Reproduce “Automatic linear measurements of the fetal brain on MRI with deep neural networks” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Netanell Avisdris, Bossmat Yehuda, Ori Ben-Zvi, Daphna Link-Sourani, Liat Ben-Sira, Elka Miller, Elena Zharkov, Dafna Ben Bashat and 1 more

An automatic pipeline computes three key linear biometric measurements of the fetal brain (Cerebral Biparietal Diameter, Bone Biparietal Diameter, and Trans-Cerebellum Diameter) from MRI scans, demonstrating performance comparable to expert radiologists while incorporating a self-assessment of measurement reliability. The method addresses the challenges of manual assessment in fetal brain MRI, providing a standardized quantitative tool.

Key insights

  • A hybrid approach, integrating deep learning for initial recognition tasks with geometric methods for precise measurement, effectively automates complex clinical workflows for fetal brain biometry.
  • The inclusion of a self-assessment mechanism for reliability is crucial for clinical acceptance, allowing the system to flag potentially unreliable measurements and maintain trust.
  • The method demonstrates consistent performance across various gestational ages and fetal brain abnormalities, indicating its robustness for diverse clinical scenarios.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.