Multiplicative intrinsic component optimization (MICO) for MRI bias field estimation and tissue segmentation

MeMGB-Diff: Memory-Efficient Multivariate Gaussian Bias Diffusion Model for 3D bias field correction

Bias fields inevitably degrade MRI that seriously interferes the diagnosis of physicians for accurate analysis, and removing it is a crucial image analysis task. Generative models (such as GANs) are used for bias field correction, and outperform traditional methods, however are hindered by the high cost of data annotation and instability during training. Recently, the diffusion-based methods have excelled over GANs in many applications, and they are powerful in removing noise from images, while the bias field can be regarded as a smooth noise. However, it is a challenge to directly apply to 3D bias field correction due to sampling inefficiency, the heavy computational demand, and implicit correction process. We propose a Memory-Efficient Multivariate Gaussian Bias Diffusion Model (MeMGB-Diff) that is an explicit, sampling, and memory both efficient diffusion model for 3D bias field correction without using clinical labels. MeMGB-Diff extends the diffusion models to multivariate Gaussian and models the bias field as a multivariate Gaussian variable, allowing direct diffusion and removal of the 3D bias fields without Gaussian noise. For memory efficiency, MeMGB-Diff performs diffusion model in smaller readable image domain at the expense of a negligible accuracy loss, based on the strong correlation among adjacent voxels of bias field. We also propose a loss function to mainly learn the intensity trend, which mainly causes the inhomogeneity of MRI, and effectively increases the correction accuracy. For comprehensive performance comparison, we propose a synthetic method for generating more varied bias fields during testing. Both quantitative and qualitative assessments on synthetic and clinical data confirm the high fidelity and uniform intensity of our results. MeMGB-Diff reduces data size by 64 times to use less memory, improves sampling efficiency by more than 10 times compared to other diffusion-based methods, and achieves optimal metrics, including SSIM, PSNR, COCO, and CV for various tissues. Hence, our MeMGB-Diff is a state-of-the-art (SOTA) method for 3D bias field correction.

Deriving tissue physical densities based on Dixon magnetic resonance images and tissue composition prior knowledge for voxel-based internal dosimetry

BACKGROUND

Magnetic resonance (MR) images have been applied in diagnostic and therapeutic nuclear medicine to improve the visualization and characterization of soft tissues and tumors. However, the physical density (ρ) and elemental composition of human tissues required for dosimetric calculation cannot be directly converted from MR images, obstructing MR-based personalized internal dosimetry. In this study, we proposed a method to derive physical densities from Dixon MR images for voxel-based internal dose calculation.

METHODS

The proposed method defined human tissues as composed of four basic tissues. The physical densities of the human tissues were calculated using the standard tissue composition of the basic tissues and the volume fraction maps calculated from Dixon images. The derived ρ map was applied to calculate the whole-body internal dosimetry using a multiple voxel S-value (MSV) approach. The accuracy of the proposed method in deriving ρ and calculating the internal dose of 18F-FDG PET imaging was evaluated by comparing with those obtained from computed tomography (CT) images of the same patient and was compared with those obtained using generative adversarial networks (GANs).

RESULTS

The proposed method was superior to the GANs in deriving ρ from Dixon MR images and the following internal dose calculation. On average of a validation set, the mean absolute percent errors (MAPEs) of the whole-body ρ derivation and internal dose calculation using the proposed method were 14.28 ± 11.11% and 3.31 ± 0.69%, respectively. The MAPEs were respectively reduced to 5.97 ± 2.51 and 2.75 ± 0.69% after excluding the intestinal gas with different locations in the Dixon MR and CT images.

CONCLUSIONS

The proposed method could be applied for accurate and efficient personalized internal dosimetry evaluation in MR-integrated nuclear medicine clinical applications.

Assessment of Age-Related Differences in Lower Leg Muscles Quality Using Radiomic Features of Magnetic Resonance Images

