Multi-Disease Segmentation of Gliomas and White Matter Hyperintensities in the BraTS Data Using a 3D Convolutional Neural Network
An important challenge in segmenting real-world biomedical imaging data is the presence of multiple disease processes within individual subjects. Most adults above age 60 exhibit a variable degree of small vessel ischemic disease, as well as chronic infarcts, which will manifest as white matter hype...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2019-12-01
|
| Series: | Frontiers in Computational Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fncom.2019.00084/full |
| _version_ | 1828429475268788224 |
|---|---|
| author | Jeffrey D. Rudie Jeffrey D. Rudie David A. Weiss Rachit Saluja Andreas M. Rauschecker Jiancong Wang Leo Sugrue Spyridon Bakas Spyridon Bakas Spyridon Bakas John B. Colby |
| author_facet | Jeffrey D. Rudie Jeffrey D. Rudie David A. Weiss Rachit Saluja Andreas M. Rauschecker Jiancong Wang Leo Sugrue Spyridon Bakas Spyridon Bakas Spyridon Bakas John B. Colby |
| author_sort | Jeffrey D. Rudie |
| collection | DOAJ |
| description | An important challenge in segmenting real-world biomedical imaging data is the presence of multiple disease processes within individual subjects. Most adults above age 60 exhibit a variable degree of small vessel ischemic disease, as well as chronic infarcts, which will manifest as white matter hyperintensities (WMH) on brain MRIs. Subjects diagnosed with gliomas will also typically exhibit some degree of abnormal T2 signal due to WMH, rather than just due to tumor. We sought to develop a fully automated algorithm to distinguish and quantify these distinct disease processes within individual subjects’ brain MRIs. To address this multi-disease problem, we trained a 3D U-Net to distinguish between abnormal signal arising from tumors vs. WMH in the 3D multi-parametric MRI (mpMRI, i.e., native T1-weighted, T1-post-contrast, T2, T2-FLAIR) scans of the International Brain Tumor Segmentation (BraTS) 2018 dataset (ntraining = 285, nvalidation = 66). Our trained neuroradiologist manually annotated WMH on the BraTS training subjects, finding that 69% of subjects had WMH. Our 3D U-Net model had a 4-channel 3D input patch (80 × 80 × 80) from mpMRI, four encoding and decoding layers, and an output of either four [background, active tumor (AT), necrotic core (NCR), peritumoral edematous/infiltrated tissue (ED)] or five classes (adding WMH as the fifth class). For both the four- and five-class output models, the median Dice for whole tumor (WT) extent (i.e., union of AT, ED, NCR) was 0.92 in both training and validation sets. Notably, the five-class model achieved significantly (p = 0.002) lower/better Hausdorff distances for WT extent in the training subjects. There was strong positive correlation between manually segmented and predicted volumes for WT (r = 0.96) and WMH (r = 0.89). Larger lesion volumes were positively correlated with higher/better Dice scores for WT (r = 0.33), WMH (r = 0.34), and across all lesions (r = 0.89) on a log(10) transformed scale. While the median Dice for WMH was 0.42 across training subjects with WMH, the median Dice was 0.62 for those with at least 5 cm3 of WMH. We anticipate the development of computational algorithms that are able to model multiple diseases within a single subject will be a critical step toward translating and integrating artificial intelligence systems into the heterogeneous real-world clinical workflow. |
| first_indexed | 2024-12-10T17:34:49Z |
| format | Article |
| id | doaj.art-651c0143c4fe4aeaad458c0373bcc6a1 |
| institution | Directory Open Access Journal |
| issn | 1662-5188 |
| language | English |
| last_indexed | 2024-12-10T17:34:49Z |
| publishDate | 2019-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Computational Neuroscience |
| spelling | doaj.art-651c0143c4fe4aeaad458c0373bcc6a12022-12-22T01:39:35ZengFrontiers Media S.A.Frontiers in Computational Neuroscience1662-51882019-12-011310.3389/fncom.2019.00084494162Multi-Disease Segmentation of Gliomas and White Matter Hyperintensities in the BraTS Data Using a 3D Convolutional Neural NetworkJeffrey D. Rudie0Jeffrey D. Rudie1David A. Weiss2Rachit Saluja3Andreas M. Rauschecker4Jiancong Wang5Leo Sugrue6Spyridon Bakas7Spyridon Bakas8Spyridon Bakas9John B. Colby10Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United StatesDepartment of Radiology & Biomedical Imaging, University of California, San Francisco, San Francisco, CA, United StatesDepartment of Bioengineering, University of Pennsylvania, Philadelphia, PA, United StatesDepartment of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, United StatesDepartment of Radiology & Biomedical Imaging, University of California, San Francisco, San Francisco, CA, United StatesDepartment of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United StatesDepartment of Radiology & Biomedical Imaging, University of California, San Francisco, San Francisco, CA, United StatesDepartment of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United StatesCenter for Biomedical Image Computing and Analytics (CBICA), University of Pennsylvania, Philadelphia, PA, United StatesDepartment of Pathology and Laboratory Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United StatesDepartment of Radiology & Biomedical Imaging, University of California, San Francisco, San Francisco, CA, United StatesAn important challenge in segmenting real-world biomedical imaging