Improving labeling efficiency in automatic quality control of MRSI data

Abstract

Active learning using uncertainty sampling is an effective way to increase the labeling efficiency for training automatic quality control classifiers. Magn Reson Med 78:2399-2405, 2017. © 2017 International Society for Magnetic Resonance in Medicine.

A convolutional neural network to filter artifacts in spectroscopic MRI

“…Furthermore, the network was wrapped into a framework that enabled rapid deployment of the filter into the clinical research workflow, and could be applied in under 2 minutes to high‐resolution EPSI data with whole‐brain coverage. The accuracy achieved is similar to that reported in previous studies using machine learning for MR spectral quality analysis, such as those using random forests with engineered spectral features . It is difficult to compare results across studies, as a result of variation in study design (e.g., how data were collected, the biases of the raters generating ground truth, and which parameters were chosen as features).…”

“…Another challenge in developing algorithms for spectral quality filtering is the low percentage of poor‐quality voxels present in a whole‐brain volume compared with good quality voxels, which yields an imbalance in class proportions and consequently can hinder algorithm performance . In the data set collected in this work, 72% of spectra were of good quality and 28% were of poor quality, which is similar to proportions (65‐84% acceptable spectra) observed in other works . To assess whether balanced class proportions would affect CNN performance, a random minority oversampling scheme was implemented, in which data from the minority class (poor spectra) were randomly sampled multiple times to artificially increase the number of samples.…”

“…13 In the data set collected in this work, 72% of spectra were of good quality and 28% were of poor quality, which is similar to proportions (65-84% acceptable spectra) observed in other works. 11,13,31 To assess whether balanced class proportions would affect CNN performance, a random minority oversampling scheme was implemented, in which data from the minority class (poor spectra) were randomly sampled multiple times to artificially increase the number of samples. A new CNN was trained using the same network architecture on this oversampled data set, with 5991 good quality and 5991 poor quality, and tuned using Bayesian optimization as described in the "Methods" section.…”

Incorporation of a spectral model in a convolutional neural network for accelerated spectral fitting

“…Machine learning has proven to have exceptional use in medical imaging, including MRSI . Hiltunen et al described an artificial neural network (ANN) architecture that could predict metabolite peak areas from magnitude spectra in patients with gliomas.…”

“…Machine learning has proven to have exceptional use in medical imaging, including MRSI. [22][23][24][25][26][27] Hiltunen et al 26 described an artificial neural network (ANN) architecture that could predict metabolite peak areas from magnitude spectra in patients with gliomas. Das et al 28 presented a multi-layer perceptron (MLP) for quantifying metabolite concentrations from synthetically generated spectra and phase-encoded 2D MRSI using results from LCModel as data for supervised training, achieving accurate predictions of metabolite concentrations, and Bhat et al 27 used an unsupervised neural network for analysis of phase-corrected 2D MRSI data.…”