Advanced search
Start date
Betweenand

Deep learning for hierarchical multimodal neuroanatomy segmentation in brain tumor patients

Grant number: 19/21964-4
Support type:Scholarships in Brazil - Doctorate
Effective date (Start): July 01, 2020
Effective date (End): June 30, 2024
Field of knowledge:Engineering - Electrical Engineering
Principal researcher:Roberto de Alencar Lotufo
Grantee:Diedre Santos do Carmo
Home Institution: Faculdade de Engenharia Elétrica e de Computação (FEEC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
Associated research grant:13/07559-3 - BRAINN - The Brazilian Institute of Neuroscience and Neurotechnology, AP.CEPID

Abstract

Automated neuroanatomy segmentation in Magnetic Resonance Imaging (MRI) is a hot topic in medical imaging processing. In practice, neuroanatomy segmentation is still mainly performed manually by experts, frequently with aid of established tools such as FreeSurfer. Manual annotations are considered to be a gold-standard when evaluating automated methods. Current automatic methods usually only work in specific tasks, failing in outlier cases a human annotator would notice. In this project, we propose to develop an automated method able to perform two different tasks, neuroanatomy segmentation and brain tumor (glioma) segmentation, accurately segmenting neuroanatomy taking into account the possible presence of glioma. Although many methods exist in the literature, most focus in one of the two: healthy neuroanatomy or brain tumor segmentation. Multimodality data from T2 and FLAIR scans will be involved due to glioma features being not visible only in T1 scans. We intend to build a large cohort of public and private data for evaluation of our method, including a private dataset of 197 in-house 3T scans. We propose a novel hierarchical approach, with plans for a novel segmentation architecture based on recent advances in semantic segmentation. We will compare our methodology with state-of-the-art techniques and subject it to qualitative evaluation from physicians. (AU)

News published in Agência FAPESP Newsletter about the scholarship:
Articles published in other media outlets (0 total):
More itemsLess items
VEICULO: TITULO (DATA)
VEICULO: TITULO (DATA)

Scientific publications
(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)
CARMO, DIEDRE; CAMPIOTTI, ISRAEL; RODRIGUES, LIVIA; FANTINI, IRENE; PINHEIRO, GUSTAVO; MORAES, DANIEL; NOGUEIRA, RODRIGO; RITTNER, LETICIA; LOTUFO, ROBERTO. Rapidly deploying a COVID-19 decision support system in one of the largest Brazilian hospitals. HEALTH INFORMATICS JOURNAL, v. 27, n. 3 JUL 2021. Web of Science Citations: 0.

Please report errors in scientific publications list by writing to: cdi@fapesp.br.