UNASSIGNED: Magnetic resonance imaging (MRI) scans are highly sensitive to acquisition and reconstruction parameters which affect feature stability and model generalizability in radiomic research. This work aims to investigate the effect of image pre-processing and harmonization methods on the stability of brain MRI radiomic features and the prediction performance of radiomic models in patients with brain metastases (BMs).
UNASSIGNED: Two T1 contrast enhanced brain MRI data-sets were used in this study. The first contained 25 BMs patients with scans at two different time points and was used for features stability analysis. The effect of gray level discretization (GLD), intensity normalization (Z-score, Nyul, WhiteStripe, and in house-developed method named N-Peaks), and ComBat harmonization on features stability was investigated and features with intraclass correlation coefficient >0.8 were considered as stable. The second data-set containing 64 BMs patients was used for a classification task to investigate the informativeness of stable features and the effects of harmonization methods on radiomic model performance.
UNASSIGNED: Applying fixed bin number (FBN) GLD, resulted in higher number of stable features compare to fixed bin size (FBS) discretization (10 ± 5.5 % higher). `Harmonization in feature domain improved the stability for non-normalized and normalized images with Z-score and WhiteStripe methods. For the classification task, keeping the stable features resulted in good performance only for normalized images with N-Peaks along with FBS discretization.
UNASSIGNED: To develop a robust MRI based radiomic model we recommend using an intensity normalization method based on a reference tissue (e.g N-Peaks) and then using FBS discretization.

Objective. Multi-parametric magnetic resonance imaging (mpMRI) has become an important tool for the detection of prostate cancer in the past two decades. Despite the high sensitivity of MRI for tissue characterization, it often suffers from a lack of specificity. Several well-established pre-processing tools are publicly available for improving image quality and removing both intra- and inter-patient variability in order to increase the diagnostic accuracy of MRI. To date, most of these pre-processing tools have largely been assessed individually. In this study we present a systematic evaluation of a multi-step mpMRI pre-processing pipeline to automate tumor localization within the prostate using a previously trained model.Approach. The study was conducted on 31 treatment-naïve prostate cancer patients with a PI-RADS-v2 compliant mpMRI examination. Multiple methods were compared for each pre-processing step: (1) bias field correction, (2) normalization, and (3) deformable multi-modal registration. Optimal parameter values were estimated for each step on the basis of relevant individual metrics. Tumor localization was then carried out via a model-based approach that takes both mpMRI and prior clinical knowledge features as input. A sequential optimization approach was adopted for determining the optimal parameters and techniques in each step of the pipeline.Main results. The application of bias field correction alone increased the accuracy of tumor localization (area under the curve (AUC) = 0.77;p-value = 0.004) over unprocessed data (AUC = 0.74). Adding normalization to the pre-processing pipeline further improved diagnostic accuracy of the model to an AUC of 0.85 (p-value = 0.000 12). Multi-modal registration of apparent diffusion coefficient images to T2-weighted images improved the alignment of tumor locations in all but one patient, resulting in a slight decrease in accuracy (AUC = 0.84;p-value = 0.30).Significance. Overall, our findings suggest that the combined effect of multiple pre-processing steps with optimal values has the ability to improve the quantitative classification of prostate cancer using mpMRI. Clinical trials: NCT03378856 and NCT03367702.

BACKGROUND: The ratio of T1-weighted (T1w) and T2-weighted (T2w) magnetic resonance imaging (MRI) images is often used as a proxy measure of cortical myelin. However, the T1w/T2w-ratio is based on signal intensities that are inherently non-quantitative and known to be affected by extrinsic factors. To account for this a variety of processing methods have been proposed, but a systematic evaluation of their efficacy is lacking. Given the dependence of the T1w/T2w-ratio on scanner hardware and T1w and T2w protocols, it is important to ensure that processing pipelines perform well also across different sites.
METHODS: We assessed a variety of processing methods for computing cortical T1w/T2w-ratio maps, including correction methods for nonlinear field inhomogeneities, local outliers, and partial volume effects as well as intensity normalisation. These were implemented in 33 processing pipelines which were applied to four test-retest datasets, with a total of 170 pairs of T1w and T2w images acquired on four different MRI scanners. We assessed processing pipelines across datasets in terms of their reproducibility of expected regional distributions of cortical myelin, lateral intensity biases, and test-retest reliability regionally and across the cortex. Regional distributions were compared both qualitatively with histology and quantitatively with two reference datasets, YA-BC and YA-B1+, from the Human Connectome Project.
RESULTS: Reproducibility of raw T1w/T2w-ratio distributions was overall high with the exception of one dataset. For this dataset, Spearman rank correlations increased from 0.27 to 0.70 after N3 bias correction relative to the YA-BC reference and from -0.04 to 0.66 after N4ITK bias correction relative to the YA-B1+ reference. Partial volume and outlier corrections had only marginal effects on the reproducibility of T1w/T2w-ratio maps and test-retest reliability. Before intensity normalisation, we found large coefficients of variation (CVs) and low intraclass correlation coefficients (ICCs), with total whole-cortex CV of 10.13% and whole-cortex ICC of 0.58 for the raw T1w/T2w-ratio. Intensity normalisation with WhiteStripe, RAVEL, and Z-Score improved total whole-cortex CVs to 5.91%, 5.68%, and 5.19% respectively, whereas Z-Score and Least Squares improved whole-cortex ICCs to 0.96 and 0.97 respectively.
CONCLUSIONS: In the presence of large intensity nonuniformities, bias field correction is necessary to achieve acceptable correspondence with known distributions of cortical myelin, but it can be detrimental in datasets with less intensity inhomogeneity. Intensity normalisation can improve test-retest reliability and inter-subject comparability. However, both bias field correction and intensity normalisation methods vary greatly in their efficacy and may affect the interpretation of results. The choice of T1w/T2w-ratio processing method must therefore be informed by both scanner and acquisition protocol as well as the given study objective. Our results highlight limitations of the T1w/T2w-ratio, but also suggest concrete ways to enhance its usefulness in future studies.

