Physical Sciences and Mathematics Commons^™

An Explainable Deep Learning Prediction Model For Severity Of Alzheimer's Disease From Brain Images, Godwin O. Ekuma

MSU Graduate Theses

Deep Convolutional Neural Networks (CNNs) have become the go-to method for medical imaging classification on various imaging modalities for binary and multiclass problems. Deep CNNs extract spatial features from image data hierarchically, with deeper layers learning more relevant features for the classification application. The effectiveness of deep learning models are hampered by limited data sets, skewed class distributions, and the undesirable "black box" of neural networks, which decreases their understandability and usability in precision medicine applications. This thesis addresses the challenge of building an explainable deep learning model for a clinical application: predicting the severity of Alzheimer's disease (AD). AD …

Prediction Of Rapid Early Progression And Survival Risk With Pre-Radiation Mri In Who Grade 4 Glioma Patients, Walia Farzana, Mustafa M. Basree, Norou Diawara, Zeina Shboul, Sagel Dubey, Marie M. Lockheart, Mohamed Hamza, Joshua D. Palmer, Khan Iftekharuddin

Electrical & Computer Engineering Faculty Publications

Rapid early progression (REP) has been defined as increased nodular enhancement at the border of the resection cavity, the appearance of new lesions outside the resection cavity, or increased enhancement of the residual disease after surgery and before radiation. Patients with REP have worse survival compared to patients without REP (non-REP). Therefore, a reliable method for differentiating REP from non-REP is hypothesized to assist in personlized treatment planning. A potential approach is to use the radiomics and fractal texture features extracted from brain tumors to characterize morphological and physiological properties. We propose a random sampling-based ensemble classification model. The proposed …

Predicting Severity Of Traumatic Brain Injury: A Residual Learning Model From Magnetic Resonance Images, Dacosta Yeboah

MSU Graduate Theses

One of the most significant frontiers for computational scientists is the engineering of human healthcare delivery based on intelligent analysis of health data. In a variety of neurological disorders such as Traumatic Brain Injury (TBI), neuro-imaging information plays a crucial role in the decision-making regarding patient care and as a potential prognostic marker for outcome. TBI is a heterogeneous neurological disorder. Due to the economic burdens of the disorder, sorting out this heterogeneity could provide more insights and better understanding of TBI recovery trajectories, thus improving overall diagnosis and treatment options. Magnetic Resonance Imaging (MRI) is a non-invasive technique that …

Integrated Multiparametric Radiomics And Informatics System For Characterizing Breast Tumor Characteristics With The Oncotypedx Gene Assay, Michael A. Jacobs, Christopher B. Umbricht, Vishwa S. Parekh, Riham H. El Khouli, Leslie Cope, Katarzyna J. Macura, Susan Harvey, Antonio C. Wolff

Radiology Faculty Publications

Optimal use of multiparametric magnetic resonance imaging (mpMRI) can identify key MRI parameters and provide unique tissue signatures defining phenotypes of breast cancer. We have developed and implemented a new machine-learning informatic system, termed Informatics Radiomics Integration System (IRIS) that integrates clinical variables, derived from imaging and electronic medical health records (EHR) with multiparametric radiomics (mpRad) for identifying potential risk of local or systemic recurrence in breast cancer patients. We tested the model in patients (n = 80) who had Estrogen Receptor positive disease and underwent OncotypeDX gene testing, radiomic analysis, and breast mpMRI. The IRIS method was trained …

Computational Modeling For Abnormal Brain Tissue Segmentation, Brain Tumor Tracking, And Grading, Syed Mohammad Shamin Reza

Electrical & Computer Engineering Theses & Dissertations

This dissertation proposes novel texture feature-based computational models for quantitative analysis of abnormal tissues in two neurological disorders: brain tumor and stroke. Brain tumors are the cells with uncontrolled growth in the brain tissues and one of the major causes of death due to cancer. On the other hand, brain strokes occur due to the sudden interruption of the blood supply which damages the normal brain tissues and frequently causes death or persistent disability. Clinical management of these brain tumors and stroke lesions critically depends on robust quantitative analysis using different imaging modalities including Magnetic Resonance (MR) and Digital Pathology …