Sarcopenia, characterised by a decline in muscle mass and strength, affects the health of the elderly, leading to increased falls, hospitalisation, and mortality rates. Muscle quality, reflecting microscopic and macroscopic muscle changes, is a critical determinant of physical function. To utilise radiomic features extracted from magnetic resonance (MR) images to assess age-related changes in muscle quality, a dataset of 24 adults, divided into older (male/female: 6/6, 66-79 years) and younger (male/female: 6/6, 21-31 years) groups, was used to investigate the radiomics features of the dorsiflexor and plantar flexor muscles of the lower leg that are critical for mobility. MR images were processed using MaZda software for feature extraction. Dimensionality reduction was performed using principal component analysis and recursive feature elimination, followed by classification using machine learning models, such as support vector machine, extreme gradient boosting, and naïve Bayes. A leave-one-out validation test was used to train and test the classifiers, and the area under the receiver operating characteristic curve (AUC) was used to evaluate the classification performance. The analysis revealed that significant differences in radiomic feature distributions were found between age groups, with older adults showing higher complexity and variability in muscle texture. The plantar flexors showed similar or higher AUC than the dorsiflexors in all models. When the dorsiflexor muscles were combined with the plantar flexor muscles, they tended to have a higher AUC than when they were used alone. Radiomic features in lower-leg MR images reflect ageing, especially in the plantar flexor muscles. Radiomic analysis can offer a deeper understanding of age-related muscle quality than traditional muscle mass assessments.

Multimodal gradients of basal forebrain connectivity across the neocortex

Cortical cholinergic projections originate from subregions of the basal forebrain (BF). To examine its organization in humans, we computed multimodal gradients of BF connectivity by combining 7 T diffusion and resting state functional MRI. Moving from anteromedial to posterolateral BF, we observe reduced tethering between structural and functional connectivity gradients, with the lowest tethering in the nucleus basalis of Meynert. In the neocortex, this gradient is expressed by progressively reduced tethering from unimodal sensory to transmodal cortex, with the lowest tethering in the midcingulo-insular network, and is also spatially correlated with the molecular concentration of VAChT, measured by [18F]fluoroethoxy-benzovesamicol (FEOBV) PET. In mice, viral tracing of BF cholinergic projections and [18F]FEOBV PET confirm a gradient of axonal arborization. Altogether, our findings reveal that BF cholinergic neurons vary in their branch complexity, with certain subpopulations exhibiting greater modularity and others greater diffusivity in the functional integration with their cortical targets.

Sex Differences in Fat Distribution and Muscle Fat Infiltration in the Lower Extremity: A Retrospective Diverse-Ethnicity 7T MRI Study in a Research Institute Setting in the USA

Background: Fat infiltration in skeletal muscle is related to declining muscle strength, whereas excess subcutaneous fat is implicated in the development of metabolic diseases. Methods: Using multi-slice axial T2-weighted (T2w) MR images, this retrospective study characterized muscle fat infiltration (MFI) and fat distribution in the lower extremity of 107 subjects (64M/43F, age 11-79 years) with diverse ethnicities (including White, Black, Latino, and Asian subjects). Results: MRI data analysis shows that MFI, evaluated by the relative intensities of the pixel histogram profile in the calf muscle, tends to increase with both age and BMI. However, statistical significance was found only for the age correlation in women (p < 0.002), and the BMI correlation in men (p = 0.04). Sex disparities were also seen in the fat distribution, which was assessed according to subcutaneous fat thickness (SFT) and the fibula bone marrow cross-sectional area (BMA). SFT tends to decrease with age in men (p < 0.01), whereas SFT tends to increase with BMI only in women (p < 0.01). In contrast, BMA tends to increase with age in women (p < 0.01) and with BMI in men (p = 0.04). Additionally, MFI is positively correlated with BMA but not with SFT, suggesting that compromised bone structure may contribute to fat infiltration in the surrounding skeletal muscle. Conclusions: The findings of this study highlight a sex factor affecting MFI and fat distribution, which may offer valuable insights into effective strategies to prevent and treat MFI in women versus men.

Enhanced Spatial Fuzzy C-Means Algorithm for Brain Tissue Segmentation in T1 Images

Magnetic Resonance Imaging (MRI) plays an important role in neurology, particularly in the precise segmentation of brain tissues. Accurate segmentation is crucial for diagnosing brain injuries and neurodegenerative conditions. We introduce an Enhanced Spatial Fuzzy C-means (esFCM) algorithm for 3D T1 MRI segmentation to three tissues, i.e. White Matter (WM), Gray Matter (GM), and Cerebrospinal Fluid (CSF). The esFCM employs a weighted least square algorithm utilizing the Structural Similarity Index (SSIM) for polynomial bias field correction. It also takes advantage of the information from the membership function of the last iteration to compute neighborhood impact. This strategic refinement enhances the algorithm's adaptability to complex image structures, effectively addressing challenges such as intensity irregularities and contributing to heightened segmentation accuracy. We compare the segmentation accuracy of esFCM against four variants of FCM, Gaussian Mixture Model (GMM) and FSL and ANTs algorithms using four various dataset, employing three measurement criteria. Comparative assessments underscore esFCM's superior performance, particularly in scenarios involving added noise and bias fields.The obtained results emphasize the significant potential of the proposed method in the segmentation of MRI images.

