Medical Image Segmentation and Localization using Deformable Templates

TL;DR

This paper introduces deformable templates for efficient segmentation and localization of biological structures in medical images, utilizing a multi-stage, multi-resolution algorithm to improve accuracy and reduce computational time.

Contribution

It proposes a novel deformable template approach combined with a multi-resolution algorithm for medical image segmentation and localization.

Findings

Effective in MRI, x-ray, and ultrasound images

Reduces computational complexity and time

Accurate localization and segmentation of structures

Abstract

This paper presents deformable templates as a tool for segmentation and localization of biological structures in medical images. Structures are represented by a prototype template, combined with a parametric warp mapping used to deform the original shape. The localization procedure is achieved using a multi-stage, multi-resolution algorithm de-signed to reduce computational complexity and time. The algorithm initially identifies regions in the image most likely to contain the desired objects and then examines these regions at progressively increasing resolutions. The final stage of the algorithm involves warping the prototype template to match the localized objects. The algorithm is presented along with the results of four example applications using MRI, x-ray and ultrasound images.