Format

Send to

Choose Destination
Magn Reson Imaging. 2018 Jul;50:125-133. doi: 10.1016/j.mri.2018.04.003. Epub 2018 Apr 9.

Detection of high GS risk group prostate tumors by diffusion tensor imaging and logistic regression modelling.

Author information

1
Department of Biomedical Engineering, Yeditepe University, Istanbul, Turkey. Electronic address: gokhan.ertas@yeditepe.edu.tr.

Abstract

PURPOSE:

To assess the value of joint evaluation of diffusion tensor imaging (DTI) measures by using logistic regression modelling to detect high GS risk group prostate tumors.

MATERIALS AND METHODS:

Fifty tumors imaged using DTI on a 3 T MRI device were analyzed. Regions of interests focusing on the center of tumor foci and noncancerous tissue on the maps of mean diffusivity (MD) and fractional anisotropy (FA) were used to extract the minimum, the maximum and the mean measures. Measure ratio was computed by dividing tumor measure by noncancerous tissue measure. Logistic regression models were fitted for all possible pair combinations of the measures using 5-fold cross validation.

RESULTS:

Systematic differences are present for all MD measures and also for all FA measures in distinguishing the high risk tumors [GS ≥ 7(4 + 3)] from the low risk tumors [GS ≤ 7(3 + 4)] (P < 0.05). Smaller value for MD measures and larger value for FA measures indicate the high risk. The models enrolling the measures achieve good fits and good classification performances (R2adj = 0.55-0.60, AUC = 0.88-0.91), however the models using the measure ratios perform better (R2adj = 0.59-0.75, AUC = 0.88-0.95). The model that employs the ratios of minimum MD and maximum FA accomplishes the highest sensitivity, specificity and accuracy (Se = 77.8%, Sp = 96.9% and Acc = 90.0%).

CONCLUSION:

Joint evaluation of MD and FA diffusion tensor imaging measures is valuable to detect high GS risk group peripheral zone prostate tumors. However, use of the ratios of the measures improves the accuracy of the detections substantially. Logistic regression modelling provides a favorable solution for the joint evaluations easily adoptable in clinical practice.

KEYWORDS:

Diffusion tensor imaging; Fractional anisotropy; Joint evaluation; Logistic regression; Mean diffusivity; Prostate cancer; Ratio

PMID:
29649574
DOI:
10.1016/j.mri.2018.04.003
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center