Zone-specific logistic regression models improve classification of prostate cancer on multi-parametric MRI

Abstract

• The ADC and T2-nSI of benign/cancer PZ are higher than benign/cancer TZ. • DCE parameters are significantly different between benign PZ and TZ, but not between cancerous PZ and TZ. • Diagnostic models containing contrast enhancement parameters have reduced performance when applied across zones.

Differentiation of prostate cancer lesions with high and with low Gleason score by diffusion-weighted MRI

“…In general, there is currently no consensus about whether bi-or trivariate modelling improves classification performance compared with using e.g. only T2 values in the transition zone and ADC values in the peripheral zone [29,30]. Another study on 25 patients derived a logistic regression model based on ADC, T2 and volume transfer constant K trans (measured by DCE-MRI) to detect prostate cancer in the peripheral zone (AUC 0.71, 95 % CI 0.69-0.72).…”

Computer-aided Detection of Prostate Cancer with MRI

“…Benign prostatic hyperplasia and other benign inflammatory conditions within the transition zone also exhibit substantial hypervascularity [40]. Diagnostic models containing contrast enhancement parameters have reduced performance when applied across zones, so zone-specific models can improve classification of prostate cancer on multi-parametric MRI [41]. …”

A comparison of Bayesian and non-linear regression methods for robust estimation of pharmacokinetics in DCE-MRI and how it affects cancer diagnosis

“…Tracer kinetic models such as the extended Toft model [5] that describe the enhancement process are often used to derive quantitative parameters and are increasingly used in diagnostic models [6] including computer aided diagnostic (CAD) software [7,8]. Accurate quantification that will be reproducible between different clinical sites is necessary for the widespread of DCE based CAD software.…”