Prostate cancer probability maps based on ultrasound RF time series and SVM classifiers.
Med Image Comput Comput Assist Interv
; 11(Pt 1): 76-84, 2008.
Article
in En
| MEDLINE
| ID: mdl-18979734
ABSTRACT
We describe a very efficient method based on ultrasound RF time series analysis and support vector machine classification for generating probabilistic prostate cancer colormaps to augment the biopsy process. To form the RF time series, we continuously record ultrasound RF echoes backscattered from tissue while the imaging probe and the tissue are stationary in position. In an in-vitro study involving 30 prostate specimens, we show that the features extracted from RF time series are significantly more accurate and sensitive compared to two other established categories of ultrasound-based tissue typing methods. The method results in an area under ROC curve of 0.95 in 10-fold cross-validation.
Search on Google
Collection:
01-internacional
Database:
MEDLINE
Main subject:
Prostatic Neoplasms
/
Algorithms
/
Pattern Recognition, Automated
/
Artificial Intelligence
/
Image Interpretation, Computer-Assisted
/
Image Enhancement
/
Ultrasonography
Type of study:
Diagnostic_studies
/
Prognostic_studies
Limits:
Humans
/
Male
Language:
En
Journal:
Med Image Comput Comput Assist Interv
Journal subject:
DIAGNOSTICO POR IMAGEM
/
INFORMATICA MEDICA
Year:
2008
Document type:
Article
Affiliation country: