Analytical, Diagnostic and Therapeutic Techniques and Equipment Commons^™

Analysis Of The Influence Of Anthropometric Dimensions Of Postural Ergonomics Using Multiple Linear Regression, Gashbeen Faisal Najmaddin, Edrees Muhammed Tahir Harki

Al-Bahir

Ergonomics is the study of designing and arranging a workspace or product to optimize the “fit” between people and their work, ensuring safety, comfort, and efficiency. The scientific literature indicates that ergonomic perspectives on the workplace are connected to the anthropometrics of societies. This study primarily aims to create a model that integrates multiple predictive variables to estimate the target variable. Multiple linear regression analysis is used to identify how different anthropometric dimensions predict postural ergonomics during prolonged sitting. Based on the regression models’ results, the predicted can be calculated using user anthropometry and existing chair dimensions. Furthermore, the primary …

Bridging Data Gaps In Retinal Imaging: From Structural Domain Adaptation To Topology-Aware Synthesis, Gözde Merve Demirci

Dissertations, Theses, and Capstone Projects

Comprehensive visualization of the retina is essential for diagnosing and monitoring blinding diseases such as Diabetic Retinopathy and Retinopathy of Prematurity (ROP), where pathological changes often extend beyond a single field of view. Despite significant advances in automated retinal image analysis, clinical deployment remains limited by two fundamental data gaps: a structural learning gap, arising from scarce expert annotations and poor generalization across imaging domains, and a spatial coverage gap, caused by the difficulty of acquiring multi-view retinal images in fragile populations. Although these challenges are often addressed independently, this dissertation argues that they are tightly coupled: accurate, …

Development Of Ultrafast Protein Digestion And Standards Free Quantitation Methods For Mass Spectrometric Analysis, Praneeth Ivan Joel Fnu

Dissertations

A wide variety of biologically important molecules, such as enzymes, antibodies, hormones, transporters and receptors are proteins by composition and they play key roles in biological functions such as cellular regulation, communication, metabolism and physiological function. Protein dysfunctions and abnormalities are associated with numerous diseases, making proteins critical targets for understanding disease mechanisms and developing therapeutic interventions. Protein-based therapeutics such as monoclonal antibodies, hormones and vaccines gained popularity due to their high specificity, efficacy, and ability to treat complex diseases that are often difficult to address with small-molecule drugs.

Given the important role of proteins in a variety of biological …

Machine Learning For Functional Outcome Prediction After Vestibular Schwannoma Surgery: A Systematic Review And Diagnostic Test Accuracy Meta-Analysis, Shiva Nischal, Shaan Patel, Musa China, Kush Kale, Yi Hein Chai, Santosh Guru, William Muirhead, Patrick Grover

Department of Neurosurgery Faculty Papers

PURPOSE: Machine learning (ML) models have been increasingly applied to predict postoperative facial nerve dysfunction and hearing preservation after vestibular schwannoma (VS) surgery. However, reported performance varies substantially, and the overall diagnostic accuracy and clinical reliability of these models remain uncertain. We conducted a systematic review and diagnostic test accuracy meta-analysis to characterise the current state and methodological readiness of ML-based prediction of these outcomes.

METHODS: PubMed, Embase, and CENTRAL were searched from inception to February 2026. Studies evaluating ML-based prediction of facial nerve function or hearing preservation following VS surgery were included. Diagnostic performance metrics were pooled using random-effects …

Clinical Utility Of An Fda-Authorized Artificial Intelligence Imaging Platform In Interstitial Lung Disease Diagnosis, Arjun Prakash Tambe, Ryan Boente, Gautam George, Fayez Kheir, Omid Tahamtani Omran, Kavitha Selvan

Division of Pulmonary, Allergy, and Critical Care Medicine Faculty Papers

Background/Objectives: The diagnosis of interstitial lung disease (ILD) is challenging and frequently delayed. Clinically accessible and minimally invasive diagnostic tools are needed to expedite the diagnosis of ILD while minimizing risk to patients. Fibresolve is an imaging artificial intelligence (AI) tool recently approved by the Food and Drug Administration (FDA) for use in ILD diagnosis and made available to clinicians. The objective of this study was to describe its utility in clinical practice. Methods: We conducted a prospective, observational study of patients across the United States (US) in whom Fibresolve was utilized during routine clinical practice between July 2024 and …

Bridging The Gap In Science Research: Preparing Students For College- Level Research In The Sciences, Victoria Helwig, Yaoguang Li

UConn Library Presentations

Many first-year students enter college unprepared to fully engage with scientific literature and academic library resources. Drawing on experiences from academic librarians working with STEM students, this session explores common gaps in science research skills, including navigating databases, identifying scholarly sources, and understanding the structure of scientific literature. Participants will be introduced to practical strategies and classroom-ready activities to better prepare students for college-level research. Discussion questions: What science research skills do students struggle with most when entering college? How can high school instruction better support these skills? Where can librarians and educators collaborate to support student success?

