Improvement of Multiparametric MR Image Segmentation by Augmenting the Data With Generative Adversarial Networks for Glioma Patients
Every year thousands of patients are diagnosed with a glioma, a type of malignant brain tumor. MRI plays an essential role in the diagnosis and treatment assessment of these patients. Neural networks show great potential to aid physicians in the medical image analysis. This study investigated the cr...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-01-01
|
| Series: | Frontiers in Computational Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fncom.2020.495075/full |
| _version_ | 1818330739650854912 |
|---|---|
| author | Eric Nathan Carver Eric Nathan Carver Zhenzhen Dai Evan Liang James Snyder Ning Wen |
| author_facet | Eric Nathan Carver Eric Nathan Carver Zhenzhen Dai Evan Liang James Snyder Ning Wen |
| author_sort | Eric Nathan Carver |
| collection | DOAJ |
| description | Every year thousands of patients are diagnosed with a glioma, a type of malignant brain tumor. MRI plays an essential role in the diagnosis and treatment assessment of these patients. Neural networks show great potential to aid physicians in the medical image analysis. This study investigated the creation of synthetic brain T1-weighted (T1), post-contrast T1-weighted (T1CE), T2-weighted (T2), and T2 Fluid Attenuated Inversion Recovery (Flair) MR images. These synthetic MR (synMR) images were assessed quantitatively with four metrics. The synMR images were also assessed qualitatively by an authoring physician with notions that synMR possessed realism in its portrayal of structural boundaries but struggled to accurately depict tumor heterogeneity. Additionally, this study investigated the synMR images created by generative adversarial network (GAN) to overcome the lack of annotated medical image data in training U-Nets to segment enhancing tumor, whole tumor, and tumor core regions on gliomas. Multiple two-dimensional (2D) U-Nets were trained with original BraTS data and differing subsets of the synMR images. Dice similarity coefficient (DSC) was used as the loss function during training as well a quantitative metric. Additionally, Hausdorff Distance 95% CI (HD) was used to judge the quality of the contours created by these U-Nets. The model performance was improved in both DSC and HD when incorporating synMR in the training set. In summary, this study showed the ability to generate high quality Flair, T2, T1, and T1CE synMR images using GAN. Using synMR images showed encouraging results to improve the U-Net segmentation performance and shows potential to address the scarcity of annotated medical images. |
| first_indexed | 2024-12-13T13:08:45Z |
| format | Article |
| id | doaj.art-9c8362a777844cb1907197c8f603eec2 |
| institution | Directory Open Access Journal |
| issn | 1662-5188 |
| language | English |
| last_indexed | 2024-12-13T13:08:45Z |
| publishDate | 2021-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Computational Neuroscience |
| spelling | doaj.art-9c8362a777844cb1907197c8f603eec22022-12-21T23:44:44ZengFrontiers Media S.A.Frontiers in Computational Neuroscience1662-51882021-01-011410.3389/fncom.2020.495075495075Improvement of Multiparametric MR Image Segmentation by Augmenting the Data With Generative Adversarial Networks for Glioma PatientsEric Nathan Carver0Eric Nathan Carver1Zhenzhen Dai2Evan Liang3James Snyder4Ning Wen5Henry Ford Health System, Detroit, MI, United StatesWayne State University, Detroit, MI, United StatesHenry Ford Health System, Detroit, MI, United StatesHenry Ford Health System, Detroit, MI, United StatesHenry Ford Health System, Detroit, MI, United StatesHenry Ford Health System, Detroit, MI, United StatesEvery year thousands of patients are diagnosed with a glioma, a type of malignant brain tumor. MRI plays an essential role in the diagnosis and treatment assessment of these patients. Neural networks show great potential to aid physicians in the medical image analysis. This study investigated the creation of synthetic brain T1-weighted (T1), post-contrast T1-weighted (T1CE), T2-weighted (T2), and T2 Fluid Attenuated Inversion Recovery (Flair) MR images. These synthetic MR (synMR) images were assessed quantitatively with four metrics. The synMR images were also assessed qualitatively by an authoring physician with notions that synMR possessed realism in its portrayal of structural boundaries but struggled to accurately depict tumor heterogeneity. Additionally, this study investigated the synMR images created by generative adversarial network (GAN) to overcome the lack of annotated medical image data in training U-Nets to segment enhancing tumor, whole tumor, and tumor core regions on gliomas. Multiple two-dimensional (2D) U-Nets were trained with original BraTS data and differing subsets of the synMR images. Dice similarity coefficient (DSC) was used as the loss function during training as well a quantitative metric. Additionally, Hausdorff Distance 95% CI (HD) was used to judge the quality of the contours created by these U-Nets. The model performance was improved in both DSC and HD when incorporating synMR in the training set. In summary, this study showed the ability to generate high quality Flair, T2, T1, and T1CE synMR images using GAN. Using synMR images showed encouraging results to improve the U-Net segmentation performance and shows potential to address the scarcity of annotated medical images.https://www.frontiersin.org/articles/10.3389/fncom.2020.495075/fullGaNU-netgliomaGBMsegmentation |
| spellingShingle | Eric Nathan Carver Eric Nathan Carver Zhenzhen Dai Evan Liang James Snyder Ning Wen Improvement of Multiparametric MR Image Segmentation by Augmenting the Data With Generative Adversarial Networks for Glioma Patients Frontiers in Computational Neuroscience GaN U-net glioma GBM segmentation |
| title | Improvement of Multiparametric MR Image Segmentation by Augmenting the Data With Generative Adversarial Networks for Glioma Patients |
| title_full | Improvement of Multiparametric MR Image Segmentation by Augmenting the Data With Generative Adversarial Networks for Glioma Patients |
| title_fullStr | Improvement of Multiparametric MR Image Segmentation by Augmenting the Data With Generative Adversarial Networks for Glioma Patients |
| title_full_unstemmed | Improvement of Multiparametric MR Image Segmentation by Augmenting the Data With Generative Adversarial Networks for Glioma Patients |
| title_short | Improvement of Multiparametric MR Image Segmentation by Augmenting the Data With Generative Adversarial Networks for Glioma Patients |
| title_sort | improvement of multiparametric mr image segmentation by augmenting the data with generative adversarial networks for glioma patients |
| topic | GaN U-net glioma GBM segmentation |
| url | https://www.frontiersin.org/articles/10.3389/fncom.2020.495075/full |
| work_keys_str_mv | AT ericnathancarver improvementofmultiparametricmrimagesegmentationbyaugmentingthedatawithgenerativeadversarialnetworksforgliomapatients AT ericnathancarver improvementofmultiparametricmrimagesegmentationbyaugmentingthedatawithgenerativeadversarialnetworksforgliomapatients AT zhenzhendai improvementofmultiparametricmrimagesegmentationbyaugmentingthedatawithgenerativeadversarialnetworksforgliomapatients AT evanliang improvementofmultiparametricmrimagesegmentationbyaugmentingthedatawithgenerativeadversarialnetworksforgliomapatients AT jamessnyder improvementofmultiparametricmrimagesegmentationbyaugmentingthedatawithgenerativeadversarialnetworksforgliomapatients AT ningwen improvementofmultiparametricmrimagesegmentationbyaugmentingthedatawithgenerativeadversarialnetworksforgliomapatients |