Brain tumor classification utilizing deep features derived from high-quality regions in MRI images

The accurate and rapid detection of brain tumors is crucial for expediting patient rehabilitation and saving lives. Brain tumors exhibit considerable variation in size, shape, and appearance, necessitating patient-specific treatment options. Radiologists are required to possess a high level of experience and skill to manually diagnose brain cancers. However, manual tumor detection can be inefficient, error-prone, and time-consuming. Developing a practical solution to overcome these limitations is essential. This work presents a less labor-intensive approach to diagnosing brain cancers using MRI imaging. The proposed method enhances an image's visual quality by employing a low-complexity algorithm. Prior to segmentation, morphological analysis is conducted to exclude non-tumor regions from the images. Employing segmentation and clustering techniques, high-quality tumor regions are identified. Based on their rankings, multiple deep neural networks extract features from these regions. An adaptive fusion network creates a hybrid feature vector, which is then used in conjunction with multiclass SVM to classify tumors. By supplementing the training data, overfitting is minimized. The presented system is trained and evaluated using a publicly accessible brain tumor dataset. In comparison to previous approaches, the proposed solution enhances the resilience and automation of the entire diagnostic process, enabling the healthcare industry to achieve an overall accuracy of approximately 98.98%.