3D-QCNet – A pipeline for automated artifact detection in diffusion MRI images. (January 2023)

• Record Type: Journal Article
• Authors: Ahmad, Adnan; Parker, Drew; Dheer, Suhani; Samani, Zahra Riahi; Verma, Ragini
• Is Part Of: Computerized medical imaging and graphics. Volume 103(2023)
• Publication Date: 2023-01
• Subjects: Quality control -- Artifacts -- MRI -- Diffusion MRI -- Deep learning; Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Diagnosis, Radioscopic -- Data processing -- Periodicals; Diagnostic Imaging -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Diagnostic imaging; Periodicals; Electronic journals; Electronic journals; 616.0754
• DOI: 10.1016/j.compmedimag.2022.102151
• Languages: English
• ISSNs: 0895-6111

Abstract

Abstract: Artifacts are a common occurrence in Diffusion MRI (dMRI) scans. Identifying and removing them is essential to ensure the accuracy and viability of any post-processing carried out on these scans. This makes quality control (QC) a crucial first step prior to any analysis of dMRI data. Several QC methods for artifact detection exist, however they suffer from problems like requiring manual intervention and the inability to generalize across different artifacts and datasets. In this paper, we propose an automated deep learning (DL) pipeline that utilizes a 3D-Densenet architecture to train a model on diffusion volumes for automatic artifact detection. Our method is validated on 9000 volumes sourced from 7 large clinical datasets spanning different acquisition protocols (with different gradient directions, high and low b-values, single-shell and multi-shell acquisitions) from multiple scanners. Additionally, they represent diverse subject demographics including age, sex and the presence or absence of pathologies. Our QC method is found to accurately generalize across this heterogenous data by correctly detecting 92% artifacts on average across our test set. This consistent performance over diverse datasets underlines the generalizability of our method, which currently is a significant barrier hindering the widespread adoption of automated QC techniques. Thus, 3D-QCNet can be integrated into diffusion pipelines to effectively automate the arduous and time-intensive process of artifact detection. Highlights: Diffusion MRI artifact detection is currently a manual and arduous process. We propose 3D-QCNet, an automated Densenet based Deep Learning method to detect artifacts. To illustrate its practical viability, we tested the method on 7 large clinical datasets with different forms of pathology. The model obtained consistent accurate results on all datasets, without the need for fine tuning. This generalizability across diverse datasets suggests that the method can be integrated into dMRI preprocessing pipelines.