Llm-As-A-Judge For Infection Prevention And Control And Antimicrobial Resistance Impact: Comparing Three Main Llms Vs. Human Experts' Assessment, Marcello Di Pumpo, Leonardo Villani, Maria Rosaria Gualano, Danilo Buonsenso, Francesca Raffaelli, Daniele Donà, Patrizia Laurenti, Vittorio Maio, Stefania Boccia, Walter Ricciardi

College of Population Health Faculty Papers

BACKGROUND: Large language models (LLMs) are increasingly used to generate health information, yet their reliability as evaluators remains unclear. This study investigated the feasibility of an LLM-as-a-judge methodology in the context of infection prevention and antimicrobial resistance (AMR), comparing automated ratings with human expert benchmarks.

METHODS: We performed a secondary analysis of an expert-annotated dataset of health messages. Three leading LLMs (ChatGPT, Claude, Gemini) independently evaluated the same messages using an adapted DISCERN tool across five domains: information reliability, quality, AMR impact, persuasiveness, and overall score. We utilized descriptive statistics, intra-rater reliability tests, and mixed-effects ordinal regression to analyze divergence …

(Re)Claiming Homeplace: Dance As Embodied Resistance & Healing For Health & Spatial Justice, Preeya G. Kannan

University Honors Theses

This thesis argues that dance functions as both an upstream public health intervention and a form of radical spatial resistance; creating healing, agency, and belonging among historically marginalized communities. Drawing on bell hooks' concept of homeplace, Jasbir Puar's assemblage theory, Nancy Krieger's eco-social theory, and Katherine McKittrick's Black geographies, I position the body as both an ecological and political landscape shaped by histories of colonialism, racial capitalism, displacement, and resilience.

Through this community-based participatory research study, Homeplace, I explore dance as a form of social prescription that centers liberation rather than pathology. Movement is often reduced in public health discourse …

Rehabvr: A Virtual Reality System For Upper-Body Orthopaedic Physical Therapy Rehabilitation, Winnie Brenda Wanjiru Waiya

Computer Science Senior Theses

Physical therapy is a central component of rehabilitation for musculoskeletal conditions, yet adherence to prescribed treatment remains persistently poor. Jack et al. identified pain, boredom, and insufficient feedback as key barriers to treatment adherence in physiotherapy outpatient settings,¹ and Rucinski et al. confirmed that non-adherence rates in orthopaedic populations remain between 50 and 70%, with patients who disengage facing elevated risk of reoperation, progressive functional decline, and poor clinical outcomes.² According to the World Health Organization, approximately 1.71 billion people globally live with musculoskeletal conditions,³ with shoulder pain specifically carrying a community prevalence ranging from 0.67 to 55.2% worldwide and …

Validation And Implementation Of Automated Planning Optimization In Utah Valley Hospital, Oluwatobi Adeniji

UNLV Theses, Dissertations, Professional Papers, and Capstones

The increasing complexity of modern radiotherapy demands planning workflows that are efficient, standardized, and dosimetrically robust across diverse disease sites. Knowledge-based planning (KBP) systems such as RapidPlan offer a data-driven approach to automate and improve treatment planning by learning geometric–dosimetric relationships from high-quality clinical plans. In this work, I am evaluating the performance, generalizability, and clinical applicability of vendor-provided RapidPlan models across seven anatomical sites: intracranial SRS, prostate SBRT, right and left lung SBRT, liver SBRT, head and neck, and glioblastoma. Subsequently, a complementary institution-specific SRS model tailored to single-isocenter multitarget workflows was created. Seventy retrospectively selected patients were replanned …

Evaluation Of The Effectiveness Of Antihypertensive Therapy Chosen Through Maternal Hemodynamic Profile Analysis, Margaret Weimer

Poster Presentations

In treatment of emergent hypertension, the American College of Obstetricians and Gynecologists (ACOG) recommends both oral labetalol and nifedipine, with no preference shown between the two. These medications have different mechanisms of action. Studies have suggested that consideration of hemodynamic profile may be an effective way to determine medication, but have not considered the Rule of 55, a simple calculation to predict hemodynamic profile.

