Biomedical Engineering and Bioengineering Commons^™

A Convolutional Neural Network Approach To Breast Cancer Tumor Boundary Detection, James Leah Matlosz

Master's Theses

Breast cancer is the second most common form of cancer and often goes undetected in its initial stages due to its subtle symptoms. As the tumors grow, they become more difficult to surgically remove with clean borders. To minimize the chance of recurrence, a 2D convolutional neural network is developed in this work for delineating tumor boundaries. Specifically, the U-shaped network model is trained, validated, and tested with longitudinal MRI scans of patients diagnosed with breast cancer and undergoing neoadjuvant therapy. For training, image masks were generated as ground truths using signal enhancement ratio segmentation, thresholding, and contour detection. The …

Measuring Neck Morphologies Using Upright Magnetic Resonance Imaging, Narayan Yoganandan, Mahmudur Rahman, Ali Warriach, Karthik Banurekha Devaraj, Brian D. Stemper, Aditya Vedantam, Christopher Wolfla, Peter Le

Biomedical Engineering Faculty Research and Publications

Introduction

Because the head supported mass worn by military pilots adds loading to the head-neck complex, morphometrical characteristics of neck muscles are expected to be different from those that do not wear the added mass. To accurately determine segmental neck loads using computational whole-body human or head-neck models, it is important to include accurate morphometrical properties of cervical muscles from the population of interest, in this case military pilots. Routine radiographic imaging (x-rays and computed tomography scans) is less optimal, while magnetic resonance imaging (MRI) is appropriate. Although MRI scanners are generally available in clinical settings, recumbent scanning does not …

A Longitudinal Analysis Of Morphological Shape Variation Of Spleen In Patients With Fontan Surgery, Varatharajan Nainamalai, Håvard Bjørke Jenssen, Mostafa Rezaeitaleshmahalleh, Djinaud Prophete, Jordan Gosnell, Sarah Khan, Marcus Haw, Jingfeng Jiang, Joseph Vettukattil

Michigan Tech Publications

Background: Splenic size serves as a surrogate biomarker for predicting portal vein hyper-tension and liver abnormalities in subjects with Fontan Associated Liver Disease (FALD). We analyze the long-term shape variation of the spleen in FALD subjects using morphological shape features of radiomic features. Methods: We used 154 (84 from computed tomography and 70 from magnetic resonance) image volumes obtained from 36 individuals who underwent stage 3 Fontan procedure and 145 computed tomography images from controls to assess splenomegaly. To understand the splenomegaly, thirteen shape features of the spleen over three 10-year intervals, and variations between controls and FALD subjects were …

Characterizing The Relationships Between Cranial Geometry, Brain Morphometry, And Brain Mechanical Properties Using Mr Imaging And Elastography, Jessica Restivo

Theses and Dissertations

Traumatic brain injury (TBI) is a global health concern, with over 69 million cases annually. TBI risk depends on subject-specific neuroanatomical variation, yet research often only considers generic finite element (FE) models, based on the geometry and material composition of a 50th percentile male head. Although highly accurate, subject-specific models require expensive magnetic resonance (MR) imaging, elastography, and time-consuming computational resources. There is a need to create subject-specific TBI models that account for subject-specific variations, without neuroimaging. This study aims to create mathematical models to predict brain morphometry (dimensions, volume) [Objective 1] and mechanical properties (shear stiffness, damping ratio, octahedral …

Average Biomechanical Responses Of The Human Brain Grouped By Age And Sex, Ahmed A. Alshareef, Aaron Carass, Yaun-Chiao Lu, Joy Mojumder, Alexa M. Diano, Olivia M. Bailey, Ruth J. Okamoto, Dzung L. Pham, Jerry L. Prince, Philip V. Bayly, Curtis L. Johnson

Faculty Publications

Traumatic brain injuries (TBIs) occur from rapid head motion that results in brain deformation. Computational models are typically used to estimate brain deformation to predict risk of injury and evaluate the effectiveness of safety countermeasures. The accuracy of these models relies on validation to experimental brain deformation data. In this study, we create the first group-average biomechanical responses of the brain, including structure, material properties, and deformation response, by age and sex from 157 subjects. Subjects were sorted intro three age groups—young, mid-age, and older—and by sex to create group-average neuroanatomy, material properties, and brain deformation response to non-injurious loading …

Automated Segmentation Of The Ulnar Nerve In Mri Using Deep Learning Techniques, Akhil Nagulapalli

Theses

Cubital Tunnel Syndrome (CuTS), a condition caused by compression of the ulnar nerve, results in numbness, tingling, pain, and even muscle atrophy, affecting fine motor skills and diminishing patient quality of life. Accurate diagnosis of CuTS is challenging, as current diagnostic methods—including clinical exams, nerve conduction studies, and unaided MRI—often lack the precision to reliably identify the nerve and detect compression in its early stages. Deep learning-based segmentation offers a promising solution, enabling precise and automated identification of nerve structures in MRI images, which could significantly improve diagnostic accuracy and support timely intervention.

A novel deep learning model for segmenting …

Stretching The Limits Of Mri—Stretchable And Modular Coil Array Using Conductive Thread Technology, Folk W. Narongrit, Thejas Vishnu Ramesh, Joseph V. Rispoli

Purdue University Libraries Open Access Publishing Fund

Objective: We propose a modular stretchable coil design using conductive threads and commercially available embroidery machines. The coil design increases customizability of coil arrays for individual patients and each body part. Methods: Eight rectangular coils were constructed with custom-fabricated stretchable tinsel copper threads incorporated onto textile. Tune, match, and detune circuits were incorporated on the coil. A hook-and-loop mechanism was used to attach and decouple the modular coils. Phantom and in vivo scans at various anatomical flexion angles were acquired to highlight performance, and a temperature test was performed to verify safety. Results: In vivo MRI experiments demonstrate high sensitivity …

Domain Adaptive Federated Learning For Multi-Institution Molecular Mutation Prediction And Bias Identification, W. Farzana, M. A. Witherow, I. Longoria, M. S. Sadique, A. Temtam, K. M. Iftekharuddin

Electrical & Computer Engineering Faculty Publications

Deep learning models have shown potential in medical image analysis tasks. However, training a generalized deep learning model requires huge amounts of patient data that is usually gathered from multiple institutions which may raise privacy concerns. Federated learning (FL) provides an alternative to sharing data across institutions. Nonetheless, FL is susceptible to a few challenges including inversion attacks on model weights, heterogenous data distributions, and bias. This study addresses heterogeneity and bias issues for multi-institution patient data by proposing domain adaptive FL modeling using several radiomics (volume, fractal, texture) features for O6-methylguanine-DNA methyltransferase (MGMT) classification across multiple institutions. The proposed …

Longitudinal Oxygen Imaging In 3d (Bio)Printed Models, Ryan Curtis O'Connell

Graduate Theses, Dissertations, and Problem Reports (ETD)

Electron paramagnetic resonance (EPR), and its molecular imaging modality, is a powerful tool to noninvasively map various biological and chemical markers within objects of interest. Reliable data acquisition is a major impeding factor for longitudinal hands-off measurements. Measurements are especially challenging in biomedical applications, as live objects are not static. Frequent changes occur that require constant fine recalibration of the EPR detection system, called the resonator. To enable longitudinal imaging, a technology permitting automatic digital control of resonator coupling, tuning, and EPR data acquisition was developed. Automation was achieved through the utilization of a microcontroller and digital peripheral components such …

Ultra-High Field Mri Methods For Precise Anatomical And Spectroscopic Measurements In The Brain And Application To Neurological And Neuropsychiatric Diseases, Judy Alper

Dissertations and Theses

Neurological and neuropsychiatric diseases and disorders are a major burden on society, impairing the health and functioning of millions of people every year. There is a need to define the biological bases of these diseases and identify potential biomarkers to improve diagnosis, monitoring, and treatment efficacy across multiple diseases.

Magnetic resonance imaging (MRI) is a noninvasive imaging technique which facilitates detection of brain lesions and visualization of the brain overall. However, limitations in contrast and resolution at clinical field strengths may hinder investigation of the underlying biological mechanisms of these diseases. Ultra-high field MRI scanners, such as those at 7-Tesla, …

Mechanical Design Of A Microwave Imaging Device For Breast Cancer Detection In Mri Scanners, Grace M. Player

Dartmouth College Master’s Theses

This project seeks to develop an updated version of a microwave imaging device for use in conjunction with breast MRI, improving upon existing technology and developing novel concepts for the device. It posits three primary redesign targets for updating the previous system: resizing the system height, making the device more iteration- friendly, and improving the overall manufacturability of the device by replacing custom components with commercially available alternatives. All three of these redesign targets are met in the new design, V2.0. The height is reduced by reducing antenna travel and height, embedding some components, and shortening the tank wall, resulting …

A Radiofrequency Coil To Facilitate Task-Based Fmri Of Awake Marmosets, Kyle Gilbert, Audrey Dureux, Azadeh Jafari, Alessandro Zanini, Peter Zeman, Ravi S. Menon, Stefan Everling

Robarts Imaging Publications

Background: The small common marmoset (Callithrix jacchus) is an ideal nonhuman primate for awake fMRI in ultra-high field small animal MRI scanners. However, it can often be challenging in task-based fMRI experiments to provide a robust stimulus within the MRI environment while using hardware (an RF coil and restraint system) that is compatible with awake imaging. New Method: Here we present an RF coil and restraint system that permits unimpeded access to an awake marmoset’s head subsequent to immobilization, thereby permitting the setup of peripheral devices and stimuli proximal to the head.

Results: As an example application, an …

Modeling Of Patient-Specific Periaortic Mechanics And Pulmonary Artery Hemodynamics Based On Phase-Contrast Magnetic Resonance Imaging Sequences., Johane H. Bracamonte

Theses and Dissertations

Inverse modeling in cardiovascular medicine is a collection of methodologies that can provide non-invasive patient-specific estimations of clinical risk factors using medical imaging as inputs. Its incorporation into clinical practice has the potential to improve diagnosis and treatment planning with low associated risks and costs.

Herein, three different phase contrast magnetic resonance imaging (MRI) modalities were implemented as input data, displacement encoding with stimulated echoes (DENSE MRI) applied, and time-resolved velocity encoding phase-contrast MRI, in 1D and 3D, applied to pulmonary artery (PA) hemodynamics.

A model to account for the effect of periaortic interactions due to static and dynamic structures …

Improving The Early Detection Of Cardiovascular Toxicity Secondary To Radiotherapy For Lung Cancer Via Patient-Specific Quantitative Magnetic Resonance Imaging, Alireza Omidi

Theses and Dissertations

Purpose: To assess the cardiopulmonary-induced dose variation on the left ventricle (LV) and evaluate the spatiotemporal evolution of cardiac/aortic function following radiotherapy (RT).

Methods: 8 lung cancer patients who were scheduled to receive RT were recruited for this study. Each patient underwent one 4D-CT at baseline. MRI scans including cine GRE, T1/T2, LGE, and 4D-flow were acquired at baseline, 3-months and 6-months post-RT to evaluate the cardiac/aortic function. Finally, image registration was used to assess the cardiopulmonary-induced dose variation on the LV.

Results: Mean RT-dose was minimum during inspiration and systole (at expiration). No significant differences were found in the …

Water Exchange Rate Across The Blood-Brain Barrier Is Associated With Csf Amyloid-Β 42 In Healthy Older Adults, Brian T. Gold, Xingfeng Shao, Tiffany L. Sudduth, Gregory A. Jicha, Donna M. Wilcock, Elayna R. Seago, Danny J. J. Wang

Sanders-Brown Center on Aging Faculty Publications

INTRODUCTION: We tested if water exchange across the blood-brain barrier (BBB), estimated with a noninvasive magnetic resonance imaging (MRI) technique, is associated with cerebrospinal fluid (CSF) biomarkers of Alzheimer's disease (AD) and neuropsychological function.

METHODS: Forty cognitively normal older adults (67–86 years old) were scanned with diffusion‐prepared, arterial spin labeling (DP‐ASL), which estimates water exchange rate across the BBB (k_w). Participants also underwent CSF draw and neuropsychological testing. Multiple linear regression models were run with kw as a predictor of CSF concentrations and neuropsychological scores.

RESULTS: In multiple brain regions, BBB kw was positively associated with CSF amyloid …

Improving Patient-Specific Assessments Of Regional Aortic Mechanics Via Quantitative Magnetic Resonance Imaging With Early Applications In Patients At Elevated Risk For Thoracic Aortopathy, Patrick A. Jones

Theses and Dissertations

Unstable aortic aneurysms and dissections are serious cardiovascular conditions associated with high mortality. The current gold standards for assessment of stability, however, rely on simple geometric measurements, like cross-sectional area or increased diameter between follow-up scans, and fail to incorporate information about underlying aortic mechanics. Displacement encoding with stimulated echoes (DENSE) magnetic resonance imaging (MRI) has been used previously to determine heterogeneous circumferential strain patterns in the aortas of healthy volunteers. Here, I introduce technical improvements to DENSE aortic analysis and early pilot application in patients at higher risk for the development of aortopathies. Modifications to the DENSE aortic postprocessing …

Cardiorespiratory Fitness Diminishes The Effects Of Age On White Matter Hyperintensity Volume, Nathan F. Johnson, Ahmed A. Bahrani, David K. Powell, Gregory A. Jicha, Brian T. Gold

Physical Therapy Faculty Publications

White matter hyperintensities (WMHs) are among the most commonly observed marker of cerebrovascular disease. Age is a key risk factor for WMH development. Cardiorespiratory fitness (CRF) is associated with increased vessel compliance, but it remains unknown if high CRF affects WMH volume. This study explored the effects of CRF on WMH volume in community-dwelling older adults. We further tested the possibility of an interaction between CRF and age on WMH volume. Participants were 76 adults between the ages of 59 and 77 (mean age = 65.36 years, SD = 3.92) who underwent a maximal graded exercise test and structural brain …

Neurobiological Markers For Remission And Persistence Of Childhood Attention-Deficit/Hyperactivity Disorder, Yuyang Luo

Dissertations

Attention-deficit/hyperactivity disorder (ADHD) is one of the most prevalent neurodevelopmental disorders in children. Symptoms of childhood ADHD persist into adulthood in around 65% of patients, which elevates the risk for a number of adverse outcomes, resulting in substantial individual and societal burden. A neurodevelopmental double dissociation model is proposed based on existing studies in which the early onset of childhood ADHD is suggested to associate with dysfunctional subcortical structures that remain static throughout the lifetime; while diminution of symptoms over development could link to optimal development of prefrontal cortex. Current existing studies only assess basic measures including regional brain activation …

Speckle-Noise Reduction In Knee Articular Cartilage Ultrasound Image Using Anisotropic Diffusion, Ali Muhammad Shoaib

Student Works (2020-2029)

Knee arthritis is the most common type of arthritis which effects the people and may cause severe pain to the patient and can lead to joint effusion. Ultrasound (US) imaging is an appropriate and consistent substitute for other imaging techniques like magnetic resonance imaging or X-rays in the investigation or screening of knee injury. Nevertheless, one of the major problems in US images which make the analysis of these images hard is the presence of speckle noise. For the reduction of speckle noise, the performance of the anisotropic method is found much better over other approaches. In removing the speckle …

Developmental And Sex Modulated Neurological Alterations In Autism Spectrum Disorder, Azeezat Azeez

