Deep learning for brain structures segmentation in MR imaging

• Grant number: 16/18332-8
• Support Opportunities: Scholarships in Brazil - Master
• Start date: January 01, 2017
• End date: September 30, 2018
• Field of knowledge: Engineering - Electrical Engineering
• Principal Investigator: Roberto de Alencar Lotufo
• Grantee: Oeslle Alexandre Soares de Lucena
• Host Institution: Faculdade de Engenharia Elétrica e de Computação (FEEC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Associated scholarship(s): 17/23747-5 - Deep-learning-based tractography for surgical planning in epilepsy treatment, BE.EP.MS

Abstract

The necessity to develop fast, robust and accurate brain MR segmentation tools that require few parameters to adjust is essential since manual segmentation performed by neurologists is a time-consuming task. Among automatic methods, Deep Learning approaches have outperformed the state-of-the-art in many computer vision problems. Deep Learning techniques major disadvantage is that they usually require large amounts of labeled data for training, which is not available in medical image segmentation problems.This M.Sc. research project intends to investigate the use of Deep Learning techniques applied to brain structure segmentation in MR imaging. Two specic applications will be investigated: the brain extraction, also known as skull-stripping, and corpus callosum (CC) segmentation problems. Our method aims to use the Simultaneous Truth and Performance Level Estimation (STAPLE) algorithm to generate labeled data and use it as input for a Convolutional Neural Network (CNN). We will compare our methodology with the state-of-the-art techniques for brain and CC segmentation. (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)

LUCENA, OESLLE; SOUZA, ROBERTO; RITTNER, LETICIA; FRAYNE, RICHARD; LOTUFO, ROBERTO; IEEE. SILVER STANDARD MASKS FOR DATA AUGMENTATION APPLIED TO DEEP-LEARNING-BASED SKULL-STRIPPING. 2018 IEEE 15TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2018), v. N/A, p. 4-pg., 2018-01-01. (16/18332-8)

SOUZA, ROBERTO; LUCENA, OESLLE; GARRAFA, JULIA; GOBBI, DAVID; SALUZZI, MARINA; APPENZELLER, SIMONE; RITTNER, LETICIA; FRAYNE, RICHARD; LOTUFO, ROBERTO. An open, multi-vendor, multi-field-strength brain MR dataset and analysis of publicly available skull stripping methods agreement. NeuroImage, v. 170, n. SI, p. 482-494, APR 15 2018. (13/23514-0, 13/07559-3, 16/18332-8)

LUCENA, OESLLE; SOUZA, ROBERTO; RITTNER, LETICIA; FRAYNE, RICHARD; LOTUFO, ROBERTO. Convolutional neural networks for skull-stripping in brain MR imaging using silver standard masks. ARTIFICIAL INTELLIGENCE IN MEDICINE, v. 98, p. 48-58, JUL 2019. (13/07559-3, 16/18332-8)

SOUZA, ROBERTO; LUCENA, OESLLE; GARRAFA, JULIA; GOBBI, DAVID; SALUZZI, MARINA; APPENZELLER, SIMONE; RITTNER, LETICIA; FRAYNE, RICHARD; LOTUFO, ROBERTO. An open, multi-vendor, multi-field-strength brain MR dataset and analysis of publicly available skull stripping methods agreement. NeuroImage, v. 170, p. 13-pg., 2018-04-15. (13/07559-3, 13/23514-0, 16/18332-8)

GRANADOS, ALEJANDRO; MANCINI, MATTEO; VOS, SJOERD B.; LUCENA, OESLLE; VAKHARIA, VEJAY; RODIONOV, ROMAN; MISEROCCHI, ANNA; MCEVOY, ANDREW W.; DUNCAN, JOHN S.; SPARKS, RACHEL; et al. A Machine Learning Approach to Predict Instrument Bending in Stereotactic Neurosurgery. MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2018, PT IV, v. 11073, p. 9-pg., 2018-01-01. (17/23747-5, 16/18332-8)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

LUCENA, Oeslle Alexandre Soares de. Aprendizado profundo para análise do cérebro em imagens de ressonância magnética. 2018. Master's Dissertation - Universidade Estadual de Campinas (UNICAMP). Faculdade de Engenharia Elétrica e de Computação Campinas, SP.