A Patient-Specific Pulmonary Arterial Tree Digital Twin to Extract Pulmonary Embolism Biomarkers

2026-05-27 · Source: Takara TLDR - Daily AI Papers · Field: Health & Wellbeing — Clinical Care & Medical Practice, Medical Devices & Health Technology, Health & Medical Research · Depth: Advanced, medium

Summary

A new automated pipeline models a patient-specific pulmonary arterial tree as a digital twin to extract image-based biomarkers for pulmonary embolism (PE) characterization. This pipeline utilizes AI-generated binary masks of arteries, emboli, lungs, and lobes to create a directed graph representation of the arterial structure. It automatically calculates established severity scores, such as Qanadli and Mastora, and derives local artery-level features including morphological information, hierarchical position, clot volume, and resulting obstruction. Additionally, it provides global patient-level biomarkers like total embolic volume distribution by lobes and hierarchical levels. Validation against an existing pipeline, anatomical expectations, and manual severity score calculations demonstrated strong agreement, supporting its potential for rapid, precise assessment of thrombotic burden and spatial clot distribution in PE diagnosis.

Key takeaway

For clinical radiologists or emergency physicians assessing pulmonary embolism severity, this automated digital twin pipeline offers a rapid, precise alternative to time-consuming manual calculations and potentially unavailable blood biomarkers. You should consider integrating such AI-powered tools to streamline risk stratification and enhance diagnostic accuracy. This approach can improve patient management in acute cardiovascular syndrome cases by providing immediate, detailed information on thrombotic burden and spatial clot distribution.

Key insights

Automated digital twins of pulmonary arteries can rapidly quantify PE severity and clot distribution.

Principles

• Image-based biomarkers enhance PE risk stratification.
• Digital twins enable comprehensive anatomical and pathological modeling.
• Automated severity scores improve clinical efficiency.

Method

The pipeline uses AI-generated binary masks to construct a directed graph digital twin of the pulmonary arterial tree, then extracts local and global image-based biomarkers, including automated Qanadli and Mastora scores.

In practice

• Integrate AI-driven digital twins for PE diagnosis.
• Automate Qanadli and Mastora score calculations.
• Characterize clot distribution by lobe and artery level.

Topics

• Pulmonary Embolism
• Digital Twins
• Image-based Biomarkers
• AI in Radiology
• Risk Stratification
• CT Pulmonary Angiography

Best for: Computer Vision Engineer, Research Scientist, AI Scientist, Domain Expert

Related on AIssential

• Dual-Modal Lung Cancer AI: Interpretable Radiology and Microscopy with Clinical Risk Integration — Integrating CT radiology and H&E microscopy with clinical data significantly enhances lung cancer diagnosis and interpretability.
• Digital Twins as Synthetic Controls in Single-Arm Trials — Digital twins enhance single-arm trials by providing robust, efficient synthetic controls via machine learning and doubly robust estimators.
• Quantitative coronary calcification analysis for prediction of myocardial ischemia using non-contrast CT calcium scoring — Quantitative calcium-omics features from CTCS scans enhance myocardial ischemia prediction beyond traditional risk factors.
• How AI Ultrasound Systems Are Improving Real-Time Diagnostic Accuracy in Clinical Settings — AI ultrasound systems enhance diagnostic accuracy and expand access by automating measurements, guiding image acquisition, and accelerating interpretation.
• Identification of shared oxidative stress related hub genes in NAFLD and atherosclerosis using bioinformatics and machine learning — Bioinformatics and machine learning can identify shared oxidative stress-related hub genes in NAFLD and atherosclerosis.
• End-to-end pipeline for automated heart failure diagnosis with clinical notes using SNOMED-CT — An end-to-end pipeline automates heart failure diagnosis from German clinical notes using zero-shot learning and SNOMED-CT.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Takara TLDR - Daily AI Papers.