Brain CT image classification based on mask RCNN and attention mechanism
Abstract Along with the computer application technology progress, machine learning, and block-chain techniques have been applied comprehensively in various fields. The application of machine learning, and block-chain techniques into medical image retrieval, classification and auxiliary diagnosis has...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-11-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-78566-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862138360299520 |
|---|---|
| author | Shoulin Yin Hang Li Lin Teng Asif Ali Laghari Ahmad Almadhor Michal Gregus Gabriel Avelino Sampedro |
| author_facet | Shoulin Yin Hang Li Lin Teng Asif Ali Laghari Ahmad Almadhor Michal Gregus Gabriel Avelino Sampedro |
| author_sort | Shoulin Yin |
| collection | DOAJ |
| description | Abstract Along with the computer application technology progress, machine learning, and block-chain techniques have been applied comprehensively in various fields. The application of machine learning, and block-chain techniques into medical image retrieval, classification and auxiliary diagnosis has become one of the research hotspots at present. Brain tumor is one of the major diseases threatening human life. The number of deaths caused by these diseases is increasing dramatically every year in the world. Aiming at the classification problem of brain CT images in healthcare. We propose a Mask RCNN with attention mechanism method in this research. First, the ResNet-10 is utilized as the backbone model to extract local features of the input brain CT images. In the partial residual module, the standard convolution is substituted by deformable convolution. Then, the spatial attention mechanism and the channel attention mechanism are connected in parallel. The deformable convolution is embedded to the two modules to extract global features. Finally, the loss function is improved to further optimize the precision of target edge segmentation in the Mask RCNN branch. Finally, we make experiments on public brain CT data set, the results show that the proposed image classification fragrance can effectively refine the edge features, increase the degree of separation between target and background, and improve the classification effect. |
| format | Article |
| id | doaj-art-2e688a8b890f4deaa5a50798632261cb |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-2e688a8b890f4deaa5a50798632261cb2025-02-09T12:38:11ZengNature PortfolioScientific Reports2045-23222024-11-0114111210.1038/s41598-024-78566-1Brain CT image classification based on mask RCNN and attention mechanismShoulin Yin0Hang Li1Lin Teng2Asif Ali Laghari3Ahmad Almadhor4Michal Gregus5Gabriel Avelino Sampedro6Software College, Shenyang Normal UniversitySoftware College, Shenyang Normal UniversitySoftware College, Shenyang Normal UniversitySoftware College, Shenyang Normal UniversityDepartment of Computer Engineering and Networks, College of Computer and Information Sciences, Jouf UniversityFaculty of Management, Comenius University in BratislavaDepartment of Computer Science, University of the Philippines DilimanAbstract Along with the computer application technology progress, machine learning, and block-chain techniques have been applied comprehensively in various fields. The application of machine learning, and block-chain techniques into medical image retrieval, classification and auxiliary diagnosis has become one of the research hotspots at present. Brain tumor is one of the major diseases threatening human life. The number of deaths caused by these diseases is increasing dramatically every year in the world. Aiming at the classification problem of brain CT images in healthcare. We propose a Mask RCNN with attention mechanism method in this research. First, the ResNet-10 is utilized as the backbone model to extract local features of the input brain CT images. In the partial residual module, the standard convolution is substituted by deformable convolution. Then, the spatial attention mechanism and the channel attention mechanism are connected in parallel. The deformable convolution is embedded to the two modules to extract global features. Finally, the loss function is improved to further optimize the precision of target edge segmentation in the Mask RCNN branch. Finally, we make experiments on public brain CT data set, the results show that the proposed image classification fragrance can effectively refine the edge features, increase the degree of separation between target and background, and improve the classification effect.https://doi.org/10.1038/s41598-024-78566-1Machine learningHealthcareBrain CT image classificationMask RCNNAttention mechanismDeformable convolution |
| spellingShingle | Shoulin Yin Hang Li Lin Teng Asif Ali Laghari Ahmad Almadhor Michal Gregus Gabriel Avelino Sampedro Brain CT image classification based on mask RCNN and attention mechanism Scientific Reports Machine learning Healthcare Brain CT image classification Mask RCNN Attention mechanism Deformable convolution |
| title | Brain CT image classification based on mask RCNN and attention mechanism |
| title_full | Brain CT image classification based on mask RCNN and attention mechanism |
| title_fullStr | Brain CT image classification based on mask RCNN and attention mechanism |
| title_full_unstemmed | Brain CT image classification based on mask RCNN and attention mechanism |
| title_short | Brain CT image classification based on mask RCNN and attention mechanism |
| title_sort | brain ct image classification based on mask rcnn and attention mechanism |
| topic | Machine learning Healthcare Brain CT image classification Mask RCNN Attention mechanism Deformable convolution |
| url | https://doi.org/10.1038/s41598-024-78566-1 |
| work_keys_str_mv | AT shoulinyin brainctimageclassificationbasedonmaskrcnnandattentionmechanism AT hangli brainctimageclassificationbasedonmaskrcnnandattentionmechanism AT linteng brainctimageclassificationbasedonmaskrcnnandattentionmechanism AT asifalilaghari brainctimageclassificationbasedonmaskrcnnandattentionmechanism AT ahmadalmadhor brainctimageclassificationbasedonmaskrcnnandattentionmechanism AT michalgregus brainctimageclassificationbasedonmaskrcnnandattentionmechanism AT gabrielavelinosampedro brainctimageclassificationbasedonmaskrcnnandattentionmechanism |