Automated Computed Tomography-Ultrasound Cross-Modality 3-D Contouring Algorithm for Prostate.

Authors:
Denis Ermacora
Denis Ermacora
Maastricht University Medical Center
Netherlands
Silvia Pesente
Silvia Pesente
Tecnologie Avanzate Srl
Francesco Pascoli
Francesco Pascoli
University of Padua
Italy
Rudy Mauro
Rudy Mauro
Datamind
Imad Abu Rumeileh
Imad Abu Rumeileh
Centro di Riferimento Oncologico of Aviano
Italy
Frank Verhaegen
Frank Verhaegen
McGill University
Canada
Davide Fontanarosa
Davide Fontanarosa
Maastricht University Medical Center
Netherlands

Ultrasound Med Biol 2015 Oct 21;41(10):2646-62. Epub 2015 Jul 21.

Department of Radiation Oncology (MAASTRO), GROW-School for Oncology and Developmental Biology, Maastricht University Medical Center, Maastricht, The Netherlands; Oncology Solutions Department, Philips Research, High Tech Campus 34, 5656 AE Eindhoven, The Netherlands. Electronic address:

A novel fully automated algorithm is introduced for 3-D cross-modality image segmentation of the prostate, based on the simultaneous use of co-registered computed tomography (CT) and 3-D ultrasound (US) images. By use of a Gabor feature detector, the algorithm can outline in three dimensions and in cross-modality the prostate, and it can be trained and optimized on specific patient populations. We applied it to 16 prostate cancer patients and evaluated the conformity between the automatically segmented prostate contours and the contours manually outlined by an experienced physician, on the CT-US fusion, using the mean distance to conformity (MDC) index. When only the CT scans were used, the average MDC value was 4.5 ± 1.7 mm (maximum value = 9.0 mm). When the US scans also were considered, the mean ± standard deviation was reduced to 3.9 ± 0.7 mm (maximum value = 5.5 mm). The cross-modality approach acted on all the largest distance values, reducing them to acceptable discrepancies.

Download full-text PDF

Source
https://linkinghub.elsevier.com/retrieve/pii/S03015629150040
Publisher Site
http://dx.doi.org/10.1016/j.ultrasmedbio.2015.05.025DOI Listing

Still can't find the full text of the article?

We can help you send a request to the authors directly.
October 2015
64 Reads

Publication Analysis

Top Keywords

prostate
5
conformity automatically
4
automatically segmented
4
evaluated conformity
4
patients evaluated
4
cancer patients
4
segmented prostate
4
prostate contours
4
outlined experienced
4
manually outlined
4
contours manually
4
contours contours
4
prostate cancer
4
experienced physician
4
cross-modality prostate
4
dimensions cross-modality
4
three dimensions
4
outline three
4
prostate trained
4
trained optimized
4

Similar Publications