Deep learning-aided segmentation combined with finite element analysis reveals a more natural biomechanic of dinosaur fossil

doi:10.1038/s41598-025-99131-4

IVPP-IR

	Deep learning-aided segmentation combined with finite element analysis reveals a more natural biomechanic of dinosaur fossil
	Zhang, Lijia 1; Cao, Zixiong 2; Zhao, Qi 3,4,5
	2025-04-22
发表期刊	SCIENTIFIC REPORTS
ISSN	2045-2322
卷号	15 期号:1 页码:9
通讯作者	Zhao, Qi(zhaoqi@ivpp.ac.cn)
摘要	Finite element analysis (FEA), a biomechanical simulation technique capable of providing direct mechanical visualization for CT-based digital models, has been extensively applied to fossil image datasets to address key evolutionary questions in paleontology. However, the rock matrix filling intertrabecular space of fossils often causes severe deviations in FEA results. Segmentation strategies such as thresholding and manual labeling have been employed to mitigate these disturbances. However, the efficiency of manual segmentation and the accuracy of thresholding remain questionable. In this study, we applied FEA combined with deep learning-based segregation on a femoral specimen of Jeholosaurus (a small bipedal dinosaur). This novel methodology efficiently generates the FE model with stress distribution that closely reflects the trabecular architecture in fossils of extinct taxa, reflecting a more natural state of biomechanical performance with high biological reality. Our approach provides a practical strategy for studying the biomechanics, functional morphology, and taxonomy of extinct species.
关键词	Deep learning FEA CT segmentation Dinosaur Interdisciplinary
DOI	10.1038/s41598-025-99131-4
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China ; [42072008] ; [42272020]
项目资助者	National Natural Science Foundation of China
WOS研究方向	Science & Technology - Other Topics
WOS类目	Multidisciplinary Sciences
WOS记录号	WOS:001472869000006
出版者	NATURE PORTFOLIO
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.205/handle/311034/24759
专题	中国科学院古脊椎动物与古人类研究所
通讯作者	Zhao, Qi
作者单位	1.Peking Union Med Coll & Chinese Acad Med Sci, Peking Union Med Coll Hosp, Dept Orthoped Surg, Beijing 100730, Peoples R China 2.Comet Technol Canada, Montreal, PQ H3B 1A7, Canada 3.Chinese Acad Sci, Inst Vertebrate Paleontol & Paleoanthropol, Beijing 100044, Peoples R China 4.Univ Chinese Acad Sci, Coll Earth & Planetary Sci, Beijing 100049, Peoples R China 5.Baoding Nat Hist Museum, Paleozool Museum China, Baoding 071000, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Lijia,Cao, Zixiong,Zhao, Qi. Deep learning-aided segmentation combined with finite element analysis reveals a more natural biomechanic of dinosaur fossil[J]. SCIENTIFIC REPORTS,2025,15(1):9.
APA	Zhang, Lijia,Cao, Zixiong,&Zhao, Qi.(2025).Deep learning-aided segmentation combined with finite element analysis reveals a more natural biomechanic of dinosaur fossil.SCIENTIFIC REPORTS,15(1),9.
MLA	Zhang, Lijia,et al."Deep learning-aided segmentation combined with finite element analysis reveals a more natural biomechanic of dinosaur fossil".SCIENTIFIC REPORTS 15.1(2025):9.