Neuroimaging studies on migraine have revealed structural and functional alterations in the hippocampus, a region involved in pain processing and stress response. This study was designed to investigate whether effective connectivity of this region is disrupted in migraine and relates to chronicity of this disease. Patients and Methods: In 39 episodic migraine (EM) patients, 17 chronic migraine (CM) patients, and 35 healthy controls, we investigated differences in the directional influences between the hippocampus and the rest of the brain by combining resting-state functional magnetic resonance imaging and Granger causality analysis (GCA), with bilateral hippocampus as seed regions. The associations between directional influences and the clinical variables were also examined. Results: Comparing each patient group to the control group, we found increased and decreased negative influence on the hippocampus exerted by the bilateral visual areas and right dorsolateral prefrontal cortex (dlPFC), respectively. The hippocampus showed increased positive influence on the right posterior insula and medial prefrontal cortex (mPFC), as well as increased negative influence on the left cerebellum in CM patients relative to EM patients and healthy controls. Furthermore, across all patients, the migraine frequency exhibited a positive and negative association with causal influence from the hippocampus to mPFC and left cerebellum, respectively. Conclusion: Migraine patients have abnormal effective connectivity between the hippocampus and multiple brain regions involved in the sensory and cognitive processing of pain. Disrupted directional influences to the hippocampus exerted by dlPFC and bilateral visual areas were common features of EM and CM patients. Directional influences from the hippocampus to mPFC and left cerebellum may be useful imaging biomarkers for assessing migraine frequency.

PurposeTo explore the value of machine learning model based on CE-MRI radiomic features in preoperative prediction of sentinel lymph node (SLN) metastasis of breast cancer.MethodsThe clinical, pathological and MRI data of 177 patients with pathologically confirmed breast cancer (81 with SLN positive and 96 with SLN negative) and underwent conventional DCE-MRI before surgery in the First Affiliated Hospital of Soochow University from January 2015 to May 2021 were analyzed retrospectively. The samples were randomly divided into the training set (n=123) and validation set (n= 54) according to the ratio of 7:3. The radiomic features were derived from DCE-MRI phase 2 images, and 1,316 original eigenvectors are normalized by maximum and minimum normalization. The optimal feature filter and selection operator (LASSO) algorithm were used to obtain the optimal features. Five machine learning models of Support Vector Machine, Random Forest, Logistic Regression, Gradient Boosting Decision Tree, and Decision Tree were constructed based on the selected features. Radiomics signature and independent risk factors were incorporated to build a combined model. The receiver operating characteristic curve and area under the curve were used to evaluate the performance of the above models, and the accuracy, sensitivity, and specificity were calculated.ResultsThere is no significant difference between all clinical and histopathological variables in breast cancer patients with and without SLN metastasis (P >0.05), except tumor size and BI-RADS classification (P< 0.01). Thirteen features were obtained as optimal features for machine learning model construction. In the validation set, the AUC (0.86) of SVM was the highest among the five machine learning models. Meanwhile, the combined model showed better performance in sentinel lymph node metastasis (SLNM) prediction and achieved a higher AUC (0.88) in the validation set.ConclusionsWe revealed the clinical value of machine learning models established based on CE-MRI radiomic features, providing a highly accurate, non-invasive, and convenient method for preoperative prediction of SLNM in breast cancer patients.