Brain MRI detection and classification: Harnessing convolutional neural networks and multi-level thresholding

• Published in: PloS one 2024-08, Vol.19 (8), p.e0306492
• Main Authors: Kamireddy, Rasool Reddy, Kandala, Rajesh N V P S, Dhuli, Ravindra, Polinati, Srinivasu, Sonti, Kamesh, Tadeusiewicz, Ryszard, Pławiak, Paweł
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Artificial neural networks; Automation; Biology and Life Sciences; Blood vessels; Brain; Brain - diagnostic imaging; Brain architecture; Brain cancer; Brain Neoplasms - diagnostic imaging; Brain research; Brain tumors; Cerebrospinal fluid; Classification; Clustering; Computational linguistics; Computer and Information Sciences; Deep learning; Evolutionary computation; Humans; Identification; Image contrast; Image enhancement; Image Processing, Computer-Assisted - methods; Language processing; Magnetic resonance; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Medical colleges; Medical imaging; Medical imaging equipment; Medicine and Health Sciences; Natural language interfaces; Neural networks; Neural Networks, Computer; Neuroimaging; Physical Sciences; Principal components analysis; Research and Analysis Methods; Support vector machines; Tumors
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0306492

Brain tumor detection in clinical applications is a complex and challenging task due to the intricate structures of the human brain. Magnetic Resonance (MR) imaging is widely preferred for this purpose because of its ability to provide detailed images of soft brain tissues, including brain tissue, cerebrospinal fluid, and blood vessels. However, accurately detecting brain tumors from MR images remains an open problem for researchers due to the variations in tumor characteristics such as intensity, texture, size, shape, and location. To address these issues, we propose a method that combines multi-level thresholding and Convolutional Neural Networks (CNN). Initially, we enhance the contrast of brain MR images using intensity transformations, which highlight the infected regions in the images. Then, we use the suggested CNN architecture to classify the enhanced MR images into normal and abnormal categories. Finally, we employ multi-level thresholding based on Tsallis entropy (TE) and differential evolution (DE) to detect tumor region(s) from the abnormal images. To refine the results, we apply morphological operations to minimize distortions caused by thresholding. The proposed method is evaluated using the widely used Harvard Medical School (HMS) dataset, and the results demonstrate promising performance with 99.5% classification accuracy and 92.84% dice similarity coefficient. Our approach outperforms existing state-of-the-art methods in brain tumor detection and automated disease diagnosis from MR images.