Brain tumour detection in MRI images using elastic net regression

Introduction: Magnetic resonance imaging (MRI) scans of the brain are used to identify signs of disease, enabling more precise diagnosis of brain-related conditions. Neurological disorders pose significant risks and can lead to the deterioration of normal bodily functions. Various strategies are employed to monitor anomalies. However, significant improvements are still required in diagnostic processes and in the detection of cerebral diseases. Methods: This method first involved preprocessing the image, followed by threshold-based segmentation. We used elastic net regression (ENR) due to its superior performance metrics compared to the approaches we evaluated for image classification. Results: This strategy yielded improved outcomes, with an accuracy of 98.7% and precision of 98.88%. The recall score was 98.75%, while the F1 score was 98.23%. Conclusion: In this study, the TSENR method was used to detect brain disease. Although many techniques are used to diagnose neurological disorders, not all of them are suitable for reliable evaluation. However, the implemented TSENR model provided a more accurate, sensitive, and predictive response. This technique can be applied to medical image analysis.