Automatic segmentation framework of X-Ray tomography data for multi-phase rock using Swin Transformer approach
Abstract A thorough understanding of the impact of the 3D meso-structure on damage and failure patterns is essential for revealing the failure conditions of composite rock materials such as coal, concrete, marble, and others. This paper presents a 3D XCT dataset of coal rock with 1372 slices (each s...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-11-01
|
| Series: | Scientific Data |
| Online Access: | https://doi.org/10.1038/s41597-023-02734-7 |
| _version_ | 1797453965142523904 |
|---|---|
| author | Hao Chen Xiaoqi Cao Xiyan Zhang Zhenyu Wang Bingjing Qiu Kehong Zheng |
| author_facet | Hao Chen Xiaoqi Cao Xiyan Zhang Zhenyu Wang Bingjing Qiu Kehong Zheng |
| author_sort | Hao Chen |
| collection | DOAJ |
| description | Abstract A thorough understanding of the impact of the 3D meso-structure on damage and failure patterns is essential for revealing the failure conditions of composite rock materials such as coal, concrete, marble, and others. This paper presents a 3D XCT dataset of coal rock with 1372 slices (each slice contains 1720 × 1771 pixels in x × y direction). The 3D XCT datasets were obtained by MicroXMT-400 using the 225/320kv Nikon Metris custom bay. The raw datasets were processed by an automatic semantic segmentation method based on the Swin Transformer (Swin-T) architecture, which aims to overcome the issue of large errors and low efficiency for traditional methods. The hybrid loss function proposed can also effectively mitigate the influence of large volume features in the training process by incorporating modulation terms into the cross entropy loss, thereby enhancing the accuracy of segmentation for small volume features. This dataset will be available to the related researchers for further finite element analysis or microstructural statistical analysis, involving complex physical and mechanical behaviors at different scales. |
| first_indexed | 2024-03-09T15:30:30Z |
| format | Article |
| id | doaj.art-b503b8c831d640849b67d190269a8873 |
| institution | Directory Open Access Journal |
| issn | 2052-4463 |
| language | English |
| last_indexed | 2024-03-09T15:30:30Z |
| publishDate | 2023-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Data |
| spelling | doaj.art-b503b8c831d640849b67d190269a88732023-11-26T12:17:53ZengNature PortfolioScientific Data2052-44632023-11-0110111210.1038/s41597-023-02734-7Automatic segmentation framework of X-Ray tomography data for multi-phase rock using Swin Transformer approachHao Chen0Xiaoqi Cao1Xiyan Zhang2Zhenyu Wang3Bingjing Qiu4Kehong Zheng5College of Mechanical Engineering, Zhejiang Sci-tech University HangzhouCollege of Mechanical Engineering, Zhejiang Sci-tech University HangzhouCenter Sinohydro Bureau 12, Co., LTD.College of Civil Engineering and Architecture, Zhejiang UniversityCollege of Civil Engineering and Architecture, Zhejiang UniversityCollege of Mechanical Engineering, Zhejiang Sci-tech University HangzhouAbstract A thorough understanding of the impact of the 3D meso-structure on damage and failure patterns is essential for revealing the failure conditions of composite rock materials such as coal, concrete, marble, and others. This paper presents a 3D XCT dataset of coal rock with 1372 slices (each slice contains 1720 × 1771 pixels in x × y direction). The 3D XCT datasets were obtained by MicroXMT-400 using the 225/320kv Nikon Metris custom bay. The raw datasets were processed by an automatic semantic segmentation method based on the Swin Transformer (Swin-T) architecture, which aims to overcome the issue of large errors and low efficiency for traditional methods. The hybrid loss function proposed can also effectively mitigate the influence of large volume features in the training process by incorporating modulation terms into the cross entropy loss, thereby enhancing the accuracy of segmentation for small volume features. This dataset will be available to the related researchers for further finite element analysis or microstructural statistical analysis, involving complex physical and mechanical behaviors at different scales.https://doi.org/10.1038/s41597-023-02734-7 |
| spellingShingle | Hao Chen Xiaoqi Cao Xiyan Zhang Zhenyu Wang Bingjing Qiu Kehong Zheng Automatic segmentation framework of X-Ray tomography data for multi-phase rock using Swin Transformer approach Scientific Data |
| title | Automatic segmentation framework of X-Ray tomography data for multi-phase rock using Swin Transformer approach |
| title_full | Automatic segmentation framework of X-Ray tomography data for multi-phase rock using Swin Transformer approach |
| title_fullStr | Automatic segmentation framework of X-Ray tomography data for multi-phase rock using Swin Transformer approach |
| title_full_unstemmed | Automatic segmentation framework of X-Ray tomography data for multi-phase rock using Swin Transformer approach |
| title_short | Automatic segmentation framework of X-Ray tomography data for multi-phase rock using Swin Transformer approach |
| title_sort | automatic segmentation framework of x ray tomography data for multi phase rock using swin transformer approach |
| url | https://doi.org/10.1038/s41597-023-02734-7 |
| work_keys_str_mv | AT haochen automaticsegmentationframeworkofxraytomographydataformultiphaserockusingswintransformerapproach AT xiaoqicao automaticsegmentationframeworkofxraytomographydataformultiphaserockusingswintransformerapproach AT xiyanzhang automaticsegmentationframeworkofxraytomographydataformultiphaserockusingswintransformerapproach AT zhenyuwang automaticsegmentationframeworkofxraytomographydataformultiphaserockusingswintransformerapproach AT bingjingqiu automaticsegmentationframeworkofxraytomographydataformultiphaserockusingswintransformerapproach AT kehongzheng automaticsegmentationframeworkofxraytomographydataformultiphaserockusingswintransformerapproach |