Automated surgical planning in spring-assisted sagittal craniosynostosis correction using finite element analysis and machine learning - PLoS ONE article

Aug 4, 2026

Sagittal synostosis results from a fused sagittal suture, causing a narrowed skull in infants, and spring-assisted cranioplasty expands the skull by placing compressed springs before six months of age. Existing planning approaches either describe skull anatomy only or require iterative finite element simulations, leaving key surgical parameters such as spring dimensions and osteotomy sizes insufficiently clarified and risking sub-optimal outcomes. This study develops an automated tool architecture combining machine learning and finite element analyses to predict post-operative outcomes, testing six algorithms and using a statistical shape model; XGBoost achieved high-accuracy cephalic index prediction, supported by finite element confirmation.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Introduction

Background on sagittal synostosis and treatment approaches

Rationale for automated planning

Methods

Finite element model and parameter simulation

Machine learning algorithms and statistical shape model

Results

XGBoost prediction of post-operative cephalic index

Finite element confirmation

Automated surgical planning in spring-assisted sagittal craniosynostosis correction using finite element analysis and machine learning Jacob, J. , & Bozkurt, S. (2023) . Automated surgical planning in spring-assisted sagittal craniosynostosis correction using finite element analysis and machine learning. PLoS ONE, 18(11), 1-15. Article e0294879 . [https://doi.org/10.1371/journal.pone.0294879](https://doi.org/10.1371/journal.pone.0294879) Link to publication record in Ulster University Research Portal Published in: PLoS ONE Publication Status: Published (in print/issue): 28/11/2023 DOI: 10.1371/journal.pone.0294879 Document Version Publisher's PDF, also known as Version of record General rights Copyright for the publications made accessible via Ulster University's Research Portal is retained by the author(s) and / or other copyright owners and it is a condition of accessing these publications that users recognise and abide by the legal requirements associated with these rights. Take down policy The Research Portal is Ulster University's institutional repository that provides access to Ulster's research outputs. Every effort has been made to ensure that content in the Research Portal does not infringe any person's rights, or applicable UK laws. If you discover content in the Research Portal that you believe breaches copyright or violates any law, please contact [pure-support@ulster.ac.uk](pure-support@ulster.ac.uk). Download date: 12/01/2024 PLOS ONE OPEN ACCESS Citation: Jacob J, Bozkurt S (2023) Automated surgical planning in spring-assisted sagittal craniosynostosis correction using finite element analysis and machine learning. PLoS ONE 18(11): e0294879 . [https://doi.org/10.1371/journal](https://doi.org/10.1371/journal). pone.0294879 Editor: Johari Yap Abdullah, Universiti Sains Malaysia, MALAYSIA Received: August 14, 2023 Accepted: November 10, 2023 Published: November 28, 2023 Copyright: © 2023 Jacob, Bozkurt. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Data Availability Statement: All relevant data are within the paper and its Supporting information files. Funding: The authors received no specific funding for this work. Competing interests: The authors declare no conflict of interest. RESEARCH ARTICLE Automated surgical planning in springassisted sagittal craniosynostosis correction using finite element analysis and machine learning Jenson Jacob, Selim Bozkurt * Ulster University, School of Engineering, Belfast, United Kingdom * [s.bozkurt1@ulster.ac.uk](s.bozkurt1@ulster.ac.uk) Abstract Sagittal synostosis is a condition caused by the fused sagittal suture and results in a narrowed skull in infants. Spring-assisted cranioplasty is a correction technique used to expand skulls with sagittal craniosynostosis by placing compressed springs on the skull before six months of age. Proposed methods for surgical planning in spring-assisted sagittal craniosynostosis correction provide information only about the skull anatomy or require iterative finite element simulations. Therefore, the selection of surgical parameters such as spring dimensions and osteotomy sizes may remain unclear and spring-assisted cranioplasty may yield sub-optimal surgical results. The aim of this study is to develop the architectural structure of an automated tool to predict post-operative surgical outcomes in sagittal craniosynostosis correction with spring-assisted cranioplasty using machine learning and finite element analyses. Six different machine learning algorithms were tested using a finite element model which simulated a combination of various mechanical and geometric properties of the calvarium, osteotomy sizes, spring characteristics, and spring implantation positions. Also, a statistical shap

FAQs

What problem does the study address in spring-assisted sagittal craniosynostosis surgery planning?

Current surgical-planning methods either provide only skull-anatomy information or rely on iterative finite element simulations, which can leave important parameters (e.g., spring dimensions and osteotomy sizes) unclear and may lead to sub-optimal results.

How does the proposed automated tool predict post-operative surgical outcomes?

It combines machine learning with finite element analyses by testing six algorithms on a finite element model that simulates mechanical and geometric properties, osteotomy sizes, spring characteristics, and implantation positions, using a statistical shape model for calvarium assessment.

Which machine learning model performed best, and how was it validated?

The XGBoost algorithm predicted the post-operative cephalic index with high accuracy, and finite element simulations confirmed the prediction results.

Aug 4, 2026

Upload by Olivia Brown