Goals: 1. Determine if tailoring the antihypertensive to patient’s hemodynamic profile is associated with better control of blood pressure. 2. Determine if the Rule of 55 is an accurate method to determine hemodynamic profile.

Dementia Detection In Low-Resource Languages: Evaluating Translation-Assisted Transfer Learning For Multilingual Clinical Assessment, Kylar A. Deloach

Honors Theses

Alzheimer's disease (AD) is a growing global health concern, with millions of people affected worldwide and cases expected to rise significantly in the coming decades. Early detection is critical for patient treatment and care, and recent advances in natural language processing (NLP) have shown promise in identifying linguistic markers associated with AD. However, most existing work has focused on English, leaving speakers of other languages with limited access to such tools. This study investigates how effective AD detection models trained on English data are at transferring to Greek, a low-resource language with limited dementia-related speech data available. We propose a …

Optimization Of Pediatric Multidetector Ct Imaging Parameters Using A Machine Learning–Based Monte Carlo Simulation Model, Ali O. Masoud, Adithya Rajnaryanan, Khamis O. Amour, Ahmed M. Jusabani, Justin E Ngaile, Manoj Kumar, Mwingereza John Kumwenda Dr

Tanzania Journal of Science

This study utilized Monte Carlo (MC) simulations to optimize radiation doses in pediatric multidetector computed tomography (MDCT) head scans by analyzing key parameters like tube current (mA), tube voltage (kV), pitch, and slice thickness. The findings indicate that reducing tube current significantly lowers the Computed Tomography Dose Index (CTDIvol) and Dose Length Product (DLP), effectively minimizing patient radiation exposure. Higher pitch values (0.7–0.9) further reduced radiation by decreasing beam overlap, while using a thinner slice thickness (0.6 mm) improved dose efficiency. A comparison highlighted the effectiveness of optimization: simulated parameters kVp 100, mAs 81, pitch 0.98 yielded a CTDIvol of …

Organic Synthesis Of A Hydrazine Functionalized Ammonium Compound For Improved Capture Of Aldehyde Metabolites From Exhaled Breath, Po'iu N. Burgo

Undergraduate Theses

Breath analysis has emerged as a non-invasive and inexpensive way to screen for respiratory diseases. This technique involves measuring concentrations of specific metabolites found in exhaled breath that serve as a biomarkers for disease. A subclass of volatile organic compounds called α,β-Unsaturated aldehydes, products of the lipid peroxidation mechanism, are underrepresented as biomarkers of lung cancer. These have been found to have relatively increased concentrations in the exhaled breath of lung cancer patients compared to a healthy patient. One of the reasons that these metabolites have been underreported is that the techniques used to measure and characterized exhaled metabolites do …

Dermal: A Multi-Input Deep Learning Model For Improving Access To Dermatological Screening, Aubreye Freeman

ATU Scholars Symposium

According to the World Health Organization's press release on December 12, 2024, global healthcare spending is dropping significantly, leaving a large percentage of the world without proper healthcare. In an attempt to alleviate this problem, with respect to the field of dermatology, we created a deep learning model, Dermatology Enhanced by Recognition and Machine Aided Learning (DERMAL), to assist in diagnosing skin conditions. DERMAL was trained on a portion of the Google and Stanford Medicine's SCIN dataset, which has more than 10,000 images of various skin conditions. The 9 most common skin conditions of the dataset were selected as the …

Interview With Orca Award Winner David Hage, Unl Chemistry; Drug-Protein Interactions, Mark Griep, David Hage

UNL ORCA Interview Series

Prof. David Hage was awarded the ORCA in 2018. He was born in La Crosse, Wisconsin, and earned a bachelor’s in chemistry at the University of Wisconsin in La Crosse. Next, he earned a doctorate from Iowa State University and did postdoctoral work at the Mayo Clinic in Rochester, Minnesota. In 1989, he joined UNL as an assistant professor of chemistry and quickly rose through the ranks. He has won many awards and, for the past 13 years, has been the James Hewet University Professor of Chemistry. Allow me to share some remarkable facts about Dave before we get into …

Evolving Solutions For Red Blood Cell Preservation, Ali Alkafaji, Charles A. Elder, Mohammad Zaidi, Kavin Parthiv, Michael A. Menze

