Convolutional neural networks for segmenting xylem vessels in stained cross-sectional images

García Pedrero, Ángel Mario and García-Cervigón Morales, Ana Isabel and Olano, José Miguel and García Hidalgo, Miguel and Lillo Saavedra, Mario and Gonzalo Martín, Consuelo and Caetano, Cristina and Calderón Ramírez, Saúl (2019). Convolutional neural networks for segmenting xylem vessels in stained cross-sectional images. "Neural Computing and Applications", v. 32 ; pp. 17927-17939. ISSN 0941-0643. https://doi.org/10.1007/s00521-019-04546-6.

Description

Title: Convolutional neural networks for segmenting xylem vessels in stained cross-sectional images
Author/s:
  • García Pedrero, Ángel Mario
  • García-Cervigón Morales, Ana Isabel
  • Olano, José Miguel
  • García Hidalgo, Miguel
  • Lillo Saavedra, Mario
  • Gonzalo Martín, Consuelo
  • Caetano, Cristina
  • Calderón Ramírez, Saúl
Item Type: Article
Journal/Publication Title: Neural Computing and Applications
Date: 2019
ISSN: 0941-0643
Volume: 32
Subjects:
Freetext Keywords: Convolutional neural networks, Dendrology, Xylem cells, Image segmentation
Faculty: E.T.S. de Ingenieros Informáticos (UPM)
Department: Arquitectura y Tecnología de Sistemas Informáticos
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (1MB) | Preview

Abstract

Xylem is a vascular tissue that conducts sap (water and dissolved minerals) from the roots to the rest of the plant while providing physical support and resources. Sap is conducted within dead hollow cells (called vessels in flowering plants) arranged to form long pipes. Once formed, vessels do not change their structure and last from years to millennia. Vessels’ configuration (size, abundance, and spatial pattern) constitutes a record of the plant–environment relationship, and therefore, a tool for monitoring responses at the plant and ecosystem level. This information can be extracted through quantitative anatomy; however, the effort to identify and measure hundreds of thousands of conductive cells is an inconvenience to the progress needed to have solid assessments of the anatomical–environment relationship. In this paper, we propose an automatic methodology based on convolutional neural networks to segment xylem vessels. It includes a post-processing stage based on the use of redundant information to improve the performance of the outcome and make it useful in different sample configurations. Three different neural networks were tested obtaining similar results (pixel accuracy about 90%), which indicates that the methodology can be effectively used for segmentation of xylem vessels into images with non-homogeneous variations of illumination. The development of accurate automatic tools using CNNs would reduce the entry barriers associated with quantitative xylem anatomy expanding the use of this technique by the scientific community.

Funding Projects

TypeCodeAcronymLeaderTitle
Government of SpainFJCI-2015-24770UnspecifiedUnspecifiedUnspecified

More information

Item ID: 67091
DC Identifier: http://oa.upm.es/67091/
OAI Identifier: oai:oa.upm.es:67091
DOI: 10.1007/s00521-019-04546-6
Official URL: https://link.springer.com/article/10.1007/s00521-019-04546-6
Deposited by: Memoria Investigacion
Deposited on: 17 May 2021 08:33
Last Modified: 17 May 2021 08:33
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM