Biomedical Engineering and Bioengineering Commons^™

Three-Dimensional Printing And Nanotechnology For Enhanced Implantable Materials, Karthik Kumar Tappa

Doctoral Dissertations

Orthopedic and oro-maxillofacial implants have revolutionized treatment of bone diseases and fractures. Currently available metallic implants have been in clinical use for more than 40 years and have proved medically efficacious. However, several drawbacks remain, such as excessive stiffness, accumulation of metal ions in surrounding tissue, growth restriction, required removal/revision surgery, inability to carry drugs, and susceptibility to infection. The need for additional revision surgery increases financial costs and prolongs recovery time for patients. These metallic implants are bulk manufactured and often do not meet patient's requirements. A surgeon must machine (cut, weld, trim or drill holes) them in order …

The Effect Of Network Transitions On Spontaneous Activity And Sycnhrony In Devloping Neural Networks, Jude P. J. Savarraj

Doctoral Dissertations

Connectivity patterns of developing neural circuits and the effects of its dynamics on network behavior, particularly the emergence of spontaneous activity and synchrony, are not clear. We attempt to quantify anatomical connectivity patterns of rat cortical cultures during different stages of development. By culturing the networks on dishes embedded with micro electrode arrays, we simultaneously record electrical activity from multiple regions of the developing network and monitor its electrical behavior, particularly its tendency to fire spontaneously and to synchronize under certain conditions. We investigate possible correlations between changes in the network connectivity patterns and spontaneous electrical activity and synchrony. Cocultures …

Modular Machine Learning Methods For Computer-Aided Diagnosis Of Breast Cancer, Mia Kathleen Markey '94

Doctoral Dissertations

The purpose of this study was to improve breast cancer diagnosis by reducing the number of benign biopsies performed. To this end, we investigated modular and ensemble systems of machine learning methods for computer-aided diagnosis (CAD) of breast cancer. A modular system partitions the input space into smaller domains, each of which is handled by a local model. An ensemble system uses multiple models for the same cases and combines the models' predictions.

Five supervised machine learning techniques (LDA, SVM, BP-ANN, CBR, CART) were trained to predict the biopsy outcome from mammographic findings (BIRADS™) and patient age based on a …