article · Current Medical Imaging Formerly Current Medical Imaging Reviews
Brain tumours are aggressive conditions where inaccurate classification or delayed detection can lead to inappropriate treatment and poorer survival outcomes. To support early and reliable detection, a computational framework called I-Brainer was developed, combining artificial intelligence and Internet of Things concepts for magnetic resonance imaging analysis. The system was evaluated using a combined dataset of 7,023 brain scans covering four categories: pituitary tumours, meningioma, glioma, and healthy cases with no tumour. The study explored a custom-built LeNet architecture alongside pre-trained EfficientNet and ResNet-50 models, extracting features and pairing them with machine learning classifiers including k-Nearest Neighbours and Support Vector Machines. Across test evaluations, the combination of EfficientNet and Support Vector Machines reached an area under the curve of 99 percent, while ResNet-50 paired with k-Nearest Neighbours achieved an accuracy of 94 percent.
Accurate and prompt diagnosis of brain tumours is essential because misclassification can result in incorrect medical interventions and reduced patient survival. Automated image classification tools can assist healthcare professionals by verifying diagnoses quickly, potentially extending diagnostic support to patients living in remote areas where specialist medical expertise may be limited.
The technology could enable diagnostic support software for medical experts and telemedicine services targeting remote patients. At this stage, it represents applied and tested computational research evaluated on existing image datasets. Moving towards clinical use would require deployment into actual Internet of Things infrastructure, software integration, and validation in live clinical environments.
AI-generated from the published abstract. Always read the original work before citing.
BACKGROUND/OBJECTIVE: Brain tumour is characterized by its aggressive nature and low survival rate and thus regarded as one of the deadliest diseases. Thus, miss-diagnosis or miss-classification of brain tumour can lead to miss treatment or incorrect treatment and reduce survival chances. Therefore, there is need to develop a technique that can identify and detect brain tumour at early stages. METHODS: Here, we proposed a framework titled I-Brainer which is an Artificial Intelligence/Internet of Things (AI/IoT)-powered classification of MRI. We employed a Br35H+SARTAJ brain MRI dataset which contain 7023 total images which include No tumour, pituitary, meningioma and glioma. In order to accurately classified MRI into 4-class, we developed LeNet model from scratch, implemented 2 pretrained models which include EfficientNet and ResNet-50 as well feature extraction of these models coupled with 2 Machine Learning classifiers k-Nearest Neighbours (KNN) and Support Vector Machines (SVM). RESULT: Evaluation and comparison of the performance of 3 models has shown that EfficientNet+SVM achieved the best result in terms of AUC (99%) and ResNet-50-KNN ranked higher in terms of accuracy (94%) on testing dataset. CONCLUSION: This framework can be harness by patients residing in remote areas and as confirmatory approach for medical experts.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.2174/0115734056333393250117164020
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
