Literature DB >> 31670238

Are multi-contrast magnetic resonance images necessary for segmenting multiple sclerosis brains? A large cohort study based on deep learning.

Ponnada A Narayana1, Ivan Coronado2, Sheeba J Sujit2, Xiaojun Sun2, Jerry S Wolinsky3, Refaat E Gabr2.   

Abstract

BACKGROUND: Magnetic resonance images with multiple contrasts or sequences are commonly used for segmenting brain tissues, including lesions, in multiple sclerosis (MS). However, acquisition of images with multiple contrasts increases the scan time and complexity of the analysis, possibly introducing factors that could compromise segmentation quality.
OBJECTIVE: To investigate the effect of various combinations of multi-contrast images as input on the segmented volumes of gray (GM) and white matter (WM), cerebrospinal fluid (CSF), and lesions using a deep neural network.
METHODS: U-net, a fully convolutional neural network was used to automatically segment GM, WM, CSF, and lesions in 1000 MS patients. The input to the network consisted of 15 combinations of FLAIR, T1-, T2-, and proton density-weighted images. The Dice similarity coefficient (DSC) was evaluated to assess the segmentation performance. For lesions, true positive rate (TPR) and false positive rate (FPR) were also evaluated. In addition, the effect of lesion size on lesion segmentation was investigated.
RESULTS: Highest DSC was observed for all the tissue volumes, including lesions, when the input was combination of all four image contrasts. All other input combinations that included FLAIR also provided high DSC for all tissue classes. However, the quality of lesion segmentation showed strong dependence on the input images. The DSC and TPR values for inputs with the four contrast combination and FLAIR alone were very similar, but FLAIR showed a moderately higher FPR for lesion size <100 μl. For lesions smaller than 20 μl all image combinations resulted in poor performance. The segmentation quality improved with lesion size.
CONCLUSIONS: Best performance for segmented tissue volumes was obtained with all four image contrasts as the input, and comparable performance was attainable with FLAIR only as the input, albeit with a moderate increase in FPR for small lesions. This implies that acquisition of only FLAIR images provides satisfactory tissue segmentation. Lesion segmentation was poor for very small lesions and improved rapidly with lesion size.
Copyright © 2019 Elsevier Inc. All rights reserved.

Entities:  

Keywords:  Deep learning; Dice similarity coefficient; False negative rate; False positive rate; Magnetic resonance imaging; Multiple sclerosis; Segmentation; U-net

Mesh:

Substances:

Year:  2019        PMID: 31670238      PMCID: PMC6918476          DOI: 10.1016/j.mri.2019.10.003

Source DB:  PubMed          Journal:  Magn Reson Imaging        ISSN: 0730-725X            Impact factor:   2.546


  24 in total

1.  Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm.

Authors:  Y Zhang; M Brady; S Smith
Journal:  IEEE Trans Med Imaging       Date:  2001-01       Impact factor: 10.048

2.  Deep 3D Convolutional Encoder Networks With Shortcuts for Multiscale Feature Integration Applied to Multiple Sclerosis Lesion Segmentation.

Authors:  Tom Brosch; Lisa Y W Tang; David K B Li; Anthony Traboulsee; Roger Tam
Journal:  IEEE Trans Med Imaging       Date:  2016-02-11       Impact factor: 10.048

3.  Unified approach for multiple sclerosis lesion segmentation on brain MRI.

Authors:  Balasrinivasa Rao Sajja; Sushmita Datta; Renjie He; Meghana Mehta; Rakesh K Gupta; Jerry S Wolinsky; Ponnada A Narayana
Journal:  Ann Biomed Eng       Date:  2006-03-09       Impact factor: 3.934

4.  Probabilistic segmentation of brain tissue in MR imaging.

Authors:  Petronella Anbeek; Koen L Vincken; Glenda S van Bochove; Matthias J P van Osch; Jeroen van der Grond
Journal:  Neuroimage       Date:  2005-10-01       Impact factor: 6.556

Review 5.  Brain MRI atrophy quantification in MS: From methods to clinical application.

Authors:  Maria A Rocca; Marco Battaglini; Ralph H B Benedict; Nicola De Stefano; Jeroen J G Geurts; Roland G Henry; Mark A Horsfield; Mark Jenkinson; Elisabetta Pagani; Massimo Filippi
Journal:  Neurology       Date:  2016-12-16       Impact factor: 9.910

6.  Segmentation of white matter hyperintensities using convolutional neural networks with global spatial information in routine clinical brain MRI with none or mild vascular pathology.

Authors:  Muhammad Febrian Rachmadi; Maria Del C Valdés-Hernández; Maria Leonora Fatimah Agan; Carol Di Perri; Taku Komura
Journal:  Comput Med Imaging Graph       Date:  2018-02-17       Impact factor: 4.790

Review 7.  Deep Learning in Medical Image Analysis.

Authors:  Dinggang Shen; Guorong Wu; Heung-Il Suk
Journal:  Annu Rev Biomed Eng       Date:  2017-03-09       Impact factor: 9.590

8.  Automatic segmentation of white matter hyperintensities in the elderly using FLAIR images at 3T.

Authors:  Erin Gibson; Fuqiang Gao; Sandra E Black; Nancy J Lobaugh
Journal:  J Magn Reson Imaging       Date:  2010-06       Impact factor: 4.813

9.  Evaluation of a deep learning approach for the segmentation of brain tissues and white matter hyperintensities of presumed vascular origin in MRI.

Authors:  Pim Moeskops; Jeroen de Bresser; Hugo J Kuijf; Adriënne M Mendrik; Geert Jan Biessels; Josien P W Pluim; Ivana Išgum
Journal:  Neuroimage Clin       Date:  2017-10-12       Impact factor: 4.881

10.  Automated detection of white matter and cortical lesions in early stages of multiple sclerosis.

Authors:  Mário João Fartaria; Guillaume Bonnier; Alexis Roche; Tobias Kober; Reto Meuli; David Rotzinger; Richard Frackowiak; Myriam Schluep; Renaud Du Pasquier; Jean-Philippe Thiran; Gunnar Krueger; Meritxell Bach Cuadra; Cristina Granziera
Journal:  J Magn Reson Imaging       Date:  2015-11-25       Impact factor: 4.813

View more
  3 in total

Review 1.  Machine Learning Approaches in Study of Multiple Sclerosis Disease Through Magnetic Resonance Images.

Authors:  Faezeh Moazami; Alain Lefevre-Utile; Costas Papaloukas; Vassili Soumelis
Journal:  Front Immunol       Date:  2021-08-11       Impact factor: 7.561

2.  Generalizing deep whole-brain segmentation for post-contrast MRI with transfer learning.

Authors:  Camilo Bermudez; Samuel W Remedios; Karthik Ramadass; Maureen McHugo; Stephan Heckers; Yuankai Huo; Bennett A Landman
Journal:  J Med Imaging (Bellingham)       Date:  2020-12-23

3.  Deep Learning Segmentation of Triple-Negative Breast Cancer (TNBC) Patient Derived Tumor Xenograft (PDX) and Sensitivity of Radiomic Pipeline to Tumor Probability Boundary.

Authors:  Kaushik Dutta; Sudipta Roy; Timothy Daniel Whitehead; Jingqin Luo; Abhinav Kumar Jha; Shunqiang Li; James Dennis Quirk; Kooresh Isaac Shoghi
Journal:  Cancers (Basel)       Date:  2021-07-28       Impact factor: 6.575

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.