Machine Vision-Based Medical Heart Image Processing Instrument for Visualization of 3D Cardiac Structure: A Visual Display Device

摘要

Modelling of anatomical structure in spatial and temporal dimensions has been widely researched in the recent decades. Medical heart image information extraction process is full of complex information. As a result, processing time for large and complex amount of information is high. This paper proposes a methodology using machine vision approach, primarily through the four stages with different algorithms to deal with the medical heart images. Firstly, smoothing algorithm is used to reduce the noise. Secondly, filtering algorithm for image analysis is utilized to identify the target area. Thirdly, further enhancement algorithm is used by target area of the image features, finding out the basic outline of the image. Eventually, restoration algorithm is utilized to build the original heart image into coloured models. Experimental results show that machine vision-based medical image processing algorithm can accurately extract the relevant data, for a limited time complexity obtained better results. Then, presentation on a 2D screen of the computer monitor and the user-defined input hardware for positional control limits the visualization capability and inhibits functional control of the model. Therefore, we developed a LCD device that is able to display a computational model at five lines of sight orthogonal to each other. The variability of model position can be achieved with better ergonomics. Such a device will be of use to medical experts who need to assess and perceive multiple sections of the anatomy at high speed and with a greater ease of control during surgical intervention. In this research, we outline the development of an instrument to enable display of 3D anatomical models with performance that is superior to existing methodologies. We have used the example of heart modelling to illustrate how our device operates and important functionalise associated with it.