Anisotropic non-rigid Iterative Closest Point Algorithm for respiratory motion abdominal surface matching

Dominik Spinczyk,Mateusz Bas

doi:10.1186/s12938-019-0643-4

Abstract

Surface registration is a one of the crucial and actual problems of computer aided surgery. This paper presents the modification of the non-rigid Iterative Closest Point Algorithm which takes into account an anisotropic noise model and landmarks as guided correspondence at the transformation step in every iteration. The presented approach was validated on human abdominal briefing surface data from a time-of-flight camera. We took the median of the resulting measures and the outcome is presented: the median of means of surfaces distance was at the same level for both variants of the ICP algorithm and is comparable with the isotropic variant, the median of mean landmark position errors decreased by 0.93 units (over 20% improvement) and the median of percentage of single correspondences in target point cloud increased by 11.96%. The results showed that the introduction of the anisotropic model of noise for the ToF camera allows for the improvement the percentage of target cloud points which had only one correspondent over 10% impartment and additional weighting of markers also improves the measure of the quality of finding real correspondents over 20% improvement. In the examined dataset, where the average initial distance between the clouds of points in the inspiratory and expiration is equal to approx. 7.5 mm, a more than 10% improvement in the quality of the correspondence improves the accuracy of matching the surface within 1 mm which is a significant value in application of minimally invasive image guided interventions.

Highlights

Nowadays there’s more and more research carried out in the field of precise and automatized acquisition of human organs as 3D models
Artificial data For analyzing improvements of each modification of non-rigid ICP algorithm separately, we used correspondence maps, which present counts of source cloud correspondents attracted by target cloud points in color scale
(Fig. 4), we present figures showing measured outcome values but grouped by point cloud pairs for better visualization of improvements: As mentioned, measure M1 is at similar level for all variations of algorithm, measures M2 and M3 have improved for almost all approaches of ICP algorithm

Summary

Introduction

Nowadays there’s more and more research carried out in the field of precise and automatized acquisition of human organs as 3D models. Such models can be used to diagnose a pathological state of an organ or enhance therapeutically procedures. A common use of 3D models of human body organs is minimally invasive surgery. Certain cases of working with 3D models require registration of point clouds for achieving an outcome in form of transformation values. That is where registration algorithms play a major role. In the few paragraphs we introduce Iterative Closest Point algorithm, the rigid and non-rigid variants of the ICP algorithm and their recently published applications are presented

Objectives

Methods

Results

Discussion

Conclusion