The Cardinal Edge

In emergencies such as natural disasters, armed conflicts, or during outer space missions, the availability of transfusable blood can mean the difference between life and death. Red blood cells (RBCs) must be stored at +4 ± 2 °C and have a shelf life of just 42 days, which makes maintaining a stable blood supply during adverse conditions extraordinarily challenging. This challenge was especially apparent during the COVID-19 pandemic when hospitals faced severe blood shortages. Freeze-drying, or lyophilization, offers a promising avenue to extend the shelf life of RBCs for transfusion during crises. However, a significant hurdle in dry preservation is …

An Ai Approach To Differentiating Lung Squamous Cell Carcinoma From Metastases Of Other Origins, Mark G Evans, Jennifer Ribeiro, Todd Maney, Anthony Helmstetter, Jennifer Johnson, Anthony Karnezis, Casey Bales, George Sledge, David Spetzler, Ari Vanderwalde, Matthew Oberley, Balazs Halmos, Hossein Borghaei, Farah Abdulla, David Bryant, Fred Hirsch, Hassan Ghani

Department of Medical Oncology Faculty Papers

IMPORTANCE: Distinguishing primary lung squamous cell carcinoma (SCC) from squamous metastases to the lung is a clinical challenge due to histopathologic similarities. Accurate diagnosis is essential to guide treatment decisions.

OBJECTIVE: To assess the utility of an artificial intelligence (AI) approach that includes evaluation of key orthogonal evidence in distinguishing primary lung SCCs from metastatic tumors of other tissue origins.

DESIGN, SETTING, AND PARTICIPANTS: This cross-sectional study used GPSai, a tissue-of-origin AI model run automatically on each sample submitted for molecular profiling, to flag potential misdiagnoses among research-eligible cases submitted as lung SCC. Molecularly profiled cases within the Caris Life …

Brain Computer Interfaces: Enhancing Low-Cost Eeg Performance Through Deep, Anwar Rassoul

Shelby Hall Graduate Research Forum Posters

The field of Brain Computer Interfacing (BCI) has traditionally been confined to clinical and research environments due to the high cost and complexity of medical-grade EEG systems. However, the emergence of low-cost hardware exemplified has catalyzed a shift toward accessible, portable BCI applications. While these devices lower the barrier to entry for developers and researchers, they often suffer from a lower signal-to-noise ratio (SNR). This increased noise makes it difficult to extract the clean neural signatures required for high-accuracy control, particularly when operating in non-shielded, real-world environments.

This research focuses on Steady-State Visually Evoked Potentials (SSVEP), a robust BCI paradigm …

Diagnostic Trends And Service Enhancements In Deaf Mental Health: A Longitudinal Analysis, Kent Schafer, Steve Hamerdinger, Frank Wu, Rie Sakai Bizmark, Charlene Crump

JADARA

A longitudinal study investigated mental health diagnostic trends and patterns among Deaf and Hearing individuals using a comprehensive dataset from Alabama Department of Mental Health spanning 2004-2024 (Deaf=4,547; Hearing=2,056,188). Chi-square analysis revealed significant proportional differences in diagnoses between the groups. Deaf individuals showed significantly higher proportions of psychotic (12.93% vs. 8.33% Hearing), mood (20.76% vs. 18.84% Hearing), and personality (0.58% vs. 0.43% Hearing) disorders. These findings suggest that increased access to specialized and competent mental health services for individuals who are Deaf, particularly following the increase of staffing patterns for the Office of Deaf Services in 2015,contributed to more accurate …

Novel R Shiny Tool For Survival Analysis With Time-Varying Covariate In Oncology Studies: Overcoming Biases And Enhancing Collaboration, Yimei Li, Yang Qiao, Fei Gao, Jordan Gauthier, Qiang Ed Zhang, Jenna Voutsinas, Wendy Leisenring, Ted Gooley, Corinne Summers, Alexandre Hirayama, Cameron Turtle, Rebecca Gardner, Jarcy Zee, Qian Vicky Wu

Wills Eye Hospital Papers

PURPOSE: Our study is motivated by evaluating the role of hematopoietic cell transplantation (HCT) after chimeric antigen receptor T-cell (CAR-T) therapy for ALL, a debated topic. Because patients may receive HCT at different times after CAR-T infusion or never, HCT post-CAR-T should be considered as a time-varying covariate (TVC).

