Format

Send to

Choose Destination
J Digit Imaging. 2018 Dec;31(6):929-939. doi: 10.1007/s10278-018-0100-0.

A Decision-Support Tool for Renal Mass Classification.

Author information

1
UtopiaCompression Corporation, 11150 W Olympic Blvd. Suite #820, Los Angeles, CA, 90064, USA. gautam@utopiacompression.com.
2
Department of Radiology, Keck School of Medicine, University of Southern California, 1500 San Pablo Street, 2nd Floor, Los Angeles, CA, 90033, USA.
3
UtopiaCompression Corporation, 11150 W Olympic Blvd. Suite #820, Los Angeles, CA, 90064, USA.
4
Department of Pathology, Keck School of Medicine, University of Southern California, 2011 Zonal Avenue, Los Angeles, CA, 90033, USA.
5
Institute of Urology, Keck School of Medicine, University of Southern California, 1441 Eastlake Ave, Los Angeles, CA, 90089, USA.

Abstract

We investigate the viability of statistical relational machine learning algorithms for the task of identifying malignancy of renal masses using radiomics-based imaging features. Features characterizing the texture, signal intensity, and other relevant metrics of the renal mass were extracted from multiphase contrast-enhanced computed tomography images. The recently developed formalism of relational functional gradient boosting (RFGB) was used to learn human-interpretable models for classification. Experimental results demonstrate that RFGB outperforms many standard machine learning approaches as well as the current diagnostic gold standard of visual qualification by radiologists.

KEYWORDS:

Clinical decision support; Multiphase CT; Radiomics; Renal mass; Statistical relational learning

PMID:
29980960
PMCID:
PMC6261185
[Available on 2019-12-01]
DOI:
10.1007/s10278-018-0100-0

Supplemental Content

Full text links

Icon for Springer
Loading ...
Support Center