Segmentation and Classification in Digital Pathology for Glioma Research: Challenges and Deep Learning Approaches
Biomedical imaging Is an important source of information in cancer research. Characterizations of cancer morphology at onset, progression, and in response to treatment provide complementary information to that gleaned from genomics and clinical data. Accurate extraction and classification of both vi...
Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2020-02-01
|
Series: | Frontiers in Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/article/10.3389/fnins.2020.00027/full |
id |
doaj-0c2926c1e89042aeb25319dba419c252 |
---|---|
record_format |
Article |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Tahsin Kurc Spyridon Bakas Spyridon Bakas Spyridon Bakas Xuhua Ren Aditya Bagari Alexandre Momeni Yue Huang Lichi Zhang Ashish Kumar Marc Thibault Qi Qi Qian Wang Avinash Kori Olivier Gevaert Yunlong Zhang Dinggang Shen Dinggang Shen Mahendra Khened Xinghao Ding Ganapathy Krishnamurthi Jayashree Kalpathy-Cramer James Davis Tianhao Zhao Rajarsi Gupta Rajarsi Gupta Joel Saltz Keyvan Farahani |
spellingShingle |
Tahsin Kurc Spyridon Bakas Spyridon Bakas Spyridon Bakas Xuhua Ren Aditya Bagari Alexandre Momeni Yue Huang Lichi Zhang Ashish Kumar Marc Thibault Qi Qi Qian Wang Avinash Kori Olivier Gevaert Yunlong Zhang Dinggang Shen Dinggang Shen Mahendra Khened Xinghao Ding Ganapathy Krishnamurthi Jayashree Kalpathy-Cramer James Davis Tianhao Zhao Rajarsi Gupta Rajarsi Gupta Joel Saltz Keyvan Farahani Segmentation and Classification in Digital Pathology for Glioma Research: Challenges and Deep Learning Approaches Frontiers in Neuroscience digital pathology radiology segmentation classification image analysis deep learning |
author_facet |
Tahsin Kurc Spyridon Bakas Spyridon Bakas Spyridon Bakas Xuhua Ren Aditya Bagari Alexandre Momeni Yue Huang Lichi Zhang Ashish Kumar Marc Thibault Qi Qi Qian Wang Avinash Kori Olivier Gevaert Yunlong Zhang Dinggang Shen Dinggang Shen Mahendra Khened Xinghao Ding Ganapathy Krishnamurthi Jayashree Kalpathy-Cramer James Davis Tianhao Zhao Rajarsi Gupta Rajarsi Gupta Joel Saltz Keyvan Farahani |
author_sort |
Tahsin Kurc |
title |
Segmentation and Classification in Digital Pathology for Glioma Research: Challenges and Deep Learning Approaches |
title_short |
Segmentation and Classification in Digital Pathology for Glioma Research: Challenges and Deep Learning Approaches |
title_full |
Segmentation and Classification in Digital Pathology for Glioma Research: Challenges and Deep Learning Approaches |
title_fullStr |
Segmentation and Classification in Digital Pathology for Glioma Research: Challenges and Deep Learning Approaches |
title_full_unstemmed |
Segmentation and Classification in Digital Pathology for Glioma Research: Challenges and Deep Learning Approaches |
title_sort |
segmentation and classification in digital pathology for glioma research: challenges and deep learning approaches |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Neuroscience |
issn |
1662-453X |
publishDate |
2020-02-01 |
description |
Biomedical imaging Is an important source of information in cancer research. Characterizations of cancer morphology at onset, progression, and in response to treatment provide complementary information to that gleaned from genomics and clinical data. Accurate extraction and classification of both visual and latent image features Is an increasingly complex challenge due to the increased complexity and resolution of biomedical image data. In this paper, we present four deep learning-based image analysis methods from the Computational Precision Medicine (CPM) satellite event of the 21st International Medical Image Computing and Computer Assisted Intervention (MICCAI 2018) conference. One method Is a segmentation method designed to segment nuclei in whole slide tissue images (WSIs) of adult diffuse glioma cases. It achieved a Dice similarity coefficient of 0.868 with the CPM challenge datasets. Three methods are classification methods developed to categorize adult diffuse glioma cases into oligodendroglioma and astrocytoma classes using radiographic and histologic image data. These methods achieved accuracy values of 0.75, 0.80, and 0.90, measured as the ratio of the number of correct classifications to the number of total cases, with the challenge datasets. The evaluations of the four methods indicate that (1) carefully constructed deep learning algorithms are able to produce high accuracy in the analysis of biomedical image data and (2) the combination of radiographic with histologic image information improves classification performance. |
topic |
digital pathology radiology segmentation classification image analysis deep learning |
url |
https://www.frontiersin.org/article/10.3389/fnins.2020.00027/full |
work_keys_str_mv |
AT tahsinkurc segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT spyridonbakas segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT spyridonbakas segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT spyridonbakas segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT xuhuaren segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT adityabagari segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT alexandremomeni segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT yuehuang segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT lichizhang segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT ashishkumar segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT marcthibault segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT qiqi segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT qianwang segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT avinashkori segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT oliviergevaert segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT yunlongzhang segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT dinggangshen segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT dinggangshen segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT mahendrakhened segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT xinghaoding segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT ganapathykrishnamurthi segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT jayashreekalpathycramer segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT jamesdavis segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT tianhaozhao segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT rajarsigupta segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT rajarsigupta segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT joelsaltz segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches AT keyvanfarahani segmentationandclassificationindigitalpathologyforgliomaresearchchallengesanddeeplearningapproaches |
_version_ |
1725111650395095040 |
spelling |
doaj-0c2926c1e89042aeb25319dba419c2522020-11-25T01:25:56ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2020-02-011410.3389/fnins.2020.00027494512Segmentation and Classification in Digital Pathology for Glioma Research: Challenges and Deep Learning ApproachesTahsin Kurc0Spyridon Bakas1Spyridon Bakas2Spyridon Bakas3Xuhua Ren4Aditya Bagari5Alexandre Momeni6Yue Huang7Lichi Zhang8Ashish Kumar9Marc Thibault10Qi Qi11Qian Wang12Avinash Kori13Olivier Gevaert14Yunlong Zhang15Dinggang Shen16Dinggang Shen17Mahendra Khened18Xinghao Ding19Ganapathy Krishnamurthi20Jayashree Kalpathy-Cramer21James Davis22Tianhao Zhao23Rajarsi Gupta24Rajarsi Gupta25Joel Saltz26Keyvan Farahani27Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, United StatesCenter for Biomedical Image Computing and Analytics, University of Pennsylvania, Philadelphia, PA, United StatesDepartment of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United StatesDepartment of Pathology and Laboratory Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United StatesInstitute for Medical Imaging Technology, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Engineering Design, Indian Institute of Technology Madras, Chennai, IndiaDepartment of Medicine and Biomedical Data Science, Stanford University, Stanford, CA, United StatesSchool of Informatics, Xiamen University, Xiamen, ChinaInstitute for Medical Imaging Technology, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Engineering Design, Indian Institute of Technology Madras, Chennai, IndiaDepartment of Medicine and Biomedical Data Science, Stanford University, Stanford, CA, United StatesSchool of Informatics, Xiamen University, Xiamen, ChinaInstitute for Medical Imaging Technology, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Engineering Design, Indian Institute of Technology Madras, Chennai, IndiaDepartment of Medicine and Biomedical Data Science, Stanford University, Stanford, CA, United StatesSchool of Informatics, Xiamen University, Xiamen, ChinaDepartment of Radiology and BRIC, The University of North Carolina at Chapel Hill, Chapel Hill, NC, United States0Department of Brain and Cognitive Engineering, Korea University, Seoul, South KoreaDepartment of Engineering Design, Indian Institute of Technology Madras, Chennai, IndiaSchool of Informatics, Xiamen University, Xiamen, ChinaDepartment of Engineering Design, Indian Institute of Technology Madras, Chennai, India1Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, United States2Department of Pathology, Stony Brook University, Stony Brook, NY, United States2Department of Pathology, Stony Brook University, Stony Brook, NY, United StatesDepartment of Biomedical Informatics, Stony Brook University, Stony Brook, NY, United States2Department of Pathology, Stony Brook University, Stony Brook, NY, United StatesDepartment of Biomedical Informatics, Stony Brook University, Stony Brook, NY, United States3Cancer Imaging Program, National Cancer Institute, National Institutes of Health, Bethesda, MD, United StatesBiomedical imaging Is an important source of information in cancer research. Characterizations of cancer morphology at onset, progression, and in response to treatment provide complementary information to that gleaned from genomics and clinical data. Accurate extraction and classification of both visual and latent image features Is an increasingly complex challenge due to the increased complexity and resolution of biomedical image data. In this paper, we present four deep learning-based image analysis methods from the Computational Precision Medicine (CPM) satellite event of the 21st International Medical Image Computing and Computer Assisted Intervention (MICCAI 2018) conference. One method Is a segmentation method designed to segment nuclei in whole slide tissue images (WSIs) of adult diffuse glioma cases. It achieved a Dice similarity coefficient of 0.868 with the CPM challenge datasets. Three methods are classification methods developed to categorize adult diffuse glioma cases into oligodendroglioma and astrocytoma classes using radiographic and histologic image data. These methods achieved accuracy values of 0.75, 0.80, and 0.90, measured as the ratio of the number of correct classifications to the number of total cases, with the challenge datasets. The evaluations of the four methods indicate that (1) carefully constructed deep learning algorithms are able to produce high accuracy in the analysis of biomedical image data and (2) the combination of radiographic with histologic image information improves classification performance.https://www.frontiersin.org/article/10.3389/fnins.2020.00027/fulldigital pathologyradiologysegmentationclassificationimage analysisdeep learning |