Harnessing multimodal data integration to advance precision oncology

2021 ◽  
Author(s):  
Kevin M. Boehm ◽  
Pegah Khosravi ◽  
Rami Vanguri ◽  
Jianjiong Gao ◽  
Sohrab P. Shah
Keyword(s):  
Data Integration ◽  
Precision Oncology ◽  
Multimodal Data

Multimodal Data Integration for Interactive and Realistic Avatar Simulation in Augmented Reality

2021 ◽  
Author(s):  
Anchen Sun ◽  
Yudong Tao ◽  
Mei-Ling Shyu ◽  
Shu-Ching Chen ◽  
Angela Blizzard ◽  
...  
Keyword(s):  
Augmented Reality ◽  
Data Integration ◽  
Multimodal Data

Deep Learning-Based Annotation Transfer between Molecular Imaging Modalities: An Automated Workflow for Multimodal Data Integration

2021 ◽  
Vol 93 (6) ◽  
pp. 3061-3071
Author(s):  
Alan M. Race ◽  
Daniel Sutton ◽  
Gregory Hamm ◽  
Gareth Maglennon ◽  
Jennifer P. Morton ◽  
...  
Keyword(s):  
Deep Learning ◽  
Molecular Imaging ◽  
Data Integration ◽  
Imaging Modalities ◽  
Multimodal Data

PRATEEK: Integration of Multimodal Neuroimaging Data to Facilitate Advanced Brain Research

2021 ◽  
pp. 1-13
Author(s):  
Anshika Goel ◽  
Saurav Roy ◽  
Khushboo Punjabi ◽  
Ritwick Mishra ◽  
Manjari Tripathi ◽  
...  
Keyword(s):  
Magnetic Resonance ◽  
Data Integration ◽  
Brain Research ◽  
Integration Scheme ◽  
Resonance Spectroscopy ◽  
Processing Scheme ◽  
Multimodal Data ◽  
Neuroimaging Data ◽  
User Friendly

Background: In vivo neuroimaging modalities such as magnetic resonance imaging (MRI), functional MRI (fMRI), magnetoencephalography (MEG), magnetic resonance spectroscopy (MRS), and quantitative susceptibility mapping (QSM) are useful techniques to understand brain anatomical structure, functional activity, source localization, neurochemical profiling, and tissue susceptibility respectively. Integrating unique and distinct information from these neuroimaging modalities will further help to enhance the understanding of complex neurological disease. Objective: To develop a processing scheme for multimodal data integration in seamless manner on healthy young population, thus establishing a generalized framework for various clinical conditions (e.g., Alzheimer’s disease). Methods: A multimodal data integration scheme has been developed to integrate the outcomes from multiple neuroimaging data (fMRI, MEG, MRS, and QSM) spatially. Furthermore, the entire scheme has been incorporated into a user-friendly toolbox- “PRATEEK”. Results: The proposed methodology and toolbox has been tested for viability among fourteen healthy young participants for bilateral occipital cortices as the region of interest. This scheme can also be extended to other anatomical regions of interest. Overlap percentage from each combination of two modalities (fMRI-MRS, MEG-MRS, fMRI-QSM, and fMRI-MEG) has been computed and also been qualitatively assessed for combinations of the three (MEG-MRS-QSM) and four (fMRI-MEG-MRS-QSM) modalities. Conclusion: This user-friendly toolbox minimizes the need of an expertise in handling different neuroimaging tools for processing and analyzing multimodal data. The proposed scheme will be beneficial for clinical studies where geometric information plays a crucial role in advance brain research.

A strategy for multimodal data integration: application to biomarkers identification in spinocerebellar ataxia

2017 ◽  
Vol 19 (6) ◽  
pp. 1356-1369 ◽  
Author(s):  
Imene Garali ◽  
Isaac M Adanyeguh ◽  
Farid Ichou ◽  
Vincent Perlbarg ◽  
Alexandre Seyer ◽  
...  
Keyword(s):  
Data Integration ◽  
Spinocerebellar Ataxia ◽  
Multimodal Data

scholarly journals Simultaneous EEG-fMRI during a neurofeedback task, a brain imaging dataset for multimodal data integration

2020 ◽  
Vol 7 (1) ◽  
Author(s):  
Giulia Lioi ◽  
Claire Cury ◽  
Lorraine Perronnet ◽  
Marsel Mano ◽  
Elise Bannier ◽  
...  
Keyword(s):  
Data Integration ◽  
Brain Imaging ◽  
Multimodal Data

scholarly journals Patient similarity by joint matrix trifactorization to identify subgroups in acute myeloid leukemia

JAMIA Open ◽  
2018 ◽  
Vol 1 (1) ◽  
pp. 75-86 ◽  
Author(s):  
F Vitali ◽  
S Marini ◽  
D Pala ◽  
A Demartini ◽  
S Montoli ◽  
...  
Keyword(s):  
Acute Myeloid Leukemia ◽  
Data Integration ◽  
Myeloid Leukemia ◽  
Synthetic Data ◽  
Heterogeneous Data ◽  
Data Sources ◽  
Precision Oncology ◽  
Data Set ◽  
Heterogeneous Data Sources ◽  
Acute Myeloid

Abstract Objective Computing patients’ similarity is of great interest in precision oncology since it supports clustering and subgroup identification, eventually leading to tailored therapies. The availability of large amounts of biomedical data, characterized by large feature sets and sparse content, motivates the development of new methods to compute patient similarities able to fuse heterogeneous data sources with the available knowledge. Materials and Methods In this work, we developed a data integration approach based on matrix trifactorization to compute patient similarities by integrating several sources of data and knowledge. We assess the accuracy of the proposed method: (1) on several synthetic data sets which similarity structures are affected by increasing levels of noise and data sparsity, and (2) on a real data set coming from an acute myeloid leukemia (AML) study. The results obtained are finally compared with the ones of traditional similarity calculation methods. Results In the analysis of the synthetic data set, where the ground truth is known, we measured the capability of reconstructing the correct clusters, while in the AML study we evaluated the Kaplan-Meier curves obtained with the different clusters and measured their statistical difference by means of the log-rank test. In presence of noise and sparse data, our data integration method outperform other techniques, both in the synthetic and in the AML data. Discussion In case of multiple heterogeneous data sources, a matrix trifactorization technique can successfully fuse all the information in a joint model. We demonstrated how this approach can be efficiently applied to discover meaningful patient similarities and therefore may be considered a reliable data driven strategy for the definition of new research hypothesis for precision oncology. Conclusion The better performance of the proposed approach presents an advantage over previous methods to provide accurate patient similarities supporting precision medicine.

Research round-up: Precision oncology

Nature ◽  
2020 ◽  
Vol 585 (7826) ◽  
pp. S2-S3
Author(s):  
Laura Vargas-Parada
Keyword(s):  
Precision Oncology
Sign in / Sign up

Export Citation Format

Share Document