Controlling Water Exchange Kinetics And Improving Paracest Imaging, Jacqueline R. Slack

Dissertations and Theses

Generating MR image contrast from exogenous contrast media through chemical exchange saturation transfer (CEST) offers several exciting new possibilities, such as multicolored imaging, the interleaving of pre- and post-contrast images, and the potential to perform ratiometric metabolic imaging. The major limitation of the deployment of CEST imaging is the comparatively high detection limits of exogenous agents and particularly at the low B_¹ power levels required to meet SAR requirements. The large chemical shifts afforded by paramagnetic (paraCEST) agents permit more rapid exchange kinetics and therefore potentially more effective contrast agents. Despite comparatively large chemical shifts, many Ln³⁺ DOTA-tetraamide …

Investigations Into The Effects Of Water Exchange And The Structure Of Lanthanide Chelates, Katherine Marie Payne

Dissertations and Theses

Lanthanide chelates are effective agents for improving contrast in MR images. Optimizing the relaxation of inner sphere water molecules is a common focus of research in this field. However, the efforts to design an optimal contrast agent have commonly over-looked the relationship of water position and water exchange kinetics. This work explores structural conformation, the impact of very fast water exchange kinetics on hydration, and differing tumbling rates for regioisomers of a number of lanthanide chelates. We have grown crystals of LnDOTMA and obtained structural data by X-ray diffraction that provide a picture of the chelate during water exchange and …

Development Of Anatomical And Functional Magnetic Resonance Imaging Measures Of Alzheimer Disease, Samaneh Kazemifar

Electronic Thesis and Dissertation Repository

Alzheimer disease is considered to be a progressive neurodegenerative condition, clinically characterized by cognitive dysfunction and memory impairments. Incorporating imaging biomarkers in the early diagnosis and monitoring of disease progression is increasingly important in the evaluation of novel treatments. The purpose of the work in this thesis was to develop and evaluate novel structural and functional biomarkers of disease to improve Alzheimer disease diagnosis and treatment monitoring. Our overarching hypothesis is that magnetic resonance imaging methods that sensitively measure brain structure and functional impairment have the potential to identify people with Alzheimer’s disease prior to the onset of cognitive decline. …

A Comparative Study Of Two Prediction Models For Brain Tumor Progression, Deqi Zhou, Loc Tran, Jihong Wang, Jiang Li, Karen O. Egiazarian (Ed.), Sos S. Agaian (Ed.), Atanas P. Gotchev (Ed.)

Electrical & Computer Engineering Faculty Publications

MR diffusion tensor imaging (DTI) technique together with traditional T1 or T2 weighted MRI scans supplies rich information sources for brain cancer diagnoses. These images form large-scale, high-dimensional data sets. Due to the fact that significant correlations exist among these images, we assume low-dimensional geometry data structures (manifolds) are embedded in the high-dimensional space. Those manifolds might be hidden from radiologists because it is challenging for human experts to interpret high-dimensional data. Identification of the manifold is a critical step for successfully analyzing multimodal MR images.

We have developed various manifold learning algorithms (Tran et al. 2011; Tran et al. …

A New Phantom And Gradient Isocenter Estimation For Magnetic Resonance Imaging Distortion Correction, Zongqi Cai

Theses Digitization Project

The purpose of this study was to develop and implement a numerical software based method that can accurately correct the distortion of MR images generated by 3T MRI scanner. To accomplish this, a new phantom has been designed from scratch to capture the distortions inside 3T MRI scanner. An algorithm has been developed, based on the unique geometric feature of the new phantom, to estimate the location of gradient isocenter of the magnetic field inside 3T MRI scanner for the first time.

