New SPARC pipeline automates fetal cardiac MRI reconstruction

Researchers have developed a new pipeline called SPARC for reconstructing 3D+time fetal cardiac MRI (fCMR) from 2D+time acquired slices. This pipeline combines physics-informed slice-to-volume reconstruction with deep learning models for thoracic segmentation and anatomical reorientation. SPARC significantly reduces reconstruction time, achieving a tenfold decrease compared to existing methods, and demonstrates high accuracy in segmentation and reorientation. The system enables fully automatic processing in a majority of cases, making it suitable for clinical deployment. AI

IMPACT This automated pipeline could significantly speed up diagnostic processes for fetal cardiac conditions, improving clinical workflows.

RANK_REASON The cluster contains a research paper detailing a new method and pipeline for medical image reconstruction. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• Arnaud Boutillon
• arXiv
• congenital heart disease
• deep learning
• Docker
• Doppler Ultrasound Detection of Tissue Motion and Flow Generated By External Energy
• echocardiography
• SPARC

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →