Automatic Brain White Matter Hypertinsities Segmentation using Deep Learning Techniques

White Matter Hyperintensities (WMH) are lesions observed in the brain as bright regions in Fluid Attenuated Inversion Recovery (FLAIR) images from Magnetic Resonance Imaging (MRI). Its presence is related to conditions such as aging, small vessel diseases, stroke, depression, and neurodegenerative diseases. Currently, WMH detection is done by specialized radiologists. However, deep learning techniques can learn the patterns from images and later recognize this kind of lesions automatically. This team participated in the MICCAI WMH segmentation challenge, which was released in 2017. A dataset of 60 pairs of human MRI images was provided by the contest, which consisted of T1, FLAIR and ground-truth images per subject. For segmenting the images a 21 layer Convolutional Neural Network-CNN with U-Net architecture was implemented. For validating the model, the contest reserved 110 additional images, which were used to test this method’s accuracy. Results showed an average of 78% accuracy and lesion recall, 74% of lesion f1, 6.24mm of Hausdorff distance, and 28% of absolute percentage difference. In general, the algorithm performance showed promising results, with the validation images not used for training. This work could lead other research teams to push the state of the art in WMH images segmentation.

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

[2]  Simon Andermatt,et al.  Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challenge , 2019, IEEE Transactions on Medical Imaging.

[3]  Nico Karssemeijer,et al.  Transfer Learning for Domain Adaptation in MRI: Application in Brain Lesion Segmentation , 2017, MICCAI.

[4]  A. Hofman,et al.  Cerebral white matter lesions, vascular risk factors, and cognitive function in a population‐based study , 1994, Neurology.

[5]  Isabelle Bloch,et al.  White Matter Hyperintensities Segmentation in a Few Seconds Using Fully Convolutional Network and Transfer Learning , 2017, BrainLes@MICCAI.

[6]  D. Louis Collins,et al.  Unbiased average age-appropriate atlases for pediatric studies , 2011, NeuroImage.

[7]  C. Almli,et al.  Unbiased nonlinear average age-appropriate brain templates from birth to adulthood , 2009, NeuroImage.

[8]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[10]  Orlando Chancay,et al.  Nuevo Biomarcador en la Enfermedad de Parkinson Mediante el Análisis y Cuantificación de Lesiones Cerebrales en Secuencias Flair Obtenidas por Resonancia Magnética (ACL-Tool) , 2015 .

[11]  B M Dawant,et al.  Brain segmentation and white matter lesion detection in MR images. , 1994, Critical reviews in biomedical engineering.

[12]  Luis Ibáñez,et al.  The Design of SimpleITK , 2013, Front. Neuroinform..

[13]  Travis E. Oliphant,et al.  Guide to NumPy , 2015 .

[14]  Nick C Fox,et al.  Neuroimaging standards for research into small vessel disease and its contribution to ageing and neurodegeneration , 2013, The Lancet Neurology.

[15]  Mark Mühlau,et al.  Multi-Scale Convolutional-Stack Aggregation for Robust White Matter Hyperintensities Segmentation , 2018, BrainLes@MICCAI.

[16]  Alan C. Evans,et al.  A fully automatic and robust brain MRI tissue classification method , 2003, Medical Image Anal..

[17]  Isabelle Bloch,et al.  A challenging issue: Detection of white matter hyperintensities in neonatal brain MRI , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

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

[19]  Elena Marchiori,et al.  Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities , 2016, Scientific Reports.

[20]  Karl J. Friston,et al.  Unified segmentation , 2005, NeuroImage.

[21]  C. Jack,et al.  FLAIR histogram segmentation for measurement of leukoaraiosis volume , 2001, Journal of magnetic resonance imaging : JMRI.

[22]  Wei-Shi Zheng,et al.  Fully convolutional network ensembles for white matter hyperintensities segmentation in MR images , 2018, NeuroImage.

[23]  Abien Fred Agarap.  Deep Learning using Rectified Linear Units (ReLU) , 2018, ArXiv.

[24]  Mohammad Reza Daliri,et al.  Automated Diagnosis of Alzheimer Disease using the Scale-Invariant Feature Transforms in Magnetic Resonance Images , 2012, Journal of Medical Systems.

[25]  N. De Stefano,et al.  Clinical use of brain volumetry , 2013, Journal of magnetic resonance imaging : JMRI.

[26]  Richard Frayne,et al.  WMH Segmentation Challenge: A Texture-Based Classification Approach , 2017, BrainLes@MICCAI.

[27]  Adam P. Harrison,et al.  White matter hyperintensity segmentation from T1 and FLAIR images using fully convolutional neural networks enhanced with residual connections , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[28]  Isabelle Bloch,et al.  From neonatal to adult brain MR image segmentation in a few seconds using 3D-like fully convolutional network and transfer learning , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[29]  Wiro J. Niessen,et al.  Multi-spectral brain tissue segmentation using automatically trained k-Nearest-Neighbor classification , 2007, NeuroImage.

[30]  Daniel S. Margulies,et al.  Nipype: A Flexible, Lightweight and Extensible Neuroimaging Data Processing Framework in Python , 2011, Front. Neuroinform..

[31]  Wes McKinney,et al.  Data Structures for Statistical Computing in Python , 2010, SciPy.

[32]  Guixia Kang,et al.  WMH segmentation challenge MICCAI 2017 , 2019 .

[33]  Stephen M. Smith,et al.  Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm , 2001, IEEE Transactions on Medical Imaging.