Logistic regression model for diagnosis of transition zone prostate cancer on multi-parametric MRI

Abstract

ObjectivesWe aimed to develop logistic regression (LR) models for classifying prostate cancer within the transition zone on multi-parametric magnetic resonance imaging (mp-MRI).MethodsOne hundred and fifty-five patients (training cohort, 70 patients; temporal validation cohort, 85 patients) underwent mp-MRI and transperineal-template-prostate-mapping (TPM) biopsy. Positive cores were classified by cancer definitions: (1) any-cancer; (2) definition-1 [≥Gleason 4 + 3 or ≥ 6 mm cancer core length (CCL)] [high risk significant]; and (3) definition-2 (≥Gleason 3 + 4 or ≥ 4 mm CCL) cancer [intermediate–high risk significant]. For each, logistic-regression mp-MRI models were derived from the training cohort and validated internally and with the temporal cohort. Sensitivity/specificity and the area under the receiver operating characteristic (ROC-AUC) curve were calculated. LR model performance was compared to radiologists’ performance.ResultsTwenty-eight of 70 patients from the training cohort, and 25/85 patients from the temporal validation cohort had significant cancer on TPM. The ROC-AUC of the LR model for classification of cancer was 0.73/0.67 at internal/temporal validation. The radiologist A/B ROC-AUC was 0.65/0.74 (temporal cohort). For patients scored by radiologists as Prostate Imaging Reporting and Data System (Pi-RADS) score 3, sensitivity/specificity of radiologist A ‘best guess’ and LR model was 0.14/0.54 and 0.71/0.61, respectively; and radiologist B ‘best guess’ and LR model was 0.40/0.34 and 0.50/0.76, respectively.ConclusionsLR models can improve classification of Pi-RADS score 3 lesions similar to experienced radiologists.Key Points• MRI helps find prostate cancer in the anterior of the gland• Logistic regression models based on mp-MRI can classify prostate cancer• Computers can help confirm cancer in areas doctors are uncertain about

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

“…A different logistic regression model combining mean ADC value, normalised T2-weighted signal and maximum enhancement measured by dynamic contrast-enhanced (DCE) MRI was recently proposed to classify prostate cancer within the transition zone [13]. When detecting lesions with a Gleason score of 4 + 3 or greater and a diameter greater than 6 mm, the model led to an AUC of 0.71 (95 % CI 0.58-0.84) following leave-one-out regression analysis in 70 patients.…”

“…As a result of the considerable overlap in ADC values between high-and low-grade lesions, a recent study combined ADC values with parameters derived from other MRI sequences in a logistic regression model to detect cancers with a high Gleason score; the accuracy of the model was found to be similar to the accuracy of experienced radiologists [13]. Another study found that intravoxel incoherent motion (IVIM) parameters (the pure diffusion coefficient D t , the pseudo-diffusion fraction F p and the pseudo-diffusion coefficient D p ) derived from a biexponential fit to DW-MRI [14,15] correlate with the cancer's aggressiveness [16].…”

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

“…For the purpose of this study and to match with the target performance of mp-MRI as defined by recent consensus [24]; histopathologists identified all locations with clinically significant cancer based on volume assessment (0.2 ml) estimated by the cancer core length (CCL)>= 4 mm and/or the presence of Gleason pattern 4 disease [25]. Small volume (<0.2 ml) and low grade (<=Gleason 3+3) tumour was identified as clinically insignificant cancer.…”

Coregistered photoacoustic and ultrasound imaging and classification of ovarian cancer:ex vivoandin vivostudies

“…31,32 Logistic regression belongs to the class of generalized linear model based on the exponential distribution family. It is a statistical model that can describe the relationship between several predictor variables X 1 ; X 2 ; : : : ; X k and a dichotomous response variable Y (0 or 1).…”