Multiple Subject Barycentric Discriminant Analysis (Musubada): How To Assign Scans To Categories Without Using Spatial Normalization, Hervé Abdi, Lynne J. Williams, Andrew C. Connolly, M. Ida Gobbini

Dartmouth Scholarship

We present a new discriminant analysis (DA) method called Multiple Subject Barycentric Discriminant Analysis (MUSUBADA) suited for analyzing fMRI data because it handles datasets with multiple participants that each provides different number of variables (i.e., voxels) that are themselves grouped into regions of interest (ROIs). Like DA, MUSUBADA (1) assigns observations to predefined categories, (2) gives factorial maps displaying observations and categories, and (3) optimally assigns observations to categories. MUSUBADA handles cases with more variables than observations and can project portions of the data table (e.g., subtables, which can represent participants or ROIs) on the factorial maps. Therefore MUSUBADA can …

Histogram Analysis Of Adc In Brain Tumor Patients, Debrup Banerjee, Jihong Wang, Jiang Li, Norbert J. Pelc (Ed.), Ehsan Samei (Ed.), Robert M. Nishikawa (Ed.)

Electrical & Computer Engineering Faculty Publications

At various stage of progression, most brain tumors are not homogenous. In this presentation, we retrospectively studied the distribution of ADC values inside tumor volume during the course of tumor treatment and progression for a selective group of patients who underwent an anti-VEGF trial. Complete MRI studies were obtained for this selected group of patients including pre- and multiple follow-up, post-treatment imaging studies. In each MRI imaging study, multiple scan series were obtained as a standard protocol which includes T1, T2, T1-post contrast, FLAIR and DTI derived images (ADC, FA etc.) for each visit. All scan series (T1, T2, FLAIR, …

Prediction Of Brain Tumor Progression Using Multiple Histogram Matched Mri Scans, Debrup Banerjee, Loc Tran, Jiang Li, Yuzhong Shen, Frederic Mckenzie, Jihong Wang, Ronald M. Summers (Ed.), Bram Van Ginneken (Ed.)

Electrical & Computer Engineering Faculty Publications

In a recent study [1], we investigated the feasibility of predicting brain tumor progression based on multiple MRI series and we tested our methods on seven patients' MRI images scanned at three consecutive visits A, B and C. Experimental results showed that it is feasible to predict tumor progression from visit A to visit C using a model trained by the information from visit A to visit B. However, the trained model failed when we tried to predict tumor progression from visit B to visit C, though it is clinically more important. Upon a closer look at the MRI scans …

White Matter Diffusion Alterations In Normal Women At Risk Of Alzheimer's Disease, Charles D. Smith, Himachandra Chebrolu, Anders H. Andersen, David A. Powell, Mark A. Lovell, Shuling Xiong, Brian T. Gold

Neurology Faculty Publications

Increased white matter mean diffusivity and decreased fractional anisotropy (FA) has been observed in subjects diagnosed with mild cognitive impairment (MCI) and Alzheimer's disease (AD). We sought to determine whether similar alterations of white matter occur in normal individuals at risk of AD. Diffusion tensor images were acquired in 42 cognitively normal right-handed women with both a family history of dementia and at least one apolipoprotein E4 allele. These were compared with images from 23 normal women without either AD risk factor. Group analyses were performed using tract-based spatial statistics. Reduced FA was observed in the fronto-occipital and inferior temporal …

Anatomy And Three-Dimensional Reconstructions Of The Brain Of A Bottlenose Dolphin (Tursiops Truncatus) From Magnetic Resonance Images, Lori Marino, Keith D. Sudheimer, Timothy L. Murphy, Kristina K. Davis, D. Ann Pabst, William A. Mclellan, James K. Rilling, John I. Johnson

Veterinary Science and Medicine Collection

Cetacean (dolphin, whale, and porpoise) brains are among the least studied mammalian brains because of the formidability of collecting and histologically preparing such relatively rare and large specimens. Magnetic resonance imaging offers a means of observing the internal structure of the brain when traditional histological procedures are not practical. Furthermore, internal structures can be analyzed in their precise anatomic positions, which is difficult to accomplish after the spatial distortions often accompanying histological processing. In this study, images of the brain of an adult bottlenose dolphin, Tursiops truncatus, were scanned in the coronal plane at 148 antero-posterior levels. From these scans …

Methods For Volume Measurement In 3d Images, Kevin J. Black

Kevin J. Black, MD