Computational Intelligence

We give a brief introduction to computational intelligence application in medicine. We review medical image processing in magnetic resonance images and nondestructive evaluation studies by ultrasonic systems. Primary processes of medical image processing are segmentation, registration and enhancement. In them, automated segmentation is received much considerable attentions. In general, several typical segmentation procedures are known as segmentation via thresholding, segmentation via clustering, supervised segmentation and rule-based segmentation. We discuss how fuzzy logic works in the segmentation procedure. To indicate the achievement, we give a clinical study to diagnose Alzheimer’s disease and a study for diagnosing meniscal tears provided by a MRI scanner. As an application of artificial neural network, we describe an identification method for cellular quantity of Bone Marrow Stromal Cells(BMCSs) in an artificial culture bone composed of β-tricalcium phosphate (βTCP). Composites of BMScs and β-TCP have been increasingly used as bone substitutes and studied as a bone graft model for bone tissue engineering. The number of seeded cells in the composites is a crucial issue for achieving successful bone tissue engineering. This study nondestructively identifies the quantity of BMCSs in the artificial culture bone by artificial neural network.