Recuperação de Imagens por Conteúdo Utilizando Atenção Visual Seletiva

• Grant number: 18/06074-0
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Start date: May 01, 2018
• End date: March 14, 2022
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Agma Juci Machado Traina
• Grantee: Oscar Alonso Cuadros Linares
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated research grant: 16/17078-0 - Mining, indexing and visualizing Big Data in clinical decision support systems (MIVisBD), AP.TEM

Abstract

Content-Based Image Retrieval (CBIR) systems aims at searching and retrieval images from a dataset by analyzing image features that describe the images following a given criteria, such as color, texture, and edges. This strategy is very useful when metadata is incomplete or not available, and to bypass the human limitations on manually analyzing a large volume of images. Nevertheless, this strategy is limited by the existence of a gap between the high-level semantic of an image and its features. On the other hand, the Selective Visual Attention (SVA) area combines computational techniques with psychology in order to develop methods similar to the human vision. In this project, we shall combine the potential of CBIR methods with the SVA strategy to develop new radiomics methods more in line with the specialists' knowledge and their professional intuition. In addition, we shall investigate and incorporate more sophisticated features extractors to improve the efficacy of the CBIR methods. In the last years, a number of applications in the image processing field have been proposed, which take advantage of the advances in the complex networks theory. We aim at bringing these methods to the radiomics field.

Scientific publications

(6)

(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)

LINARES, OSCAR CUADROS; HAMANN, BERND; BATISTA NETO, JOAO. Segmenting Cellular Retinal Images by Optimizing Super-Pixels, Multi-Level Modularity, and Cell Boundary Representation. IEEE Transactions on Image Processing, v. 29, p. 809-818, 2020. (18/06074-0, 12/24036-1)

CLEMENTINO, JOSE M., JR.; FAICAL, BRUNO S.; BONES, CHRISTIAN C.; TRAINA, CAETANO, JR.; GUTIERREZ, MARCO A.; TRAINA, AGMA J. M.; ALMEIDA, JR; GONZALEZ, AR; SHEN, L; KANE, B; et al. Multilevel Clustering Explainer: An Explainable Approach to Electronic Health Records. 2021 IEEE 34TH INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS (CBMS), v. N/A, p. 6-pg., 2021-01-01. (20/07200-9, 16/17078-0, 18/06074-0, 19/04660-1, 18/06228-7)

CLEMENTINO JR, JOSE M.; BONES, CHRISTIAN C.; FAICAL, BRUNO S.; LINARES, OSCAR C.; LIMA, DANIEL M.; GUTIERREZ, MARCO A.; TRAINA JR, CAETANO; TRAINA, AGMA J. M.; DEHERRERA, AGS; GONZALEZ, AR; et al. Bag-of-Attributes Representation: a Vector Space Model for Electronic Health Records Analysis in OMOP. 2020 IEEE 33RD INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS(CBMS 2020), v. N/A, p. 6-pg., 2020-01-01. (18/06228-7, 16/17078-0, 20/07200-9, 19/04660-1, 18/06074-0)

LINARES, OSCAR CUADROS; SORIANO-VARGAS, AUREA AUREA; FAICAL, BRUNO S.; HAMANN, BERND; FABRO, ALEXANDRE T.; TRAINA, AGMA J. M.; DEHERRERA, AGS; GONZALEZ, AR; SANTOSH, KC; TEMESGEN, Z; et al. Efficient Segmentation of Cell Nuclei in Histopathological Images. 2020 IEEE 33RD INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS(CBMS 2020), v. N/A, p. 6-pg., 2020-01-01. (16/17078-0, 18/06228-7, 18/06074-0, 20/07200-9)

BELIZARIO, IVAR VARGAS; LINARES, OSCAR CUADROS; SANTO BATISTA NETO, JOAO DO ESPIRITO. Automatic image segmentation based on label propagation. IET IMAGE PROCESSING, v. 15, n. 11, p. 2532-2547, SEP 2021. (18/06074-0, 21/00360-3)

LINARES, OSCAR CUADROS; FAICAL, BRUNO S.; BARBOSA, PAULO RENATO C.; HAMANN, BERND; FABRO, ALEXANDRE T.; TRAINA, AGMA J. M.; IEEE. How to Automatically Identify Regions of Interest in High-resolution Images of Lung Biopsy for Interstitial Fibrosis Diagnosis. 2019 IEEE 32ND INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS (CBMS), v. N/A, p. 4-pg., 2019-01-01. (16/17078-0, 18/06228-7, 18/06074-0)