Morgane Devismes-Ferrandini , Tan-Nhu Nguyen , Tien-Tuan Dao
{"title":"From clinical measurements to articulated foetus: Statistical shape modeling of bone contours using PLSR for enhanced childbirth simulation","authors":"Morgane Devismes-Ferrandini , Tan-Nhu Nguyen , Tien-Tuan Dao","doi":"10.1016/j.cmpb.2025.108934","DOIUrl":null,"url":null,"abstract":"<div><h3>Background and objective</h3><div>The prediction of childbirth-related complications requires realistic patient-specific childbirth simulations with articulated foetal bodies. However, the foetal models used in current simulations are oversimplified and generally based on scaled generic models. This study presents the development and evaluation of a full-body (hands and feet excluded) foetal statistical shape model (SSM) based on CT scans to generate fast and accurate foetal geometries and lower the simulation errors due to linear scaling.</div></div><div><h3>Methods</h3><div>The developed SSM was based on a dataset of 96 subjects under one year of age. All scans were segmented and articulated to put the subjects in a similar posture. Then, the bone contours were extracted using an alpha-shape algorithm to decrease the model’s complexity. Bones were individually fitted to a template mesh to obtain point correspondences, and a PCA was conducted on the concatenated skeletons to capture the morphological variations between subjects. A PLSR was trained to allow skeletal geometry prediction using a set of anthropometrical data and bone measurements.</div></div><div><h3>Results</h3><div>Our shape model predicted the bone geometry with a root mean square error (RMSE) of 2.10 ± 1.42 mm for the head-only model and with an RMSE = 6.69 ± 3.85 mm for the full-body model. For all models, the SSM performed better at predicting the bone geometries than the mean shape obtained by PCA, considered as a baseline.</div></div><div><h3>Conclusions</h3><div>The present study proposed a first complete foetal SSM, allowing a fast and accurate prediction of the bone geometries using a reduced set of easily accessible predictors. This opens new avenues in the realistic childbirth modeling with articulated foetus for predicting physiological delivery and associated complication scenarios.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"270 ","pages":"Article 108934"},"PeriodicalIF":4.8000,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer methods and programs in biomedicine","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0169260725003517","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0
Abstract
Background and objective
The prediction of childbirth-related complications requires realistic patient-specific childbirth simulations with articulated foetal bodies. However, the foetal models used in current simulations are oversimplified and generally based on scaled generic models. This study presents the development and evaluation of a full-body (hands and feet excluded) foetal statistical shape model (SSM) based on CT scans to generate fast and accurate foetal geometries and lower the simulation errors due to linear scaling.
Methods
The developed SSM was based on a dataset of 96 subjects under one year of age. All scans were segmented and articulated to put the subjects in a similar posture. Then, the bone contours were extracted using an alpha-shape algorithm to decrease the model’s complexity. Bones were individually fitted to a template mesh to obtain point correspondences, and a PCA was conducted on the concatenated skeletons to capture the morphological variations between subjects. A PLSR was trained to allow skeletal geometry prediction using a set of anthropometrical data and bone measurements.
Results
Our shape model predicted the bone geometry with a root mean square error (RMSE) of 2.10 ± 1.42 mm for the head-only model and with an RMSE = 6.69 ± 3.85 mm for the full-body model. For all models, the SSM performed better at predicting the bone geometries than the mean shape obtained by PCA, considered as a baseline.
Conclusions
The present study proposed a first complete foetal SSM, allowing a fast and accurate prediction of the bone geometries using a reduced set of easily accessible predictors. This opens new avenues in the realistic childbirth modeling with articulated foetus for predicting physiological delivery and associated complication scenarios.
期刊介绍:
To encourage the development of formal computing methods, and their application in biomedical research and medical practice, by illustration of fundamental principles in biomedical informatics research; to stimulate basic research into application software design; to report the state of research of biomedical information processing projects; to report new computer methodologies applied in biomedical areas; the eventual distribution of demonstrable software to avoid duplication of effort; to provide a forum for discussion and improvement of existing software; to optimize contact between national organizations and regional user groups by promoting an international exchange of information on formal methods, standards and software in biomedicine.
Computer Methods and Programs in Biomedicine covers computing methodology and software systems derived from computing science for implementation in all aspects of biomedical research and medical practice. It is designed to serve: biochemists; biologists; geneticists; immunologists; neuroscientists; pharmacologists; toxicologists; clinicians; epidemiologists; psychiatrists; psychologists; cardiologists; chemists; (radio)physicists; computer scientists; programmers and systems analysts; biomedical, clinical, electrical and other engineers; teachers of medical informatics and users of educational software.