Název:	Impact of PCA-based preprocessing and different CNN structures on deformable registration of sonograms
Autoři:	Schmidt, Martin Overhoff, Heinrich Martin
Citace zdrojového dokumentu:	WSCG 2022: full papers proceedings: 30. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 181-188.
Datum vydání:	2022
Nakladatel:	Václav Skala - UNION Agency
Typ dokumentu:	conferenceObject
URI:	http://hdl.handle.net/11025/49593
ISBN:	978-80-86943-33-6
ISSN:	2464-4617
Klíčová slova:	registrace lékařského snímku;deformovatelná registrace;sonogramy;Voxelmorph;CNN
Klíčová slova v dalším jazyce:	medical image registration;deformable registration;sonograms;Voxelmorph;CNN
Abstrakt v dalším jazyce:	Central venous catheters (CVC) are commonly inserted into the large veins of the neck, e.g. the internal jugu- lar vein (IJV). CVC insertion may cause serious complications like misplacement into an artery or perforation of cervical vessels. Placing a CVC under sonographic guidance is an appropriate method to reduce such adverse events, if anatomical landmarks like venous and arterial vessels can be detected reliably. This task shall be solved by registration of patient individual images vs. an anatomically labelled reference image. In this work, a linear, affine transformation is performed on cervical sonograms, followed by a non-linear transformation to achieve a more precise registration. Voxelmorph (VM), a learning-based library for deformable image registration using a convolutional neural network (CNN) with U-Net structure was used for non-linear transformation. The impact of principal component analysis (PCA)-based pre-denoising of patient individual images, as well as the impact of modified net structures with differing complexities on registration results were examined visually and quan- titatively, the latter using metrics for deformation and image similarity. Using the PCA-approximated cervical sonograms resulted in decreased mean deformation lengths between 18% and 66% compared to their original image counterparts, depending on net structure. In addition, reducing the number of convolutional layers led to improved image similarity with PCA images, while worsening in original images. Despite a large reduction of network parameters, no overall decrease in registration quality was observed, leading to the conclusion that the original net structure is oversized for the task at hand.
Práva:	© Václav Skala - UNION Agency
Vyskytuje se v kolekcích:	WSCG 2022: Full Papers Proceedings

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.