Biomedical Engineering and Bioengineering Commons^™

Segmentation Of Intracranial Structures From Noncontrast Ct Images With Deep Learning, Evan Porter

Wayne State University Dissertations

Presented in this work is an investigation of the application of artificially intelligent algorithms, namely deep learning, to generate segmentations for the application in functional avoidance radiotherapy treatment planning. Specific applications of deep learning for functional avoidance include generating hippocampus segmentations from computed tomography (CT) images and generating synthetic pulmonary perfusion images from four-dimensional CT (4DCT).A single institution dataset of 390 patients treated with Gamma Knife stereotactic radiosurgery was created. From these patients, the hippocampus was manually segmented on the high-resolution MR image and used for the development of the data processing methodology and model testing. It was determined that …

Incorporating Cardiac Substructures Into Radiation Therapy For Improved Cardiac Sparing, Eric Daniel Morris

Wayne State University Dissertations

Growing evidence suggests that radiation therapy (RT) doses to the heart and cardiac substructures (CS) are strongly linked to cardiac toxicities, though only the heart is considered clinically. This work aimed to utilize the superior soft-tissue contrast of magnetic resonance (MR) to segment CS, quantify uncertainties in their position, assess their effect on treatment planning and an MR-guided environment.

Automatic substructure segmentation of 12 CS was completed using a novel hybrid MR/computed tomography (CT) atlas method and was improved upon using a 3-dimensional neural network (U-Net) from deep learning. Intra-fraction motion due to respiration was then quantified. The inter-fraction setup …

Identification Of Streptococcus Pyogenes Using Raman Spectroscopy, Ehsan Majidi

Wayne State University Dissertations

Despite the attention that Raman Spectroscopy has gained recently in the area of pathogen identification, the spectra analyses techniques are not well developed. In most scenarios, they rely on expert intervention to detect and assign the peaks of the spectra to specific molecular vibration. Although some investigators have used machine-learning techniques to classify pathogens, these studies are usually limited to a specific application, and the generalization of these techniques is not clear. Also, a wide range of algorithms have been developed for classification problems, however, there is less insight to applying such methods on Raman spectra. Furthermore, analyzing the Raman …

Europium(Ii)-Containing Complexes For Responsive Magnetic Resonance Imaging, Levi Alexander Ekanger

Wayne State University Dissertations

The research projects described in this dissertation are focused on studying the oxidation of EuII-containing complexes within the context of responsive MRI. Prior to this research, EuII had not been explored within the context of oxidation-responsive MRI nor had the use of this ion been reported in vivo. The results of these studies enable predictions about the oxidation-responsive behavior of EuII-containing complexes in vitro and in vivo.

The EuII-containing cryptate 1.33 was used to evaluate EuII-based positive contrast enhancement after intravenous, intraperitoneal, and subcutaneous injections. The transitory behavior of the positive contrast enhancement correlated with reported levels of oxygenation and …

Fe3o4 Nanoparticles For Magnetic Hyperthermia And Drug Delivery: Synthesis, Characterization And Cellular Studies, Maheshika Palihawadana Arachchige

Wayne State University Dissertations

In recent years, magnetic nanoparticles (MNPs), especially superparamagnetic Fe3O4nanoparticles, have attracted a great deal of attention because of their potential applications in biomedicine. Among the other applications, Magnetic hyperthermia (MHT), where localized heating is generated by means of relaxation processes in MNPs when subjected to a radio frequency magnetic field, has a great potential as a non-invasive cancer therapy treatment. Specific absorption rate (SAR), which measures the efficiency of heat generation, depends on magnetic properties of the particles such as saturation magnetization (Ms), magnetic anisotropy (K), particle size distribution, magnetic dipolar interactions, and the rheological properties of the target medium.We …

Frequency Domain Ultrasound Waveform Tomography Breast Imaging, Gursharan Singh Sandhu