Dissertations

Autism Spectrum Disorder (ASD) was first described in 1943 by Dr. Leo Kranner in a case study published in The Nervous Child. It is a neurodevelopment disorder, with a range of clinical symptoms. According to the Diagnostic and Statistical Manual of Mental Disorders (DSM-5), used by clinicians to diagnose mental disorders, a child needs to have persistent social deficits, language impairments, and repetitive behaviors, that cannot be explained by neurological damage or intellectual disability. It is known that children diagnosed with ASD are often are developmentally delayed therefore alterations in the typical developmental trajectory should be a major factor in …

Muscle Activation Via Mri: Comparison Of Techniques, Logan Thorneloe, Neal Bangerter

Journal of Undergraduate Research

Muscle functional magnetic resonance imaging (mfMRI) is a proven concept to non-invasively identify muscle activation1. Noninvasively identifying muscle activation can be used to diagnose metabolic muscle disease, identify and pinpoint muscular dysfunction, observe muscle deterioration in aging individuals, and help researchers better understand the biological foundation of musclechemistry2. Current proven methods of mfMRI include analyzing pre- and post-exercise T2-weighted images, T2 maps, and sodium images of muscle; however, there is considerable debate around the best of these techniques1-4. We tested these three imaging techniques to determine which has the greatest post-exercise shift in signal intensity.

Novel Calibrated Short Tr Recovery (Castrr) Method For Brain-Blood Partition Coefficient Correction Enhances Gray-White Matter Contrast In Blood Flow Measurements In Mice, Scott W. Thalman, David K. Powell, Ai-Ling Lin

Biomedical Engineering Faculty Publications

The goal of the study was to develop a novel, rapid Calibrated Short TR Recovery (CaSTRR) method to measure the brain-blood partition coefficient (BBPC) in mice. The BBPC is necessary for quantifying cerebral blood flow (CBF) using tracer-based techniques like arterial spin labeling (ASL), but previous techniques required prohibitively long acquisition times so a constant BBPC equal to 0.9 mL/g is typically used regardless of studied species, condition, or disease. An accelerated method of BBPC correction could improve regional specificity in CBF maps particularly in white matter. Male C57Bl/6N mice (n = 8) were scanned at 7T using CaSTRR …

Use Of Magnetic Resonance Image Registration To Estimate Displacement In The Human Earcanal Due To The Insertion Of In-Ear Devices, Simon Benacchio, Olivier Doutres, Arthur Varoquaux, Éric Wagnac, Arnaud Le Troter, Virginie Callot, Franck Sgard

Études primaires

In-ear devices are used in a wide range of applications for which the device's usability and/or efficiency is strongly related to comfort aspects that are influenced by the mechanical interaction between the device and the walls of the earcanal. Although the displacement of the earcanal walls due to the insertion of the device is an important characteristic of this interaction, existing studies on this subject are very limited. This paper proposes a method to estimate this displacement in vivo using a registration technique on magnetic resonance images. The amplitude, the location and the direction of the earcanal wall displacement are …

Review Of Methods For Intraoperative Margin Detection For Breast Conserving Surgery, Benjamin W. Maloney, David M. Mcclatchy, Brian W. Pogue, Keith D. Paulsen, Wendy A. Wells, Richard J. Barth

Dartmouth Scholarship

Breast conserving surgery (BCS) is an effective treatment for early-stage cancers as long as the margins of the resected tissue are free of disease according to consensus guidelines for patient management. However, 15% to 35% of patients undergo a second surgery since malignant cells are found close to or at the margins of the original resection specimen. This review highlights imaging approaches being investigated to reduce the rate of positive margins, and they are reviewed with the assumption that a new system would need high sensitivity near 95% and specificity near 85%. The problem appears to be twofold. The first …

Tissue Oxygen Saturation Predicts Response To Breast Cancer Neoadjuvant Chemotherapy Within 10 Days Of Treatment, Jeffrey M. Cochran, David R. Busch, Anais Leproux, Zheng Zhang, Thomas D. O'Sullivan, Albert E. Cerussi, Philip M. Carpenter, Rita S. Mehta, Darren Roblyer, Wei Yang, Keith D. Paulsen, Brian Pogue, Shudong Jiang, Peter A. Kaufman

