Browse

Computer-aided prostate cancer detection using texture features and clinical features in ultrasound image

Cited 35 time in Web of Science Cited 41 time in Scopus
Authors
Han, Seok Min; Lee, Hak Jong; Choi, Jin Young
Issue Date
2008-03-07
Publisher
Springer Verlag
Citation
J Digit Imaging. 21 Suppl 1:S121-S133
Keywords
Decision Support TechniquesDiagnosis, Computer-Assisted/instrumentation/methodsFuzzy LogicHumans*Image Interpretation, Computer-AssistedImage Processing, Computer-Assisted/*methodsMalePattern Recognition, Automated/*methodsProstatic Neoplasms/diagnosis/*ultrasonographySensitivity and SpecificityUltrasonography, Doppler/methods
Abstract
In this paper, we propose a new prostate detection method using multiresolution autocorrelation texture features and clinical features such as location and shape of tumor. With the proposed method, we can detect cancerous tissues efficiently with high specificity (about 90-95%)and high sensitivity (about 92-96%) by the measurement of the number of correctly classified pixels. Multiresolution autocorrelation can detect cancerous tissues efficiently, and clinical knowledge helps to discriminate the cancer region by location and shape of the region and increases specificity. The support vector machine is used to classify tissues based on those features. The proposed method will be helpful in formulating a more reliable diagnosis, increasing diagnosis efficiency.
ISSN
1618-727X (Electronic)
Language
English
URI
http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&dopt=Citation&list_uids=18322751

http://www.springerlink.com/content/55230724v15htk5r/fulltext.pdf

https://hdl.handle.net/10371/67856
DOI
https://doi.org/10.1007/s10278-008-9106-3
Files in This Item:
There are no files associated with this item.
Appears in Collections:
College of Medicine/School of Medicine (의과대학/대학원)Radiology (영상의학전공)Journal Papers (저널논문_영상의학전공)
  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse