Invest in the future of healthcare innovation and manufacturing

AI transforms ocular disorders diagnostics to personalize treatment at the BIOTRANSPORT SYSTEMS DEVELOPMENTS

About The Website
At the forefront of healthcare innovation, Biotransport Systems Developments leads groundbreaking research in personalized medicine. Utilizing advanced and robust AI/ML models, we decode disease patterns, extending insights into ocular diseases, cardiovascular disorders, mental health, Alzheimer's, and cancer, shaping a future where data-driven approaches revolutionize healthcare with unparalleled impact.
Our expert insights will keep you informed about new AI-driven manufacturing models. Explore the forefront of biotransport systems developments with us today.
Our Extensive Biomedical Database
Our models are trained on over 100,000 biomedical images—including fundus images, MRI, OCT, OCT-A, PET, cardiovascular scans, and B-scan ultrasonography—from a diverse population encompassing all ages, races, genders, and health conditions. This diversity enables our models to achieve, on average, 93% prediction accuracy, ensuring reliable and precise outcomes.

A diverse and abundant database is key to maintaining the exceptional accuracy and reliability of our AI models.

Products

Modeling Ocular Phenomena

Transforming Intravitreal Drug Delivery with Deep Learning

Our innovative Physics-Informed Neural Network (PINN) framework accurately predicts the transport of drugs within the vitreous humor by integrating advanced neural network architectures with the physics of intravitreal fluid dynamics.

Glaucoma Detection Through Multi-Modal Integration of Retinal Images and Clinical Biomarkers

We developed a hybrid fusion model integrating Vision Transformers and ResNet50 with clinical biomarker analysis to enhance glaucoma detection accuracy up to 99.4%. This innovative approach combines deep learning with clinical data to provide a comprehensive, highly accurate diagnostic tool, significantly improving early detection and management of glaucoma.

Treatment Plans with AI-Driven Medical Protocols

We utilize advanced AI to create personalized medical protocols, optimizing treatment plans by analyzing patient data and clinical research. 1. Tailored protocol design for individualized treatment plans that enhance patient outcomes. 2. Innovative, data-driven protocols for healthcare professionals that improve standard practices. 3. Comprehensive clinical protocol development to ensure consistency and quality in the treatment pipeline. 4. Advanced data-driven pharmacokinetics protocols to streamline drug development processes.

Products

Modeling Beyond the Eyes

Cardiovascular Screening

We utilize advanced deep learning techniques to revolutionize non-invasive cardiovascular disease prediction through the examination of vascular biomarkers from different ocular regions, including conjunctival and retinal fundus images. Relevant learning approaches adopted with attention-based UNet architectures integrated with a pretrained encoder gave us precision and recall rates above 85% on RFI datasets and above 75% precision with 80% recall on conjunctival image analyses. Furthermore, we are exploring few-shot segmentation with self-supervised transformer architectures to improve adaptability in cases with limited data access, which is a common challenge in this area. The above segmentation lays down a solid basis for morphological assessment and subsequent biomarker extraction, which would be further utilized to connect ocular and cardiovascular biomarkers to evaluate the comprehensive risk of CVD.

Alzheimer’s

Our advanced product pipeline for improving Alzheimer's disease detection combines the power of computer vision and biomedical innovation. Utilizing Optical Coherence Tomography scans, our platform is built on the EfficientNetB6 model, trained on a comprehensive dataset of nearly 84,000 images across categories such as CNV, DRUSEN, DME, and Normal. Achieving an accuracy of 97% on test data, it surpasses traditional models like ResNet50 and sets a new benchmark in precision diagnostics. Designed for scalability and future growth, our platform enables optic nerve segmentation and the tracking of retinal layer changes. This innovation opens new possibilities for early detection and monitoring of neurodegenerative conditions, empowering clinicians with deeper insights to improve patient outcomes.