Wayne State University Dissertations

Ultrasound tomography is an emerging modality for imaging breast tissue for the detection of disease. Using the principles of full waveform inversion, high-resolution quantitative sound speed and attenuation maps of the breast can be created. In this thesis, we introduce some basic principles of imaging breast disease and the formalism of sound wave propagation. We present numerical methods to model acoustic wave propagation as well methods to solve the corresponding inverse problem. Numerical simulations of sound speed and attenuation reconstructions are used to assess the efficacy of the algorithm. A careful review of the preprocessing techniques needed for the successful …

Novel Incorportation Of Biomedical Engineering Algorithms (Bispectral Index Guided Or Anesthetic Concentration Guided) In Real-Time Decision Support To Prevent Intraoperative Awareness Using An Electronic Anesthesia Information Mananagement System, Amy Melanie Shanks

Wayne State University Dissertations

Background: Intraoperative awareness with explicit recall (AWR) is a feared complication of surgery that can lead to significant psychological distress. Several large prospective trials have been completed comparing two methods of monitoring anesthetic depth [minimum alveolar concentration (MAC) or electroencephalography (EEG) monitoring using the bispectral index (BIS)] for the prevention of AWR. However, these trials were conducted in high risk populations, limiting generalizability.

Research Hypothesis: Real-time decision support with Anesthesia Information Management System alerts based on a novel anesthetic concentration algorithm (incorporating the use of intravenous anesthetics) or an EEG-guided algorithm will reduce the known incidence of AWR.

Methods: First, …

Visual Exploration And Information Analytics Of High-Dimensional Medical Images, Darshan Pai

Wayne State University Dissertations

Data visualization has transformed how we analyze increasingly large and complex data sets. Advanced visual tools logically represent data in a way that communicates the most important information inherent within it and culminate the analysis with an insightful conclusion. Automated analysis disciplines - such as data mining, machine learning, and statistics - have traditionally been the most dominant fields for data analysis. It has been complemented with a near-ubiquitous adoption of specialized hardware and software environments that handle the storage, retrieval, and pre- and postprocessing of digital data. The addition of interactive visualization tools allows an active human participant in …

Raman Spectroscopy And Diffuse Reflectance Spectroscopy For Diagnosis Of Human Cancer And Acanthosis Nigricans, Suneetha Devpura

Wayne State University Dissertations

Cancer and diabetes are common chronic diseases in today's world causing numerous deaths in adults as well as children. Most common types of cancers in adults include prostate, lung, breast, colorectal and head and neck squamous cell carcinoma, while among children; leukemia, and brain and central nervous system cancers are quite common. In each of these cases, early detection of the cancer or disease dramatically increases the chances of successful treatment. In recent years, there has been much interest in using Raman spectroscopy and diffuse reflectance spectroscopy as analytical optical spectroscopic methods for early diagnosis of diseases. Raman spectroscopy can …

Techniques For Sensor-Integrated Robotic Systems: Raman Spectra Analysis, Image Guidance, And Kinematic Calibration, Luke Anthony Reisner

Wayne State University Dissertations

Robotics and sensor technology have made impressive advancements over the years. There are now robotic systems that help perform surgeries or explore the surface of Mars, and there are sensors that detect trace amounts of explosives or identify diseased human tissue. The most powerful systems integrate robots and sensors, which are natural complements to each other. Sensors can provide information that might otherwise be unavailable due to indirect robotic manipulation (e.g., images of the target environment), and robots can provide suitably precise positioning of an analytical sensor.

To have an effective sensor-integrated robotic system, multiple capabilities are needed in the …

Identification Of Neuroblastoma And Its Prognostic Markers Using Raman Spectroscopy, Rachel Kast

Wayne State University Dissertations

Introduction: Neuroblastoma is the most common cancer of infancy. It is one of several peripheral nervous system tumors, including ganglioneuroma, peripheral nerve sheath tumor, and pheochromocytoma. It is commonly situated on the adrenal gland. It displays similar histology to other small round blue cell tumors, including non-Hodgkin lymphoma, rhabdomyosarcoma, and Ewing sarcoma. One method of judging neuroblastoma aggressiveness uses tumor histology factors, including mitosis-karyorrhexis index, Schwannian stromal development, degree of differentiation, and patient age. Tumor aggressiveness can also be judged based on the amplification of certain genes, including MYCN. Raman spectroscopy is a physics-based method which identifies the biochemical …