Name
Title | ||
|---|---|---|
A study of T2-weighted MR image texture features and diffusion-weighted MR image features for computer-aided diagnosis of prostate cancer |
Abstract | ||
|---|---|---|
The purpose of this study was to study T-2-weighted magnetic resonance (MR) image texture features and diffusion-weighted (DW) MR image features in distinguishing prostate cancer (PCa) from normal tissue. We collected two image datasets: 23 PCa patients (25 PCa and 23 normal tissue regions of interest [ROIs]) imaged with Philips MR scanners, and 30 PCa patients (41 PCa and 26 normal tissue ROIs) imaged with GE MR scanners. A radiologist drew ROIs manually via consensus histology-MR correlation conference with a pathologist. A number of T-2-weighted texture features and apparent diffusion coefficient (ADC) features were investigated, and linear discriminant analysis (LDA) was used to combine select strong image features. Area under the receiver operating characteristic (ROC) curve (AUC) was used to characterize feature effectiveness in distinguishing PCa from normal tissue ROIs. Of the features studied, ADC 10th percentile, ADC average, and T-2-weighted sum average yielded AUC values (+/- standard error) of 0.95 +/- 0.03, 0.94 +/- 0.03, and 0.85 +/- 0.05 on the Phillips images, and 0.91 +/- 0.04, 0.89 +/- 0.04, and 0.70 +/- 0.06 on the GE images, respectively. The three-feature combination yielded AUC values of 0.94 +/- 0.03 and 0.89 +/- 0.04 on the Phillips and GE images, respectively. ADC 10th percentile, ADC average, and T-2-weighted sum average, are effective in distinguishing PCa from normal tissue, and appear robust in images acquired from Phillips and GE MR scanners. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1117/12.2007979 | Proceedings of SPIE |
Keywords | Field | DocType |
Computer-aided diagnosis,prostate cancer,magnetic resonance imaging,T-2-weighted,diffusion-weighted,apparent diffusion coefficient,cross validation,texture analysis | Effective diffusion coefficient,Computer vision,Receiver operating characteristic,Pattern recognition,Feature (computer vision),Image texture,Computer science,Computer-aided diagnosis,Artificial intelligence,Linear discriminant analysis,Principal component analysis,Percentile | Conference |
Volume | ISSN | Citations |
8670 | 0277-786X | 5 |
PageRank | References | Authors |
0.48 | 0 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| yahui peng | 1 | 19 | 8.60 |
| Yulei Jiang | 2 | 80 | 8.90 |
| tatjana antic | 3 | 5 | 0.48 |
| Maryellen L. Giger | 4 | 393 | 85.89 |
| scott eggener | 5 | 5 | 0.48 |
| Aytekin Oto | 6 | 59 | 6.59 |