Intelligent Objective Osteon Segmentation Based on Deep Learning

doi:10.3389/feart.2022.783481

CASIA OpenIR > 中科院工业视觉智能装备工程实验室 > 精密感知与控制

	Intelligent Objective Osteon Segmentation Based on Deep Learning
	Qin, Zichuan 1; Qin, Fangbo2 ; Li, Ying2 ; Yu, Congyu 3,4
发表期刊	FRONTIERS IN EARTH SCIENCE
	2022-02-03
卷号	10 页码:8
通讯作者	Yu, Congyu(cyu@amnh.org)
摘要	Histology is key to understand physiology, development, growth and even reproduction of extinct animals. However, the identification and interpretation of certain structures, such as osteons, medullary bone (MB), and Lines of Arrested Growth (LAGs), are not only based on personal judgments, but also require considerable labor for subsequent analysis. Due to the dearth of available specimens, only a few quantitative histological studies have been proceeded for limited dinosaur taxa, most of which focus primarily on their growth, namely, LAGs and other growth lines without much attention to other histological structures. Here we develop a deep convolutional neural network-based method for automated osteohistological segmentation. Raw images are firstly divided into sub-images and the borders are expanded to guarantee the osteon regions integrity. ResNet-50 is employed as feature extractor and atrous spatial pyramid pooling (ASPP) is used to capture multi-scale information. A dual-resolution segmentation strategy is designed to observe the primary and secondary osteon regions from the matrix background. Finally, a segmented map with different osteon regions is obtained. This deep convolutional neural network-based model is tested on a histological dataset derived from various taxa in Alvarezsauria, a highly specialized group of non-avian theropod dinosaurs. The results show that large-scale quantitative histological analysis can be achieved by neural network-based methods, and previously hidden information by traditional methods can be revealed. Phylogenetic mapping of osteon segmentation results suggests a developmental pathway towards miniaturized body sizes in the evolution of Alvarezsauria, which may resemble the transition from non-avian dinosaurs to birds.
关键词	dinosaur histology osteon deep learning segmentation alvarezsauria
DOI	10.3389/feart.2022.783481
关键词[WOS]	GROWTH ; THEROPODA ; FEATURES ; HISTORY
收录类别	SCI
语种	英语
资助项目	Newt and Calista Gingrich Endowment
项目资助者	Newt and Calista Gingrich Endowment
WOS研究方向	Geology
WOS类目	Geosciences, Multidisciplinary
WOS记录号	WOS:000759927200001
出版者	FRONTIERS MEDIA SA
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://ir.ia.ac.cn/handle/173211/47624
专题	中科院工业视觉智能装备工程实验室_精密感知与控制
通讯作者	Yu, Congyu
作者单位	1.Univ Bristol, Fac Sci, Sch Earth Sci, Bristol, Avon, England 2.Chinese Acad Sci, Inst Automat, Res Ctr Precis Sensing & Control, Beijing, Peoples R China 3.Amer Museum Nat Hist, Div Paleontol, New York, NY 10024 USA 4.Columbia Univ, Dept Earth & Environm Sci, New York, NY 10027 USA
推荐引用方式 GB/T 7714	Qin, Zichuan,Qin, Fangbo,Li, Ying,et al. Intelligent Objective Osteon Segmentation Based on Deep Learning[J]. FRONTIERS IN EARTH SCIENCE,2022,10:8.
APA	Qin, Zichuan,Qin, Fangbo,Li, Ying,&Yu, Congyu.(2022).Intelligent Objective Osteon Segmentation Based on Deep Learning.FRONTIERS IN EARTH SCIENCE,10,8.
MLA	Qin, Zichuan,et al."Intelligent Objective Osteon Segmentation Based on Deep Learning".FRONTIERS IN EARTH SCIENCE 10(2022):8.