AUCseg: An Automatically Unsupervised Clustering Toolbox for 3D-Segmentation of High-Grade Gliomas in Multi-Parametric MR Images
The segmentation of high-grade gliomas (HGG) using magnetic resonance imaging (MRI) data is clinically meaningful in neurosurgical practice, but a challenging task. Currently, most segmentation methods are supervised learning with labeled training sets. Although these methods work well in most cases...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-06-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2021.679952/full |
| _version_ | 1818450685965893632 |
|---|---|
| author | Botao Zhao Botao Zhao Yan Ren Ziqi Yu Ziqi Yu Jinhua Yu Tingying Peng Xiao-Yong Zhang Xiao-Yong Zhang Xiao-Yong Zhang |
| author_facet | Botao Zhao Botao Zhao Yan Ren Ziqi Yu Ziqi Yu Jinhua Yu Tingying Peng Xiao-Yong Zhang Xiao-Yong Zhang Xiao-Yong Zhang |
| author_sort | Botao Zhao |
| collection | DOAJ |
| description | The segmentation of high-grade gliomas (HGG) using magnetic resonance imaging (MRI) data is clinically meaningful in neurosurgical practice, but a challenging task. Currently, most segmentation methods are supervised learning with labeled training sets. Although these methods work well in most cases, they typically require time-consuming manual labeling and pre-trained models. In this work, we propose an automatically unsupervised segmentation toolbox based on the clustering algorithm and morphological processing, named AUCseg. With our toolbox, the whole tumor was first extracted by clustering on T2-FLAIR images. Then, based on the mask acquired with whole tumor segmentation, the enhancing tumor was segmented on the post-contrast T1-weighted images (T1-CE) using clustering methods. Finally, the necrotic regions were segmented by morphological processing or clustering on T2-weighted images. Compared with K-means, Mini-batch K-means, and Fuzzy C Means (FCM), the Gaussian Mixture Model (GMM) clustering performs the best in our toolbox. We did a multi-sided evaluation of our toolbox in the BraTS2018 dataset and demonstrated that the whole tumor, tumor core, and enhancing tumor can be automatically segmented using default hyper-parameters with Dice score 0.8209, 0.7087, and 0.7254, respectively. The computing time of our toolbox for each case is around 22 seconds, which is at least 3 times faster than other state-of-the-art unsupervised methods. In addition, our toolbox has an option to perform semi-automatic segmentation via manually setup hyper-parameters, which could improve the segmentation performance. Our toolbox, AUCseg, is publicly available on Github. (https://github.com/Haifengtao/AUCseg). |
| first_indexed | 2024-12-14T20:55:14Z |
| format | Article |
| id | doaj.art-4ae24c7cd7e1455ca0c06837b1132abd |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-12-14T20:55:14Z |
| publishDate | 2021-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-4ae24c7cd7e1455ca0c06837b1132abd2022-12-21T22:47:43ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2021-06-011110.3389/fonc.2021.679952679952AUCseg: An Automatically Unsupervised Clustering Toolbox for 3D-Segmentation of High-Grade Gliomas in Multi-Parametric MR ImagesBotao Zhao0Botao Zhao1Yan Ren2Ziqi Yu3Ziqi Yu4Jinhua Yu5Tingying Peng6Xiao-Yong Zhang7Xiao-Yong Zhang8Xiao-Yong Zhang9Institute of Science and Technology for Brain-inspired Intelligence, Fudan University, Shanghai, ChinaKey Laboratory of Computational Neuroscience and Brain-Inspired Intelligence (Fudan University), Ministry of Education, Shanghai, ChinaDepartment of Radiology, Huashan Hospital, Fudan University, Shanghai, ChinaInstitute of Science and Technology for Brain-inspired Intelligence, Fudan University, Shanghai, ChinaKey Laboratory of Computational Neuroscience and Brain-Inspired Intelligence (Fudan University), Ministry of Education, Shanghai, ChinaSchool of Information Science and Technology, Fudan University, Shanghai, ChinaHelmholtz AI, Helmholtz zentrum Muenchen, Munich, GermanyInstitute of Science and Technology for Brain-inspired Intelligence, Fudan University, Shanghai, ChinaKey Laboratory of Computational Neuroscience and Brain-Inspired Intelligence (Fudan University), Ministry of Education, Shanghai, ChinaMinistry of Education (MOE) Frontiers Center for Brain Science, Fudan University, Shanghai, ChinaThe segmentation of high-grade gliomas (HGG) using magnetic resonance