Biomedical Engineering and Bioengineering Commons^™

Can We Explain Machine Learning-Based Prediction For Rupture Status Assessments Of Intracranial Aneurysms?, Nan Mu, M. Rezaeitaleshmahalleh, Z. Lyu, M. Wang, J. Tang, C. M. Strother, J. J. Gemmete, A. S. Pandey, J. Jiang

Michigan Tech Publications, Part 1

Although applying machine learning (ML) algorithms to rupture status assessment of intracranial aneurysms (IA) has yielded promising results, the opaqueness of some ML methods has limited their clinical translation. We presented the first explainability comparison of six commonly used ML algorithms: multivariate logistic regression (LR), support vector machine (SVM), random forest (RF), extreme gradient boosting (XGBoost), multi-layer perceptron neural network (MLPNN), and Bayesian additive regression trees (BART). A total of 112 IAs with known rupture status were selected for this study. The ML-based classification used two anatomical features, nine hemodynamic parameters, and thirteen morphologic variables. We utilized permutation feature importance, …

Finite Element Modeling Of Meniscal Tears Using Continuum Damage Mechanics And Digital Image Correlation, Derek Q. Nesbitt, Dylan E. Burruel, Bradley S. Henderson, Trevor J. Lujan

Mechanical and Biomedical Engineering Faculty Publications and Presentations

Meniscal tears are a common, painful, and debilitating knee injury with limited treatment options. Computational models that predict meniscal tears may help advance injury prevention and repair, but first these models must be validated using experimental data. Here we simulated meniscal tears with finite element analysis using continuum damage mechanics (CDM) in a transversely isotropic hyperelastic material. Finite element models were built to recreate the coupon geometry and loading conditions of forty uniaxial tensile experiments of human meniscus that were pulled to failure either parallel or perpendicular to the preferred fiber orientation. Two damage criteria were evaluated for all experiments: …

Efficient Scopeformer: Towards Scalable And Rich Feature Extraction For Intracranial Hemorrhage Detection Using Hybrid Convolution And Vision Transformer Networks, Yassine Barhoumi

Theses and Dissertations

The field of medical imaging has seen significant advancements through the use of artificial intelligence (AI) techniques. The success of deep learning models in this area has led to the need for further research. This study aims to explore the use of various deep learning algorithms and emerging modeling techniques to improve training paradigms in medical imaging. Convolutional neural networks (CNNs) are the go-to architecture for computer vision problems, but they have limitations in mapping long-term dependencies within images. To address these limitations, the study explores the use of techniques such as global average pooling and self-attention mechanisms. Additionally, the …

Impact Of Adipose-Derived Stem Cells On Aortic Tensile Strength In A Model Of Abdominal Aortic Aneurysm, Keshav Kooragayala, Johanna Lou, Vaishali Krishnadoss, Brian Zilberman, Nicholas Deleo, Olga Ostrovsky, Ping Zhang, Iman Noshadi, Spencer Brown, Jeffrey P. Carpenter

Henry M. Rowan College of Engineering Departmental Research

Introduction: Abdominal Aortic Aneurysm (AAA) is a highly morbid condition and is the 11th leading cause of death in the United States. Treatment options are limited to operative interventions, with minimal non-operative options. Prior literature has demonstrated a benefit to the use of mesenchymal stem cells (MSCs) in attenuating AAA formation. We demonstrate the utility of MSCs in treating AAA in swine, focusing on the mechanical and structural characteristics of aortic tissue after treatment. Methods: 16 Yorkshire pigs underwent retroperitoneal exposure of the infrarenal aorta, with subsequent induction of AAA with peri-adventitial elastase and collagenase. A 1 × 4 cm …

Self-Healing Properties Of Augmented Injectable Hydrogels Over Time, Connor Castro, Zachary R. Brown, Erik Brewer

