Analysis and refinement of machine learning methods for blood vessel morphometry

• Grant number: 21/12354-8
• Support Opportunities: Regular Research Grants
• Duration: February 01, 2022 - January 31, 2024
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Cesar Henrique Comin
• Grantee: Cesar Henrique Comin
• Host Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil

Abstract

The vascular system has fundamental importance for many different types of animal tissues. Through the propagation of nutrients, oxygen, and blood cells, the vascular system helps in fighting diseases and inflammation, in the homeostasis of organisms, and in several other physiological processes. As a consequence, the characterization of blood vessels is of fundamental importance in the diagnosis of diseases and also for several state-of-the-art studies in biology. One common research topic concerns blood vessel morphometry, which involves defining properties to characterize the shape and connectivity of tissue vascularization. Given the large number of blood vessels present in cellular tissues, the systematic analysis of vascular morphometry requires the application of automated or semi-automated computational methodologies for processing images acquired using different imaging modalities. In this project, four main studies related to different aspects of the computational process necessary for the identification and characterization of blood vessels will be carried out: i) the development of techniques for interpreting and improving Convolutional Neural Networks for blood vessel segmentation; ii) the study of the influence that segmentation errors have on blood vessel morphometry; iii) the generation of realistic artificial vascular networks for training Machine Learning algorithms and iv) characterization and correction of the topology of vascularization graphs using Convolutional Graph Networks. The developed methodologies will be used for studying the development and function of the blood-brain barrier in mice. (AU)

Scientific publications

(5)

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

DA SILVA, MATHEUS V.; OUELLETTE, JULIE; LACOSTE, BAPTISTE; COMIN, CESAR H.. An analysis of the influence of transfer learning when measuring the tortuosity of blood vessels. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, v. 225, p. 11-pg., 2022-07-29. (18/09125-4, 21/12354-8)

LITHOPOULOS, MARISSA A.; TOUSSAY, XAVIER; ZHONG, SHUMEI; XU, LIQUN; MUSTAFA, SHAMIMUNISA B.; OUELLETTE, JULIE; FREITAS-ANDRADE, MOISES; COMIN, CESAR H.; BASSAM, HAYAM A.; BAKER, ADAM N.; et al. Neonatal hyperoxia in mice triggers long-term cognitive deficits via impairments in cerebrovascular function and neurogenesis. Journal of Clinical Investigation, v. 132, n. 22, p. 21-pg., 2022-11-15. (21/12354-8, 18/09125-4)

TOKUDA, ERIC K.; COMIN, CESAR H.; COSTA, LUCIANO DA F.. Impact of the topology of urban streets on mobility optimization. JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT, v. 2022, n. 10, p. 20-pg., 2022-10-01. (18/09125-4, 21/12354-8, 19/01077-3, 15/22308-2)

FREITAS-ANDRADE, MOISES; COMIN, CESAR H.; VAN DYKEN, PETER; OUELLETTE, JULIE; RAMAN-NAIR, JOANNA; BLAKELEY, NICOLE; LIU, QING YAN; LECLERC, SONIA; PAN, YOULIAN; LIU, ZIYING; et al. Astroglial Hmgb1 regulates postnatal astrocyte morphogenesis and cerebrovascular maturation. NATURE COMMUNICATIONS, v. 14, n. 1, p. 20-pg., 2023-08-16. (21/12354-8, 15/22308-2)

BENATTI, ALEXANDRE; DE ARRUDA, HENRIQUE FERRAZ; SILVA, FILIPI NASCIMENTO; COMIN, CESAR HENRIQUE; COSTA, LUCIANO DA FONTOURA. On the stability of citation networks. PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, v. 610, p. 14-pg., 2022-12-23. (18/10489-0, 21/12354-8, 15/22308-2)