Dilated SE-DenseNet for brain tumor MRI classification
Abstract In the field of medical imaging, particularly MRI-based brain tumor classification, we propose an advanced convolutional neural network (CNN) leveraging the DenseNet-121 architecture, enhanced with dilated convolutional layers and Squeeze-and-Excitation (SE) networks’ attention mechanisms....
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-025-86752-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571831995858944 |
|---|---|
| author | Yuannong Mao Jiwook Kim Lena Podina Mohammad Kohandel |
| author_facet | Yuannong Mao Jiwook Kim Lena Podina Mohammad Kohandel |
| author_sort | Yuannong Mao |
| collection | DOAJ |
| description | Abstract In the field of medical imaging, particularly MRI-based brain tumor classification, we propose an advanced convolutional neural network (CNN) leveraging the DenseNet-121 architecture, enhanced with dilated convolutional layers and Squeeze-and-Excitation (SE) networks’ attention mechanisms. This novel approach aims to improve upon state-of-the-art methods of tumor identification. Our model, trained and evaluated on a comprehensive Kaggle brain tumor dataset, demonstrated superior performance over established convolution-based and transformer-based models: ResNet-101, VGG-19, original DenseNet-121, MobileNet-V2, ViT-L/16, and Swin-B across key metrics: F1-score, accuracy, precision, and recall. The results underscore the effectiveness of our architectural enhancements in medical image analysis. Future research directions include optimizing dilation layers and exploring various architectural configurations. The study highlights the significant role of machine learning in improving diagnostic accuracy in medical imaging, with potential applications extending beyond brain tumor detection to other medical imaging tasks. |
| format | Article |
| id | doaj-art-eba45620509748598ecd4bc750261d13 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-eba45620509748598ecd4bc750261d132025-02-02T12:16:58ZengNature PortfolioScientific Reports2045-23222025-01-0115111010.1038/s41598-025-86752-yDilated SE-DenseNet for brain tumor MRI classificationYuannong Mao0Jiwook Kim1Lena Podina2Mohammad Kohandel3Department of Applied Mathematics, University of WaterlooDepartment of Applied Mathematics, University of WaterlooDavid R. Cheriton School of Computer Science, University of WaterlooDepartment of Applied Mathematics, University of WaterlooAbstract In the field of medical imaging, particularly MRI-based brain tumor classification, we propose an advanced convolutional neural network (CNN) leveraging the DenseNet-121 architecture, enhanced with dilated convolutional layers and Squeeze-and-Excitation (SE) networks’ attention mechanisms. This novel approach aims to improve upon state-of-the-art methods of tumor identification. Our model, trained and evaluated on a comprehensive Kaggle brain tumor dataset, demonstrated superior performance over established convolution-based and transformer-based models: ResNet-101, VGG-19, original DenseNet-121, MobileNet-V2, ViT-L/16, and Swin-B across key metrics: F1-score, accuracy, precision, and recall. The results underscore the effectiveness of our architectural enhancements in medical image analysis. Future research directions include optimizing dilation layers and exploring various architectural configurations. The study highlights the significant role of machine learning in improving diagnostic accuracy in medical imaging, with potential applications extending beyond brain tumor detection to other medical imaging tasks.https://doi.org/10.1038/s41598-025-86752-y |
| spellingShingle | Yuannong Mao Jiwook Kim Lena Podina Mohammad Kohandel Dilated SE-DenseNet for brain tumor MRI classification Scientific Reports |
| title | Dilated SE-DenseNet for brain tumor MRI classification |
| title_full | Dilated SE-DenseNet for brain tumor MRI classification |
| title_fullStr | Dilated SE-DenseNet for brain tumor MRI classification |
| title_full_unstemmed | Dilated SE-DenseNet for brain tumor MRI classification |
| title_short | Dilated SE-DenseNet for brain tumor MRI classification |
| title_sort | dilated se densenet for brain tumor mri classification |
| url | https://doi.org/10.1038/s41598-025-86752-y |
| work_keys_str_mv | AT yuannongmao dilatedsedensenetforbraintumormriclassification AT jiwookkim dilatedsedensenetforbraintumormriclassification AT lenapodina dilatedsedensenetforbraintumormriclassification AT mohammadkohandel dilatedsedensenetforbraintumormriclassification |