Henry M. Rowan College of Engineering Departmental Research

Injectable polymers offer great benefits compared to other types of implants; however, they tend to suffer from increased mechanical wear and may need a replacement implant to restore these mechanical properties. The purpose of this experiment is to investigate an injectable hydrogel's self-healing ability to augment itself to a previously molded implant. This was accomplished by performing a tensile strength test to examine potential diminishing mechanical properties with increasing time, as well as dye penetration tests to examine the formation of interfacial bonds between healed areas of hydrogels. There were several time points in between injections that were explored, from …

Molecular And Cellular Level Characterization Of Cytoskeletal Mechanics Using A Quartz Crystal Microbalance, Emily M. Kerivan, Lyle Tobin, Mihir Basil, Dana N. Reinemann

Faculty and Student Publications

A quartz crystal microbalance (QCM) is an instrument that has the ability to measure nanogram-level changes in mass on a quartz sensor and is traditionally used to probe surface interactions and assembly kinetics of synthetic systems. The addition of dissipation monitoring (QCM-D) facilitates the study of viscoelastic systems, such as those relevant to molecular and cellular mechanics. Due to real-time recording of frequency and dissipation changes and single protein-level precision, the QCM-D is effective in interrogating the viscoelastic properties of cell surfaces and in vitro cellular components. However, few studies focus on the application of this instrument to cytoskeletal systems, …

Raman Spectroscopy - An Analytical Tool For Biologics, Cindy Mayorga, Shreya Milind Athalye, Mohit Verma

Graduate Industrial Research Symposium

Raman Spectroscopy (RS) is a non-invasive technique that analyses biomolecules qualitatively and quantitatively. Raman spectroscopy measures the inelastic scattering of light due to molecular vibrations. It can be applied to liquid, solid, or semi-solid forms of the biological sample reducing the sample preparation measures. The minimal sample preparation and non-invasive nature of Raman Spectroscopy can be applied in developing a Process analytical technology (PAT) tool and as a diagnostic tool. We demonstrated qualitative and quantitative measurements of biologics with Raman spectroscopy through our previous studies. Our results indicate that RS distinguishes various Gram-positive and Gram-negative bacteria, fungi, and a mixture …

Sea-Phages Course-Based Undergraduate Research Experience For Creating A Biotechnology Workforce Development Pipeline, Daphne Fauber, Kari Clase, Carol Weaver

Graduate Industrial Research Symposium

Purdue University has been a member of the SEA-PHAGES (Science Education Alliance-Phage Hunters Advancing Genomics and Evolutionary Science) program since 2011. This program, created in conjunction with the Howard Hughes Medical Institute (HHMI), facilitates undergraduate curriculum for the authentic discovery of novel bacteriophages within the classroom. Since joining the program, undergraduates at Purdue have harnessed wet lab and bioinformatics principles to contribute over 200 previously uncharacterized bacteriophages and 25 novel genomes to the wider scientific literature. The SEA-PHAGES classes at Purdue have resulted in tangible professional deliverables for students through conference presentations and publications. Student outcomes also include transferable skills …

The Next-Gen Crop Nutrient Stress Identification With High-Precision Sensing Technology In Digital Agriculture, Zhihang Song, Ziling Chen, Xing Wei, Jian Jin

Graduate Industrial Research Symposium

Crop yields are facing significant losses from nutrient deficiencies. Over-fertilizing also has negative economic and environmental impacts. It is challenging to optimize fertilizing without an accurate diagnosis. Recently, plant phenotyping has demonstrated outstanding capabilities in estimating crop traits. As one of the leading technologies, LeafSpec, provides high-quality crop image data for improving phenotyping quality. In this study, novel algorithms are developed for LeafSpec to identify crop nutrient deficiencies more accurately. Combined with UAV system, this technology will bring growers a robust solution for fertilizing diagnosis and scientific crop management.

