Abstract
Translation of radiomics into the clinic may require a more comprehensive understanding of the underlying morphologic tissue characteristics they reflect. In the context of prostate cancer (PCa), some studies have correlated gross histological measurements of gland lumen, epithelium, and nuclei with disease appearance on MRI. Quantitative histomorphometry (QH), like radiomics for radiologic images, is the computer based extraction of features for describing tumor morphology on digitized tissue images. In this work, we attempt to establish the histomorphometric basis for radiomic features for prostate cancer by (1) identifying the radiomic features from T2w MRI most discriminating of low vs. intermediate/high Gleason score, (2) identifying QH features correlated with the most discriminating radiomic features previously identified, and (3) evaluating the discriminative ability of QH features found to be correlated with spatially co-localized radiomic features. On a cohort of 36 patients (23 for training, 13 for validation), Gabor texture features were identified as being most predictive of Gleason grade on MRI (AUC of 0.69) and gland lumen shape features were identified as the most predictive QH features (AUC = 0.75). Our results suggest that the PCa grade discriminability of Gabor features is a consequence of variations in gland shape and morphology at the tissue level.
Highlights
Radiomics involves extracting quantitative features from medical images for disease characterization. [1,2,3] radiomic features attempt to capture sub-visual image attributes of the disease that may not be visually discernible
Viswanath et al [25] found that Gabor and Haralick features extracted from 3 Tesla (T) endorectal, in vivo T2-weighted (T2w) magnetic resonance imaging (MRI) were able to detect prostate cancer (PCa) with area under the curve (AUC) of the receiver operating characteristic (ROC) curve of 0.86 within the central gland and 0.73 within the peripheral zone
There have been some recent works looking at radiomic features from prostate MRI which are predictive of Gleason score in vivo. [5, 6, 28, 70] Previously, Haralick texture features as well as edge orientation features such as Sobel, Kirsch, and gradient features have been found to be discriminating of low and high Gleason score. [5, 6, 28, 70] none of these studies have explicitly sought to identify the cellular or morphologic basis of why these features have been found to be predictive of Gleason score
Summary
Radiomics involves extracting quantitative features from medical images for disease characterization. [1,2,3] radiomic features attempt to capture sub-visual image attributes of the disease that may not be visually discernible. In the context of prostate cancer, radiomic approaches have been presented in order to identify disease presence on magnetic resonance imaging (MRI) and to non-invasively grade and stratify disease risk. Viswanath et al [25] found that Gabor and Haralick features extracted from 3 Tesla (T) endorectal, in vivo T2-weighted (T2w) MRI were able to detect prostate cancer (PCa) with area under the curve (AUC) of the receiver operating characteristic (ROC) curve of 0.86 within the central gland and 0.73 within the peripheral zone. Tiwari et al [28] found that a non-linear embedding based fusion approach for combining magnetic resonance spectroscopy (MRS) and directional (Sobel, Kirsch, and gradient) and Haralick texture features of T2w MRI was able to distinguish low from high Gleason grades (a well established surrogate for PCa risk) with an AUC of 0.89 on N = 29 patients
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
