Deep learning-based high-resolution pseudo-CT to detect cranial bone abnormalities for pediatric patients using MRI

Parna Eshraghi Boroojeni, Yasheng Chen, Cihat Eldeniz, Paul K. Commean, Gary B. Skolnick, Kamlesh B. Patel, Hongyu AnProceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition 2023 · DOI

Abstract

Head trauma is common in the pediatric population. Craniosynostosis is abnormal early fusion of a cranial suture, causing an irregular-shaped cranium.3D high-resolution head CT scans are commonly used in these pediatric patients to identify skull fractures and sutures. However, CT exposespediatric patients to ionizing radiationand increases risk of cancer. We developed a robust and automated deep learning method to convert MR images to pseudo-CT (pCT) that can facilitate translating MR cranial bone imaging into clinical practice. An average Dice Coefficient of 0.89 and mean absolute error of 72.45 HU between pCT and CT were achieved.
BibTeX
@inproceedings{boroojeni2023deep,
  author = {Parna Eshraghi Boroojeni and Yasheng Chen and Cihat Eldeniz and Paul K. Commean and Gary B. Skolnick and Kamlesh B. Patel and Hongyu An},
  title = {{Deep learning-based high-resolution pseudo-CT to detect cranial bone abnormalities for pediatric patients using MRI}},
  booktitle = {Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition},
  year = {2023},
  doi = {10.58530/2022/0174},
}

Loading related content...

Figure