Dendrimer And Dendrimer Gel-Derived Drug Delivery Systems: Breaking Bottlenecks Of Topical Administration Of Glaucoma Medications, Juan Wang, Boxuan Li, Uday B. Kompella, Hu Yang

Chemical and Biochemical Engineering Faculty Research & Creative Works

Due to high structural flexibility, multidrug carrying capability, and tunable size, dendrimers have been used as suitable carriers for ophthalmic drug delivery. Drug molecules can be either encapsulated or chemically coupled to dendrimers. the nanoscopic size, spheroidal shape, and cationic surface of Poly amidoamine (PAMAM) dendrimers promote their interaction with the cornea and result in prolonged precorneal retention. Dendrimers could be further cross-linked to produce three-dimensional hydrogel networks or dendrimer hydrogels (DH). the properties of the DH can be readily adjusted to maintain both fluidity and adhesiveness, making them suitable for developing topical ocular drug formulations. Micro-/nano- sized DHs, that …

Hypoxic Incubator Control System, Marina Zellers, Jennifer Rojas, Derek Tran

Biomedical Engineering

This paper describes the functionality of the current Hypoxic Incubator, a project started by BMED graduate students Simone Helfrich and Makenzie Jones, with the objective being to redesign the device to address potential areas of improvement. The hypoxic incubator has been designed to allow for the control of the O₂, CO₂, and N₂ levels such that researchers can grow and study cell culture in hypoxic conditions; however, its efficacy and efficiency are limited by the fact that it often overshoots the desired setpoints for O₂ and CO₂ in addition to being difficult to …

Postpartum Hemorrhage Detection Device, Kaitlyn Bailey, Adrian Diaz, Alcides Caballero

Biomedical Engineering

During a cesarean section, blood loss greater than 1000 mL is classified as a hemorrhage. Quantified blood loss methods are used to detect hemorrhage, however existing methods are inaccurate and time consuming. Our proposed device is inserted vaginally during a cesarean section to collect and quantify blood lost via the cervix during and after the procedure. The device also applies light suction to the uterus, which can aid in uterus collapse and decrease the risk of postpartum hemorrhage.

Biomaterials Redesign Of Microvascular Anastomotic Coupler, Nick Glatter, Sophie Jackson, Samuel Leingang

Biomedical Engineering

The key factors in the redesign of this part include the use of biomaterials, the redesign of the part geometry to include these biomaterials, and the proposition of production scale manufacturing methods suitable for these redesigns. The choice of biodegradable material was guided by previous literature, during which we found the PLGA polymer used in similar predicate devices with a biodegradability timeline similar to our goals. The model of coupler serving as the inspiration for the redesign utilizes two very strong but bioinert materials, polyethylene, and stainless steel. These high strength materials can withstand much greater forces than the biodegradable …

Gait Analysis Device For Elderly Fall Prediction, Ryan Hahn, Claudia Miller, Evan Yakligian

Biomedical Engineering

This document serves to outline the design process and final design for our project to address elderly independent living in collaboration with Apple. Included in this document is necessary academic literature of current fall risk assessments and descriptions of the current market of wearable gait analysis devices. Based on this research and data, we then outline a plan for design, manufacturing, prototyping, and testing a device to fulfill the original prompt given by our sponsors: create a device that will increase the ability of an aging loved one to live at home safely. This device is a wearable that collects …

Development Of Fibroblast/Endothelial Cell-Seeded Collagen Scaffolds For In Vitro Prevascularization, Daniela S. Masson-Meyers, Fahimeh Tabatabaei, Lane Steinhaus, Jeffrey M. Toth, Lobat Tayebi

Biomedical Engineering Faculty Research and Publications

The development of vascularized scaffolds remains one of the major challenges in tissue engineering, and co-culturing with endothelial cells is known as one of the possible approaches for this purpose. In this approach, optimization of cell culture conditions, scaffolds, and fabrication techniques is needed to develop tissue equivalents that will enable in vitro formation of a capillary network. Prevascularized equivalents will be more physiologically comparable to the native tissues and potentially prevent insufficient vascularization after implantation. This study aimed to culture human umbilical vein endothelial cells (HUVECs), alone or in co-culture with fibroblasts, on collagen scaffolds prepared by simple fabrication …

