QC-Automator: Deep Learning-Based Automated Quality Control for Diffusion MR Images

  title={QC-Automator: Deep Learning-Based Automated Quality Control for Diffusion MR Images},
  author={Zahra Riahi Samani and Jacob A. Alappatt and Drew Parker and Abdol Aziz Ould Ismail and Ragini Verma},
  journal={Frontiers in Neuroscience},
Quality assessment of diffusion MRI (dMRI) data is essential prior to any analysis, so that appropriate pre-processing can be used to improve data quality and ensure that the presence of MRI artifacts do not affect the results of subsequent image analysis. Manual quality assessment of the data is subjective, possibly error-prone, and infeasible, especially considering the growing number of consortium-like studies, underlining the need for automation of the process. In this paper, we have… 

3D-QCNet - A Pipeline for Automated Artifact Detection in Diffusion MRI images

An automated deep learning pipeline that utilizes a 3D-Densenet architecture to train a model on diffusion volumes for automatic artifact detection and is found to accurately generalize across this heterogenous data by correctly detecting 92% artifacts on average across the authors' test set.

Automatic detection of Gibbs artefact in MR images with transfer learning approach.

It is shown that transfer learning can be successfully used to detect Gibbs artefacts on magnetic resonance images, which shows the potential of transfer learning for the more general task of detecting artefacts in magnetic resonance image of patients, which consequently can improve and speed up the process of quality assessment in medical imaging practice.

Automatic Multi-Class Cardiovascular Magnetic Resonance Image Quality Assessment using Unsupervised Domain Adaptation in Spatial and Frequency Domains

This study provides an automated approach to assess image quality from cardiovascular magnetic resonance (CMR) imaging at scale by identifying four common CMR imaging artefacts, including respiratory motion, cardiac motion, Gibbs ringing, and aliasing.

MRI Quality Control Algorithm Based on Image Analysis Using Convolutional and Recurrent Neural Networks

A method based on neural networks that takes into account the three-dimensional context through the use of bidirectional LSTM, as well as a pre-training method based upon a prediction of no-reference quality metrics using EfficientNet convolutional neural network that allows the useof unlabeled data is proposed.

Incorporating outlier information into diffusion MR tractogram filtering for robust structural brain connectivity and microstructural analyses

A novel augmentation to tractogram filtering method that accounts for subject motion related signal dropout artefacts in diffusion weighted images and shows that even if data has 10% of motion corrupted slices the authors' method is capable to mitigate their effect in structural brain connectivity analyses and microstructural mapping.

Transfer Learning in Magnetic Resonance Brain Imaging: A Systematic Review

A systematic literature search for articles that applied transfer learning to MR brain imaging tasks found 129 articles, and a new categorization to group specific, widely-used approaches such as pre-training and fine-tuning CNNs was proposed.

Distinct tumor signatures using deep learning-based characterization of the peritumoral microenvironment in glioblastomas and brain metastases

The results demonstrate that the extracellular water content of the peritumoral tissue, as captured by the free water volume fraction, is best able to characterize the differences between infiltrative and vasogenic per itumoral regions, paving the way for its use in classifying and benchmarking perituoral tissue with varying degrees of infiltration.

Automating the optical identification of abrasive wear on electrical contact pins

This work proposes and test a novel pipeline which combines a deep network for image segmentation with geometric priors of the problem, and introduces a new automation pipeline for the quantification of wear on electrical contact pins.



DTIPrep: quality control of diffusion-weighted images

This manuscript presents the open-source software, DTIPrep, as a unified, user friendly platform for thorough QC of dMRI data, and focuses on newly added capabilities related to directional artifacts and bias analysis.

Retrospective Head Motion Estimation in Structural Brain MRI with 3D CNNs

A supervised learning method to retrospectively estimate motion from plain MRI, using a 3D convolutional neural network to assess if voxels are corrupted by motion or not, and shows that the proposed measure of motion explains away 37% of the variation in cortical thickness.

k-Space tutorial: an MRI educational tool for a better understanding of k-space

This work introduces 'k-Space tutorial', a MATLAB-based educational environment to learn how the image and the k-space are related, andHow the image can be affected through k- space modifications.

Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?

This paper considered four distinct medical imaging applications in three specialties involving classification, detection, and segmentation from three different imaging modalities, and investigated how the performance of deep CNNs trained from scratch compared with the pre-trained CNNs fine-tuned in a layer-wise manner.