Introduction: [18F]-FDG PET is a widely used imaging modality that visualizes cellular glucose uptake and provides functional information on the metabolic state of different tissues in vivo. Various quantification methods can be used to evaluate glucose metabolism in the brain, including the cerebral metabolic rate of glucose (CMRglc) and standard uptake values (SUVs). Especially in the brain, these (semi-)quantitative measures can be affected by several physiological factors, such as blood glucose level, age, gender, and stress. Next to this inter- and intra-subject variability, the use of different PET acquisition protocols across studies has created a need for the standardization and harmonization of brain PET evaluation. In this study we present a framework for statistical voxel-based analysis of glucose uptake in the rat brain using histogram-based intensity normalization. Methods: [18F]-FDG PET images of 28 normal rat brains were coregistered and voxel-wisely averaged. Ratio images were generated by voxel-wisely dividing each of these images with the group average. The most prevalent value in the ratio image was used as normalization factor. The normalized PET images were voxel-wisely averaged to generate a normal rat brain atlas. The variability of voxel intensities across the normalized PET images was compared to images that were either normalized by whole brain normalization, or not normalized. To illustrate the added value of this normal rat brain atlas, 9 animals with a striatal hemorrhagic lesion and 9 control animals were intravenously injected with [18F]-FDG and the PET images of these animals were voxel-wisely compared to the normal atlas by group- and individual analyses. Results: The average coefficient of variation of the voxel intensities in the brain across normal [18F]-FDG PET images was 6.7% for the histogram-based normalized images, 11.6% for whole brain normalized images, and 31.2% when no normalization was applied. Statistical voxel-based analysis, using the normal template, indicated regions of significantly decreased glucose uptake at the site of the ICH lesion in the ICH animals, but not in control animals. Conclusion: In summary, histogram-based intensity normalization of [18F]-FDG uptake in the brain is a suitable data-driven approach for standardized voxel-based comparison of brain PET images.

Image normalization is a building block in medical image analysis. Conventional approaches are customarily employed on a per-dataset basis. This strategy, however, prevents the current normalization algorithms from fully exploiting the complex joint information available across multiple datasets. Consequently, ignoring such joint information has a direct impact on the processing of segmentation algorithms. This paper proposes to revisit the conventional image normalization approach by, instead, learning a common normalizing function across multiple datasets. Jointly normalizing multiple datasets is shown to yield consistent normalized images as well as an improved image segmentation when intensity shifts are large. To do so, a fully automated adversarial and task-driven normalization approach is employed as it facilitates the training of realistic and interpretable images while keeping performance on par with the state-of-the-art. The adversarial training of our network aims at finding the optimal transfer function to improve both, jointly, the segmentation accuracy and the generation of realistic images. We have evaluated the performance of our normalizer on both infant and adult brain images from the iSEG, MRBrainS and ABIDE datasets. The results indicate that our contribution does provide an improved realism to the normalized images, while retaining a segmentation accuracy at par with the state-of-the-art learnable normalization approaches.

In brain MRI radiomics studies, the non-biological variations introduced by different image acquisition settings, namely scanner effects, affect the reliability and reproducibility of the radiomics results. This paper assesses how the preprocessing methods (including N4 bias field correction and image resampling) and the harmonization methods (either the six intensity normalization methods working on brain MRI images or the ComBat method working on radiomic features) help to remove the scanner effects and improve the radiomic feature reproducibility in brain MRI radiomics. The analyses were based on in vitro datasets (homogeneous and heterogeneous phantom data) and in vivo datasets (brain MRI images collected from healthy volunteers and clinical patients with brain tumors). The results show that the ComBat method is essential and vital to remove scanner effects in brain MRI radiomic studies. Moreover, the intensity normalization methods, while not able to remove scanner effects at the radiomic feature level, still yield more comparable MRI images and improve the robustness of the harmonized features to the choice among ComBat implementations.

