Abstract
Localization of features and structures in images is an important task in medical image-processing. Characteristic structures and features are used in diagnostics and surgery planning for spatial adjustments of the volumetric data, including image registration or localization of bone-anchors and fiducials. Since this task is highly recurrent, a fast, reliable and automated approach without human interaction and parameter adjustment is of high interest. In this paper we propose and compare four image processing pipelines, including algorithms for automatic detection and localization of spherical features within 3D MRI data. We developed a convolution based method as well as algorithms based on connected-components labeling and analysis and the circular Hough-transform. A blob detection related approach, analyzing the Hessian determinant, was examined. Furthermore, we introduce a novel spherical MRI-marker design. In combination with the proposed algorithms and pipelines, this allows the detection and spatial localization, including the direction, of fiducials and bone-anchors.
Highlights
Published: 30 June 2021Processing volumetric medical image data plays a major role in diagnostics and surgery planning
Manual segmentation was conducted by five scientific associates of the Department of Neurosurgery, University of Leipzig, trained in segmentation of medical images, using D2P (DICOM To Print) by 3D SYSTEMS Inc., Rock Hill, SC 29730, USA, a commercial image processing software
By developing and comparing four different methods for spherical fiducial detection in both, T1- and T2-weighted images acquired at different voxel sizes, we have found that the Connected Component Analysis serves the most robust and accurate results
Summary
Published: 30 June 2021Processing volumetric medical image data plays a major role in diagnostics and surgery planning. Characteristic image features are extracted from the image data in order to register images stemming from different imaging modalities, or to determine a specific target point for a subsequent surgical intervention. In this context, the spherical feature shape is of particular importance. Due to its isotropic geometry, sphere-shaped features may serve as fiducial markers for positional alignment and image registration [1,2]. Despite the fact that computer vision provides elementary methods for spherical and circular feature detection [3], the implementation in automatic image processing pipelines is rather difficult due to strongly use-case-specific parameter dependencies and required manual parameter adjustments. A comparitive study of different sphere detection approaches could provide essential information to develop automated workflows and prevent the necessity of a time consuming manual segmentation
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