imaging (MRI) data is clinically meaningful in neurosurgical practice, but a challenging task. Currently, most segmentation methods are supervised learning with labeled training sets. Although these methods work well in most cases, they typically require time-consuming manual labeling and pre-trained models. In this work, we propose an automatically unsupervised segmentation toolbox based on the clustering algorithm and morphological processing, named AUCseg. With our toolbox, the whole tumor was first extracted by clustering on T2-FLAIR images. Then, based on the mask acquired with whole tumor segmentation, the enhancing tumor was segmented on the post-contrast T1-weighted images (T1-CE) using clustering methods. Finally, the necrotic regions were segmented by morphological processing or clustering on T2-weighted images. Compared with K-means, Mini-batch K-means, and Fuzzy C Means (FCM), the Gaussian Mixture Model (GMM) clustering performs the best in our toolbox. We did a multi-sided evaluation of our toolbox in the BraTS2018 dataset and demonstrated that the whole tumor, tumor core, and enhancing tumor can be automatically segmented using default hyper-parameters with Dice score 0.8209, 0.7087, and 0.7254, respectively. The computing time of our toolbox for each case is around 22 seconds, which is at least 3 times faster than other state-of-the-art unsupervised methods. In addition, our toolbox has an option to perform semi-automatic segmentation via manually setup hyper-parameters, which could improve the segmentation performance. Our toolbox, AUCseg, is publicly available on Github. (https://github.com/Haifengtao/AUCseg).https://www.frontiersin.org/articles/10.3389/fonc.2021.679952/fullgliomaunsupervised segmentationMRItoolboxclustering |
| spellingShingle | Botao Zhao Botao Zhao Yan Ren Ziqi Yu Ziqi Yu Jinhua Yu Tingying Peng Xiao-Yong Zhang Xiao-Yong Zhang Xiao-Yong Zhang AUCseg: An Automatically Unsupervised Clustering Toolbox for 3D-Segmentation of High-Grade Gliomas in Multi-Parametric MR Images Frontiers in Oncology glioma unsupervised segmentation MRI toolbox clustering |
| title | AUCseg: An Automatically Unsupervised Clustering Toolbox for 3D-Segmentation of High-Grade Gliomas in Multi-Parametric MR Images |
| title_full | AUCseg: An Automatically Unsupervised Clustering Toolbox for 3D-Segmentation of High-Grade Gliomas in Multi-Parametric MR Images |
| title_fullStr | AUCseg: An Automatically Unsupervised Clustering Toolbox for 3D-Segmentation of High-Grade Gliomas in Multi-Parametric MR Images |
| title_full_unstemmed | AUCseg: An Automatically Unsupervised Clustering Toolbox for 3D-Segmentation of High-Grade Gliomas in Multi-Parametric MR Images |
| title_short | AUCseg: An Automatically Unsupervised Clustering Toolbox for 3D-Segmentation of High-Grade Gliomas in Multi-Parametric MR Images |
| title_sort | aucseg an automatically unsupervised clustering toolbox for 3d segmentation of high grade gliomas in multi parametric mr images |
| topic | glioma unsupervised segmentation MRI toolbox clustering |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2021.679952/full |
| work_keys_str_mv | AT botaozhao aucseganautomaticallyunsupervisedclusteringtoolboxfor3dsegmentationofhighgradegliomasinmultiparametricmrimages AT botaozhao aucseganautomaticallyunsupervisedclusteringtoolboxfor3dsegmentationofhighgradegliomasinmultiparametricmrimages AT yanren aucseganautomaticallyunsupervisedclusteringtoolboxfor3dsegmentationofhighgradegliomasinmultiparametricmrimages AT ziqiyu aucseganautomaticallyunsupervisedclusteringtoolboxfor3dsegmentationofhighgradegliomasinmultiparametricmrimages AT ziqiyu aucseganautomaticallyunsupervisedclusteringtoolboxfor3dsegmentationofhighgradegliomasinmultiparametricmrimages AT jinhuayu aucseganautomaticallyunsupervisedclusteringtoolboxfor3dsegmentationofhighgradegliomasinmultiparametricmrimages AT tingyingpeng aucseganautomaticallyunsupervisedclusteringtoolboxfor3dsegmentationofhighgradegliomasinmultiparametricmrimages AT xiaoyongzhang aucseganautomaticallyunsupervisedclusteringtoolboxfor3dsegmentationofhighgradegliomasinmultiparametricmrimages AT xiaoyongzhang aucseganautomaticallyunsupervisedclusteringtoolboxfor3dsegmentationofhighgradegliomasinmultiparametricmrimages AT xiaoyongzhang aucseganautomaticallyunsupervisedclusteringtoolboxfor3dsegmentationofhighgradegliomasinmultiparametricmrimages |