcat:4eig7uzqnfbkxh2xauoefz5iiy

DeepMedic for Brain Tumor Segmentation [chapter]

Konstantinos Kamnitsas, Enzo Ferrante, Sarah Parisot, Christian Ledig, Aditya V. Nori, Antonio Criminisi, Daniel Rueckert, Ben Glocker
2016 Lecture Notes in Computer Science  
Accurate automatic algorithms for the segmentation of brain tumours have the potential of improving disease diagnosis, treatment planning, as well as enabling large-scale studies of the pathology.  ...  In this work we employ DeepMedic [1], a 3D CNN architecture previously presented for lesion segmentation, which we further improve by adding residual connections.  ...  We gratefully acknowledge the support of NVIDIA Corporation with the donation of two Titan X GPUs for our research.  ... 
doi:10.1007/978-3-319-55524-9_14 fatcat:habqlt25lzavtgqwuv3gye7zbi

Glioblastoma Synthesis and Segmentation with 3D Multi-Modal MRI: A Study using Generative Adversarial Networks

Edmond Wang
2021 International Journal on Computational Science & Applications  
The Grade IV cancer Glioblastoma is an extremely common and aggressive brain tumour.  ...  To see networks in action, an adjusted and calibrated Vox2Vox network - a 3D implementation of the Pix2Pix translator - is trained on the biggest public brain tumour dataset BraTS 2020.  ...  For Glioblastoma/brain tumour segmentation, both CycleGAN and Pix2Pix GAN are the state-of-the-art industry standards.  ... 
doi:10.5121/ijcsa.2021.11601 fatcat:4wjwcix2jrdrlckuoiwxnelhqq

C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation [article]

Qihang Yu, Dong Yang, Holger Roth, Yutong Bai, Yixiao Zhang, Alan L. Yuille, Daguang Xu
2020 arXiv   pre-print
the effectiveness and generalization of our searched models.  ...  Recently, Neural Architecture Search (NAS) is proposed to solve this problem by searching for the best network architecture automatically.  ...  . : brain tumours, lung tumours, hippocampus, hepatic vessel and tumours, pancreas tumours, and liver tumours, respectively.  ... 
arXiv:1912.09628v2 fatcat:zedl7ihv5zgqnk5og6rrgybi4m
« Previous Showing results 1 — 15 out of 717 results