BACKGROUND: The objective of the study is to define the most appropriate region for intensity normalization in brain 18FDG PET semi-quantitative analysis. The best option could be based on previous absolute quantification studies, which showed that the metabolic changes related to ageing affect the quasi-totality of brain regions in healthy subjects. Consequently, brain metabolic changes related to ageing were evaluated in two populations of healthy controls who underwent conventional (n = 56) or digital (n = 78) 18FDG PET/CT. The median correlation coefficients between age and the metabolism of each 120 atlas brain region were reported for 120 distinct intensity normalizations (according to the 120 regions). SPM linear regression analyses with age were performed on most significant normalizations (FWE, p < 0.05).
RESULTS: The cerebellum and pons were the two sole regions showing median coefficients of correlation with age less than - 0.5. With SPM, the intensity normalization by the pons provided at least 1.7- and 2.5-fold more significant cluster volumes than other normalizations for conventional and digital PET, respectively.
CONCLUSIONS: The pons is the most appropriate area for brain 18FDG PET intensity normalization for examining the metabolic changes through ageing.

In multisite neuroimaging studies there is often unwanted technical variation across scanners and sites. These \"scanner effects\" can hinder detection of biological features of interest, produce inconsistent results, and lead to spurious associations. We propose mica (multisite image harmonization by cumulative distribution function alignment), a tool to harmonize images taken on different scanners by identifying and removing within-subject scanner effects. Our goals in the present study were to (1) establish a method that removes scanner effects by leveraging multiple scans collected on the same subject, and, building on this, (2) develop a technique to quantify scanner effects in large multisite studies so these can be reduced as a preprocessing step. We illustrate scanner effects in a brain MRI study in which the same subject was measured twice on seven scanners, and assess our method\'s performance in a second study in which ten subjects were scanned on two machines. We found that unharmonized images were highly variable across site and scanner type, and our method effectively removed this variability by aligning intensity distributions. We further studied the ability to predict image harmonization results for a scan taken on an existing subject at a new site using cross-validation.

The lack of standardization of intensity normalization methods and its unknown effect on the quantification output is recognized as a major drawback for the harmonization of brain FDG-PET quantification protocols. The aim of this work is the ground truth-based evaluation of different intensity normalization methods on brain FDG-PET quantification output.
Realistic FDG-PET images were generated using Monte Carlo simulation from activity and attenuation maps directly derived from 25 healthy subjects (adding theoretical relative hypometabolisms on 6 regions of interest and for 5 hypometabolism levels). Single-subject statistical parametric mapping (SPM) was applied to compare each simulated FDG-PET image with a healthy database after intensity normalization based on reference regions methods such as the brain stem (RRBS), cerebellum (RRC) and the temporal lobe contralateral to the lesion (RRTL), and data-driven methods, such as proportional scaling (PS), histogram-based method (HN) and iterative versions of both methods (iPS and iHN). The performance of these methods was evaluated in terms of the recovery of the introduced theoretical hypometabolic pattern and the appearance of unspecific hypometabolic and hypermetabolic findings.
Detected hypometabolic patterns had significantly lower volumes than the introduced hypometabolisms for all intensity normalization methods particularly for slighter reductions in metabolism . Among the intensity normalization methods, RRC and HN provided the largest recovered hypometabolic volumes, while the RRBS showed the smallest recovery. In general, data-driven methods overcame reference regions and among them, the iterative methods overcame the non-iterative ones. Unspecific hypermetabolic volumes were similar for all methods, with the exception of PS, where it became a major limitation (up to 250 cm3) for extended and intense hypometabolism. On the other hand, unspecific hypometabolism was similar far all methods, and usually solved with appropriate clustering.
Our findings showed that the inappropriate use of intensity normalization methods can provide remarkable bias in the detected hypometabolism and it represents a serious concern in terms of false positives. Based on our findings, we recommend the use of histogram-based intensity normalization methods. Reference region methods performance was equivalent to data-driven methods only when the selected reference region is large and stable.

Image synthesis learns a transformation from the intensity features of an input image to yield a different tissue contrast of the output image. This process has been shown to have application in many medical image analysis tasks including imputation, registration, and segmentation. To carry out synthesis, the intensities of the input images are typically scaled-i.e., normalized-both in training to learn the transformation and in testing when applying the transformation, but it is not presently known what type of input scaling is optimal. In this paper, we consider seven different intensity normalization algorithms and three different synthesis methods to evaluate the impact of normalization. Our experiments demonstrate that intensity normalization as a preprocessing step improves the synthesis results across all investigated synthesis algorithms. Furthermore, we show evidence that suggests intensity normalization is vital for successful deep learning-based MR image synthesis.