Peripheral quantitative computed tomography is a valid imaging technique for tracking changes in skeletal muscle cross-sectional area

Peripheral quantitative computed tomography (pQCT) has recently expanded to quantifying skeletal muscle, however its validity to determine muscle cross-sectional area (mCSA) compared to magnetic resonance imaging (MRI) is unknown. Eleven male participants (age: 22 ± 3 y) underwent pQCT and MRI dual-leg mid-thigh imaging before (PRE) and after (POST) 6 weeks of resistance training for quantification of mid-thigh mCSA and change in mCSA. mCSA agreement at both time points and absolute change in mCSA across time was assessed using Bland-Altman plots for mean bias and 95% limits of agreement (LOA), as well as Lin's concordance correlation coefficients (CCC). Both pQCT and MRI mCSA increased following 6 weeks of resistance training (∆mCSApQCT: 6.7 ± 5.4 cm2, p < 0.001; ∆mCSAMRI: 6.0 ± 6.4 cm2, p < 0.001). Importantly, the change in mCSA was not different between methods (p = 0.39). Bland-Altman analysis revealed a small mean bias (1.10 cm2, LOA: -6.09, 8.29 cm2) where pQCT tended to overestimate mCSA relative to MRI when comparing images at a single time point. Concordance between pQCT and MRI mCSA at PRE and POST was excellent yielding a CCC of 0.982. For detecting changes in mCSA, Bland-Altman analysis revealed excellent agreement between pQCT and MRI (mean bias: -0.73 cm2, LOA: -8.37, 6.91 cm2). Finally, there was excellent concordance between pQCT and MRI mCSA change scores (CCC = 0.779). Relative to MRI, pQCT imaging is a valid technique for measuring both mid-thigh mCSA at a single time point and mCSA changes following a resistance training intervention.

Automatic reorientation to generate short-axis myocardial PET images

BACKGROUND

Accurately redirecting reconstructed Positron emission tomography (PET) images into short-axis (SA) images shows great significance for subsequent clinical diagnosis. We developed a system for automatic redirection and quantitative analysis of myocardial PET images.

METHODS

A total of 128 patients were enrolled for 18 F-FDG PET/CT myocardial metabolic images (MMIs), including 3 image classifications: without defects, with defects, and excess uptake. The automatic reorientation system includes five modules: regional division, myocardial segmentation, ellipsoid fitting, image rotation and quantitative analysis. First, the left ventricular geometry-based canny edge detection (LVG-CED) was developed and compared with the other 5 common region segmentation algorithms, the optimized partitioning was determined based on partition success rate. Then, 9 myocardial segmentation methods and 4 ellipsoid fitting methods were combined to derive 36 cross combinations for diagnostic performance in terms of Pearson correlation coefficient (PCC), Kendall correlation coefficient (KCC), Spearman correlation coefficient (SCC), and determination coefficient. Finally, the deflection angles were computed by ellipsoid fitting and the SA images were derived by affine transformation. Furthermore, the polar maps were used for quantitative analysis of SA images, and the redirection effects of 3 different image classifications were analyzed using correlation coefficients.

RESULTS

On the dataset, LVG-CED outperformed other methods in the regional division module with a 100% success rate. In 36 cross combinations, PSO-FCM and LLS-SVD performed the best in terms of correlation coefficient. The linear results indicate that our algorithm (LVG-CED, PSO-FCM, and LLS-SVD) has good consistency with the reference manual method. In quantitative analysis, the similarities between our method and the reference manual method were higher than 96% at 17 segments. Moreover, our method demonstrated excellent performance in all 3 image classifications.

CONCLUSION

Our algorithm system could realize accurate automatic reorientation and quantitative analysis of PET MMIs, which is also effective for images suffering from interference.

Hydrophilic Coating Microstructure Mediates Acute Drug Transfer in Drug-Coated Balloon Therapy

