Detecção de leucócitos em imagens de vídeo de microscopia intravital usando a técnica de congruência de fase

• Ano de defesa: 2016
• Autor(a) principal: Souza, Kathiani Elisa de
• Orientador(a): Ferrari, Ricardo José
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de São Carlos; Câmpus São Carlos
• Programa de Pós-Graduação: Programa de Pós-Graduação em Ciência da Computação - PPGCC
• Palavras-chave em Português: Detecção de leucócitos; Congruência de fase; Microscopia intravital
• Palavras-chave em Inglês: Detection of leuckocytes; Phase congruency; Intravital microscopy
• Área do conhecimento CNPq: CIENCIAS EXATAS E DA TERRA
• Link de acesso: https://repositorio.ufscar.br/handle/20.500.14289/7836

Counting the number of leukocytes present in the blood vessels is an important task to understand inflammation mechanisms and to assess the effects of drugs that are being developed for the treatment of inflammatory diseases. In general, leukocyte counting is done by an observer (laboratory technician or specialist) using a sequence of intravital microscopy images obtained from blood vessel of an animal testing. However, this procedure is time-consuming, prone to errors, due to visual fatigue of the observer, and biased, due to inter and intra-observer variability. Thus, the objective of this work was the development of computational technique for the automatic detection of leukocytes in intravital video microscopy images. For this, the detection of leukocytes was performed in two main stages. In stage 1, the phase congruency measure, which is invariant to changes of contrast and lighting images, was used to calculate a blobness measure used to detect circular structures in intravital microscopy images. In stage 2, the circular structures detected in stage 1 were analyzed locally to identify only those corresponding to true leukocytes. The results were evaluated using the precision, recall and F1-measure metrics and the area under the precision-recall curves. Furthermore, the proposed technique was compared with the template matching technique.