Objective: Alcohol use disorder (AUD) remains a leading cause of worldwide mortality and morbidity. The development of neuroanatomical biomarkers offers the potential of novel clinical indicators to guide prevention, early diagnosis, and treatment. Methods: In 76 participants with DSM-5 diagnosed AUD (Mage = 35.75; 51.3% female) and 79 controls (Mage = 34.71; 59.5% female), we utilized magnetic resonance imaging (MRI) to investigate four novel measures: hippocampal and amygdalar subregion volumes, sulcal morphology (SM), and fractal dimensionality (FD). MRI processing, segmentation, and SM and FD quantification were completed using FreeSurfer v6.0 and v7.0, and MATLAB toolboxes, respectively. A significance value of p < .05 was employed for analysis and sex, age, and intracranial volume were included as covariates. Results: Volumes of the right presubiculum, subiculum, and molecular layer head; left lateral and accessory basal nuclei; and corticoamygdaloid transition area were significantly lower in AUD participants relative to healthy controls. Widths of the left occipito-temporal, right middle occipital and lunate, and right marginal part of the cingulate sulci and depth of the post-central sulci were significantly increased in AUD participants relative to controls. Finally, decreased left caudate, left thalamus, right putamen and right pallidum FD and greater inferior lateral and third ventricle FD were observed in AUD participants relative to controls. Each novel measure’s reliability was assessed using test-retest data from the Human Connectome Project and indicated high reliability with median intraclass correlations of .93, .91, .88, and .93 for the hippocampal subfields, amygdalar nuclei, SM, and FD, respectively. Conclusion: These results indicate selectively decreased hippocampal and amygdala subregion volume, increased sulcal depth and width, and differences in FD as promising neuroanatomical biomarkers for AUD. / Thesis / Master of Health Sciences (MSc)

Machine learning (ML) and deep learning (DL) are powerful techniques that allow for analysis and classification of large MRI datasets. With the growing accessibility of high-powered computing and large data storage, there has been an explosive interest in their uses for assisting clinical analysis and interpretation. Though these methods can provide insights into the data which are not possible through human analysis alone, they require significantly large datasets for training which can difficult for anyone (researcher and clinician) to obtain on their own. The growing use of publicly available, multi-site databases helps solve this problem. Inadvertently, however, these databases can sometimes contain outliers or incorrectly labeled data as the subjects may or may not have subclinical or underlying pathology unbeknownst to them or to those who did the data collection. Due to the outlier sensitivity of ML and DL techniques, inclusion of such data can lead to poor classification rates and subsequent low specificity and sensitivity. Thus, the focus of this work was to evaluate large brain MRI datasets, specifically diffusion tensor imaging (DTI), for the presence of anomalies and to validate and compare different methods of anomaly detection. A total of 1029 male and female subjects ages 22 to 35 were downloaded from a global imaging repository and divided into 6 cohorts depending on their age and sex. Care was made to minimize variance due to hardware and hence only data from a specific vendor (General Electric Healthcare) and MRI B0 field strength (i.e. 3 Tesla) were obtained. The raw DTI data (i.e. in this case DICOM images) was first preprocessed into scalar metrics (i.e. FA, RD, AD, MD) and warped to MNI152 T1 1mm standardized space using the FMRIB software library (FSL). Subsequently data was segmented into regions of interest (ROI) using the JHU DTI-based white-matter atlas and a mean was calculated for each ROI defined by that atlas. The ROI data was standardized and a Z-score, for each ROI over all subjects, was calculated. Four different algorithms were used for anomaly detection, including Z-score outlier detection, maximum likelihood estimator (MLE) and minimum covariance determinant (MCD) based Mahalanobis distance outlier detection, one-class support vector machine (OCSVM) outlier detection, and OCSVM novelty detection trained on MCD based Mahalanobis distance data. The best outlier detector was found to be MCD based Mahalanobis distance, with the OCSVM novelty detector performing exceptionally well on the MCD based Mahalanobis distance data. From the results of this study, it is clear that these global databases contain outliers within their healthy control datasets, further reinforcing the need for the inclusion of outlier or novelty detection as part of the preprocessing pipeline for ML and DL related studies. / Thesis / Master of Applied Science (MASc) / Artificial intelligence (AI) refers to the ability of a computer or robot to mimic human traits such as problem solving or learning. Recently there has been an explosive interest in its uses for assisting in clinical analysis. However, successful use of these methods require a significantly large training set which can often contain outliers or incorrectly labeled data. Due to the sensitivity of these techniques to outliers, this often leads to poor classification rates as well as low specificity and sensitivity. The focus of this work was to evaluate different methods of outlier detection and investigate the presence of anomalies in large brain MRI datasets. The results of this study show that these large brain MRI datasets contain anomalies and provide a method best fit for identifying them.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.