Drug-coated balloon (DCB) therapy is a promising endovascular treatment for obstructive arterial disease. The goal of DCB therapy is restoration of lumen patency in a stenotic vessel, whereby balloon deployment both mechanically compresses the offending lesion and locally delivers an antiproliferative drug, most commonly paclitaxel (PTX) or derivative compounds, to the arterial wall. Favorable long-term outcomes of DCB therapy thus require predictable and adequate PTX delivery, a process facilitated by coating excipients that promotes rapid drug transfer during the inflation period. While a variety of excipients have been considered in DCB design, there is a lack of understanding about the coating-specific biophysical determinants of essential device function, namely, acute drug transfer. We consider two hydrophilic excipients for PTX delivery, urea (UR) and poly(ethylene glycol) (PEG), and examine how compositional and preparational variables in the balloon surface spray-coating process impact resultant coating microstructure and in turn acute PTX transfer to the arterial wall. Specifically, we use scanning electron image analyses to quantify how coating microstructure is altered by excipient solid content and balloon-to-nozzle spray distance during the coating procedure and correlate obtained microstructural descriptors of coating aggregation to the efficiency of acute PTX transfer in a one-dimensional ex vivo model of DCB deployment. Experimental results suggest that despite the qualitatively different coating surface microstructures and apparent PTX transfer mechanisms exhibited with these excipients, the drug delivery efficiency is generally enhanced by coating aggregation on the balloon surface. We illustrate this microstructure-function relation with a finite element-based computational model of DCB deployment, which along with our experimental findings suggests a general design principle to increase drug delivery efficiency across a broad range of DCB designs.

Quantitative and Visual Analysis of Data Augmentation and Hyperparameter Optimization in Deep Learning-Based Segmentation of Low-Grade Glioma Tumors Using Grad-CAM

This study executes a quantitative and visual investigation on the effectiveness of data augmentation and hyperparameter optimization on the accuracy of deep learning-based segmentation of LGG tumors. The study employed the MobileNetV2 and ResNet backbones with atrous convolution in DeepLabV3+ structure. The Grad-CAM tool was also used to interpret the effect of augmentation and network optimization on segmentation performance. A wide investigation was performed to optimize the network hyperparameters. In addition, the study examined 35 different models to evaluate different data augmentation techniques. The results of the study indicated that incorporating data augmentation techniques and optimization can improve the performance of segmenting brain LGG tumors up to 10%. Our extensive investigation of the data augmentation techniques indicated that enlargement of data from 90° and 225° rotated data,up to down and left to right flipping are the most effective techniques. MobilenetV2 as the backbone,"Focal Loss" as the loss function and "Adam" as the optimizer showed the superior results. The optimal model (DLG-Net) achieved an overall accuracy of 96.1% with a loss value of 0.006. Specifically, the segmentation performance for Whole Tumor (WT), Tumor Core (TC), and Enhanced Tumor (ET) reached a Dice Similarity Coefficient (DSC) of 89.4%, 70.1%, and 49.9%, respectively. Simultaneous visual and quantitative assessment of data augmentation and network optimization can lead to an optimal model with a reasonable performance in segmenting the LGG tumors.

Repeatability of deuterium metabolic imaging of healthy volunteers at 3 T

BACKGROUND

Magnetic resonance (MR) imaging of deuterated glucose, termed deuterium metabolic imaging (DMI), is emerging as a biomarker of pathway-specific glucose metabolism in tumors. DMI is being studied as a useful marker of treatment response in a scan-rescan scenario. This study aims to evaluate the repeatability of brain DMI.

METHODS

A repeatability study was performed in healthy volunteers from December 2022 to March 2023. The participants consumed 75 g of [6,6'-2H2]glucose. The delivery of 2H-glucose to the brain and its conversion to 2H-glutamine + glutamate, 2H-lactate, and 2H-water DMI was imaged at baseline and at 30, 70, and 120 min. DMI was performed using MR spectroscopic imaging on a 3-T system equipped with a 1H/2H-tuned head coil. Coefficients of variation (CoV) were computed for estimation of repeatability and between-subject variability. In a set of exploratory analyses, the variability effects of region, processing, and normalization were estimated.

RESULTS

Six male participants were recruited, aged 34 ± 6.5 years (mean ± standard deviation). There was 42 ± 2.7 days between sessions. Whole-brain levels of glutamine + glutamate, lactate, and glucose increased to 3.22 ± 0.4 mM, 1.55 ± 0.3 mM, and 3 ± 0.7 mM, respectively. The best signal-to-noise ratio and repeatability was obtained at the 120-min timepoint. Here, the within-subject whole-brain CoVs were -10% for all metabolites, while the between-subject CoVs were -20%.

CONCLUSIONS

DMI of glucose and its downstream metabolites is feasible and repeatable on a clinical 3 T system.

TRIAL REGISTRATION

ClinicalTrials.gov, NCT05402566 , registered the 25th of May 2022.

RELEVANCE STATEMENT

Brain deuterium metabolic imaging of healthy volunteers is repeatable and feasible at clinical field strengths, enabling the study of shifts in tumor metabolism associated with treatment response.

