A Contrast Augmentation Approach to Improve Multi-Scanner Generalization in MRI.

Most data-driven methods are very susceptible to data variability. This problem is particularly apparent when applying Deep Learning (DL) to brain Magnetic Resonance Imaging (MRI), where intensities and contrasts vary due to acquisition protocol, scanner- and center-specific factors. Most publicly available brain MRI datasets originate from the same center and are homogeneous in terms of scanner and used protocol. As such, devising robust methods that generalize to multi-scanner and multi-center data is crucial for transferring these techniques into clinical practice. We propose a novel data augmentation approach based on Gaussian Mixture Models (GMM-DA) with the goal of increasing the variability of a given dataset in terms of intensities and contrasts. The approach allows to augment the training dataset such that the variability in the training set compares to what is seen in real world clinical data, while preserving anatomical information. We compare the performance of a state-of-the-art U-Net model trained for segmenting brain structures with and without the addition of GMM-DA. The models are trained and evaluated on single- and multi-scanner datasets. Additionally, we verify the consistency of test-retest results on same-patient images (same and different scanners). Finally, we investigate how the presence of bias field influences the performance of a model trained with GMM-DA. We found that the addition of the GMM-DA improves the generalization capability of the DL model to other scanners not present in the training data, even when the train set is already multi-scanner. Besides, the consistency between same-patient segmentation predictions is improved, both for same-scanner and different-scanner repetitions. We conclude that GMM-DA could increase the transferability of DL models into clinical scenarios.

Automated MRI volumetry as a diagnostic tool for Alzheimer's disease: Validation of icobrain dm.

Brain volumes computed from magnetic resonance images have potential for assisting with the diagnosis of individual dementia patients, provided that they have low measurement error and high reliability. In this paper we describe and validate icobrain dm, an automatic tool that segments brain structures that are relevant for differential diagnosis of dementia, such as the hippocampi and cerebral lobes. Experiments were conducted in comparison to the widely used FreeSurfer software. The hippocampus segmentations were compared against manual segmentations, with significantly higher Dice coefficients obtained with icobrain dm (25-75th quantiles: 0.86-0.88) than with FreeSurfer (25-75th quantiles: 0.80-0.83). Other brain structures were also compared against manual delineations, with icobrain dm showing lower volumetric errors overall. Test-retest experiments show that the precision of all measurements is higher for icobrain dm than for FreeSurfer except for the parietal cortex volume. Finally, when comparing volumes obtained from Alzheimer's disease patients against age-matched healthy controls, all measures achieved high diagnostic performance levels when discriminating patients from cognitively healthy controls, with the temporal cortex volume measured by icobrain dm reaching the highest diagnostic performance level (area under the receiver operating characteristic curve = 0.99) in this dataset.

Analysis of metabolic abnormalities in high-grade glioma using MRSI and convex NMF.

Clinical use of MRSI is limited by the level of experience required to properly translate MRSI examinations into relevant clinical information. To solve this, several methods have been proposed to automatically recognize a predefined set of reference metabolic patterns. Given the variety of metabolic patterns seen in glioma patients, the decision on the optimal number of patterns that need to be used to describe the data is not trivial. In this paper, we propose a novel framework to (1) separate healthy from abnormal metabolic patterns and (2) retrieve an optimal number of reference patterns describing the most important types of abnormality. Using 41 MRSI examinations (1.5 T, PRESS, TE 135 ms) from 22 glioma patients, four different patterns describing different types of abnormality were detected: edema, healthy without Glx, active tumor and necrosis. The identified patterns were then evaluated on 17 MRSI examinations from nine different glioma patients. The results were compared against BraTumIA, an automatic segmentation method trained to identify different tumor compartments on structural MRI data. Finally, the ability to predict future contrast enhancement using the proposed approach was also evaluated.

On the relation between MR spectroscopy features and the distance to MRI-visible solid tumor in GBM patients.

PURPOSE: To improve the detection of peritumoral changes in GBM patients by exploring the relation between MRSI information and the distance to the solid tumor volume (STV) defined using structural MRI (sMRI). METHODS: Twenty-three MRSI studies (PRESS, TE 135 ms) acquired from different patients with untreated GBM were used in this study. For each MRSI examination, the STV was identified by segmenting the corresponding sMRI images using BraTumIA, an automatic segmentation method. The relation between different metabolite ratios and the distance to STV was analyzed. A regression forest was trained to predict the distance from each voxel to STV based on 14 metabolite ratios. Then, the trained model was used to determine the expected distance to tumor (EDT) for each voxel of the MRSI test data. EDT maps were compared against sMRI segmentation. RESULTS: The features showing abnormal values at the longest distances to the tumor were: %NAA, Glx/NAA, Cho/NAA, and Cho/Cr. These four features were also the most important for the prediction of the distances to STV. Each EDT value was associated with a specific metabolic pattern, ranging from normal brain tissue to actively proliferating tumor and necrosis. Low EDT values were highly associated with malignant features such as elevated Cho/NAA and Cho/Cr. CONCLUSION: The proposed method enables the automatic detection of metabolic patterns associated with different distances to the STV border and may assist tumor delineation of infiltrative brain tumors such as GBM.

