🎉 Latest News: Our paper on "Vision-Language Transformers in 3D MRI Synthesis" has been accepted at MICCAI 2026!
Frontier Medical AI Research

Transforming Healthcare through Medical Computer Vision & AI

At MedVis AI Lab, we build state-of-the-art multimodal vision models, 3D volumetric segmentation algorithms, and explainable AI systems to assist radiologists, pathologists, and clinicians worldwide.

5+ Publications
5 Active Projects
9 Researchers
4 Open Datasets
3D MRI Tumor Segmentation AI
Multimodal Vision-Language LLM
Gigapixel Digital Pathology Analysis
3D Ultrasound AI Guidance
Core Pillars

Key Research Focus Areas

Our multi-disciplinary team operates at the intersection of computer vision, deep learning theory, and clinical medicine.

Deep Learning

Deep Learning & Neural Networks

Advanced deep network architectures, vision transformers, self-supervised representation learning, and model optimization for medical intelligence.

Cardiovascular

Cardiovascular AI

Real-time echocardiography automated segmentation, 4D flow MRI analysis, and predictive AI models for cardiovascular diagnostics.

Computer Vision

Computer Vision

3D volumetric imaging, automated lesion segmentation, organ registration, and multimodal vision analysis for CT, MRI, and X-ray scans.

Pathology

Pathology Analysis

Gigapixel whole-slide tissue image analysis, cell nuclei segmentation, automated cancer grading, and digital biomarker profiling.

Data Mining

Medical Data Mining

Large-scale EHR analytics, clinical time-series sequence mining, multi-center longitudinal patient outcome prediction, and health insights.

Ethics & Security

AI Ethics & Security

Privacy-preserving federated learning, adversarial robustness, clinical safety verification, explainable AI (XAI), and algorithmic fairness.

Innovations & Field Work

Ongoing Research Projects

Cutting-edge medical AI initiatives currently underway at MedVis AI Laboratory.

Grant Funded ($1.8M) Cardiovascular AI

CardioVision-Net: Real-Time Echocardiogram Segmentation

Developing lightweight neural networks deployable on point-of-care cardiac ultrasound devices for low-resource clinics and emergency respons...

PyTorch Ultrasound Real-Time Inference
NIH Sponsored ($2.4M) 3D Computer Vision

NeuroSynth-3D: Synthetic Brain MRI Generation

Generative 3D diffusion models capable of producing privacy-preserving synthetic dataset extensions for rare neurodegenerative disease resea...

Diffusion Models 3D Volumetric MRI Synthetic Data
Industry Partnered Digital Pathology

PathoScan-AI: Gigapixel Histology Biomarker Profiling

Foundation vision transformer models trained on over 50,000 whole-slide biopsies for rapid automated cancer grading and margin profiling.

Vision Transformers Gigapixel WSI Digital Pathology
View All Active & Past Projects →
Peer-Reviewed Papers

Recent Publications & Papers

Our latest findings published in top-tier medical imaging journals and international AI research conferences.

Nature Medicine (2026)

Deep Learning for Automated Brain Tumor Segmentation in Multi-Parametric MRI

Md. Emon Shikder, Sarah Jenkins, Alan Turing

This paper presents a novel multi-parametric MRI segmentation model using vision transformers, achieving state-of-the-art Dice sco...

MICCAI 2026 (Oral) (2026)

OmniVision-3D: Self-Supervised 3D Vision Transformers for Zero-Shot Volumetric Tumor Detection

Dr. Sarah Chen, Alex Rivera, Prof. Michael Zhang, Dr. Elena...

We propose OmniVision-3D, a self-supervised foundation model trained on over 50,000 unannotated 3D CT/MRI scans for zero-shot volu...

arXiv Repository (2026)

Self-Supervised Whole Slide Image Analysis in Digital Pathology

Alan Turing, Md. Emon Shikder

Self-supervised contrastive learning paradigm designed specifically for gigapixel histology Whole Slide Images (WSI) in computatio...

Browse All Publications →
Our Minds

Meet Our Key Researchers

World-class computer scientists, biomedical engineers, and clinical collaborators working together.

Dr. Sarah Chen

Dr. Sarah Chen

Founder & Research Director

Leading research on self-supervised 3D medical vision transformers and multimodal clinical foundation models.

Prof. James Harrison, MD

Prof. James Harrison, MD

Clinical Advisory Chair

Senior Neuroradiologist overseeing clinical trial validation and diagnostic safety frameworks for MedVis AI mo...

Prof. Robert Kapoor, PhD

Prof. Robert Kapoor, PhD

AI Ethics & Strategy Advisor

Advising on privacy-preserving federated learning, algorithmic fairness, and HIPAA governance.

Prof. Michael Zhang

Prof. Michael Zhang

Head of Multimodal AI Division

Pioneering vision-language pre-training for automated DICOM radiology report generation.

View Full Team Directory →
Next-Gen Genomic & Medical AI

Shape the Future of Healthcare with Frontier Medical AI

Whether you are a clinical physician seeking diagnostic AI tools, a researcher looking for open datasets, or a prospective PhD student aiming to publish at MICCAI/CVPR — we welcome global collaboration.

Grant & NIH Funded Open Source Codebases Multi-Hospital Clinical Network