Cognitive Computation - Special Issue Call for Papers: Advances in Multi-modal Deep and Shallow Neural Networks for Neuroimaging Applications

Special Issue Call for Papers: Advances in Multi-modal Deep and Shallow Neural Networks for Neuroimaging Applications

 

Guest Editors:

M. Tanveer (Coordinator), Indian Institute of Technology Indore, India, Email: mtanveer@iiti.ac.in (this opens in a new tab)

Chin-Teng Lin, University of Technology Sydney, Australia, Email: Chin-Teng.Lin@uts.edu.au (this opens in a new tab)

Yu-dong Zhang, University of Leicester (UK), Email: yudongzhang@ieee.org (this opens in a new tab)

Kaizhu Huang, Xi’an Jiaotong-Liverpool University, China, Email: kh476@duke.edu (this opens in a new tab)

 

 

Aim and Motivation:

Over the past few decades, there has been an exponential increase in the volume, veracity and variety of multi-modal Big data generated from medical imaging applications. This has led to growing challenges for machine learning researchers to effectively extract hidden features and reduce artifacts automatically from images, in order to enhance disease classification, diagnosis, prognosis, segmentation and risk assessment (such as ionizing radiation exposure and side effect of contrast agents). Most existing solutions to these problems are suboptimal owing to risks associated with model training that often lead to inaccurate image acquisition and analysis on account of e.g. overfitting, noise in image, class imbalance and inappropriate features selection. Hence, automated and reliable quality control in medical imaging is a crucial factor for future widespread clinical deployment of machine learning based solutions.

In the context of neuroimaging applications, neuroimaging scans are being increasingly and contextually used, along with social, clinical and laboratory data, to detect and diagnose neurological diseases, such as Alzheimer’s disease, Multiple sclerosis, Parkinson’s disease etc.  The sources of neuroimaging modalities are from a wide variety of clinical settings, including electrocardiography (ECG), electroencephalography (EEG), magnetic resonance imaging (MRI), functional MRI (fMRI), positron emission tomography (PET). Recent literature has shown the potential of deep and shallow neural network-based multimodal learning algorithms to address a range of neuroimaging challenges on account of their automatic multimodal feature selection, learning and generalisation capabilities. 

This timely special issue aims to bring together world-leading cutting-edge research (from both academia and industry) on multimodal neural network algorithms, including integrated deep and shallow models, that can increase the diagnosis and prognosis accuracy in analysis of neuroimaging Big data.
 

Topics: Topics include but are not limited to:

• Multimodal deep neural networks
• Multimodal shallow neural networks
• Integrated deep and shallow models for multimodal learning
• Real-time segmentation, clustering and classification
• Sparse, interpretable and privacy preserving data analytics
• Real-time Image acquisition, resolution, registration and production
• Automated multimodal artifacts reduction in neuroimaging Automated quality assessment and clinical validation models
• Emerging multimodal neuroimaging applications

 

Deadlines:

 

Submissions deadline: Extended to July 31st, 2022

First notification of acceptance: June 30, 2022

Submission of revised papers: August 30, 2022

Final notification to authors: October 30, 2022

Rolling publication of special issue: late 2022/early 2023

 

Submission Instructions:

Prepare your paper in accordance with the Journal guidelines: www.springer.com/12559 (this opens in a new tab). Submit manuscripts at:  http://www.editorialmanager.com/cogn/ (this opens in a new tab).  Select “SI: Advances in Multi-modal Deep and Shallow Neural Networks for Neuroimaging Applications” for the special issue under “Additional Information.”  Your paper must contain significant and original work that has not been published nor submitted to any journals. All papers will be reviewed following standard reviewing procedures of the Journal.