Brain tumor segmentation by optimizing deep learning U-Net model.
Authors
Affiliations (11)
Affiliations (11)
- Radiological Sciences Department, College of Applied Medical Sciences, Najran University, Najran, Kingdom of Saudi Arabia.
- Department of Computer Science & IT, King Abdullah Campus, The University of Azad Jammu and Kashmir, Muzaffarabad, Pakistan.
- Department of Computer Science & IT, Neelum Campus, The University of Azad Jammu and Kashmir, Athmuqam, Pakistan.
- Electrical Engineering Department, College of Engineering, Najran University, Najran, Kingdom of Saudi Arabia.
- Department of Anatomy, Faculty of Medicine, Najran University, Najran, Kingdom of Saudi Arabia.
- Eviden Romania SRL LTD, Riyadh, Kingdom of Saudi Arabia.
- Department of Radiological Sciences, College of Applied Medical Science, King Khalid University, Abha, Kingdom of Saudi Arabia.
- Radiology and Medical Imaging Department, College of Applied Medical Sciences, Prince Sattam bin Abdulaziz University, Kharj, Kingdom of Saudi Arabia.
- Radiological Sciences Department, College of Applied Medical Sciences, Taif University, Taif, Kingdom of Saudi Arabia.
- Department of Learning Sciences and Digital Technologies, University of Foggia, Foggia, Italy.
- Department of Psychology and Educational Sciences, Pegaso University, Rome, Italy.
Abstract
BackgroundMagnetic Resonance Imaging (MRI) is a cornerstone in diagnosing brain tumors. However, the complex nature of these tumors makes accurate segmentation in MRI images a demanding task.ObjectiveAccurate brain tumor segmentation remains a critical challenge in medical image analysis, with early detection crucial for improving patient outcomes.MethodsTo develop and evaluate a novel UNet-based architecture for improved brain tumor segmentation in MRI images. This paper presents a novel UNet-based architecture for improved brain tumor segmentation. The UNet model architecture incorporates Leaky ReLU activation, batch normalization, and regularization to enhance training and performance. The model consists of varying numbers of layers and kernel sizes to capture different levels of detail. To address the issue of class imbalance in medical image segmentation, we employ focused loss and generalized Dice (GDL) loss functions.ResultsThe proposed model was evaluated on the BraTS'2020 dataset, achieving an accuracy of 99.64% and Dice coefficients of 0.8984, 0.8431, and 0.8824 for necrotic core, edema, and enhancing tumor regions, respectively.ConclusionThese findings demonstrate the efficacy of our approach in accurately predicting tumors, which has the potential to enhance diagnostic systems and improve patient outcomes.