Optimizing Tumor Detection in Brain MRI with One-Class SVM and Convolutional Neural Network-Based Feature Extraction
The early detection of brain tumors is critical for improving clinical outcomes and patient survival. However, medical imaging datasets frequently exhibit class imbalance, posing significant challenges for traditional classification algorithms that rely on balanced data distributions. To address thi...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/11/7/207 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849246384243343360 |
|---|---|
| author | Azeddine Mjahad Alfredo Rosado-Muñoz |
| author_facet | Azeddine Mjahad Alfredo Rosado-Muñoz |
| author_sort | Azeddine Mjahad |
| collection | DOAJ |
| description | The early detection of brain tumors is critical for improving clinical outcomes and patient survival. However, medical imaging datasets frequently exhibit class imbalance, posing significant challenges for traditional classification algorithms that rely on balanced data distributions. To address this issue, this study employs a One-Class Support Vector Machine (OCSVM) trained exclusively on features extracted from healthy brain MRI images, using both deep learning architectures—such as DenseNet121, VGG16, MobileNetV2, InceptionV3, and ResNet50—and classical feature extraction techniques. Experimental results demonstrate that combining Convolutional Neural Network (CNN)-based feature extraction with OCSVM significantly improves anomaly detection performance compared with simpler handcrafted approaches. DenseNet121 achieved an accuracy of 94.83%, a precision of 99.23%, and a sensitivity of 89.97%, while VGG16 reached an accuracy of 95.33%, a precision of 98.87%, and a sensitivity of 91.32%. MobileNetV2 showed a competitive trade-off between accuracy (92.83%) and computational efficiency, making it suitable for resource-constrained environments. Additionally, the pure CNN model—trained directly for classification without OCSVM—outperformed hybrid methods with an accuracy of 97.83%, highlighting the effectiveness of deep convolutional networks in directly learning discriminative features from MRI data. This approach enables reliable detection of brain tumor anomalies without requiring labeled pathological data, offering a promising solution for clinical contexts where abnormal samples are scarce. Future research will focus on reducing inference time, expanding and diversifying training datasets, and incorporating explainability tools to support clinical integration and trust in AI-based diagnostics. |
| format | Article |
| id | doaj-art-1910bb2955e54faf8d03cf2be66d35cf |
| institution | Kabale University |
| issn | 2313-433X |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj-art-1910bb2955e54faf8d03cf2be66d35cf2025-08-20T03:58:31ZengMDPI AGJournal of Imaging2313-433X2025-06-0111720710.3390/jimaging11070207Optimizing Tumor Detection in Brain MRI with One-Class SVM and Convolutional Neural Network-Based Feature ExtractionAzeddine Mjahad0Alfredo Rosado-Muñoz1GDDP, Department Electronic Engineering, School of Engineering, University of Valencia, 46100 Burjassot, Valencia, SpainGDDP, Department Electronic Engineering, School of Engineering, University of Valencia, 46100 Burjassot, Valencia, SpainThe early detection of brain tumors is critical for improving clinical outcomes and patient survival. However, medical imaging datasets frequently exhibit class imbalance, posing significant challenges for traditional classification algorithms that rely on balanced data distributions. To address this issue, this study employs a One-Class Support Vector Machine (OCSVM) trained exclusively on features extracted from healthy brain MRI images, using both deep learning architectures—such as DenseNet121, VGG16, MobileNetV2, InceptionV3, and ResNet50—and classical feature extraction techniques. Experimental results demonstrate that combining Convolutional Neural Network (CNN)-based feature extraction with OCSVM significantly improves anomaly detection performance compared with simpler handcrafted approaches. DenseNet121 achieved an accuracy of 94.83%, a precision of 99.23%, and a sensitivity of 89.97%, while VGG16 reached an accuracy of 95.33%, a precision of 98.87%, and a sensitivity of 91.32%. MobileNetV2 showed a competitive trade-off between accuracy (92.83%) and computational efficiency, making it suitable for resource-constrained environments. Additionally, the pure CNN model—trained directly for classification without OCSVM—outperformed hybrid methods with an accuracy of 97.83%, highlighting the effectiveness of deep convolutional networks in directly learning discriminative features from MRI data. This approach enables reliable detection of brain tumor anomalies without requiring labeled pathological data, offering a promising solution for clinical contexts where abnormal samples are scarce. Future research will focus on reducing inference time, expanding and diversifying training datasets, and incorporating explainability tools to support clinical integration and trust in AI-based diagnostics.https://www.mdpi.com/2313-433X/11/7/207brain tumor detectionCNNsOCSVMdimensionality reductionfrequency analysisfeature-based methods |
| spellingShingle | Azeddine Mjahad Alfredo Rosado-Muñoz Optimizing Tumor Detection in Brain MRI with One-Class SVM and Convolutional Neural Network-Based Feature Extraction Journal of Imaging brain tumor detection CNNs OCSVM dimensionality reduction frequency analysis feature-based methods |
| title | Optimizing Tumor Detection in Brain MRI with One-Class SVM and Convolutional Neural Network-Based Feature Extraction |
| title_full | Optimizing Tumor Detection in Brain MRI with One-Class SVM and Convolutional Neural Network-Based Feature Extraction |
| title_fullStr | Optimizing Tumor Detection in Brain MRI with One-Class SVM and Convolutional Neural Network-Based Feature Extraction |
| title_full_unstemmed | Optimizing Tumor Detection in Brain MRI with One-Class SVM and Convolutional Neural Network-Based Feature Extraction |
| title_short | Optimizing Tumor Detection in Brain MRI with One-Class SVM and Convolutional Neural Network-Based Feature Extraction |
| title_sort | optimizing tumor detection in brain mri with one class svm and convolutional neural network based feature extraction |
| topic | brain tumor detection CNNs OCSVM dimensionality reduction frequency analysis feature-based methods |
| url | https://www.mdpi.com/2313-433X/11/7/207 |
| work_keys_str_mv | AT azeddinemjahad optimizingtumordetectioninbrainmriwithoneclasssvmandconvolutionalneuralnetworkbasedfeatureextraction AT alfredorosadomunoz optimizingtumordetectioninbrainmriwithoneclasssvmandconvolutionalneuralnetworkbasedfeatureextraction |