A novel hybrid model for brain tumor analysis with CNN and Moth Flame Optimization
Early and accurate detection of brain tumors is vital for improving patient outcomes and treatment decisions. This study presents a Hybrid Brain Tumor Analysis (BTA) framework that integrates Moth Flame Optimization (MFO) and Convolutional Neural Networks (CNNs) for tumor identification, segmentatio...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Informatics in Medicine Unlocked |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352914825000590 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849254298509115392 |
|---|---|
| author | Mohit Prakram Kirti Rawal Arun Singh Ankur Goyal Shiv Kant Shakeel Ahmed Saiprasad Potharaju |
| author_facet | Mohit Prakram Kirti Rawal Arun Singh Ankur Goyal Shiv Kant Shakeel Ahmed Saiprasad Potharaju |
| author_sort | Mohit Prakram |
| collection | DOAJ |
| description | Early and accurate detection of brain tumors is vital for improving patient outcomes and treatment decisions. This study presents a Hybrid Brain Tumor Analysis (BTA) framework that integrates Moth Flame Optimization (MFO) and Convolutional Neural Networks (CNNs) for tumor identification, segmentation, and classification using MRI scans. A hybrid segmentation approach is employed, combining K-means clustering with MFO and a custom fitness function to extract tumor regions. Feature extraction is followed by MFO-based feature selection to reduce dimensionality and enhance classification performance. The refined features are used to train a custom CNN architecture, BTA-Net, for classifying tumors into meningioma, glioma, and pituitary types. The proposed model achieves a 3.22 % improvement in classification accuracy compared to baseline methods, along with notable gains in precision (4.07 %), recall (2.46 %), and F-measure (3.25 %). Statistical validation confirms the significance of these results, making the BTA framework a robust tool for automated brain tumor analysis. |
| format | Article |
| id | doaj-art-108784fc44bc42ea8be30ef77e833921 |
| institution | Kabale University |
| issn | 2352-9148 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Informatics in Medicine Unlocked |
| spelling | doaj-art-108784fc44bc42ea8be30ef77e8339212025-08-20T03:56:04ZengElsevierInformatics in Medicine Unlocked2352-91482025-01-015710167110.1016/j.imu.2025.101671A novel hybrid model for brain tumor analysis with CNN and Moth Flame OptimizationMohit Prakram0Kirti Rawal1Arun Singh2Ankur Goyal3Shiv Kant4Shakeel Ahmed5Saiprasad Potharaju6Department of Computer Science & Engineering, Lovely Professional University, Phagwara, Punjab, IndiaDepartment of Electronics and communication, Lovely Professional University, Phagwara, Punjab, IndiaDepartment of Computer Science & Engineering, Lovely Professional University, Phagwara, Punjab, IndiaDept of CSE, Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, 412115, India; Corresponding author.Department of Computer Science & Engineering(AI & DS), Greater Noida Institute of Technology (GNIOT), Greater Noida, Delhi/NCR, IndiaSchool of Computer Science (SCS), Taylor's University, Subang Jaya, 47500, MalaysiaDept of CSE, Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, 412115, IndiaEarly and accurate detection of brain tumors is vital for improving patient outcomes and treatment decisions. This study presents a Hybrid Brain Tumor Analysis (BTA) framework that integrates Moth Flame Optimization (MFO) and Convolutional Neural Networks (CNNs) for tumor identification, segmentation, and classification using MRI scans. A hybrid segmentation approach is employed, combining K-means clustering with MFO and a custom fitness function to extract tumor regions. Feature extraction is followed by MFO-based feature selection to reduce dimensionality and enhance classification performance. The refined features are used to train a custom CNN architecture, BTA-Net, for classifying tumors into meningioma, glioma, and pituitary types. The proposed model achieves a 3.22 % improvement in classification accuracy compared to baseline methods, along with notable gains in precision (4.07 %), recall (2.46 %), and F-measure (3.25 %). Statistical validation confirms the significance of these results, making the BTA framework a robust tool for automated brain tumor analysis.http://www.sciencedirect.com/science/article/pii/S2352914825000590Brain tumorCancerMRITraditional segmentationClusteringK-means |
| spellingShingle | Mohit Prakram Kirti Rawal Arun Singh Ankur Goyal Shiv Kant Shakeel Ahmed Saiprasad Potharaju A novel hybrid model for brain tumor analysis with CNN and Moth Flame Optimization Informatics in Medicine Unlocked Brain tumor Cancer MRI Traditional segmentation Clustering K-means |
| title | A novel hybrid model for brain tumor analysis with CNN and Moth Flame Optimization |
| title_full | A novel hybrid model for brain tumor analysis with CNN and Moth Flame Optimization |
| title_fullStr | A novel hybrid model for brain tumor analysis with CNN and Moth Flame Optimization |
| title_full_unstemmed | A novel hybrid model for brain tumor analysis with CNN and Moth Flame Optimization |
| title_short | A novel hybrid model for brain tumor analysis with CNN and Moth Flame Optimization |
| title_sort | novel hybrid model for brain tumor analysis with cnn and moth flame optimization |
| topic | Brain tumor Cancer MRI Traditional segmentation Clustering K-means |
| url | http://www.sciencedirect.com/science/article/pii/S2352914825000590 |
| work_keys_str_mv | AT mohitprakram anovelhybridmodelforbraintumoranalysiswithcnnandmothflameoptimization AT kirtirawal anovelhybridmodelforbraintumoranalysiswithcnnandmothflameoptimization AT arunsingh anovelhybridmodelforbraintumoranalysiswithcnnandmothflameoptimization AT ankurgoyal anovelhybridmodelforbraintumoranalysiswithcnnandmothflameoptimization AT shivkant anovelhybridmodelforbraintumoranalysiswithcnnandmothflameoptimization AT shakeelahmed anovelhybridmodelforbraintumoranalysiswithcnnandmothflameoptimization AT saiprasadpotharaju anovelhybridmodelforbraintumoranalysiswithcnnandmothflameoptimization AT mohitprakram novelhybridmodelforbraintumoranalysiswithcnnandmothflameoptimization AT kirtirawal novelhybridmodelforbraintumoranalysiswithcnnandmothflameoptimization AT arunsingh novelhybridmodelforbraintumoranalysiswithcnnandmothflameoptimization AT ankurgoyal novelhybridmodelforbraintumoranalysiswithcnnandmothflameoptimization AT shivkant novelhybridmodelforbraintumoranalysiswithcnnandmothflameoptimization AT shakeelahmed novelhybridmodelforbraintumoranalysiswithcnnandmothflameoptimization AT saiprasadpotharaju novelhybridmodelforbraintumoranalysiswithcnnandmothflameoptimization |