Honors Theses, Ohio Dominican University, 2018, Honors Theses

The domesticated dog (Canis familiaris) is the most popular household pet in America. There are approximately 42.5 million dogs kept as pets in the United States. Despite dogs being the most popular pet, methods for dogs' age determination are limited and lack precision. After eruption of the final permanent teeth at about 7 months of age there is no quality method for determining age. Characteristics such as development of cataracts, tooth wear, and acquisition of grey hair become the leading factors in age determination; however, the aforementioned factors are variable in all dogs. The use of a pulp cavity/tooth width ratio, measured using dental radiographs, was applied to Canis familiaris to determine a more reliable method for determining age in dogs. This, more accurate method for determining age in dogs, will allow a reduction in shelter euthanasia and allow veterinarians and pet owners to more easily determine treatment plans.

Committee: William Chastain D.V.M. (Advisor); Blake Mathys Ph.D. (Committee Chair); John Marazita Ph.D. (Committee Chair) Subjects: Veterinary Services

Doctor of Philosophy (Ph.D.), University of Dayton, 2022, Electrical Engineering

Chest radiography is a medical imaging modality widely used in computer-aided detection (CADe) and computer-aided diagnosis (CADx) systems to detect and diagnose pulmonary diseases. Chest radiographs (CRs) are susceptible to unforeseen variations that could lead a CADe/CADx (CAD) system to fail. We propose a solution to this problem by analyzing multiple methods including two new methods, No-skip U-Net (NSU-Net-X) and Eigen-X, for CRs. Each method's performance is measured for three classification tasks: classification between lung images and not-lung images, identifying color-inverted CRs, and detecting rotated CRs. The NSU-Net-X, which is an adaptation of U-Net, shows an average performance of 0.99 for the three tasks. The Eigen-X approach, built similar to a widely used face detection method, shows a 0.98 average performance. Following the image screening algorithm, we propose applying lung segmentation on CRs due to its important role in computer-aided detection and diagnosis using CRs. Currently, the U-Net and DeepLabv3+ convolutional neural network architectures are widely used to perform CR lung segmentation. To boost performance, ensemble methods are often used, whereby probability map outputs from several networks operating on the same input image are averaged. However, not all networks perform adequately for any specific patient image, even if the average network performance is good. To address this, we present a novel multi-network ensemble method that employs a selector network. The selector network evaluates the segmentation outputs from several networks; on a case-by-case basis, it selects which outputs are fused to form the final segmentation for that patient. Our candidate lung segmentation networks include U-Net, with five different encoder depths, and DeepLabv3+, with two different backbone networks (ResNet50 and ResNet18). Our selector network is a ResNet18 image classifier. We perform training of the segmentation networks and the selector net (open full item for complete abstract)

Committee: Russell Hardie Ph.D. (Advisor); Barath Narayanan Narayanan Ph.D. (Committee Member); Vijayan Asari Ph.D. (Committee Member); Eric Balster Ph.D. (Committee Member) Subjects: Artificial Intelligence; Engineering; Medical Imaging

Doctor of Philosophy (Ph.D.), University of Dayton, 2017, Electrical and Computer Engineering

Early detection of pulmonary lung nodules plays a significant role in the diagnosis of lung cancer. Radiologists use Computed Tomography (CT) and Chest Radiographs (CRs) to detect such nodules. In this research, we propose various pattern recognition algorithms to enhance the classification performance of the Computer Aided Detection (CAD) system for lung nodule detection in both modalities. We propose a novel optimized method of feature selection for clustering that would aid the performance of the classifier. We make use of an independent CR database for training purposes. Testing is implemented on a publicly available database created by the Standard Digital Image Database Project Team of the Scientific Committee of the Japanese Society of Radiological Technology (JRST). The JRST database comprises 154 CRs containing one radiologist confirmed nodule in each. We make use of 107 CT scans from publicly available dataset created by Lung Image Database Consortium (LIDC) for this study. We compare the performance of the cluster-classifier architecture to a single aggregate classifier architecture. Overall, with a specificity of 3 false positives per case on an average, we show a classifier performance boost of 7.7% for CRs and 5.0% for CT scans when compared to single aggregate classifier architecture. Furthermore, we study the performance of a CAD system in CT scans as a function of slice thickness. We believe this study has implication for how CT is acquired, processed and stored. We make use of CT cases acquired at a thickness of 1.25mm from the publicly available Lung Nodule Analysis 2016 (LUNA16) dataset for this research. We study the CAD performance at a native thickness of 1.25mm and various other down-sampled stages. Our study indicates that CAD performance at 2.5mm is comparable to 1.25mm and is much better than at higher thicknesses. In addition, we propose and compare three different training methodologies for utilizing non-homogenous thickness training (open full item for complete abstract)

Committee: Russell C. Hardie (Advisor) Subjects: Biomedical Research; Electrical Engineering; Medical Imaging

Doctor of Philosophy, Case Western Reserve University, 2017, Biology

The spheno-occipital synchondrosis (SOS) is a cartilaginous growth center between the occipital and sphenoid bones. The chronological age of SOS fusion is believed to occur during adolescence, but the physiological changes in facial and mandibular ontogeny that occur during SOS fusion remains unknown. In my studies, I show sexual dimorphism in SOS fusion age with female subjects always ahead of male subjects in each SOS fusion stage. The SOS fusion rate in females is faster than males and the duration of SOS fusion was shorter in females than males. This research demonstrates a significant positive relationship between hand-wrist skeletal maturity and SOS fusion stages in both genders. Moreover, this study has shown that the maximum amount of mandibular growth occurred while the SOS was still fusing; and the minimum amount of mandibular growth occurred when SOS is already fused. As the orthodontic treatment is influenced by the amount of remaining mandibular and facial growth, this data shows that SOS fusion stages could be used as a biological indicator and help in craniofacial skeletal maturity assessment.

Committee: Scott Simpson PhD (Advisor) Subjects: Dentistry; Developmental Biology; Physical Anthropology