Multimodal Infant Brain Segmentation by Fuzzy-Informed Deep Learning

Faculty Computer Science Year: 2021
Type of Publication: ZU Hosted Pages: Page(s): 1088 - 1101
Authors:
Journal: IEEE Transactions on Fuzzy Systems IEEE Volume: Volume: 30
Keywords : Multimodal Infant Brain Segmentation , Fuzzy-Informed Deep    
Abstract:
Magnetic resonance imaging (MRI) is a prevailing method of modal infant brain tissue analysis that precisely segments brain tissue and is vitally important for diagnosis, remediation, and analysis of early brain development. To achieve such segmentation is challenging, particularly for the brain of a six-month-old, owing to several factors: poor image quality; isointense contrast between white and gray matter and the simple incomplete volume consequence of a tiny brain size; and discrepancies in brain tissues, illumination settings, and the vagarious region. This article addresses these challenges with a fuzzy-informed deep learning segmentation network that takes T1- and T2-weighted MRIs as inputs. First, a fuzzy logic layer encodes input to the fuzzy domain. Second, a volumetric fuzzy pooling (VFP) layer models the local fuzziness of the volumetric convolutional maps by applying fuzzification, accumulation, and defuzzification on the adjacency feature map neighborhoods. Third, the VFP layer is employed to design the fuzzy-enabled multiscale feature learning module to enable the extraction of brain features in different receptive fields. Finally, we redesign the Project & Excite module using the VPF layer to enable modeling uncertainty during feature recalibration, and a comprehensive training paradigm is used to learn the ideal parameters of every building block. Extensive experimental comparative studies substantiate the efficiency and accuracy of the proposed model in terms of different evaluation metrics to solve multimodal infant brain segmentation problems on the iSeg-2017 dataset.
   
     
 
       

Author Related Publications

  • Hosam Rada mohamed abdel megeed hawash, "RCTE: A reliable and consistent temporal-ensembling framework for semi-supervised segmentation of COVID-19 lesions", ElSEVIER, 2021 More
  • Hosam Rada mohamed abdel megeed hawash, "PV-Net: An innovative deep learning approach for efficient forecasting of short-term photovoltaic energy production", ElSEVIER, 2021 More
  • Hosam Rada mohamed abdel megeed hawash, "Two-Stage Deep Learning Framework for Discrimination between COVID-19 and Community-Acquired Pneumonia from Chest CT scans", ElSEVIER, 2021 More
  • Hosam Rada mohamed abdel megeed hawash, "Deep learning approaches for human centered IoT applications in smart indoor environments: a contemporary survey", Springer, 2021 More
  • Hosam Rada mohamed abdel megeed hawash, "ST-DeepHAR: Deep Learning Model for Human Activity Recognition in IoHT Applications", IEEE, 2020 More

Department Related Publications

  • Ahmed Raafat Abass Mohamed Saliem, "BERT-CNN: A Deep Learning Model for Detecting Emotions from Text", Tech Science Press, 2021 More
  • Ibrahiem Mahmoud Mohamed Elhenawy, "BERT-CNN: A Deep Learning Model for Detecting Emotions from Text", Tech Science Press, 2021 More
  • Ahmed Raafat Abass Mohamed Saliem, "Using General Regression with Local Tuning for Learning Mixture Models from Incomplete Data Sets", ScienceDirect, 2010 More
  • Ahmed Raafat Abass Mohamed Saliem, "On determining efficient finite mixture models with compact and essential components for clustering data", ScienceDirect, 2013 More
  • Ahmed Raafat Abass Mohamed Saliem, "Unsupervised learning of mixture models based on swarm intelligence and neural networks with optimal completion using incomplete data", ScienceDirect, 2012 More
Tweet