Cargando…

A Novel Approach for Fully Automatic Intra-Tumor Segmentation With 3D U-Net Architecture for Gliomas

Purpose: Gliomas are the most common primary brain malignancies, with varying degrees of aggressiveness and prognosis. Understanding of tumor biology and intra-tumor heterogeneity is necessary for planning personalized therapy and predicting response to therapy. Accurate tumoral and intra-tumoral se...

Descripción completa

Detalles Bibliográficos
Autores principales: Baid, Ujjwal, Talbar, Sanjay, Rane, Swapnil, Gupta, Sudeep, Thakur, Meenakshi H., Moiyadi, Aliasgar, Sable, Nilesh, Akolkar, Mayuresh, Mahajan, Abhishek
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7041417/
https://www.ncbi.nlm.nih.gov/pubmed/32132913
http://dx.doi.org/10.3389/fncom.2020.00010
_version_ 1783501155762962432
author Baid, Ujjwal
Talbar, Sanjay
Rane, Swapnil
Gupta, Sudeep
Thakur, Meenakshi H.
Moiyadi, Aliasgar
Sable, Nilesh
Akolkar, Mayuresh
Mahajan, Abhishek
author_facet Baid, Ujjwal
Talbar, Sanjay
Rane, Swapnil
Gupta, Sudeep
Thakur, Meenakshi H.
Moiyadi, Aliasgar
Sable, Nilesh
Akolkar, Mayuresh
Mahajan, Abhishek
author_sort Baid, Ujjwal
collection PubMed
description Purpose: Gliomas are the most common primary brain malignancies, with varying degrees of aggressiveness and prognosis. Understanding of tumor biology and intra-tumor heterogeneity is necessary for planning personalized therapy and predicting response to therapy. Accurate tumoral and intra-tumoral segmentation on MRI is the first step toward understanding the tumor biology through computational methods. The purpose of this study was to design a segmentation algorithm and evaluate its performance on pre-treatment brain MRIs obtained from patients with gliomas. Materials and Methods: In this study, we have designed a novel 3D U-Net architecture that segments various radiologically identifiable sub-regions like edema, enhancing tumor, and necrosis. Weighted patch extraction scheme from the tumor border regions is proposed to address the problem of class imbalance between tumor and non-tumorous patches. The architecture consists of a contracting path to capture context and the symmetric expanding path that enables precise localization. The Deep Convolutional Neural Network (DCNN) based architecture is trained on 285 patients, validated on 66 patients and tested on 191 patients with Glioma from Brain Tumor Segmentation (BraTS) 2018 challenge dataset. Three dimensional patches are extracted from multi-channel BraTS training dataset to train 3D U-Net architecture. The efficacy of the proposed approach is also tested on an independent dataset of 40 patients with High Grade Glioma from our tertiary cancer center. Segmentation results are assessed in terms of Dice Score, Sensitivity, Specificity, and Hausdorff 95 distance (ITCN intra-tumoral classification network). Result: Our proposed architecture achieved Dice scores of 0.88, 0.83, and 0.75 for the whole tumor, tumor core and enhancing tumor, respectively, on BraTS validation dataset and 0.85, 0.77, 0.67 on test dataset. The results were similar on the independent patients' dataset from our hospital, achieving Dice scores of 0.92, 0.90, and 0.81 for the whole tumor, tumor core and enhancing tumor, respectively. Conclusion: The results of this study show the potential of patch-based 3D U-Net for the accurate intra-tumor segmentation. From experiments, it is observed that the weighted patch-based segmentation approach gives comparable performance with the pixel-based approach when there is a thin boundary between tumor subparts.
format Online
Article
Text
id pubmed-7041417
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-70414172020-03-04 A Novel Approach for Fully Automatic Intra-Tumor Segmentation With 3D U-Net Architecture for Gliomas Baid, Ujjwal Talbar, Sanjay Rane, Swapnil Gupta, Sudeep Thakur, Meenakshi H. Moiyadi, Aliasgar Sable, Nilesh Akolkar, Mayuresh Mahajan, Abhishek Front Comput Neurosci Neuroscience Purpose: Gliomas are the most common primary brain malignancies, with varying degrees of aggressiveness and prognosis. Understanding of tumor biology and intra-tumor heterogeneity is necessary for planning personalized therapy and predicting response to therapy. Accurate tumoral and intra-tumoral segmentation on MRI is the first step toward understanding the tumor biology through computational methods. The purpose of this study was to design a segmentation algorithm and evaluate its performance on pre-treatment brain MRIs obtained from patients with gliomas. Materials and Methods: In this study, we have designed a novel 3D U-Net architecture that segments various radiologically identifiable sub-regions like edema, enhancing tumor, and necrosis. Weighted patch extraction scheme from the tumor border