Automatic Detection of Cerebral Microbleed Using Bounding Box Based Watershed Segmentation from MR Images

EasyChair Preprint 4937

Abstract

Cerebral microbleeds(CMB) are also referred to as cerebral micro haemorrhages caused by structural abnormalities of the small vessels of the brain. They have been identified as a major diagnostic biomarker for many cerebrovascular diseases and cognitive dysfunctions. In current clinical routine CMBs are manually labelled by radiologists but this method is difficult, time wasting and error prone. In this paper, we propose a new automatic method to detect CMBs from magnetic resonance images (MR images).presently, the analysis of microbleeds is performed by skilled neurologist based on their database that is by scanning the image, detecting the black dots and identifying whether black dots are micro-bleeds or mimics. The most important part of image processing in medical is image segmentation. The conventional watershed algorithm for medical images is widespread because of its advantage to completely segment the medical images. However, the common drawback of watershed segmentation which is over segmentation and its sensitivity to false edges segmentation. This paper introduces a novel scheme to overcome the listed limitations by first applying the bounding box and watershed segmentation. This proposed method demonstrates a significant improvement that may serves as a computer aided tools for radiologists in detecting microbleeds in MRI images and achieved a high sensitivity of  98.58% .

Keyphrases: Cerebral microbleed, bounding box, watershed segmentation

@booklet{EasyChair:4937,
  author    = {T.Grace Berin and C. Helen Sulochana},
  title     = {Automatic Detection of Cerebral Microbleed Using Bounding Box Based Watershed Segmentation from MR Images},
  howpublished = {EasyChair Preprint 4937},
  year      = {EasyChair, 2021}}