首页|New Machine Learning Study Findings Reported from University of Cologne (Automat ed quality control of small animal MR neuroimaging data)
New Machine Learning Study Findings Reported from University of Cologne (Automat ed quality control of small animal MR neuroimaging data)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Data detailed on artificial intelligen ce have been presented. According to news reporting from Cologne, Germany, by Ne wsRx journalists, research stated, “MRI is a valuable tool for studying brain st ructure and function in animal and clinical studies. With the growth of public M RI repositories, access to data has finally become easier.” The news journalists obtained a quote from the research from University of Colog ne: “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 small animal MRI quality assessment. Quality control features include signal-to-noise ratio (SNR), temporal SNR, and motion. All fea tures are automatically calculated and no regions of interest are needed. Automa ted outlier detection for a given dataset combines the interquartile range and t he machine learning methods one-class support vector machine, isolation forest, local outlier factor, and elliptic envelope. To evaluate the reliability of indi vidual quality control metrics, a simulation of noise (Gaussian, salt and pepper , speckle) and motion was performed. In outlier detection, single scans with ind uced artifacts were successfully identified by AIDAqc. AIDAqc was challenged in a large heterogeneous dataset collected from 19 international laboratories, incl uding data from mice, rats, rabbits, hamsters, and gerbils, obtained with differ ent hardware and at different field strengths. The results show that the manual inter-rater agreement (mean Fleiss Kappa score 0.17) is low when identifying poo r-quality data. A direct comparison of AIDAqc results, therefore, showed only lo w to moderate concordance.”
University of CologneCologneGermanyEuropeCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
