Computer-aided detection and characterization of stroke lesion – a short review on the current state-of-the art methods

The fast advancements in the field of computer vision, progress in radiology, image processing, modelling and simulation have changed the medical science to diagnose people in an efficient way. To be exact, the headways in medical imaging have prompted better diagnostic planning and accuracy in surgical methodology with little human–machine intervention. Stroke remains the third driving reason for death, after heart attack and cancer. Automatic computer-aided diagnosis of brain diseases has been gaining significant attention in the last two decades. The aim of this work is to review the current state-of-the-art techniques employed for segmentation, classification and detection of stroke lesion and present the key challenges in it. By investigating the advanced aspects and significant pitfalls of the different surveyed techniques, an overview on the performance of these methods is presented in this work.