Semantic segmentation of vertebrate microfossils from computed tomography data using a deep learning approach

doi:10.5194/jm-40-163-2021

CORC > 古脊椎动物与古人类研究所 > 中国科学院古脊椎动物与古人类研究所 > 图书馆1

	Semantic segmentation of vertebrate microfossils from computed tomography data using a deep learning approach
	Hou, Yemao 3,4,5; Canul-Ku, Mario 2; Cui, Xindong 1,3,4; Hasimoto-Beltran, Rogelio 2; Zhu, Min 1,3,4
刊名	JOURNAL OF MICROPALAEONTOLOGY
	2021-10-22
卷号	40 期号:2 页码:163-173
ISSN号	0262-821X
DOI	10.5194/jm-40-163-2021
英文摘要	Vertebrate microfossils have broad applications in evolutionary biology and stratigraphy research areas such as the evolution of hard tissues and stratigraphic correlation. Classification is one of the basic tasks of vertebrate microfossil studies. With the development of techniques for virtual paleontology, vertebrate microfossils can be classified efficiently based on 3D volumes. The semantic segmentation of different fossils and their classes from CT data is a crucial step in the reconstruction of their 3D volumes. Traditional segmentation methods adopt thresholding combined with manual labeling, which is a time-consuming process. Our study proposes a deep-learning-based (DL-based) semantic segmentation method for vertebrate microfossils from CT data. To assess the performance of the method, we conducted extensive experiments on nearly 500 fish microfossils. The results show that the intersection over union (IoU) performance metric arrived at least 94.39 %, meeting the semantic segmentation requirements of paleontologists. We expect that the DL-based method could also be applied to other fossils from CT data with good performance.
资助项目	Chinese Academy of Sciences[XDB26000000] ; Chinese Academy of Sciences[XDA19050102] ; Chinese Academy of Sciences[QYZDJ-SSW-DQC002] ; National Natural Science Foundation of China[42130209]
WOS关键词	VIRTUAL WORLD ; IMAGE
WOS研究方向	Paleontology
语种	英语
出版者	COPERNICUS GESELLSCHAFT MBH
WOS记录号	WOS:000710814100001
内容类型	期刊论文
源URL	[http://119.78.100.205/handle/311034/19052]
专题	古脊椎动物与古人类研究所_图书馆1
通讯作者	Hasimoto-Beltran, Rogelio; Zhu, Min
作者单位	1.Univ Chinese Acad Sci, Coll Earth & Planetary Sci, Beijing 100049, Peoples R China 2.Ctr Invest Matemat CIMAT, Guanajuato 36023, Mexico 3.CAS Ctr Excellence Life & Paleoenvironm, Beijing 100044, Peoples R China 4.Chinese Acad Sci, Key Lab Vertebrate Evolut & Human Origins, Inst Vertebrate Paleontol & Paleoanthropol, Beijing 100044, Peoples R China 5.Xidian Univ, Sch Life Sci & Technol, Xian 710071, Peoples R China
推荐引用方式 GB/T 7714	Hou, Yemao,Canul-Ku, Mario,Cui, Xindong,et al. Semantic segmentation of vertebrate microfossils from computed tomography data using a deep learning approach[J]. JOURNAL OF MICROPALAEONTOLOGY,2021,40(2):163-173.
APA	Hou, Yemao,Canul-Ku, Mario,Cui, Xindong,Hasimoto-Beltran, Rogelio,&Zhu, Min.(2021).Semantic segmentation of vertebrate microfossils from computed tomography data using a deep learning approach.JOURNAL OF MICROPALAEONTOLOGY,40(2),163-173.
MLA	Hou, Yemao,et al."Semantic segmentation of vertebrate microfossils from computed tomography data using a deep learning approach".JOURNAL OF MICROPALAEONTOLOGY 40.2(2021):163-173.