Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries

The Dice overlap ratio is commonly used to evaluate the performance of image segmentation algorithms. While Dice overlap is very useful as a standardized quantitative measure of segmentation accuracy in many applications, it offers a very limited picture of segmentation quality in complex segmentation tasks where the number of target objects is not known a priori, such as the segmentation of white matter lesions or lung nodules. While Dice overlap can still be used in these applications, segmentation algorithms may perform quite differently in ways not reflected by differences in their Dice score. Here we propose a new set of evaluation techniques that offer new insights into the behavior of segmentation algorithms. We illustrate these techniques with a case study comparing two popular multiple sclerosis (MS) lesion segmentation algorithms: OASIS and LesionTOADS.

[1]  Youngjin Yoo,et al.  Modeling the Variability in Brain Morphology and Lesion Distribution in Multiple Sclerosis by Deep Learning , 2014, MICCAI.

[2]  Ezequiel Geremia,et al.  Spatial Decision Forests for Glioma Segmentation in Multi-Channel MR Images , 2011 .

[3]  Nicholas Ayache,et al.  A Generative Model for Brain Tumor Segmentation in Multi-Modal Images , 2010, MICCAI.

[4]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[5]  Sébastien Ourselin,et al.  Scalable multimodal convolutional networks for brain tumour segmentation , 2017, MICCAI.

[6]  D. Louis Collins,et al.  A Generative Model for Automatic Detection of Resolving Multiple Sclerosis Lesions , 2014, BAMBI.

[7]  Konstantinos Kamnitsas,et al.  Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation , 2016, Medical Image Anal..

[8]  Christos Davatzikos,et al.  Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features , 2017, Scientific Data.

[9]  Sébastien Ourselin,et al.  DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  D. Louis Collins,et al.  Temporal Hierarchical Adaptive Texture CRF for Automatic Detection of Gadolinium-Enhancing Multiple Sclerosis Lesions in Brain MRI , 2015, IEEE Transactions on Medical Imaging.

[11]  Parashkev Nachev,et al.  Computer Methods and Programs in Biomedicine NiftyNet: a deep-learning platform for medical imaging , 2022 .

[12]  D. Louis Collins,et al.  Detection of Gad-Enhancing Lesions in Multiple Sclerosis Using Conditional Random Fields , 2010, MICCAI.

[13]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[14]  Qi Tian,et al.  DisturbLabel: Regularizing CNN on the Loss Layer , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Hao Chen,et al.  Deep Contextual Networks for Neuronal Structure Segmentation , 2016, AAAI.

[16]  Massimo Filippi,et al.  Association between pathological and MRI findings in multiple sclerosis , 2012, The Lancet Neurology.

[17]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[18]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[19]  Ben Glocker,et al.  Decision Forests for Tissue-Specific Segmentation of High-Grade Gliomas in Multi-channel MR , 2012, MICCAI.

[20]  Guido Gerig,et al.  Level-set evolution with region competition: automatic 3-D segmentation of brain tumors , 2002, Object recognition supported by user interaction for service robots.

[21]  Stefan Bauer,et al.  Fully Automatic Segmentation of Brain Tumor Images Using Support Vector Machine Classification in Combination with Hierarchical Conditional Random Field Regularization , 2011, MICCAI.

[22]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[23]  Bjoern H. Menze,et al.  Local Structure Prediction with Convolutional Neural Networks for Multimodal Brain Tumor Segmentation , 2015, MCV@MICCAI.

[24]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Irene Cheng,et al.  Fluid Vector Flow and Applications in Brain Tumor Segmentation , 2009, IEEE Transactions on Biomedical Engineering.

[26]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[27]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[28]  P M Matthews,et al.  Defining multiple sclerosis disease activity using MRI T2-weighted difference imaging. , 1998, Brain : a journal of neurology.

[29]  Gözde B. Ünal,et al.  Tumor-Cut: Segmentation of Brain Tumors on Contrast Enhanced MR Images for Radiosurgery Applications , 2012, IEEE Transactions on Medical Imaging.

[30]  D. Louis Collins,et al.  Automatic Detection of Gadolinium-Enhancing Multiple Sclerosis Lesions in Brain MRI Using Conditional Random Fields , 2012, IEEE Transactions on Medical Imaging.

[31]  Maria Pia Sormani,et al.  Magnetic resonance active lesions as individual-level surrogate for relapses in multiple sclerosis , 2011, Multiple sclerosis.

[32]  Hao Chen,et al.  DCAN: Deep Contour-Aware Networks for Accurate Gland Segmentation , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Antonio Criminisi,et al.  Segmentation of Brain Tumor Tissues with Convolutional Neural Networks , 2014 .

[34]  Mohammad Havaei,et al.  HeMIS: Hetero-Modal Image Segmentation , 2016, MICCAI.

[35]  Lixu Gu,et al.  A homotopy-based sparse representation for fast and accurate shape prior modeling in liver surgical planning , 2015, Medical Image Anal..