Quality of clinical brain tumor MR spectra judged by humans and machine learning tools.

PURPOSE: To investigate and compare human judgment and machine learning tools for quality assessment of clinical MR spectra of brain tumors. METHODS: A very large set of 2574 single voxel spectra with short and long echo time from the eTUMOUR and INTERPRET databases were used for this analysis. Original human quality ratings from these studies as well as new human guidelines were used to train different machine learning algorithms for automatic quality control (AQC) based on various feature extraction methods and classification tools. The performance was compared with variance in human judgment. RESULTS: AQC built using the RUSBoost classifier that combats imbalanced training data performed best. When furnished with a large range of spectral and derived features where the most crucial ones had been selected by the TreeBagger algorithm it showed better specificity (98%) in judging spectra from an independent test-set than previously published methods. Optimal performance was reached with a virtual three-class ranking system. CONCLUSION: Our results suggest that feature space should be relatively large for the case of MR tumor spectra and that three-class labels may be beneficial for AQC. The best AQC algorithm showed a performance in rejecting spectra that was comparable to that of a panel of human expert spectroscopists. Magn Reson Med 79:2500-2510, 2018. © 2017 International Society for Magnetic Resonance in Medicine.

Improving labeling efficiency in automatic quality control of MRSI data.

PURPOSE: To improve the efficiency of the labeling task in automatic quality control of MR spectroscopy imaging data. METHODS: 28'432 short and long echo time (TE) spectra (1.5 tesla; point resolved spectroscopy (PRESS); repetition time (TR)= 1,500 ms) from 18 different brain tumor patients were labeled by two experts as either accept or reject, depending on their quality. For each spectrum, 47 signal features were extracted. The data was then used to run several simulations and test an active learning approach using uncertainty sampling. The performance of the classifiers was evaluated as a function of the number of patients in the training set, number of spectra in the training set, and a parameter α used to control the level of classification uncertainty required for a new spectrum to be selected for labeling. RESULTS: The results showed that the proposed strategy allows reductions of up to 72.97% for short TE and 62.09% for long TE in the amount of data that needs to be labeled, without significant impact in classification accuracy. Further reductions are possible with significant but minimal impact in performance. CONCLUSION: 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.

Quality management in in vivo proton MRS.

The quality of MR-Spectroscopy data can easily be affected in in vivo applications. Several factors may produce signal artefacts, and often these are not easily detected, not even by experienced spectroscopists. Reliable and reproducible in vivo MRS-data requires the definition of quality requirements and goals, implementation of measures to guarantee quality standards, regular control of data quality, and a continuous search for quality improvement. The first part of this review includes a general introduction to different aspects of quality management in MRS. It is followed by the description of a series of tests and phantoms that can be used to assure the quality of the MR system. In the third part, several methods and strategies used for quality control of the spectroscopy data are presented. This review concludes with a reference to a few interesting techniques and aspects that may help to further improve the quality of in vivo MR-spectra.

Automatic quality control in clinical (1)H MRSI of brain cancer.

MRSI grids frequently show spectra with poor quality, mainly because of the high sensitivity of MRS to field inhomogeneities. These poor quality spectra are prone to quantification and/or interpretation errors that can have a significant impact on the clinical use of spectroscopic data. Therefore, quality control of the spectra should always precede their clinical use. When performed manually, quality assessment of MRSI spectra is not only a tedious and time-consuming task, but is also affected by human subjectivity. Consequently, automatic, fast and reliable methods for spectral quality assessment are of utmost interest. In this article, we present a new random forest-based method for automatic quality assessment of (1)H MRSI brain spectra, which uses a new set of MRS signal features. The random forest classifier was trained on spectra from 40 MRSI grids that were classified as acceptable or non-acceptable by two expert spectroscopists. To account for the effects of intra-rater reliability, each spectrum was rated for quality three times by each rater. The automatic method classified these spectra with an area under the curve (AUC) of 0.976. Furthermore, in the subset of spectra containing only the cases that were classified every time in the same way by the spectroscopists, an AUC of 0.998 was obtained. Feature importance for the classification was also evaluated. Frequency domain skewness and kurtosis, as well as time domain signal-to-noise ratios (SNRs) in the ranges 50-75 ms and 75-100 ms, were the most important features. Given that the method is able to assess a whole MRSI grid faster than a spectroscopist (approximately 3 s versus approximately 3 min), and without loss of accuracy (agreement between classifier trained with just one session and any of the other labelling sessions, 89.88%; agreement between any two labelling sessions, 89.03%), the authors suggest its implementation in the clinical routine. The method presented in this article was implemented in jMRUI's SpectrIm plugin.