regions is proposed to address the problem of class imbalance between tumor and non-tumorous patches. The architecture consists of a contracting path to capture context and the symmetric expanding path that enables precise localization. The Deep Convolutional Neural Network (DCNN) based architecture is trained on 285 patients, validated on 66 patients and tested on 191 patients with Glioma from Brain Tumor Segmentation (BraTS) 2018 challenge dataset. Three dimensional patches are extracted from multi-channel BraTS training dataset to train 3D U-Net architecture. The efficacy of the proposed approach is also tested on an independent dataset of 40 patients with High Grade Glioma from our tertiary cancer center. Segmentation results are assessed in terms of Dice Score, Sensitivity, Specificity, and Hausdorff 95 distance (ITCN intra-tumoral classification network). Result: Our proposed architecture achieved Dice scores of 0.88, 0.83, and 0.75 for the whole tumor, tumor core and enhancing tumor, respectively, on BraTS validation dataset and 0.85, 0.77, 0.67 on test dataset. The results were similar on the independent patients' dataset from our hospital, achieving Dice scores of 0.92, 0.90, and 0.81 for the whole tumor, tumor core and enhancing tumor, respectively. Conclusion: The results of this study show the potential of patch-based 3D U-Net for the accurate intra-tumor segmentation. From experiments, it is observed that the weighted patch-based segmentation approach gives comparable performance with the pixel-based approach when there is a thin boundary between tumor subparts. Frontiers Media S.A. 2020-02-18 /pmc/articles/PMC7041417/ /pubmed/32132913 http://dx.doi.org/10.3389/fncom.2020.00010 Text en Copyright © 2020 Baid, Talbar, Rane, Gupta, Thakur, Moiyadi, Sable, Akolkar and Mahajan. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Baid, Ujjwal
Talbar, Sanjay
Rane, Swapnil
Gupta, Sudeep
Thakur, Meenakshi H.
Moiyadi, Aliasgar
Sable, Nilesh
Akolkar, Mayuresh
Mahajan, Abhishek
A Novel Approach for Fully Automatic Intra-Tumor Segmentation With 3D U-Net Architecture for Gliomas
title A Novel Approach for Fully Automatic Intra-Tumor Segmentation With 3D U-Net Architecture for Gliomas
title_full A Novel Approach for Fully Automatic Intra-Tumor Segmentation With 3D U-Net Architecture for Gliomas
title_fullStr A Novel Approach for Fully Automatic Intra-Tumor Segmentation With 3D U-Net Architecture for Gliomas
title_full_unstemmed A Novel Approach for Fully Automatic Intra-Tumor Segmentation With 3D U-Net Architecture for Gliomas
title_short A Novel Approach for Fully Automatic Intra-Tumor Segmentation With 3D U-Net Architecture for Gliomas
title_sort novel approach for fully automatic intra-tumor segmentation with 3d u-net architecture for gliomas
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7041417/
https://www.ncbi.nlm.nih.gov/pubmed/32132913
http://dx.doi.org/10.3389/fncom.2020.00010
work_keys_str_mv AT baidujjwal anovelapproachforfullyautomaticintratumorsegmentationwith3dunetarchitectureforgliomas
AT talbarsanjay anovelapproachforfullyautomaticintratumorsegmentationwith3dunetarchitectureforgliomas
AT raneswapnil anovelapproachforfullyautomaticintratumorsegmentationwith3dunetarchitectureforgliomas
AT guptasudeep anovelapproachforfullyautomaticintratumorsegmentationwith3dunetarchitectureforgliomas
AT thakurmeenakshih anovelapproachforfullyautomaticintratumorsegmentationwith3dunetarchitectureforgliomas
AT moiyadialiasgar anovelapproachforfullyautomaticintratumorsegmentationwith3dunetarchitectureforgliomas
AT sablenilesh anovelapproachforfullyautomaticintratumorsegmentationwith3dunetarchitectureforgliomas
AT akolkarmayuresh anovelapproachforfullyautomaticintratumorsegmentationwith3dunetarchitectureforgliomas
AT mahajanabhishek anovelapproachforfullyautomaticintratumorsegmentationwith3dunetarchitectureforgliomas
AT baidujjwal novelapproachforfullyautomaticintratumorsegmentationwith3dunetarchitectureforgliomas
AT talbarsanjay novelapproachforfullyautomaticintratumorsegmentationwith3dunetarchitectureforgliomas
AT raneswapnil novelapproachforfullyautomaticintratumorsegmentationwith3dunetarchitectureforgliomas
AT guptasudeep novelapproachforfullyautomaticintratumorsegmentationwith3dunetarchitectureforgliomas
AT thakurmeenakshih novelapproachforfullyautomaticintratumorsegmentationwith3dunetarchitectureforgliomas
AT moiyadialiasgar novelapproachforfullyautomaticintratumorsegmentationwith3dunetarchitectureforgliomas
AT sablenilesh novelapproachforfullyautomaticintratumorsegmentationwith3dunetarchitectureforgliomas
AT akolkarmayuresh novelapproachforfullyautomaticintratumorsegmentationwith3dunetarchitectureforgliomas
AT mahajanabhishek novelapproachforfullyautomaticintratumorsegmentationwith3dunetarchitectureforgliomas