Segmentation of prostate from CT scans using a combined voxel random forests classification with spherical harmonics regularization

Commandeur, Frédéric; Acosta, Oscar; Simon, Antoine; Arango, Jaime; Dillenseger, Jean-Louis; Mathiéu, Romain; Haigron, Pascal; Crevoisier, R. de

doi:10.1117/12.2073489

Search citation statements

Order By: Relevance

Paper Sections

Select...

Introduction1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2020

2024

Publication Types

Select...

Article2

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We gave special importance to the time in which the reconstruction of an object was carried out, as we tried to bring it as close as possible to real time. To make all this possible we decided to use parallel computation to solve linear systems [7], [1], [6] for problems such as enriching the image scanned by CT [2].…”

Section: Introductionmentioning

confidence: 99%

LAPACK library for mathematical modeling used in 3D object reconstruction

Lixandru

Monescu

2020

MIF

View full text Add to dashboard Cite

Over time, multiple solutions have been sought for building 3D models in the fastest and most accurate way possible. For this reason, this article proposes the use of LAPACK library for a quick solution of linear systems generated by least square method calculation. A mathematical and physical component used in the reconstruction of models consists in the use of Spherical Harmonics which represent some special functions often used in solving partial differential equations in different scientific areas. This problem finds its place in multiple domains such as medicine, engineering, programming. The target of the work described by this paper is to achieve optimization in the reconstruction of 3D models. We aim to perform real-time model reconstruction for large data sets by using Spherical Harmonics functions.

show abstract