Hybrid model integration with explainable AI for brain tumor diagnosis: a unified approach to MRI analysis and prediction
Abstract Effective treatment for brain tumors relies on accurate detection because this is a crucial health condition. Medical imaging plays a pivotal role in improving tumor detection and diagnosis in the early stage. This study presents two approaches to the tumor detection problem focusing on the...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-06455-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849769082668187648 |
|---|---|
| author | D. Vamsidhar Parth Desai Sagar Joshi Shrikrishna Kolhar Nilkanth Deshpande Shilpa Gite |
| author_facet | D. Vamsidhar Parth Desai Sagar Joshi Shrikrishna Kolhar Nilkanth Deshpande Shilpa Gite |
| author_sort | D. Vamsidhar |
| collection | DOAJ |
| description | Abstract Effective treatment for brain tumors relies on accurate detection because this is a crucial health condition. Medical imaging plays a pivotal role in improving tumor detection and diagnosis in the early stage. This study presents two approaches to the tumor detection problem focusing on the healthcare domain. A combination of image processing, vision transformer (ViT), and machine learning algorithms is the first approach that focuses on analyzing medical images. The second approach is the parallel model integration technique, where we first integrate two pre-trained deep learning models, ResNet101, and Xception, followed by applying local interpretable model-agnostic explanations (LIME) to explain the model. The results obtained an accuracy of 98.17% for the combination of vision transformer, random forest and contrast-limited adaptive histogram equalization and 99. 67% for the parallel model integration (ResNet101 and Xception). Based on these results, this paper proposed the deep learning approach—parallel model integration technique as the most effective method. Future work aims to extend the model to multi-class classification for tumor type detection and improve model generalization for broader applicability. |
| format | Article |
| id | doaj-art-7751f586e47e435d9908f4fa1031ccb6 |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-7751f586e47e435d9908f4fa1031ccb62025-08-20T03:03:36ZengNature PortfolioScientific Reports2045-23222025-07-0115112610.1038/s41598-025-06455-2Hybrid model integration with explainable AI for brain tumor diagnosis: a unified approach to MRI analysis and predictionD. Vamsidhar0Parth Desai1Sagar Joshi2Shrikrishna Kolhar3Nilkanth Deshpande4Shilpa Gite5Symbiosis Institute of Technology, Symbiosis International (Deemed University)Symbiosis Institute of Technology, Symbiosis International (Deemed University)Symbiosis Institute of Technology, Symbiosis International (Deemed University)Symbiosis Institute of Technology, Symbiosis International (Deemed University)Symbiosis Institute of Technology, Symbiosis International (Deemed University)Symbiosis Institute of Technology, Symbiosis International (Deemed University)Abstract Effective treatment for brain tumors relies on accurate detection because this is a crucial health condition. Medical imaging plays a pivotal role in improving tumor detection and diagnosis in the early stage. This study presents two approaches to the tumor detection problem focusing on the healthcare domain. A combination of image processing, vision transformer (ViT), and machine learning algorithms is the first approach that focuses on analyzing medical images. The second approach is the parallel model integration technique, where we first integrate two pre-trained deep learning models, ResNet101, and Xception, followed by applying local interpretable model-agnostic explanations (LIME) to explain the model. The results obtained an accuracy of 98.17% for the combination of vision transformer, random forest and contrast-limited adaptive histogram equalization and 99. 67% for the parallel model integration (ResNet101 and Xception). Based on these results, this paper proposed the deep learning approach—parallel model integration technique as the most effective method. Future work aims to extend the model to multi-class classification for tumor type detection and improve model generalization for broader applicability.https://doi.org/10.1038/s41598-025-06455-2Artificial intelligenceBrain tumor diagnosisDeep learningExplainable artificial intelligenceLIMEMagnetic resonance imaging |
| spellingShingle | D. Vamsidhar Parth Desai Sagar Joshi Shrikrishna Kolhar Nilkanth Deshpande Shilpa Gite Hybrid model integration with explainable AI for brain tumor diagnosis: a unified approach to MRI analysis and prediction Scientific Reports Artificial intelligence Brain tumor diagnosis Deep learning Explainable artificial intelligence LIME Magnetic resonance imaging |
| title | Hybrid model integration with explainable AI for brain tumor diagnosis: a unified approach to MRI analysis and prediction |
| title_full | Hybrid model integration with explainable AI for brain tumor diagnosis: a unified approach to MRI analysis and prediction |
| title_fullStr | Hybrid model integration with explainable AI for brain tumor diagnosis: a unified approach to MRI analysis and prediction |
| title_full_unstemmed | Hybrid model integration with explainable AI for brain tumor diagnosis: a unified approach to MRI analysis and prediction |
| title_short | Hybrid model integration with explainable AI for brain tumor diagnosis: a unified approach to MRI analysis and prediction |
| title_sort | hybrid model integration with explainable ai for brain tumor diagnosis a unified approach to mri analysis and prediction |
| topic | Artificial intelligence Brain tumor diagnosis Deep learning Explainable artificial intelligence LIME Magnetic resonance imaging |
| url | https://doi.org/10.1038/s41598-025-06455-2 |
| work_keys_str_mv | AT dvamsidhar hybridmodelintegrationwithexplainableaiforbraintumordiagnosisaunifiedapproachtomrianalysisandprediction AT parthdesai hybridmodelintegrationwithexplainableaiforbraintumordiagnosisaunifiedapproachtomrianalysisandprediction AT sagarjoshi hybridmodelintegrationwithexplainableaiforbraintumordiagnosisaunifiedapproachtomrianalysisandprediction AT shrikrishnakolhar hybridmodelintegrationwithexplainableaiforbraintumordiagnosisaunifiedapproachtomrianalysisandprediction AT nilkanthdeshpande hybridmodelintegrationwithexplainableaiforbraintumordiagnosisaunifiedapproachtomrianalysisandprediction AT shilpagite hybridmodelintegrationwithexplainableaiforbraintumordiagnosisaunifiedapproachtomrianalysisandprediction |