Authors:
Celeste Marques Oliveira
1
and
Pedro Pereira Rodrigues
2
Affiliations:
1
Faculty of Medicine of the University of Porto, Faculty of Sciences of the University of Porto and Portuguese Institute of Oncology Francisco Gentil, Portugal
;
2
Faculty of Medicine of the University of Porto and University of Porto, Portugal
Keyword(s):
Radiotherapy planning, Prostatic neoplasms, Computer-assisted methods, Tomography X-ray computed, Image processing.
Related
Ontology
Subjects/Areas/Topics:
Biomedical Engineering
;
Clinical Problems and Applications
;
Health Information Systems
;
Software Systems in Medicine
;
Therapeutic Systems and Technologies
Abstract:
Prostate cancer is a common cancer worldwide and a leading cause of death. Radiotherapy is usually the first-line treatment for patients with slow-growing cancer that is confined to the prostate. In Radiation Therapy Planning (RTP), the recognition and outlining of clinical volumes in computed tomography (CT) images are one of the most time-consuming steps carried out by human experts. The aim of this review is to identify and summarize evidence of the use of automatic organ delineation of CT images for radiotherapy planning in prostate cancer. From the literature search, a total of seven studies, reported between 1994 and 2009, were selected. We associate the selected studies in order to compare results, in spite of their differences in methodology and outcome evaluators. Most of the studies conclude that the automatic approach is faster, while having equivalent accuracy to manual method. Concerning the observer’s variability, automatic segmentation reaches significant gains in repr
oducibility. As future directions, it is recommended the improvement of the segmentation algorithms in the delineation of problematic soft tissues and future validation studies with large scale trials and possible studies of meta-analysis in the specific problems.
(More)