Biomedical Commons^™

Explainable Machine Learning For Biomedical Diagnostics: Optical Imaging And Eeg Signal Analysis, Fozia Rajbdad

LSU Doctoral Dissertations

The growing convenience of complex biomedical data begins new roads for better disease detection and functional identification via artificial intelligence (AI). Nevertheless, conventional analysis methods often rely on basic metrics that drop sensitive biotic differences, and various AI systems are difficult to infer, limiting their clinical reliability and practical use. There is a growing need for explainable, physiologically relevant computational models that can extract key biomarkers from diverse biomedical data sources. This dissertation addresses this problem by obtaining explainable machine learning and deep learning procedures for studying biomedical signals and optical imaging data.

This dissertation is divided into two parts; …

Polymer Microstructures For Advanced Biomanufacturing, Tongyao Wu

LSU Doctoral Dissertations

With the continued growth of the biopharmaceutical industry, the demand for scalable, robust, and resource-efficient platforms for large-scale mammalian cell culture is amplified. Recent developments in microfluidic technology, such as precise control of the microenvironment, showed the potential to improve the performance of cell culture systems. However, constrained by scalability and operational efficiency, applying such approaches to large-scale cell culture and biopharmaceutical production presents challenges. This dissertation addresses these challenges through three independent but conceptually related technological developments. First, a roll-to-roll (R2R) fabrication process was developed for the scalable production of hollow microcarriers (HMCs). HMCs provide three-dimensional microenvironments suitable for …

Exploring Longitudinal Stability Of Spatiotemporal Sequential Patterns By Means Of Autoencoder Schemes For Eeg Based Personal Identification, Muhammed E. Oztemel

LSU Doctoral Dissertations

Robust personal identification remains a critical and challenging task in the digital era. Electroencephalography (EEG) offers a unique biometric modality that captures individual brain dynamics through complex neural signals. This dissertation proposes autoencoder (AE) based feature extraction and subject identification through these features. EEG recordings are first transformed into topographic maps to represent spatial brain activity. Consecutive topomaps are then concatenated to capture temporal transitions across frames. Convolutional autoencoders (CAEs) are used to learn spatial and temporal patterns, while domain-adaptive AEs are designed to model evoked potential based responses. Additionally, self-attention mechanism is incorporated to enhance feature representation. To analyze …

Deep Learning Applications For Predictive Modeling In Cancer Therapy And Enzyme Encoding, Mengmeng Liu

LSU Doctoral Dissertations

Predictive modeling has revolutionized computational biology and molecular bioinformatics, enabling significant advancements in cancer therapy and functional enzyme characterization. Despite considerable progress, significant challenges remain in accurately predicting combinational cancer therapies and systematically representing enzyme functions for computational applications. Traditional methods struggle with capturing the complex interactions between drugs and biological networks, as well as representing hierarchical relationships within enzyme classifications. This dissertation addresses these limitations by developing advanced deep learning models tailored to enhance predictive performance in both domains.

First, a data augmentation strategy is introduced to improve anticancer drug synergy prediction by generating pharmacologically relevant drug pairs based …

Improving Cellphone-Based Bio-Imaging Technique For Fluorescence Detection, Erteza T. Efaz

LSU Master's Theses

The research presented in this thesis focuses on the design, development, and evaluation of a fluorescence detection system. The system is implemented primarily as an Android application, Auto Camera, which leverages smartphone cameras to capture and analyze fluorescent images. The application provides a user-friendly interface with some configurable features like exposure time, ISO speed, and storage limit; as well as defining detection thresholds and setting acquisition intervals. This study begins with the architectural framework of the Android application, which is written in Java using Android Studio. The API compatibility is set to version 33, and users are prompted to grant …

Novel Platforms For Large-Scale Adherent Culture Of Mammalian Cells, Ashkan Yekrangsafakar

LSU Doctoral Dissertations

With recent advances in biotechnology, there is a strong and urgent need for robust platforms to culture mammalian cells on a large scale to produce biopharmaceuticals. To this end, various bioreactors have been developed over the past decades, but their capacity and efficiency are often limited by insufficient mass transfer rate and excessive shear stress. In this work, multiple novel bioreactors for the large-scale adherent culture of anchorage-dependent cells were developed.

Hollow MicroCarriers (HMC) was developed as an alternative solution for the microcarrier-based culture system in a stirred-tank bioreactor. In the conventional microcarrier technique, cells are exposed to the harmful …

Design And Fabrication Of A Low-Cost, Portable, Battery-Operated Surface Enhanced Raman Scattering (Sers) Optical Device, Blessing Adewumi

LSU Doctoral Dissertations

Raman Spectroscopy is a time-honored, non-invasive method for analyzing and identifying the molecular composition of materials. However, unenhanced Raman Spectroscopy has extremely low sensitivity which limits its sensing capability. SERS brings rough nano-metallic surfaces in contact with the material molecules to enormously enhance the Raman signals.

