Artificial Intelligence-based Myelinated White Matter Segmentation for a Pediatric Brain - A Challenging Task

Background: Segmentation of a baby brain, in particular, myelinated white matter is a very challenging and important task in medical image analysis, because of the ongoing process of myelination and structural differences present in magnetic resonance images of a baby. Most available algorithms for the segmentation of a baby brain are atlas-based segmentation, which may not be accurate because baby brain Magnetic Resonance Images (MRI) are very subjective. Objective: Artificial intelligence-based methods for myelinated white matter segmentation. Methods: Fuzzy C-means Clustering with Level Set Method (FCMLSM), Adaptively Regularized Kernel-based Fuzzy C - means clustering (ARKFCM), Multiplicative Intrinsic Component Optimization (MICO) and Particle Swarm Optimization (PSO). Results: Signal to Noise Ratio (SNR), Edge Preservation Index (EPI), Structural Similarity Index (SSIM) and Peak Signal to noise Ratio (PSNR) Accuracy, Precision, Dice and Jaccard values are maintained good and Mean squared error (MSE) is less for FCMLSM. Conclusion: FCMLSM is a very suitable method for myelinated white matter segmentation when compared to ARKFCM, MICO and PSO.