Mental Health

Utilizing deep learning techniques, we aim to predict major mental health disorders, including Schizophrenia, Conduct Disorder, and Autism. The ABCD study dataset serves as a foundation, integrating advanced methodologies like neuroimaging and genomic analysis for comprehensive model training. The interdisciplinary approach encourages collaboration across diverse fields, with a primary objective of advancing early diagnosis and personalized treatment through deep learning. Additionally, a commitment to transparency is demonstrated by providing an open-source pre-trained model, with anticipated future applications in MRI-based diagnosis to enhance overall diagnostic accuracy.

Projects

AI Assistant for Visually Impaired People

We will develop multiple smart phone applications to gain accessibility for visually impaired people.

Customized Ocular Software Solutions

At Biotransport Systems Developments, we specialize in developing customized ocular software solutions tailored to the unique needs of clinics. Our software enhances operational efficiency by streamlining workflows and reducing inefficiencies.

Multi-modal Image Processing and Analysis

Our Multi-Modal Image Processing and Analysis platform provides key insights into disease mechanisms and accelerates drug development by analyzing diverse imaging data. It empowers clinicians and researchers to develop more targeted and effective treatments. 1. Developing new biomarkers. 2. Feature enhancing for image database creation. 3. Highlight key pathologies on imaging data.

Postvitreal Detachment (PVD)

At Biotransport Systems Developments, we will evaluate the factors for high-risk patients in PVD (retinal tear). We will develop ML/DL methods to identify and determine pathological features in vitreo-retinal disorders to evaluate the quality of training datasets and simultaneously provide diagnoses for PVD status and the necessity of further examination and/or treatment. Such algorithms would be crucially important in predicting PVD occurrence and progression, so that timely and adequate treatment can be instituted.

Iridology: Big Scale Disease Detection

Harnessing advanced AI and image processing, Biotransport Systems Developments transforms iridology into a scalable diagnostic tool for early disease detection. Our platform enables non-invasive, accurate, and cost-effective healthcare solutions to enhance patient outcomes.

Dry Eye

This innovative work aims to revolutionize the diagnosis of dry eye syndrome by developing a cutting-edge method that effectively distinguishes healthy eyes from those affected by dryness by focusing on critical biomarkers such as tear break-up time, tear meniscus height, and meibomian gland structure. This way we can detect subtle structural differences that are often overlooked. The integration of DINOv2 embeddings with ALPNet unlocks the potential for few-shot segmentation, enhancing feature extraction and leading to accurate identification of dry eye disease.

AI in Manufacturing

Smart Injection Molding

To reduce the human intervention in the gate design process, a new optimization program is designed to place multiple molding gates complex compoenent surface while minimizing the shrinkage and warpage. The main procedure of the analysis include: 1) using Poisson disk sampling (PDS) to preselect candidate gate locations automatically within the suitable gating region specified by designers; 2) using a space-filling initialization strategy and efficient global optimization to find the optimal gate locations. In the present setting, the molding gate design problem is formalized as a discrete optimization problem. The PDS is employed to construct the discrete solution space and EGO is used to efficiently search through a large solution space for the best design.

Data Quality Assessment

A novel software with state of the art analytics are developed to evaluate the data suitability from the aspects of detectability assessment, diagnosability assessment, and prognosability assessment. The software provide both visualization tools and quantitative metrics to assess the data suitability for AI application development. New assessment procedures and algorithms are established by using a series of similarity metrics between data vectors or data distribution. The effectiveness of the methodology is demonstrated by using real-world examples about the ball screw degradation and boring tool degradation.

Big Data Visualization

Clustering the factory-wide (life-cycle) inspection data is of critical importance for practitioners to understand the subclusters of product defects, recognize novel clusters or anomalies, and develop fast reactions to quality issues. This analytic tool utilizes vision transformer with multi-head attention to convert product images of different sizes into condensed feature vectors for efficient clustering. Then, the Topological Data Analysis (TDA), which is widely used in biomedical applications, is employed to visualize the data clusters and identify the anomalies. The TDA yields a topological representation of high-dimensional big data as well as its local clusters by creating a graph that shows nodes corresponding to the clusters within the data.

