No abstract

doi: medRxiv preprint NOTE: This preprint reports new research that has not been certified by peer review and should not be used to guide clinical practice.

Contrast-enhanced cardiac magnetic resonance imaging (MRI) is routinely used to determine myocardial scar burden and make therapeutic decisions for coronary revascularization. Currently, there are no optimized deep-learning algorithms for the automated classification of scarred vs. normal myocardium. We report a modified Generative Adversarial Network (GAN) augmentation method to improve the binary classification of myocardial scar using both pre-clinical and clinical approaches. For the initial training of the MobileNetV2 platform, we used the images generated from a high-field (9.4T) cardiac MRI of a mouse model of acute myocardial infarction (MI). Once the system showed 100% accuracy for the classification of acute MI in mice, we tested the translational significance of this approach in 91 patients with an ischemic myocardial scar, and 31 control subjects without evidence of myocardial scarring. To obtain a comparable augmentation dataset, we rotated scar images 8-times and control images 72-times, generating a total of 6,684 scar images and 7,451 control images. In humans, the use of Progressive Growing GAN (PGGAN)-based augmentation showed 93% classification accuracy, which is far superior to conventional automated modules. The use of other attention modules in our CNN further improved the classification accuracy by up to 5%. These data are of high translational significance and warrant larger multicenter studies in the future to validate the clinical implications.

Cocaine use disorder (CUD) is a prevalent substance abuse disorder, and repetitive transcranial magnetic stimulation (rTMS) has shown potential in reducing cocaine cravings. However, a robust and replicable biomarker for CUD phenotyping is lacking, and the association between CUD brain phenotypes and treatment response remains unclear. Our study successfully establish a corss-validated functional connectivity signature for accurate CUD phenotyping, using resting-state functional magnetic resonance imaging from a discovery cohort, and demonstrated its generalizability in an independent replication cohort. We identified phenotyping FCs involving increased connectivity between the visual network and dorsal attention network, and between the frontoparietal control network and ventral attention network, as well as decreased connectivity between the default mode network and limbic network in CUD patients compared to healthy controls. These abnormal connections correlated significantly with other drug use history and cognitive dysfunctions, like non-planning impulsivity. We used the CUD-discriminative FCs to predict rTMS treatment response in CUD patients receiving either active (N = 25) or sham rTMS (N = 20) separately, finding that the most predictive FCs for active treatment responses were involving the frontoparietal control and default mode networks. Our findings provide insights into the neurobiological mechanisms of CUD and the association between CUD phenotypes and rTMS treatment response, offering promising targets for future therapeutic development.

IMPORTANCE: Though sertraline is commonly prescribed in patients with major depressive disorder (MDD), its superiority over placebo is only marginal. This is in part due to the neurobiological heterogeneity of the individuals. Characterizing individual-unique functional architecture of the brain may help better dissect the heterogeneity, thereby defining treatment-predictive signatures to guide personalized medication. OBJECTIVE: To characterize individualized brain functional connectivity (FC) and determine whether it can define signatures of antidepressant and placebo treatment in MDD. DESIGN, SETTING, AND PARTICIPANTS: The data used in the present work were collected by the Establishing Moderators and Biosignatures of Antidepressant Response in Clinical Care (EMBARC) study. Recruitment started from July 29, 2011, to December 15, 2015. A sample of 296 subjects was randomly assigned to antidepressant sertraline or placebo double-blind treatment for 8 weeks. The whole-brain FC networks were constructed from pre-treatment resting-state functional magnetic resonance imaging (rs-fMRI) at 4 clinical sites. Individualized FC was quantified by removing the common components from the raw baseline FC to train regression-based connectivity predictive models. The data analysis was performed from January 7, 2022 to August 24, 2022. INTERVENTIONS: The MDD patients received either antidepressant sertraline or placebo for 8 weeks. MAIN OUTCOMES AND MEASURES: Treatment response was measured as pre- minus post-treatment change in total score of the 17-item Hamilton Depression Rating Scale (HAMD17). RESULTS: With individualized FC features, the established prediction models successfully identified signatures that explained 22% variance for the sertraline group and 31% variance for the placebo group in predicting HAMD17 change. Compared with the raw FC-based models, the individualized FC-defined signatures significantly improved the prediction performance, as confirmed by the 10\times10-fold cross-validation (Wilcoxon signed-rank test result of R2 difference; sertraline: windividualized vs raw = 2.57, pindividualized vs raw = 0.014; placebo: windividualized vs raw = 3.02, pindividualized vs raw = 0.006). For sertraline treatment, predictive FC metrics were predominantly located in the left middle temporal cortex (MTC) and right insula. Lower FC between the right temporal pole and right insula predicted a better response to sertraline. For placebo, predictive FC metrics were primarily located in the bilateral cingulate cortex and left superior temporal cortex (STC). Lower FC between the right anterior cingulate cortex and left posterior cingulate cortex (PCC) indicated a better placebo response. The right prefrontal lobe was critical for predicting responses to both treatment arms. CONCLUSIONS AND RELEVANCE: Our findings demonstrated that individualization of FC metrics through removal of common FC components enhanced the prediction performance compared to the raw FC. The proposed individualized FC predictive modeling framework was highly adaptable to precise diagnosis and prognosis of other mental disorders. Associated with previous MDD clinical studies, our identified predictive biomarkers provided new insights into the neuropathology of antidepressant and placebo treatment. Clinical Trial Registration ID #: NCT01407094.