Machine learning algorithms along with magnetic resonance imaging (MRI) provides promising techniques to overcome the drawbacks of the current clinical screening techniques. In this study the resting-state functional magnetic resonance imaging (fMRI) to see the level of activity in a patient's brain and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) to explore the level of improvement of neo-adjuvant chemotherapy in patients with locally advanced breast cancer were considered. As the first project, we considered fMRI of patients before and after they underwent a double-blind smoking cessation treatment. For the first time, this study aims at developing new theory-driven biomarkers by implementing and evaluating novel techniques from resting-state scans that can be used in relapse prediction in nicotine-dependent patients and future treatment efficacy. In this regards, two classes of patients have been studied, one took the drug N-acetylcysteine and the other took a placebo. Our goal was to classify the patients as treatment or non-treatment, based on their fMRI scans. The image slices of brain are used as the variable. We have applied different voxel selection schemes and data reduction algorithms on all images. Then, we compared several multivariate classifiers and deep learning algorithms and also investigated how the different data reductions affect classification performance. For the second part, we have employed multi-parametric magnetic resonance imaging (mpMRI) using different morphological and functional MRI parameters such as T2-weighted, dynamic contrast-enhanced (DCE) MRI, and diffusion weighted imaging (DWI) has emerged as the method of choice for the early response assessments to NAC. Although, mpMRI is superior to conventional mammography for predicting treatment response, and evaluating residual disease, yet there is still room for improvement. In the past decade, the field of medical imaging analysis has grown exponentially, with an increased numbers of pattern recognition tools, and an increase in data sizes. These advances have heralded the field of radiomics. Radiomics allows the high-throughput extraction of the quantitative features that result in the conversion of images into mineable data, and the subsequent analysis of the data for an improved decision support with response monitoring during NAC being no exception. In this study. we determined the importance and ranking of the extracted parameters from mpMRI using T2-weighted, DCE, and DWI for prediction of pCR and patient outcomes with respect to metastases and disease-specific death employing different machine learning algorithms. / A Dissertation submitted to the Department of Scientific Computing in partial fulfillment of the requirements for the degree of Doctor of Philosophy. / Summer Semester 2018. / July 6, 2018. / Breast Cancer, Data Mining, Machine Learning, Medical Imaging, Neuroimaging / Includes bibliographical references. / Anke Meyer-Baese, Professor Directing Dissertation; Simon Y. Foo, University Representative; Katja Pinker-Domenig, Committee Member; Peter Beerli, Committee Member; Dennis Slice, Committee Member.

The maxilla and mandible may be affected by a wide variety of lesions of developmental, neoplastic or inflammatory origin. These lesions have a vast array of clinical and radiographic presentations from which a dentist forms a clinical provisional diagnosis and treats the lesions accordingly. The aim of this study was to determine the range, demographic and clinical features of all histologically diagnosed radiolucent jaw lesions in a New Zealand population over a twenty-year period. Additionally, the provisional diagnosis was compared to the histopathological diagnosis in an effort to gain an insight into the difficulties practitioners face in clinically diagnosing radiolucent jaw lesions. Material and Methods: From the histopathology diagnostic service at the University of Otago School of Dentistry all specimens with a diagnosis of a radiolucent jaw lesion between 1986 and 2006 were retrieved and classified into six diagnostic categories. For each lesion the age, gender, site, clinical presentation, clinicians provisional diagnosis and the final histological diagnosis was gathered and analysed. Results: During the study period 4983 specimens were identified as radiolucent jaw lesions. The diagnostic category with the largest number of specimens was inflammatory lesions (72.8%), followed by developmental odontogenic cysts (21.8%). Malignant tumours accounted for less than 1% of all specimens. Concordance of provisional and histopathological diagnoses ranged from 81.0% for nasopalatine duct cyst to 0% for the majority of intra-osseous malignant tumours. Conclusions: The range and demographic features of radiolucent jaw lesions in this study are comparable to that of other populations with a European majority. No radiolucent jaw lesion can be reliably accurately diagnosed from clinical presentation and radiographic appearance alone.

Graduation date: 2005

Thesis (Ph. D.)--University of Texas at Austin, 2000. / Vita. Includes bibliographical references. Available also from UMI/Dissertation Abstracts International.

Thesis (MTech (Radiography))--Peninsula Technikon, 2003. / Word processed copy. Summary in English. Includes bibliographical references. Also available online.

Thesis (M.D.S.)--University of Hong Kong, 2000. / Includes bibliographical references (leaves 69-85).

Thesis (Ph. D.)--University of Texas at Austin, 2000. / Vita. Includes bibliographical references (leaves 197-200). Available also in a digital version from Dissertation Abstracts.

Thesis (M.S.)--University of Florida, 2002. / Title from title page of source document. Includes vita. Includes bibliographical references.

published_or_final_version / Anatomy / Master / Master of Medical Sciences

Not available / text