CONSULTING
Consulting services include: 
Product design
Manufacturing
Initial coding for products proof-of-concept
Medical imaging analysis
Drug delivery analysis
Drug repurposing
Disease development/patient medical history analysis

In these areas:
Bio-medicine 
Bio-technologies
Pharmaceutical technologies
Clinical Medicine

Team

Anita Penkova

CEO and Founder

Dr. Penkova's focus is on developing patient data-driven algorithms to derive patient-specific physiological information from extensive imaging data, ultimately reducing diagnostic and therapeutic errors and advancing personalized care. These efforts involve extracting valuable information from inner surface eye imaging to diagnose non-ocular conditions such as diabetes, cardiovascular disorders, and mental illness. Our developed codes/software also includes the development of therapeutic drugs for glaucoma patients, which are informed by experimentation and modeling of glaucoma-related fluid transport. My expertise encompasses ML, DL, computer vision, ocular fluid dynamics and transport, oxygen transport processes in the eye, the effect of shear flow on protein clustering and aggregation, and studies on glaucoma-related fluid transport.

Xiaodong Jia

Co-Founder

Dr. Xiaodong Jia’s research focuses on developing advanced analytical solutions, including advanced sensing, monitoring, and advanced data analytics for maintenance and service innovations in next-generation industry systems. His research works have been successfully implemented in a broad range of applications, including semiconductor manufacturing processes, high-precision optical lens manufacturing, Traumatic Brain Injury (TBI) prognosis, high- precision linear motion equipment, wind turbines, among others. To date, Dr. Xiaodong Jia has successfully published 60+ peer-reviewed research articles, delivered 20+ research projects sponsored by various industry companies and government agencies, and maintained close collaborations with 30+ industry companies around the globe.

Rishikesh Sivakumar

Partner

Rishikesh Sivakumar is a ML Engineer specializing in computer vision and deep learning for medical diagnostics. His pioneering work includes developing a hybrid model that combines Vision Transformers and CNNs to detect glaucoma with 99.4% accuracy, using both retinal images and clinical biomarkers. Published in the "Engineering Applications of Artificial Intelligence" journal, his research enhances early glaucoma detection and he is actively exploring other methodologies for diagnosing diabetic retinopathy (DR) and other medical conditions, offering a significant stride towards non-invasive and precise medical diagnostics.

Qilong Pan

Partner

Qilong Pan specializes in machine learning engineering and software development, with expertise in ocular health diagnostics and predictive analytics. His current research involves developing innovative ocular ultrasound analytics tools aimed at constructing detailed vitreous liquefaction maps, integrated with advanced Physics-Informed Neural Networks (PINNs) for accurate prediction of intravitreal drug flow dynamics. Additionally, Qilong successfully developed an advanced U-Net-based neural network capable of diagnosing diabetes from ocular images with accuracy exceeding 95%. Beyond his research contributions, he actively collaborates on software development projects, transforming cutting-edge research findings into practical healthcare products.

Share Your Eye Images
Your eye imaging data could make a real difference. By sharing your OCT scans, fundus images, ultrasound data, and more, you can help us to develop highly comprehensive predictive algorithms for early screening and treating eye disorders. 

We ensure your privacy, and contributions can be completely anonymous, though including basic information like your medical history, age, and gender is strongly encouraged.

Please click on the button below and use the contact form to upload your eye images.
Join Us in Advancing Healthcare Innovation
We invite medical professionals, hospitals, and health workers to partner with us. Your collaboration will help drive advancements in healthcare technology, ultimately benefiting patients worldwide.
Invest in Us
 Join us in shaping healthcare innovation through strategic sponsorship, unlocking transformative potential. Let's shape the future of healthcare together.

Contact

*