A5002688306- Ocular Infections and Treatments
- Ocular Diseases and Behçet’s Syndrome
- Glaucoma and retinal disorders
- Legionella and Acanthamoeba research
- Ocular Oncology and Treatments
- Speech and Audio Processing
- Retinal Diseases and Treatments
- Advanced Image and Video Retrieval Techniques
- Corneal Surgery and Treatments
- Human Mobility and Location-Based Analysis
- Energy Load and Power Forecasting
- Music and Audio Processing
- Indoor and Outdoor Localization Technologies
- Speech Recognition and Synthesis
- Retinal Imaging and Analysis
- Ocular Surface and Contact Lens
- Energy Efficient Wireless Sensor Networks
- Wireless Networks and Protocols
- Electricity Theft Detection Techniques
- Retinal and Optic Conditions
- Corneal surgery and disorders
University of Tennessee Health Science Center
2024-2025
Shahid Beheshti University
2020-2023
To develop an artificial intelligence (AI) model to diagnose Acanthamoeba keratitis (AK) based on in vivo confocal microscopy (IVCM) images extracted from the Heidelberg Retinal Tomograph 3 (HRT 3).
Abstract Infectious keratitis (IK) is a major cause of corneal opacity. IK can be caused by variety microorganisms. Typically, fungal ulcers carry the worst prognosis. Fungal cases subdivided into filamentous and yeasts, which shows fundamental differences. Delays in diagnosis or initiation treatment increase risk ocular complications. Currently, mainly based on slit-lamp examination scrapings. Notably, these diagnostic methods have their drawbacks, including experience-dependency, tissue...
This study aimed to evaluate the performance of three large language models (LLMs), namely ChatGPT-3.5, ChatGPT-4o (o1 Preview), and Google Gemini, in producing patient education materials (PEMs) improving readability online PEMs on childhood myopia. LLM-generated responses were assessed using prompts. Prompt A requested "Write educational material myopia." B added a modifier specifying "a sixth-grade reading level FKGL (Flesch-Kincaid Grade Level) formula." C rewrite existing FKGL. Reponses...
Abstract Retinoblastoma is a rare form of cancer that predominantly affects young children as the primary intraocular malignancy. Studies conducted in developed and some developing countries have revealed early detection can successfully cure over 90% with retinoblastoma. An unusual white reflection pupil most common presenting symptom. Depending on tumor size, shape, location, medical experts may opt for different approaches treatments, results varying significantly due to high reliance...
Machine learning can be used to identify risk factors associated with graft rejection after corneal transplantation for keratoconus. The study included all keratoconus eyes that underwent primary from 1994 2021. Data relating the recipient, donor, surgery, and postoperative course might occurrence of a reaction were compiled. This five supervised algorithms including artificial neural network, support vector machine, gradient boosting, extra trees classifier, random survival forests select...
Numerous studies have investigated automatic speech recognition tasks, such as content-based recognition, using machine learning techniques, deep learning. In general, each sample contains four main human-based attributes: i.e., content, emotion, gender, and speaker identity. Among them, the content has lowest correlation with other three attributes. However, to classify samples concerning attribute, model ignores existence of unrelated This study shows that information on these non-content...
Human activity recognition (HAR) based on Wi-Fi signals has attracted significant attention due to its convenience and the availability of infrastructures sensors. Channel State Information (CSI) measures how propagate through environment. However, many scenarios applications have insufficient training data constraints such as cost, time, or resources. This poses a challenge for achieving high accuracy levels with machine learning techniques. In this study, multiple deep models HAR were...
ABSTRACT Purpose To assess the colocalization of ellipsoid zone (EZ) disruption with nonperfusion in choriocapillaris (CC), retinal superficial capillary plexus (SCP), and deep (DCP) diabetic patients using en face optical coherence tomography (OCT) OCT angiography (OCTA). Methods Macular OCTA scans (3 × 3 mm) 41 retinopathy were obtained an RTVue XR Avanti instrument. After correcting shadow artifacts, EZ integrity was assessed slab Gaussian mixture model clustering method compared...
Abstract Retinoblastoma is a rare type of cancer that can appear in young children as the most common primary intraocular malignancy. Studies developed and some developing countries have shown more than 90% with retinoblastoma been successfully cured thanks to early detections. The presenting sign an unusual white reflection pupil. Medical experts may choose different approaches treatments for retinoblastoma, based on size, shape location tumors. Given high dependence process prior...