Detection of Aspergilloma Disease Using Feature-Selection-Based Vision Transformers
<b>Background</b>: Aspergilloma disease is a fungal mass found in organs such as the sinuses and lungs, caused by the fungus <i>Aspergillus</i>. This disease occurs due to the accumulation of mucus, inflamed cells, and altered blood elements. Various surgical methods are used...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/15/1/26 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549255245824000 |
|---|---|
| author | Siyami Aydın Mehmet Ağar Muharrem Çakmak Mustafa Koç Mesut Toğaçar |
| author_facet | Siyami Aydın Mehmet Ağar Muharrem Çakmak Mustafa Koç Mesut Toğaçar |
| author_sort | Siyami Aydın |
| collection | DOAJ |
| description | <b>Background</b>: Aspergilloma disease is a fungal mass found in organs such as the sinuses and lungs, caused by the fungus <i>Aspergillus</i>. This disease occurs due to the accumulation of mucus, inflamed cells, and altered blood elements. Various surgical methods are used in clinical settings for the treatment of aspergilloma disease. Expert opinion is crucial for the diagnosis of the disease. Recent advancements in next-generation technologies have made them crucial for disease detection. Deep-learning models, which benefit from continuous technological advancements, are already integrated into current early diagnosis systems. <b>Methods</b>: This study is distinguished by the use of vision transformers (ViTs) rather than traditional deep-learning models. The data used in this study were obtained from patients treated at the Department of Thoracic Surgery at Fırat University. The dataset consists of two class types: aspergilloma disease images and non-aspergilloma disease images. The proposed approach consists of pre-processing, model training, feature extraction, efficient feature selection, feature fusion, and classification processes. In the pre-processing step, unnecessary regions of the images were cropped and data augmentation techniques were applied for model training. Three types of ViT models (vit_base_patch16, vit_large_patch16, and vit_base_resnet50) were used for model training. The feature sets obtained from training the models were merged, and the combined feature set was processed using feature selection methods (<i>Chi</i>2, mRMR, and Relief). Efficient features selected by these methods (<i>Chi</i>2 and mRMR, <i>Chi</i>2 and Relief, and mRMR and Relief) were combined in certain proportions to obtain more effective feature sets. Machine-learning methods were used in the classification process. <b>Results</b>: The most successful result in the detection of aspergilloma disease was achieved using Support Vector Machines (SVMs). The SVM method achieved a 99.70% overall accuracy with the cross-validation technique in classification. <b>Conclusions</b>: These results highlight the benefits of the suggested method for identifying aspergilloma. |
| format | Article |
| id | doaj-art-2e239caba3054fb89adde2b3b5a07743 |
| institution | Kabale University |
| issn | 2075-4418 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj-art-2e239caba3054fb89adde2b3b5a077432025-01-10T13:16:29ZengMDPI AGDiagnostics2075-44182024-12-011512610.3390/diagnostics15010026Detection of Aspergilloma Disease Using Feature-Selection-Based Vision TransformersSiyami Aydın0Mehmet Ağar1Muharrem Çakmak2Mustafa Koç3Mesut Toğaçar4Department of Thoracic Surgery, Faculty of Medicine, Firat University, 23119 Elazig, TurkeyDepartment of Thoracic Surgery, Faculty of Medicine, Firat University, 23119 Elazig, TurkeyDepartment of Thoracic Surgery, Faculty of Medicine, Firat University, 23119 Elazig, TurkeyDepartment of Radiology, Faculty of Medicine, Firat University, 23119 Elazig, TurkeyDepartment of Management Information Systems, Faculty of Economics and Administrative Sciences, Firat University, 23119 Elazig, Turkey<b>Background</b>: Aspergilloma disease is a fungal mass found in organs such as the sinuses and lungs, caused by the fungus <i>Aspergillus</i>. This disease occurs due to the accumulation of mucus, inflamed cells, and altered blood elements. Various surgical methods are used in clinical settings for the treatment of aspergilloma disease. Expert opinion is crucial for the diagnosis of the disease. Recent advancements in next-generation technologies have made them crucial for disease detection. Deep-learning models, which benefit from continuous technological advancements, are already integrated into current early diagnosis systems. <b>Methods</b>: This study is distinguished by the use of vision transformers (ViTs) rather than traditional deep-learning models. The data used in this study were obtained from patients treated at the Department of Thoracic Surgery at Fırat University. The dataset consists of two class types: aspergilloma disease images and non-aspergilloma disease images. The proposed approach consists of pre-processing, model training, feature extraction, efficient feature selection, feature fusion, and classification processes. In the pre-processing step, unnecessary regions of the images were cropped and data augmentation techniques were applied for model training. Three types of ViT models (vit_base_patch16, vit_large_patch16, and vit_base_resnet50) were used for model training. The feature sets obtained from training the models were merged, and the combined feature set was processed using feature selection methods (<i>Chi</i>2, mRMR, and Relief). Efficient features selected by these methods (<i>Chi</i>2 and mRMR, <i>Chi</i>2 and Relief, and mRMR and Relief) were combined in certain proportions to obtain more effective feature sets. Machine-learning methods were used in the classification process. <b>Results</b>: The most successful result in the detection of aspergilloma disease was achieved using Support Vector Machines (SVMs). The SVM method achieved a 99.70% overall accuracy with the cross-validation technique in classification. <b>Conclusions</b>: These results highlight the benefits of the suggested method for identifying aspergilloma.https://www.mdpi.com/2075-4418/15/1/26aspergilloma diseaseaspergilloma detectionvision transformersmerge-based feature selectionmachine learning |
| spellingShingle | Siyami Aydın Mehmet Ağar Muharrem Çakmak Mustafa Koç Mesut Toğaçar Detection of Aspergilloma Disease Using Feature-Selection-Based Vision Transformers Diagnostics aspergilloma disease aspergilloma detection vision transformers merge-based feature selection machine learning |
| title | Detection of Aspergilloma Disease Using Feature-Selection-Based Vision Transformers |
| title_full | Detection of Aspergilloma Disease Using Feature-Selection-Based Vision Transformers |
| title_fullStr | Detection of Aspergilloma Disease Using Feature-Selection-Based Vision Transformers |
| title_full_unstemmed | Detection of Aspergilloma Disease Using Feature-Selection-Based Vision Transformers |
| title_short | Detection of Aspergilloma Disease Using Feature-Selection-Based Vision Transformers |
| title_sort | detection of aspergilloma disease using feature selection based vision transformers |
| topic | aspergilloma disease aspergilloma detection vision transformers merge-based feature selection machine learning |
| url | https://www.mdpi.com/2075-4418/15/1/26 |
| work_keys_str_mv | AT siyamiaydın detectionofaspergillomadiseaseusingfeatureselectionbasedvisiontransformers AT mehmetagar detectionofaspergillomadiseaseusingfeatureselectionbasedvisiontransformers AT muharremcakmak detectionofaspergillomadiseaseusingfeatureselectionbasedvisiontransformers AT mustafakoc detectionofaspergillomadiseaseusingfeatureselectionbasedvisiontransformers AT mesuttogacar detectionofaspergillomadiseaseusingfeatureselectionbasedvisiontransformers |