METHODS: Standard Cox models and Kaplan-Meier (KM) curves (naïve method) assume that TVC status is known and fixed at baseline, which can yield biased estimates. Landmark analysis is a popular alternative but depends on a chosen landmark time. Time-dependent (TD) Cox model is better suited for TVC although visualizing survival curves …

Use Of Electrocardiograms To Identify Coronary Artery Disease: Cross-Validation Of An Artificial Intelligence Model, Michael Leasure, Indu Poornima, Adam Butchy, Utkars Jain, Devin Vasoya, Michael Warnick, Brent Williams, John Rehder, Prahlad Menon, Veronica A. Covalesky, Gary S. Mintz

Department of Medicine Faculty Papers

BACKGROUND: The current gold standard for the diagnosis of coronary artery disease (CAD) is invasive angiography; however, it is an invasive procedure. Therefore, we developed an artificial intelligence model designed to predict significant CAD from a resting digital 12-lead electrocardiogram (ECG).

OBJECTIVES: This retrospective study assessed the model's ability to predict clinically significant CAD in a patient population presenting for coronary angiography.

METHODS: From 2019 to 2021, 16,476 patients had a resting 12-lead digital ECG recorded within 90 days prior to coronary angiography. The artificial intelligence model was developed using 10-fold cross-validation methodology. Clinically significant disease was defined as angiographic …

Task-Optimized Brain Parcellations Reveal Latent Functional Organization For Enhanced Connectivity-Based Neuroimaging Classification, Andrew Hannum, Mario A. Lopez

Computer Science: Faculty Scholarship

Brain parcellation schemes are fundamental to neuroimaging, yet general-purpose atlases may obscure the specific functional architecture relevant to a given cognitive task or clinical condition. This reflects a growing consensus that the “optimal” brain map is context-dependent. Here, we introduce a novel framework that validates this principle by generating task-optimized human brain parcellation maps directly from supervised learning objectives. Our method defines functional parcels by grouping brain regions based on the similarity of their contributions to a classifier's decision boundary for a specific goal (e.g., cognitive state decoding or clinical group separation). This approach prioritizes a region's discriminative role over …

Identifying Relevant Covariates In Rna-Seq Analysis By Pseudo-Variable Augmentation, Yet Nguyen, Dan Nettleton

Mathematics & Statistics Faculty Publications

RNA-sequencing (RNA-seq) technology allows for the identification of differentially expressed genes, which are genes whose mean transcript abundance levels vary across conditions. In practice, RNA-seq datasets often include covariates that are of primary interest in addition to a set of covariates that are subject to selection. Some of these covariates may be relevant to gene expression levels, while others may be irrelevant. Ignoring relevant covariates or attempting to adjust for the effect of irrelevant covariates can compromise the identification of differentially expressed genes. To address this issue, we propose a variable selection method that uses pseudo-variables to control the expected …

Utilizing Machine Learning Techniques For Computer-Aided Covid-19 Screening Based On Clinical Data, Honglun Xu, Andrews T. Anum, Michael Pokojovy, Sreenath Chalil Madathil, Yuxin Wen, Md Fashiar Rahman, Tzu-Liang (Bill) Tseng, Scott Moen, Eric Walser

Mathematics & Statistics Faculty Publications

The COVID-19 pandemic has highlighted the importance of rapid clinical decision-making to facilitate the efficient usage of healthcare resources. Over the past decade, machine learning (ML) has caused a tectonic shift in healthcare, empowering data-driven prediction and decision-making. Recent research demonstrates how ML was used to respond to the COVID-19 pandemic. This paper puts forth new computer-aided COVID-19 disease screening techniques using six classes of ML algorithms (including penalized logistic regression, random forest, artificial neural networks, and support vector machines) and evaluates their performance when applied to a real-world clinical dataset containing patients’ demographic information and vital indices (such as …

Ai-Assisted Surface-Enhanced Raman Spectroscopy For Cardiovascular Diagnostics: From Plasmonic Materials To Clinical Translation, Anju Joshi, Gymama Slaughter

Center for Bioelectronics Publications

Raman spectroscopy (SERS) has emerged as a powerful analytical technique, offering molecular fingerprint specificity and ultrasensitive detection of cardiac biomarkers. Recent advances in plasmonic nanostructures, surface functionalization strategies, and flexible sensing platforms have significantly improved the analytical performance of SERS-based biosensors. In parallel, the integration of artificial intelligence (AI) and machine learning has enabled robust interpretation of complex spectral datasets, facilitating automated biomarker classification and improved diagnostic accuracy in heterogeneous biological environments. Despite these advances, the field remains fragmented, with limited integration between nanomaterial design, biomarker selection, and data-driven analysis, and persistent challenges related to reproducibility, standardization, and clinical validation. …

Mechanical-Medical Convergence In Heart Failure: Artificial Intelligence, Finite-Element Modeling, And 3d Printing For Diagnosis And Prognosis, Quazi Noor E. Sabrina, Quazi Md Zobaer Shah, Quazi Noor E. Sohela, Md Mahabub Hasan Mousum, Md. Moyeen Uddin Chisty, Quazi Md. Akbar Shah

Mechanical & Aerospace Engineering Faculty Publications

Heart failure remains a leading cause of global morbidity and mortality, yet routine clinical indices often miss the regional biomechanical disturbances that drive progression and shape treatment response. This State-of-the-Art review examines how finite-element (FE) modeling, additive manufacturing, and artificial intelligence (AI) are converging to improve the diagnosis, phenotyping, procedural planning, and prognostic assessment of heart failure (HF). Although these technologies have matured in structural heart disease and transcatheter intervention research, their greatest translational potential may lie in HF, where patient-specific ventricular remodeling, myocardial stress–strain heterogeneity, valve-ventricular coupling, and device-tissue interaction are incompletely captured by conventional clinical indices. We synthesize …

Consensus And Controversies Of International Guidelines For The Diagnosis, Surveillance, And Management Of Fetal Growth Restriction: An Updated Comparison, Daniele Diane Mascio, Suneet P. Chauhan, Tullio Ghi, Asma Khalil, Juliana G. Martins, Sara Sorrenti, Tamara Stampalija, Fabrizio Zullo, Francesc Figueras

Department of Obstetrics & Gynecology Faculty Publications

OBJECTIVE: To compare areas of consensus and disagreements across contemporary international and national guidelines on the diagnosis, surveillance, and management of fetal growth restriction (FGR).

DATA SOURCES: Electronic searches of MEDLINE from database inception up to March 2026 using MeSH terms and keywords related to FGR and guidelines. STUDY ELIGIBILITY CRITERIA: Critical, structured comparison of national or international guidelines on FGR published since 2010. Final inclusion required unanimous agreement from all authors.

STUDY APPRAISAL AND SYNTHESIS METHODS: Pre-specified extraction across domains: definition; prediction/prevention; surveillance tools and frequency; delivery timing and mode; and labor induction methods. Dual data …

Improving Medical Diagnostics With Vision-Language Models: Convex Hull-Based Uncertainty Analysis, Ferhat Ozgur Catak, Murat Kuzlu, Taylor Patrick, Michel Audette

Engineering Technology Faculty Publications

In recent years, vision-language models (VLMs) have been applied to various fields, including healthcare, education, finance, and manufacturing, with remarkable performance. However, concerns remain regarding VLMs' consistency and uncertainty, particularly in critical applications such as healthcare, which demand a high level of trust and reliability. This paper proposes a novel approach to evaluate uncertainty in VLMs' responses using a convex hull approach on a healthcare application for visual question answering (VQA). For any VLM, temperature refers to a sampling parameter used in probabilistic generation, which controls the randomness of the model's output. The LLM-CXR model is selected as the medical …

Maxgrnet: A Multi-Axis Vision Transformer With Improved Generalization For Eye Disease Classification Using Explainable Ai With Insertion-Deletion Operations On Fundus Images, Md Mehedi Hasan Santo, Fuyad Hasan Bhoyan, Fuad Ibne Jashim Farhad, Fahmid Al Farid, Sovon Chakraborty, Md Humaion Kabir Mehedi, Jia Uddin, Hezerul Bin Abdul Karim

Computer Science Faculty Publications

Eye diseases, including diabetic retinopathy (DR), glaucoma, and cataracts, represent a major global health concern and can lead to severe visual impairment or blindness if not identified in a timely manner. This study proposes a novel eye disease classification framework based on a multi-axis vision transformer (MaxViT) applied to color fundus images with Explainable Artificial Intelligence (XAI) techniques to enhance model transparency. The proposed architecture integrates transformer-based attention mechanisms with Global Response Normalization (GRN)-based multi-layer perceptron (MLP) layers to capture complex spatial and contextual relationships within fundus images effectively. The model was evaluated on a publicly available eye disease classification …