Journal Article
. 2014 Jun;41(5).
doi: 10.1002/jmri.24676.

Novel PCA-VIP scheme for ranking MRI protocols and identifying computer-extracted MRI measurements associated with central gland and peripheral zone prostate tumors

Shoshana B Ginsburg 1 Satish E Viswanath  B Nicolas Bloch  Neil M Rofsky  Elizabeth M Genega  Robert E Lenkinski  Anant Madabhushi  
  • PMID: 24943647
  •     17 citations


Purpose: To identify computer-extracted features for central gland and peripheral zone prostate cancer localization on multiparametric magnetic resonance imaging (MRI).

Materials And Methods: Preoperative T2-weighted (T2w), diffusion-weighted imaging (DWI), and dynamic contrast-enhanced (DCE) MRI were acquired from 23 men with confirmed prostate cancer. Following radical prostatectomy, the cancer extent was delineated by a pathologist on ex vivo histology and mapped to MRI by nonlinear registration of histology and corresponding MRI slices. In all, 244 computer-extracted features were extracted from MRI, and principal component analysis (PCA) was employed to reduce the data dimensionality so that a generalizable classifier could be constructed. A novel variable importance on projection (VIP) measure for PCA (PCA-VIP) was leveraged to identify computer-extracted MRI features that discriminate between cancer and normal prostate, and these features were used to construct classifiers for cancer localization.

Results: Classifiers using features selected by PCA-VIP yielded an area under the curve (AUC) of 0.79 and 0.85 for peripheral zone and central gland tumors, respectively. For tumor localization in the central gland, T2w, DCE, and DWI MRI features contributed 71.6%, 18.1%, and 10.2%, respectively; for peripheral zone tumors T2w, DCE, and DWI MRI contributed 29.6%, 21.7%, and 48.7%, respectively.

Conclusion: PCA-VIP identified relatively stable subsets of MRI features that performed well in localizing prostate cancer on MRI.

Keywords: computer-extracted features; feature selection; model interpretation; principal component analysis; prostate cancer.

Computer-extracted Features Can Distinguish Noncancerous Confounding Disease from Prostatic Adenocarcinoma at Multiparametric MR Imaging.
Geert J S Litjens, Robin Elliott, +6 authors, Anant Madabhushi.
Radiology, 2015 Jul 21; 278(1). PMID: 26192734    Free PMC article.
Computer-aided Detection of Prostate Cancer with MRI: Technology and Applications.
Lizhi Liu, Zhiqiang Tian, Zhenfeng Zhang, Baowei Fei.
Acad Radiol, 2016 May 03; 23(8). PMID: 27133005    Free PMC article.
Prostate Cancer Detection with Multiparametric Magnetic Resonance Imaging: Prostate Imaging Reporting and Data System Version 1 versus Version 2.
Zhao-Yan Feng, Liang Wang, +3 authors, Jie Cai.
Chin Med J (Engl), 2016 Oct 18; 129(20). PMID: 27748338    Free PMC article.
Evaluating stability of histomorphometric features across scanner and staining variations: prostate cancer diagnosis from whole slide images.
Patrick Leo, George Lee, +3 authors, Anant Madabhushi.
J Med Imaging (Bellingham), 2016 Nov 03; 3(4). PMID: 27803941    Free PMC article.
Radiomics based targeted radiotherapy planning (Rad-TRaP): a computational framework for prostate cancer treatment planning with MRI.
Rakesh Shiradkar, Tarun K Podder, +3 authors, Anant Madabhushi.
Radiat Oncol, 2016 Nov 11; 11(1). PMID: 27829431    Free PMC article.
Radiomic features for prostate cancer detection on MRI differ between the transition and peripheral zones: Preliminary findings from a multi-institutional study.
Shoshana B Ginsburg, Ahmad Algohary, +16 authors, Anant Madabhushi.
J Magn Reson Imaging, 2016 Dec 19; 46(1). PMID: 27990722    Free PMC article.
Computational imaging reveals shape differences between normal and malignant prostates on MRI.
Mirabela Rusu, Andrei S Purysko, +15 authors, Anant Madabhushi.
Sci Rep, 2017 Feb 02; 7. PMID: 28145532    Free PMC article.
An integrated segmentation and shape-based classification scheme for distinguishing adenocarcinomas from granulomas on lung CT.
Mehdi Alilou, Niha Beig, +9 authors, Anant Madabhushi.
Med Phys, 2017 Mar 16; 44(7). PMID: 28295386    Free PMC article.
Discriminative Scale Learning (DiScrn): Applications to Prostate Cancer Detection from MRI and Needle Biopsies.
Haibo Wang, Satish Viswanath, Anant Madabhushi.
Sci Rep, 2017 Sep 30; 7(1). PMID: 28959011    Free PMC article.
Radiomic features on MRI enable risk categorization of prostate cancer patients on active surveillance: Preliminary findings.
Ahmad Algohary, Satish Viswanath, +16 authors, Anant Madabhushi.
J Magn Reson Imaging, 2018 Feb 23;. PMID: 29469937    Free PMC article.
Radiomic features from pretreatment biparametric MRI predict prostate cancer biochemical recurrence: Preliminary findings.
Rakesh Shiradkar, Soumya Ghose, +4 authors, Anant Madabhushi.
J Magn Reson Imaging, 2018 May 08; 48(6). PMID: 29734484    Free PMC article.
Quantitative nuclear histomorphometry predicts oncotype DX risk categories for early stage ER+ breast cancer.
Jon Whitney, German Corredor, +6 authors, Anant Madabhushi.
BMC Cancer, 2018 Jun 01; 18(1). PMID: 29848291    Free PMC article.
Identifying the morphologic basis for radiomic features in distinguishing different Gleason grades of prostate cancer on MRI: Preliminary findings.
Gregory Penzias, Asha Singanamalli, +13 authors, Anant Madabhushi.
PLoS One, 2018 Sep 01; 13(8). PMID: 30169514    Free PMC article.
Novel Quantitative Imaging for Predicting Response to Therapy: Techniques and Clinical Applications.
Kaustav Bera, Vamsidhar Velcheti, Anant Madabhushi.
Am Soc Clin Oncol Educ Book, 2018 Sep 21; 38. PMID: 30231314    Free PMC article.
Repeatability of radiomics and machine learning for DWI: Short-term repeatability study of 112 patients with prostate cancer.
Harri Merisaari, Pekka Taimen, +7 authors, Ivan Jambor.
Magn Reson Med, 2019 Nov 09; 83(6). PMID: 31703155    Free PMC article.
Radiomics and machine learning of multisequence multiparametric prostate MRI: Towards improved non-invasive prostate cancer characterization.
Jussi Toivonen, Ileana Montoya Perez, +9 authors, Ivan Jambor.
PLoS One, 2019 Jul 10; 14(7). PMID: 31283771    Free PMC article.
Combination of Peri-Tumoral and Intra-Tumoral Radiomic Features on Bi-Parametric MRI Accurately Stratifies Prostate Cancer Risk: A Multi-Site Study.
Ahmad Algohary, Rakesh Shiradkar, +13 authors, Anant Madabhushi.
Cancers (Basel), 2020 Aug 13; 12(8). PMID: 32781640    Free PMC article.