data is the presence of multiple disease processes within individual subjects. Most adults above age 60 exhibit a variable degree of small vessel ischemic disease, as well as chronic infarcts, which will manifest as white matter hyperintensities (WMH) on brain MRIs. Subjects diagnosed with gliomas will also typically exhibit some degree of abnormal T2 signal due to WMH, rather than just due to tumor. We sought to develop a fully automated algorithm to distinguish and quantify these distinct disease processes within individual subjects’ brain MRIs. To address this multi-disease problem, we trained a 3D U-Net to distinguish between abnormal signal arising from tumors vs. WMH in the 3D multi-parametric MRI (mpMRI, i.e., native T1-weighted, T1-post-contrast, T2, T2-FLAIR) scans of the International Brain Tumor Segmentation (BraTS) 2018 dataset (ntraining = 285, nvalidation = 66). Our trained neuroradiologist manually annotated WMH on the BraTS training subjects, finding that 69% of subjects had WMH. Our 3D U-Net model had a 4-channel 3D input patch (80 × 80 × 80) from mpMRI, four encoding and decoding layers, and an output of either four [background, active tumor (AT), necrotic core (NCR), peritumoral edematous/infiltrated tissue (ED)] or five classes (adding WMH as the fifth class). For both the four- and five-class output models, the median Dice for whole tumor (WT) extent (i.e., union of AT, ED, NCR) was 0.92 in both training and validation sets. Notably, the five-class model achieved significantly (p = 0.002) lower/better Hausdorff distances for WT extent in the training subjects. There was strong positive correlation between manually segmented and predicted volumes for WT (r = 0.96) and WMH (r = 0.89). Larger lesion volumes were positively correlated with higher/better Dice scores for WT (r = 0.33), WMH (r = 0.34), and across all lesions (r = 0.89) on a log(10) transformed scale. While the median Dice for WMH was 0.42 across training subjects with WMH, the median Dice was 0.62 for those with at least 5 cm3 of WMH. We anticipate the development of computational algorithms that are able to model multiple diseases within a single subject will be a critical step toward translating and integrating artificial intelligence systems into the heterogeneous real-world clinical workflow.https://www.frontiersin.org/article/10.3389/fncom.2019.00084/fullsegmentationglioblastomaconvolutional neural networkwhite matter hyperintensitiesdeep learningradiology |
| spellingShingle | Jeffrey D. Rudie Jeffrey D. Rudie David A. Weiss Rachit Saluja Andreas M. Rauschecker Jiancong Wang Leo Sugrue Spyridon Bakas Spyridon Bakas Spyridon Bakas John B. Colby Multi-Disease Segmentation of Gliomas and White Matter Hyperintensities in the BraTS Data Using a 3D Convolutional Neural Network Frontiers in Computational Neuroscience segmentation glioblastoma convolutional neural network white matter hyperintensities deep learning radiology |
| title | Multi-Disease Segmentation of Gliomas and White Matter Hyperintensities in the BraTS Data Using a 3D Convolutional Neural Network |
| title_full | Multi-Disease Segmentation of Gliomas and White Matter Hyperintensities in the BraTS Data Using a 3D Convolutional Neural Network |
| title_fullStr | Multi-Disease Segmentation of Gliomas and White Matter Hyperintensities in the BraTS Data Using a 3D Convolutional Neural Network |
| title_full_unstemmed | Multi-Disease Segmentation of Gliomas and White Matter Hyperintensities in the BraTS Data Using a 3D Convolutional Neural Network |
| title_short | Multi-Disease Segmentation of Gliomas and White Matter Hyperintensities in the BraTS Data Using a 3D Convolutional Neural Network |
| title_sort | multi disease segmentation of gliomas and white matter hyperintensities in the brats data using a 3d convolutional neural network |
| topic | segmentation glioblastoma convolutional neural network white matter hyperintensities deep learning radiology |
| url | https://www.frontiersin.org/article/10.3389/fncom.2019.00084/full |
| work_keys_str_mv | AT jeffreydrudie multidiseasesegmentationofgliomasandwhitematterhyperintensitiesinthebratsdatausinga3dconvolutionalneuralnetwork AT jeffreydrudie multidiseasesegmentationofgliomasandwhitematterhyperintensitiesinthebratsdatausinga3dconvolutionalneuralnetwork AT davidaweiss multidiseasesegmentationofgliomasandwhitematterhyperintensitiesinthebratsdatausinga3dconvolutionalneuralnetwork AT rachitsaluja multidiseasesegmentationofgliomasandwhitematterhyperintensitiesinthebratsdatausinga3dconvolutionalneuralnetwork AT andreasmrauschecker multidiseasesegmentationofgliomasandwhitematterhyperintensitiesinthebratsdatausinga3dconvolutionalneuralnetwork AT jiancongwang multidiseasesegmentationofgliomasandwhitematterhyperintensitiesinthebratsdatausinga3dconvolutionalneuralnetwork AT leosugrue multidiseasesegmentationofgliomasandwhitematterhyperintensitiesinthebratsdatausinga3dconvolutionalneuralnetwork AT spyridonbakas multidiseasesegmentationofgliomasandwhitematterhyperintensitiesinthebratsdatausinga3dconvolutionalneuralnetwork AT spyridonbakas multidiseasesegmentationofgliomasandwhitematterhyperintensitiesinthebratsdatausinga3dconvolutionalneuralnetwork AT spyridonbakas multidiseasesegmentationofgliomasandwhitematterhyperintensitiesinthebratsdatausinga3dconvolutionalneuralnetwork AT johnbcolby multidiseasesegmentationofgliomasandwhitematterhyperintensitiesinthebratsdatausinga3dconvolutionalneuralnetwork |