Busca avançada
Ano de início
Entree
(Referência obtida automaticamente do Web of Science, por meio da informação sobre o financiamento pela FAPESP e o número do processo correspondente, incluída na publicação pelos autores.)

Pixel-Level Tissue Classification for Ultrasound Images

Texto completo
Autor(es):
Pazinato, Daniel V. [1] ; Stein, Bernardo V. [1] ; de Almeida, Waldir R. [1] ; Werneck, Rafael de O. [1] ; Mendes Junior, Pedro R. [1] ; Penatti, Otavio A. B. [1, 2] ; Torres, Ricardo da S. [1] ; Menezes, Fabio H. [3] ; Rocha, Anderson [1]
Número total de Autores: 9
Afiliação do(s) autor(es):
[1] Univ Estadual Campinas, Inst Comp, RECOD Lab, BR-13083852 Campinas, SP - Brazil
[2] Samsung Res Inst, Adv Technol Grp, BR-13083852 Campinas, SP - Brazil
[3] Univ Estadual Campinas, Fac Med Sci, BR-13083852 Campinas, SP - Brazil
Número total de Afiliações: 3
Tipo de documento: Artigo Científico
Fonte: IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS; v. 20, n. 1, p. 256-267, JAN 2016.
Citações Web of Science: 9
Resumo

Background: Pixel-level tissue classification for ultrasound images, commonly applied to carotid images, is usually based on defining thresholds for the isolated pixel values. Ranges of pixel values are defined for the classification of each tissue. The classification of pixels is then used to determine the carotid plaque composition and, consequently, to determine the risk of diseases (e.g., strokes) and whether or not a surgery is necessary. The use of threshold-based methods dates from the early 2000s but it is still widely used for virtual histology. Methodology/Principal Findings: We propose the use of descriptors that take into account information about a neighborhood of a pixel when classifying it. We evaluated experimentally different descriptors (statistical moments, texture-based, gradient-based, local binary patterns, etc.) on a dataset of five types of tissues: blood, lipids, muscle, fibrous, and calcium. The pipeline of the proposed classification method is based on image normalization, multiscale feature extraction, including the proposal of a new descriptor, and machine learning classification. We have also analyzed the correlation between the proposed pixel classification method in the ultrasound images and the real histology with the aid of medical specialists. Conclusions/Significance: The classification accuracy obtained by the proposed method with the novel descriptor in the ultrasound tissue images (around 73%) is significantly above the accuracy of the state-of-the-art threshold-based methods (around 54%). The results are validated by statistical tests. The correlation between the virtual and real histology confirms the quality of the proposed approach showing it is a robust ally for the virtual histology in ultrasound images. (AU)

Processo FAPESP: 12/20465-5 - Análise e classificação de estenoses carotídeas por imagens de ultrassonografia duplex
Beneficiário:Daniel Vatanabe Pazinato
Linha de fomento: Bolsas no Brasil - Iniciação Científica