Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Boosting Skull-Stripping Performance for Pediatric Brain Images (2402.16634v1)

Published 26 Feb 2024 in eess.IV, cs.CV, and q-bio.QM

Abstract: Skull-stripping is the removal of background and non-brain anatomical features from brain images. While many skull-stripping tools exist, few target pediatric populations. With the emergence of multi-institutional pediatric data acquisition efforts to broaden the understanding of perinatal brain development, it is essential to develop robust and well-tested tools ready for the relevant data processing. However, the broad range of neuroanatomical variation in the developing brain, combined with additional challenges such as high motion levels, as well as shoulder and chest signal in the images, leaves many adult-specific tools ill-suited for pediatric skull-stripping. Building on an existing framework for robust and accurate skull-stripping, we propose developmental SynthStrip (d-SynthStrip), a skull-stripping model tailored to pediatric images. This framework exposes networks to highly variable images synthesized from label maps. Our model substantially outperforms pediatric baselines across scan types and age cohorts. In addition, the <1-minute runtime of our tool compares favorably to the fastest baselines. We distribute our model at https://w3id.org/synthstrip.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (25)
  1. Bruce Fischl, “FreeSurfer,” NeuroImage, vol. 62, no. 2, pp. 774–781, 2012.
  2. Lilla Zöllei et al., “Infant FreeSurfer: An automated segmentation and surface extraction pipeline for T1-weighted neuroimaging data of infants 0–2 years,” NeuroImage, vol. 218, pp. 116946, 2020.
  3. Christian Gaser et al., “CAT–A computational anatomy toolbox for the analysis of structural MRI data,” biorxiv, pp. 2022–06, 2022.
  4. Rebecca C Knickmeyer et al., “A structural MRI study of human brain development from birth to 2 years,” Journal of Neuroscience, vol. 28, no. 47, pp. 12176–12182, 2008.
  5. Stephen M Smith, “Fast robust automated brain extraction,” Hum Brain Mapp, vol. 17, no. 3, pp. 143–155, 2002.
  6. “Robust brain extraction across datasets and comparison with publicly available methods,” IEEE TMI, vol. 30, no. 9, pp. 1617–1634, 2011.
  7. Fabian Isensee et al., “Automated brain extraction of multisequence MRI using artificial neural networks,” Hum Brain Mapp, vol. 40, no. 17, pp. 4952–4964, 2019.
  8. Olaf Ronneberger et al., “U-net: Convolutional networks for biomedical image segmentation,” in MICCAI. Springer, 2015, pp. 234–241.
  9. Amod Jog et al., “Fast Infant MRI Skullstripping with Multiview 2D Convolutional Neural Networks,” arXiv preprint arXiv:1904.12101, 2019.
  10. Li Wang et al., “iBEAT V2.0: a multisite-applicable, deep learning-based pipeline for infant cerebral cortical surface reconstruction,” Nature Protocols, vol. 18, 2023.
  11. “Learning MRI contrast-agnostic registration,” in 2021 IEEE ISBI. IEEE, 2021, pp. 899–903.
  12. Benjamin Billot et al., “Robust machine learning segmentation for large-scale analysis of heterogeneous clinical brain MRI datasets,” PNAS, vol. 120, no. 9, pp. e2216399120, 2023.
  13. Malte Hoffmann et al., “Anatomy-specific acquisition-agnostic affine registration learned from fictitious images,” in Medical Imaging 2023: Image Processing. SPIE, 2023, vol. 12464, p. 1246402.
  14. Andrew Hoopes et al., “Learning the Effect of Registration Hyperparameters with HyperMorph,” Machine Learning for Biomedical Imaging, vol. 1, no. IPMI 2021 special issue, pp. 1–30, 2022.
  15. “Anatomy-aware and acquisition-agnostic joint registration with SynthMorph,” arXiv preprint arXiv:2301.11329, 2024.
  16. “Partial volume segmentation of brain MRI scans of any resolution and contrast,” in MICCAI. Springer, 2020, pp. 177–187.
  17. Benjamin Billot et al., “SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining,” Medical image analysis, vol. 86, pp. 102789, 2023.
  18. “SynthStrip: Skull-stripping for any brain image,” NeuroImage, vol. 260, pp. 119474, 2022.
  19. Fleur L Warton et al., “Prenatal methamphetamine exposure is associated with reduced subcortical volumes in neonates,” Neurotoxicology and teratology, vol. 65, pp. 51–59, 2018.
  20. FL Warton et al., “Maternal choline supplementation mitigates alcohol exposure effects on neonatal brain volumes,” Alcoholism: Clinical and Experimental Research, vol. 45, no. 9, pp. 1762–1774, Sep 2021.
  21. Bonnie Alexander et al., “A new neonatal cortical and subcortical brain atlas: the Melbourne Children’s Regional Infant Brain (M-CRIB) atlas,” NeuroImage, vol. 147, pp. 841–851, 2017.
  22. Brittany R Howell et al., “The UNC/UMN Baby Connectome Project (BCP): An overview of the study design and protocol development,” NeuroImage, vol. 185, pp. 891–905, 2019.
  23. Emer J Hughes et al., “A dedicated neonatal brain imaging system,” Magn Reson Med, vol. 78, no. 2, pp. 794–804, 2017.
  24. Antonios Makropoulos et al., “The developing human connectome project: A minimal processing pipeline for neonatal cortical surface reconstruction,” NeuroImage, vol. 173, pp. 88–112, 2018.
  25. Lukas Fisch et al., “Deepbet: Fast brain extraction of T1-weighted MRI using Convolutional Neural Networks,” arXiv preprint arXiv:2308.07003, 2023.
Citations (4)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now