Prognosis of primary dysmenorrhea in pain-free phase using MRI based categorization

Primary tabs

Prognosis of primary dysmenorrhea in pain-free phase using MRI based categorization

The grey matter volume may be used as an inherent imaging marker for the evaluation of menstrual pain intervention, as the GM volume predict the primary dysmenorrhea (PDM) patients during the pain-free phase and the fluctuations in the intensity of menstrual pain explained by the investigators of the Center for Brain Imaging, Xidian University.

A total of 60 PDM patients and 54 matched healthy control (HC) went through the pelvic and head MRI scans to measure myometrium apparent diffusion coefficient (ADC) and GM volume during their periovulatory phase.  The participants also filled the questionnaire. The classification model was developed using a support vector machine algorithm and the significance of model performance by the permutation test. The relationship between discriminative features and intensity of menstrual pain were investigated using the multiple regression analysis.

Brain-based classification results demonstrated that 75.44% of subjects were correctly classified, with 83.33% identification of the patients with PDM. The demographics and myometrium ADC-based categorisations unable to clear the permutation tests. Further, the regression analysis exhibited 29.37% of the variance in pain intensity for myometrium ADC and demographical indicators. After reverting out these factors, GM characteristics demonstrated 60.33% of the remaining variance.



Link to the source:

Original title of the article:

Whole brain structural MRI based classification of primary dysmenorrhea in pain-free phase: a machine learning study.


Tao Chen et al.

Diagnostic, Primary Dysmenorrhea, Pelvic pain, Machine Learning Study, MRI, Apparent Diffusion Coefficient
Log in or register to post comments