PDF Viewer

BUILDER'S SANDBOX

Build This Paper

Use an AI coding agent to implement this research.

OpenAI Codex
OpenAI CodexAI Agent

Lightweight coding agent in your terminal.

Claude Code
Claude CodeAI Agent

Agentic coding tool for terminal workflows.

AntiGravity IDE
AntiGravity IDEScaffolding

AI agent mindset installer and workflow scaffolder.

Cursor
CursorIDE

AI-first code editor built on VS Code.

VS Code
VS CodeIDE

Free, open-source editor by Microsoft.

MVP Investment

$9K - $12K
6-10 weeks
Engineering
$8,000
Cloud Hosting
$240
SaaS Stack
$300
Domain & Legal
$100

6mo ROI

2-4x

3yr ROI

10-20x

Lightweight AI tools can reach profitability quickly. At $500/mo average contract, 20 customers = $10K MRR by 6mo, 200+ by 3yr.

Talent Scout

M

Mahmut S. Gokmen

University of Kentucky

M

Moneera N. Haque

University of Kentucky

S

Steve W. Leung

University of Kentucky

C

Caroline N. Leach

University of Kentucky

Find Similar Experts

Medical experts on LinkedIn & GitHub

References (27)

[1]
AI Opportunistic Coronary Calcium Screening at Veterans Affairs Hospitals.
2025Raffi Hagopian, Timothy Strebel et al.
[2]
Performance of fully automated deep-learning-based coronary artery calcium scoring in ECG-gated calcium CT and non-gated low-dose chest CT
2025Sihwan Kim, Eun-Ah Park et al.
[3]
Lesion-specific coronary artery calcium score to predict stent underexpansion
2025Wentao Yang, K. Xu et al.
[4]
Artificial Intelligence in Coronary Artery Calcium Scoring Detection and Quantification
2024Khaled Abdelrahman, A. Shiyovich et al.
[5]
Fully automated coronary artery calcium quantification on electrocardiogram-gated non-contrast cardiac computed tomography using deep-learning with novel Heart-labelling method
2023D. Takahashi, S. Fujimoto et al.
[6]
Combating Coronary Calcium Scoring Bias for Non-gated CT by Semantic Learning on Gated CT
2023Jiajian Li, A. Li et al.
[7]
Accuracy of incidental visual coronary artery calcium assessment compared with dedicated coronary artery calcium scoring.
2023Viraj Raygor, Natalie Hoeting et al.
[8]
Vision Transformers Need Registers
2023Timothée Darcet, Maxime Oquab et al.
[9]
DINOv2: Learning Robust Visual Features without Supervision
2023M. Oquab, Timothée Darcet et al.
[10]
Heart Disease and Stroke Statistics—2023 Update: A Report From the American Heart Association
2023C. Tsao, A. Aday et al.
[11]
Fully automatic coronary calcium scoring in non-ECG-gated low-dose chest CT: comparison with ECG-gated cardiac CT
2022Y. J. Suh, Cherry Kim et al.
[12]
MONAI Label: A framework for AI-assisted Interactive Labeling of 3D Medical Images
2022A. Diaz-Pinto, Sachidanand Alle et al.
[13]
Accuracy of non-gated low-dose non-contrast chest CT with tin filtration for coronary artery calcium scoring
2022Ying Liu, Xuezhi Chen et al.
[14]
LeViT-UNet: Make Faster Encoders with Transformer for Medical Image Segmentation
2021Guoping Xu, Xingrong Wu et al.
[15]
Automated coronary calcium scoring using deep learning with multicenter external validation
2021David Eng, C. Chute et al.
[16]
Deep convolutional neural networks to predict cardiovascular risk from computed tomography
2021R. Zeleznik, B. Foldyna et al.
[17]
Automatic coronary calcium scoring in chest CT using a deep neural network in direct comparison with non-contrast cardiac CT: A validation study.
2020M. Assen, M. Assen et al.
[18]
Open Health Imaging Foundation Viewer: An Extensible Open-Source Framework for Building Web-Based Imaging Applications to Support Cancer Research
2020Erik Ziegler, T. Urban et al.
[19]
2019 ESC Guidelines for the diagnosis and management of chronic coronary syndromes.
2019J. Knuuti, William Wijns et al.
[20]
The Orthanc Ecosystem for Medical Imaging
2018S. Jodogne

Showing 20 of 27 references

Founder's Pitch

"AI-enhanced framework that generalizes coronary artery calcium scoring across different CT modalities for scalable cardiovascular screening."

Medical AIScore: 6View PDF ↗

Commercial Viability Breakdown

0-10 scale

High Potential

3/4 signals

7.5

Quick Build

4/4 signals

10

Series A Potential

3/4 signals

7.5

Sources used for this analysis

arXiv Paper

Full-text PDF analysis of the research paper

GitHub Repository

Code availability, stars, and contributor activity

Citation Network

Semantic Scholar citations and co-citation patterns

Community Predictions

Crowd-sourced unicorn probability assessments

Analysis model: GPT-4o · Last scored: 2/25/2026

🔭 Research Neighborhood

Generating constellation...

~3-8 seconds

Why It Matters

This research addresses a significant gap in cardiovascular risk screening by automating coronary artery calcium scoring in non-specialist settings. By enabling the use of non-gated CT scans, this method allows for more frequent and widespread screening without requiring additional imaging resources, thus optimizing healthcare resource utilization and potentially identifying at-risk patients sooner.

Product Angle

The framework could be productized as a cloud-based or on-premise software tool for healthcare providers, allowing integration with existing CT imaging devices and systems via industry-standard interfaces like OHIF and MONAI for seamless clinical deployment.

Disruption

This tool could replace or significantly augment current manual or semi-manual calcium scoring processes, which are often operator-dependent and time-consuming, thereby streamlining diagnosis workflows and increasing patient throughput.

Product Opportunity

The target is healthcare providers who want to improve cardiovascular disease risk assessment by leveraging CT imaging they already perform for other conditions. The market for cardiovascular diagnostics, especially in middle to large hospitals worldwide, is sizable, offering significant uptake potential.

Use Case Idea

An application for hospitals and clinics that incorporates the AI framework to process both gated and non-gated CT scans for automated coronary calcium scoring, enabling better cardiovascular risk assessment in routine clinical workflows.

Science

The framework uses a Vision Transformer model, CARD-ViT, pretrained on gated CT scan data to perform coronary artery calcium scoring. Through self-supervised learning with the DINO technique, it can generalize well from only gated CT training data to non-gated CT applications. This approach facilitates automated calcium detection and scoring without needing domain-specific annotations, overcoming significant challenges in cross-domain adaptation.

Method & Eval

The framework was evaluated using internal and external datasets. It achieved high segmentation and scoring accuracy on gated CT datasets, and demonstrated comparable performance to existing models trained specifically on non-gated datasets, proving the effectiveness of the cross-domain approach.

Caveats

Potential challenges include integration with various hospital IT systems, ensuring HIPAA compliance, and gaining trust among radiologists accustomed to established methods. False positives from improved models may also pose issues if not addressed effectively in clinical settings.

Author Intelligence

Mahmut S. Gokmen

University of Kentucky

Moneera N. Haque

University of Kentucky

Steve W. Leung

University of Kentucky

Caroline N. Leach

University of Kentucky

Seth Parker

University of Kentucky

Stephen B. Hobbs

University of Kentucky

Vincent L. Sorrell

University of Kentucky

W. Brent Seales

University of Kentucky

V. K. Cody Bumgardner

University of Kentucky