Prediction Of Persistent Post-Traumatic Headache With Long Short-Term Memory Networks, Todd C. Campo

Theses and Dissertations

Military members in combat situations are at a high risk for experiencing a Traumatic Brain Injury (TBI), often leaving them with Post-Traumatic Headache (PTH). There is currently a poor understanding of what factors predict if a patient will endure acute (short-term) PTH or Persistent PTH (PPTH). The Concussion Assessment, Research, and Education (CARE) Consortium dataset contains a variety of pre-and-post-injury concussion assessments taken by NCAA athletes and service academy cadets between 2014 and 2018. Participants in this study (n = 1769) suffered a TBI. Using this longitudinal data, three models were constructed: an LSTM model using the raw assessment scores, …

Analytical Methods For Determining Connectivity Leakage In Collaboration With Meissner Filtration Products, Ennis Cuhadaroglu, Finn Mccarthy, Alvin Ng

Biomedical Engineering

The scope of our project involved choosing existing testing procedures and determining a viable sample size to determine an accurate leakage rate of single-use system connections (SUS). Another goal was to assess the effects of gamma irradiation on the material integrity of the hose barb to tubing connections.

Our key customer requirements included: being able to determine an overall leakage rate and making a repeatable testing process. The importance of these requirements was determined through our house of quality and Pugh charts. To achieve the requirements, we tested the leakage in low-pressure and high-pressure scenarios with a large enough sample …

A Biochemical Necroptosis Model Explains Cell-Type-Specific Responses To Cell Death Cues, Geena V. Ildefonso, Marie Oliver Metzig, Alexander Hoffmann, Leonard A. Harris, Carlos F. Lopez

Biomedical Engineering Faculty Publications and Presentations

Necroptosis is a form of regulated cell death associated with degenerative disorders, autoimmune and inflammatory diseases, and cancer. To better understand the biochemical mechanisms regulating necroptosis, we constructed a detailed computational model of tumor necrosis factor-induced necroptosis based on known molecular interactions from the literature. Intracellular protein levels, used as model inputs, were quantified using label-free mass spectrometry, and the model was calibrated using Bayesian parameter inference to experimental protein time course data from a well-established necroptosis-executing cell line. The calibrated model reproduced the dynamics of phosphorylated mixed lineage kinase domain-like protein, an established necroptosis reporter. A subsequent dynamical systems …

Early Introduction Of 3d Modeling Modules Promotes The Development Of Simulation Skills In Downstream Biomedical Engineering Curricula, Mary S. Jia, Raj R. Rao, Mostafa Elsaadany

Biomedical Engineering Faculty Publications and Presentations

Background

Recent advancements in additive manufacturing have made 3D design a desirable skill in combating the historically slow development of biomedical products. Due to the broad applicability of additive manufacturing to biomedical engineering, 3D design and 3D printing are attractive educational tools for biomedical engineering students. However, due to the multidisciplinary nature of biomedical engineering, finding a suitable spot in the curriculum to teach students basic and application-based skills for 3D manufacturing is difficult. Furthermore, prior training in fundamental 3D design skills may be needed to support the use of application-based supplementary content.

Results

We designed a SolidWorks Simulations toolkit …

Split And Join: An Efficient Approach For Simulating Stapled Intestinal Anastomosis In Virtual Reality, Di Qi, Suvranu De

Engineering Faculty Articles and Research

Colorectal cancer is a life-threatening disease. It is the second leading cause of cancer-related deaths in the United States. Stapled anastomosis is a rapid treatment for colorectal cancer and other intestinal diseases and has become an integral part of routine surgical practice. However, to the best of our knowledge, there is no existing work simulating intestinal anastomosis that often involves sophisticated soft tissue manipulations such as cutting and stitching. In this paper, for the first time, we propose a novel split and join approach to simulate a side-to-side stapled intestinal anastomosis in virtual reality. We mimic the intestine model using …