The sensitivity of SERS can be exploited in probe applications where the spectrometer needs to be brought near the specimen. For example, a long optical fiber coupled to a SERS device can be used to characterize and identify easy-to-reach cancerous tissues in organisms. Unfortunately, background signals in a long fiber can easily mask any …

Error Prevention In Sensors And Sensor Systems, Pedro J. Chacon Dominguez

LSU Doctoral Dissertations

Achievements in all fields of engineering and fabrication methods have led towards optimization and integration of multiple sensing devices into a concise system. These advances have caused significant innovation in various commercial, industrial, and research efforts. Integrations of subsystems have important applications for sensor systems in particular. The need for reporting and real time awareness of a device’s condition and surroundings have led to sensor systems being implemented in a wide variety of fields. From environmental sensors for agriculture, to object characterization and biomedical sensing, the application for sensor systems has impacted all modern facets of innovation. With these innovations, …

Indocyanine-Green-Assisted Near-Infrared Dental Fluorescence Imaging To Detect Common Dental Diseases, As Compared With Dental X-Ray, Yoshita Viraj Holamoge

LSU Master's Theses

Oral health is indicative of a person’s overall health. Even with advances in medical science, dental diseases are very much prevalent in our society. Dental imaging techniques help in the early detection of these dental diseases and eventually avoids the risk of poor oral health as well as medical expenses. Current dental imaging techniques rely mostly on X-ray imaging whose ionizing property is a concern amongst the population. Near-infrared spectrum is known to have tissue penetration property and they belong to the non-ionizing part of the electromagnetic spectrum. This study utilized a contrast agent assisted near-infrared imaging for common dental …

Graph Information Processing For Artificial Intelligence, Limeng Pu

LSU Doctoral Dissertations

In the last decade, techniques for artificial intelligence (AI) has advanced tremendously, which lead to solutions to many problems that have long-troubled us. Such examples include image/video recognition, speech recognition, and 3D scenario recognition. As the tool become more and more powerful, we started to explore data types that have never been handled in an AI fashion. Graph is undoubtedly the first one that comes to mind. Many important real-life data is or can be represented as graphs or networks: social networks, communication networks, protein-protein interaction networks, molecular structures, etc. Yet very little attention has been devoted to the study …

Developing An Optomechanical Approach For Characterizing Mechanical Properties Of Single Adherent Cells, Ali Mehrnezhad

LSU Doctoral Dissertations

Mechanical properties of a cell reflect its biological and pathological conditions including cellular disorders and fundamental cellular processes such as cell division and differentiation. There have been active research efforts to develop high-throughput platforms to mechanically characterize single cells. Yet, many of these research efforts are focused on suspended cells and use a flow-through configuration. Therefore, adherent cells are detached prior to the characterization, which seriously perturbs the cellular conditions. Also, methods for adherent cells are limited in their throughput.

My study is aimed to fill the technical gap in the field of single cell analysis, which is a high-throughput …

Design And Optimization Of An Ionizing-Radiation-Free Dental Imaging Scheme By Near Infrared Fluorescence, Thomas Hartzler

LSU Master's Theses

There is a global need for access to oral health care. Proper oral health care is necessary for physiological and psychological health, as well as social and economic issues. Major oral diseases that must be screened include caries, cracked teeth, and impacted molars. These diseases are screened and diagnosed using a variety of medical imaging methods, computed tomography (CT) X-ray being the most popular and efficient method. The challenges in screening with X-ray technology include financial and time cost as well as health risk, including radiation exposure induced cancer (REIC). This thesis summarizes research to explore the possibility of overcoming …

Hyperspectral Imaging For Characterizing Single Plasmonic Nanostructure And Single-Cell Analysis, Nishir Sanatkumar Mehta

LSU Master's Theses

Orientation of plasmonic nanostructures is an important feature in many nanoscale applications such as photovoltaics, catalyst, biosensors DNA interactions, protein detections, hotspot of surface-enhanced Raman spectroscopy (SERS), and fluorescence resonant energy transfer (FRET) experiments. Silver nanocubes with significant spectral signatures between 400-700 nm are observed in this experimental research. Whereas study of single cells will enable the analysis of cell-to-cell variations within a heterogeneous population. These variations are important for further analysis and understanding of disease propagation, drug development, stem cell differentiation, embryos development, and how cells respond to each other and their environment. Adipose-derived mesenchymal stem cells possess the …

Image Processing Applications In Real Life: 2d Fragmented Image And Document Reassembly And Frequency Division Multiplexed Imaging, Houman Kamran Habibkhani

LSU Doctoral Dissertations

In this era of modern technology, image processing is one the most studied disciplines of signal processing and its applications can be found in every aspect of our daily life. In this work three main applications for image processing has been studied.

In chapter 1, frequency division multiplexed imaging (FDMI), a novel idea in the field of computational photography, has been introduced. Using FDMI, multiple images are captured simultaneously in a single shot and can later be extracted from the multiplexed image. This is achieved by spatially modulating the images so that they are placed at different locations in the …

Hierarchical Fusion Based Deep Learning Framework For Lung Nodule Classification, Kazim Sekeroglu

LSU Doctoral Dissertations

Lung cancer is the leading cancer type that causes the mortality in both men and women. Computer aided detection (CAD) and diagnosis systems can play a very important role for helping the physicians in cancer treatments. This dissertation proposes a CAD framework that utilizes a hierarchical fusion based deep learning model for detection of nodules from the stacks of 2D images. In the proposed hierarchical approach, a decision is made at each level individually employing the decisions from the previous level. Further, individual decisions are computed for several perspectives of a volume of interest (VOI). This study explores three different …