Back to Search
Start Over
Radiomics and machine learning of multisequence multiparametric prostate MRI: Towards improved non-invasive prostate cancer characterization.
- Source :
- PLoS ONE; 7/8/2019, Vol. 14 Issue 7, p1-23, 23p
- Publication Year :
- 2019
-
Abstract
- Purpose: To develop and validate a classifier system for prediction of prostate cancer (PCa) Gleason score (GS) using radiomics and texture features of T<subscript>2</subscript>-weighted imaging (T<subscript>2</subscript>w), diffusion weighted imaging (DWI) acquired using high b values, and T<subscript>2</subscript>-mapping (T<subscript>2</subscript>). Methods: T<subscript>2</subscript>w, DWI (12 b values, 0–2000 s/mm<superscript>2</superscript>), and T<subscript>2</subscript> data sets of 62 patients with histologically confirmed PCa were acquired at 3T using surface array coils. The DWI data sets were post-processed using monoexponential and kurtosis models, while T<subscript>2</subscript>w was standardized to a common scale. Local statistics and 8 different radiomics/texture descriptors were utilized at different configurations to extract a total of 7105 unique per-tumor features. Regularized logistic regression with implicit feature selection and leave pair out cross validation was used to discriminate tumors with 3+3 vs >3+3 GS. Results: In total, 100 PCa lesions were analysed, of those 20 and 80 had GS of 3+3 and >3+3, respectively. The best model performance was obtained by selecting the top 1% features of T<subscript>2</subscript>w, ADC<subscript>m</subscript> and K with ROC AUC of 0.88 (95% CI of 0.82–0.95). Features from T<subscript>2</subscript> mapping provided little added value. The most useful texture features were based on the gray-level co-occurrence matrix, Gabor transform, and Zernike moments. Conclusion: Texture feature analysis of DWI, post-processed using monoexponential and kurtosis models, and T<subscript>2</subscript>w demonstrated good classification performance for GS of PCa. In multisequence setting, the optimal radiomics based texture extraction methods and parameters differed between different image types. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 19326203
- Volume :
- 14
- Issue :
- 7
- Database :
- Complementary Index
- Journal :
- PLoS ONE
- Publication Type :
- Academic Journal
- Accession number :
- 137368519
- Full Text :
- https://doi.org/10.1371/journal.pone.0217702