Dartmouth Scholarship

Ideally, neoadjuvant chemotherapy (NAC) assessment should predict pathologic complete response (pCR), a surrogate clinical endpoint for 5-year survival, as early as possible during typical 3- to 6-month breast cancer treatments. We introduce and demonstrate an approach for predicting pCR within 10 days of initiating NAC. The method uses a bedside diffuse optical spectroscopic imaging (DOSI) technology and logistic regression modeling. Tumor and normal tissue physiological properties were measured longitudinally throughout the course of NAC in 33 patients enrolled in the American College of Radiology Imaging Network multicenter breast cancer DOSI trial (ACRIN-6691). An image analysis scheme, employing z-score normalization to …

Optimizing Filter-Probe Diffusion Weighting In The Rat Spinal Cord For Human Translation, Matthew D. Budde, Nathan P. Skinner, L. Tugan Muftuler, Brian D. Schmit, Shekar N. Kurpad

Biomedical Engineering Faculty Research and Publications

No abstract provided.

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 …

Diffusion Tensor Imaging Correlates With Short-Term Myelopathy Outcome In Patients With Cervical Spondylotic Myelopathy, Aditya Vedantam, Avinash Rao, Shekar N. Kurpad, Michael B. Jirjis, Gerald Eckardt, Brian D. Schmit, Marjorie C. Wang

Biomedical Engineering Faculty Research and Publications

Objective

To determine if spinal cord diffusion tensor imaging indexes correlate with short-term clinical outcome in patients undergoing elective cervical spine surgery for cervical spondylotic myelopathy (CSM).

Methods

A prospective consecutive cohort study was performed in patients undergoing elective cervical spine surgery for CSM. After obtaining informed consent, patients with CSM underwent preoperative T2-weighted magnetic resonance imaging and diffusion tensor imaging of the cervical spine. Fractional anisotropy (FA) values at the level of maximum cord compression and at the noncompressed C1-2 level were calculated on axial images. We recorded the modified Japanese Orthopaedic Association (mJOA) scale, Neck Disability Index, and …

Multi-Modality Magnetic Resonance Imaging In Typical And Atypical Developmental Human Brain, Minhui Ouyang

Bioengineering Dissertations - Archive

Human brain development is structurally and functionally a nonlinear process and even with the tremendous advancements in the field of neuroimaging based on Magnetic Resonance Imaging (MRI) several significant questions remain un-answered. Although brain change and adaption are part of a lifelong process, the earliest phases of maturation, especially from birth to early childhood, are perhaps the most dramatic and important. During this early developmental period, the structural and functional organization of the brain are continuously shaped by a combination of synaptogenesis, dendritic arborization, myelination and synaptic pruning. The current research aims to use more recently developed MRI techniques of …

Cardiovascular Magnetic Resonance Imaging-Based Computational Fluid Dynamics/Fluid-Structure Interaction Pilot Study To Detect Early Vascular Changes In Pediatric Patients With Type 1 Diabetes, Margaret M. Samyn, Ronak Jashwant Dholakia, Hongfeng Wang, Jennifer Co-Vu, Ke Yan, Michael E. Widlansky, John F. Ladisa Jr., Pippa Simpson, Ramin Alemzadeh

Biomedical Engineering Faculty Research and Publications

We hypothesized that pediatric patients with type 1 diabetes have cardiac magnetic resonance (CMR) detectable differences in thoracic aortic wall properties and hemodynamics leading to significant local differences in indices of wall shear stress, when compared with age-matched control subjects without diabetes. Pediatric patients with type 1 diabetes were recruited from Children’s Hospital of Wisconsin and compared with controls. All underwent morning CMR scanning, 4-limb blood pressure, brachial artery reactivity testing, and venipuncture. Patient-specific computational fluid dynamics modeling with fluid–structure interaction, based on CMR data, determined regional time-averaged wall shear stress (TAWSS) and oscillatory shear index (OSI). Twenty type 1 …