GreyNet
ItphyQuality checks at acquisition
Evaluates Grashey X-ray positioning and quality to request an immediate retake from the radiographer when needed, enabling quality checks before the patient leaves the imaging room.
Inha University · Digital Medicine
TMI-lab
Translational
Medical Intelligence
We develop AI to support clinical decisions and workflows.
Translation
From research
to clinical impact.
Coreline Soft · 2024
AVIEW NeuroCAD
Image-based triage for time-critical hemorrhage care
Analyzes suspected hemorrhage and its volume in brain CT to prioritize review. Image-based triage supports faster clinical decisions when timely treatment matters.
- Used in over 100 emergency departments
- MFDS Innovative Medical Device designation
A portfolio of translation
FlatNet
PromediusMore objective flatfoot assessment
Detects landmarks on weight-bearing lateral foot X-rays. A comparative study found lower landmark errors than an orthopedic surgeon, supporting more consistent measurements for flatfoot assessment.
Read the comparative studyProRetina
PromediusSegmentation with quality assessment
Uses Bayesian U-Net uncertainty to improve retinal vessel segmentation while assessing image quality, bringing the analysis and its reliability into the same model.
Image quality
Check image quality
before the patient leaves.
GreyNet detects landmarks in Grashey X-rays to check positioning and quality, requesting an immediate retake from the radiographer when needed. Its purpose is to connect acquisition and quality assurance in one workflow.
Read the studyOur mission
From information
to intelligence.
We aim to reduce delays in imaging and interpretation, anticipate surgical outcomes, and support evidence-based treatment choices through clinical workflows, digital twins, and precision medicine.
Clinical questions
Define a clinical question
Work with clinicians to identify research questions in measurement, interpretation, and information management.
Data & methods
Connect data and methods
Understand images, text, and biosignals, then design AI methods suited to the problem.
Clinical evaluation
Evaluate for use
Examine performance and errors, and assess utility on new data and within clinical workflows.
Research
Clinical workflow
The right insight, at the right moment.
We connect AI outputs to the next clinical action: prioritizing suspected hemorrhage, checking image quality at acquisition, and automating repeated measurements so clinicians can focus on decisions that matter.
From analysis to action
- Image acquisition
- AI analysis · quality check
- Priority review · retake request
Support clinical decisions and workflows
Research
Digital twins
Anticipate outcomes before surgery.
We study surgical digital twins that use preoperative images and clinical data to predict a patient’s postoperative state. Our goal is to compare treatment scenarios and build evidence for surgical planning and patient discussions.
Connect before and after surgery
- Preoperative images · clinical data
- Patient-specific digital twin
- Predicted postoperative state
Research toward planning and patient discussions
Research
Precision medicine
Evidence for each patient’s treatment.
We combine medical images, biosignals, and clinical information to study individual differences and treatment response. Quantitative measurements and uncertainty estimates help build evidence for evaluating treatment choices and outcomes.
Selected publications
Publications
Transforming large language models into medical specialists via knowledge injection
Deep learning-based assessment of coronary artery disease using curved-multiplanar reconstruction: comprehensive evaluation of stenosis, calcification, and plaque
Automated landmark detection and view positioning assessment of shoulder grashey view radiographs using cascade deep learning: A dual‐center validation study
No publications match your search.
Patents
Patents & applications
Device and method for classifying and segmenting ct image based on machine learning model
Method and apparatus for analyzing blood vessels based on machine learning model
Method for analyzing electrocardiogram signals using a deep learning model and device for analyzing electrocardiogram signals
KR102854968B1Granted patent
Device and method for classifying and segmenting ct image based on machine learning model
KR102787021B1Granted patent
Method and apparatus for analyzing blood vessels based on machine learning model
Earlier industrial research patents
KR102289952B1Granted patent
Device for ouputting protectsound, vehicle and method for controlling thereof
KR101814977B1Granted patent
Vehicle and controlling method thereof
People
People
Keewon Shin
Assistant Professor · PhD
Translational research brings advances in AI into clinical practice. His work connects medical imaging, biosignals, and multimodal AI with clinical workflows, surgical outcome prediction, and evidence-based treatment.
Education · Career & academic service
Education
- 2023 · PhD, Biomedical Engineering, University of Ulsan
- 2013 · MS, Mechanical Engineering, Hanyang University
- 2011 · BS, Mechanical Engineering, Hanyang University
Career & academic service
- 2025–present · Scientific Committee Member, Korean Society of Artificial Intelligence in Medicine
- 2024–present · Area/Program Chair, MICCAI
- 2026–present · Assistant Professor, Inha University College of Medicine
- 2025–2026 · Research Professor, University of Ulsan College of Medicine
- 2023–2025 · Research Professor, Korea University College of Medicine
- 2018–2023 · Researcher and Postdoctoral Fellow, Asan Medical Center
- 2013–2018 · Researcher, Hyundai Motor Company
Contact
Research collaboration
& inquiries
For medical AI collaboration and research inquiries, please contact us at the work email below.
- kevinkwshin@inha.ac.kr
- Office
- Room 318, 60th Anniversary Memorial Hall, Inha University