Automated quality control of small animal MR neuroimaging data

MRI is a valuable tool for studying brain structure and function in animal and clinical studies. With the growth of public MRI repositories, access to data has finally become easier. However, filtering large data sets for potential poor quality outliers can be a challenge. We present AIDAqc, a machine learning-assisted automated Python-based command-line tool for the quality assessment of small animal MRI data. Quality control features include signal-to-noise ratio (SNR), temporal SNR, and motion. All features are automatically calculated and no regions of interest are needed. Automated outlier detection is based on the combination of interquartile range and the machine learning methods one-class support vector machine, isolation forest, local outlier factor, and elliptic envelope. AIDAqc was challenged in a large heterogeneous dataset collected from 18 international laboratories, including data from mice, rats, rabbits, hamsters, and gerbils, obtained with different hardware and at different field strengths. The results show that the manual inter-rater variability (mean Fleiss Kappa score 0.17) is high when identifying poor quality data. A direct comparison of AIDAqc results therefore showed only low to moderate concordance. In a manual post-hoc validation of AIDAqc output, agreement was high (>70%). The outlier data can have a significant impact on further post-processing, as shown in representative functional and structural connectivity analysis. In summary, this pipeline optimized for small animal MRI provides researchers with a valuable tool to efficiently and effectively assess the quality of their MRI data, which is essential for improved reliability and reproducibility.