[36]  Xinhua Zhuang,et al.  Image Analysis Using Mathematical Morphology , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[37]  Doina Precup,et al.  IMaGe: Iterative Multilevel Probabilistic Graphical Model for Detection and Segmentation of Multiple Sclerosis Lesions in Brain MRI , 2015, IPMI.

[38]  Su Ruan,et al.  Graph cut segmentation with a statistical shape model in cardiac MRI , 2013, Comput. Vis. Image Underst..

[39]  Christopher Joseph Pal,et al.  Brain tumor segmentation with Deep Neural Networks , 2015, Medical Image Anal..

[40]  Kawal S. Rhode,et al.  CardiacNET: Segmentation of Left Atrium and Proximal Pulmonary Veins from MRI Using Multi-view CNN , 2017, MICCAI.

[41]  D. Louis Collins,et al.  Temporally Consistent Probabilistic Detection of New Multiple Sclerosis Lesions in Brain MRI , 2013, IEEE Transactions on Medical Imaging.

[42]  Lisa Tang,et al.  Deep Learning of Brain Lesion Patterns for Predicting Future Disease Activity in Patients with Early Symptoms of Multiple Sclerosis , 2016, LABELS/DLMIA@MICCAI.

[43]  Nan Zhang,et al.  Kernel feature selection to fuse multi-spectral MRI images for brain tumor segmentation , 2011, Comput. Vis. Image Underst..

[44]  Brian B. Avants,et al.  The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) , 2015, IEEE Transactions on Medical Imaging.

[45]  Tal Arbel,et al.  Adaptive multi-level conditional random fields for detection and segmentation of small enhanced pathology in medical images , 2016, Medical Image Anal..

[46]  Bruce R. Rosen,et al.  Sequential 3D U-Nets for Biologically-Informed Brain Tumor Segmentation , 2017, ArXiv.

[47]  Sébastien Ourselin,et al.  Generalised Wasserstein Dice Score for Imbalanced Multi-class Segmentation using Holistic Convolutional Networks , 2017, BrainLes@MICCAI.

[48]  Ramón Díaz-Uriarte,et al.  Gene selection and classification of microarray data using random forest , 2006, BMC Bioinformatics.

[49]  Doina Precup,et al.  Predicting Future Disease Activity and Treatment Responders for Multiple Sclerosis Patients Using a Bag-of-Lesions Brain Representation , 2017, MICCAI.

[50]  Gaël Varoquaux,et al.  The NumPy Array: A Structure for Efficient Numerical Computation , 2011, Computing in Science & Engineering.

[51]  A. Dale,et al.  Whole Brain Segmentation Automated Labeling of Neuroanatomical Structures in the Human Brain , 2002, Neuron.

[52]  Rohit Bakshi,et al.  MRI in multiple sclerosis: current status and future prospects , 2008, The Lancet Neurology.

[53]  Guido Gerig,et al.  A brain tumor segmentation framework based on outlier detection , 2004, Medical Image Anal..

[54]  Ron Kikinis,et al.  Adaptive, template moderated, spatially varying statistical classification , 2000, Medical Image Anal..

[55]  Mark W. Schmidt,et al.  Segmenting Brain Tumors with Conditional Random Fields and Support Vector Machines , 2005, CVBIA.

[56]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[57]  Guang Yang,et al.  Automatic Brain Tumor Detection and Segmentation Using U-Net Based Fully Convolutional Networks , 2017, MIUA.

[58]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[59]  Paul A. Yushkevich,et al.  Multi-Atlas Segmentation with Joint Label Fusion , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[60]  Seyed-Ahmad Ahmadi,et al.  Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields , 2016, MICCAI.

[61]  Liu Jin,et al.  A survey of MRI-based brain tumor segmentation methods , 2014 .

[62]  Meritxell Bach Cuadra,et al.  A review of atlas-based segmentation for magnetic resonance brain images , 2011, Comput. Methods Programs Biomed..

[63]  Koenraad Van Leemput,et al.  Brain Tumor Segmentation Using a Generative Model with an RBM Prior on Tumor Shape , 2015, Brainles@MICCAI.

[64]  Hao Chen,et al.  VoxResNet: Deep Voxelwise Residual Networks for Volumetric Brain Segmentation , 2016, ArXiv.

[65]  Sébastien Ourselin,et al.  Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations , 2017, DLMIA/ML-CDS@MICCAI.

[66]  Christos Davatzikos,et al.  GLISTR: Glioma Image Segmentation and Registration , 2012, IEEE Transactions on Medical Imaging.

[67]  R. Kikinis,et al.  Automated segmentation of MR images of brain tumors. , 2001, Radiology.

[68]  C. Guttmann,et al.  MR Imaging Intensity Modeling of Damage and Repair In Multiple Sclerosis: Relationship of Short-Term Lesion Recovery to Progression and Disability , 2007, American Journal of Neuroradiology.

[69]  Sébastien Ourselin,et al.  On the Compactness, Efficiency, and Representation of 3D Convolutional Networks: Brain Parcellation as a Pretext Task , 2017, IPMI.