KEY POINTS

• Deuterium metabolic imaging is an emerging tumor biomarker with unknown repeatability.  • The repeatability of deuterium metabolic imaging is on par with FDG-PET.  • The study of deuterium metabolic imaging in clinical populations is feasible.

Image Recovery Matters: A Recovery-Extraction Framework for Robust Fetal Brain Extraction From MR Images

The extraction of the fetal brain from magnetic resonance (MR) images is a challenging task. In particular, fetal MR images suffer from different kinds of artifacts introduced during the image acquisition. Among those artifacts, intensity inhomogeneity is a common one affecting brain extraction. In this work, we propose a deep learning-based recovery-extraction framework for fetal brain extraction, which is particularly effective in handling fetal MR images with intensity inhomogeneity. Our framework involves two stages. First, the artifact-corrupted images are recovered with the proposed generative adversarial learning-based image recovery network with a novel region-of-darkness discriminator that enforces the network focusing on artifacts of the images. Second, we propose a brain extraction network for more effective fetal brain segmentation by strengthening the association between lower- and higher-level features as well as suppressing task-irrelevant features. Thanks to the proposed recovery-extraction strategy, our framework is able to accurately segment fetal brains from artifact-corrupted MR images. The experiments show that our framework achieves promising performance in both quantitative and qualitative evaluations, and outperforms state-of-the-art methods in both image recovery and fetal brain extraction.

Selective image segmentation driven by region, edge and saliency functions

Present active contour methods often struggle with the segmentation of regions displaying variations in texture, color, or intensity a phenomenon referred to as inhomogeneities. These limitation impairs their ability to precisely distinguish and outline diverse components within an image. Further some of these methods employ intricate mathematical formulations for energy minimization. Such complexity introduces computational sluggishness, making these methods unsuitable for tasks requiring real-time processing or rapid segmentation. Moreover, these methods are susceptible to being trapped in energy configurations corresponding to local minimum points. Consequently, the segmentation process fails to converge to the desired outcome. Additionally, the efficacy of these methods diminishes when confronted with regions exhibiting weak or subtle boundaries. To address these limitations comprehensively, our proposed approach introduces a fresh paradigm for image segmentation through the synchronization of region-based, edge-based, and saliency-based segmentation techniques. Initially, we adapt an intensity edge term based on the zero crossing feature detector (ZCD), which is used to highlight significant edges of an image. Secondly, a saliency function is formulated to detect salient regions from an image. We have also included a globally tuned region based SPF (signed pressure force) term to move contour away and capture homogeneous regions. ZCD, saliency and global SPF are jointly incorporated with some scaled value for the level set evolution to develop an effective image segmentation model. In addition, proposed method is capable to perform selective object segmentation, which enables us to choose any single or multiple objects inside an image. Saliency function and ZCD detector are considered feature enhancement tools, which are used to get important features of an image, so this method has a solid capacity to segment nature images (homogeneous or inhomogeneous) precisely. Finally, the adaption of the Gaussian kernel removes the need of any penalization term for level set reinitialization. Experimental results will exhibit the efficiency of the proposed method.

B1 mapping using pre-learned subspaces for quantitative brain imaging

PURPOSE

To develop a machine learning-based method for estimation of both transmitter and receiver B1 fields desired for correction of the B1 inhomogeneity effects in quantitative brain imaging.

THEORY AND METHODS

A subspace model-based machine learning method was proposed for estimation of B1t and B1r fields. Probabilistic subspace models were used to capture scan-dependent variations in the B1 fields; the subspace basis and coefficient distributions were learned from pre-scanned training data. Estimation of the B1 fields for new experimental data was achieved by solving a linear optimization problem with prior distribution constraints. We evaluated the performance of the proposed method for B1 inhomogeneity correction in quantitative brain imaging scenarios, including T1 and proton density (PD) mapping from variable-flip-angle spoiled gradient-echo (SPGR) data as well as neurometabolic mapping from MRSI data, using phantom, healthy subject and brain tumor patient data.

RESULTS

In both phantom and healthy subject data, the proposed method produced high-quality B1 maps. B1 correction on SPGR data using the estimated B1 maps produced significantly improved T1 and PD maps. In brain tumor patients, the proposed method produced more accurate and robust B1 estimation and correction results than conventional methods. The B1 maps were also applied to MRSI data from tumor patients and produced improved neurometabolite maps, with better separation between pathological and normal tissues.

CONCLUSION

This work presents a novel method to estimate B1 variations using probabilistic subspace models and machine learning. The proposed method may make correction of B1 inhomogeneity effects more robust in practical applications.

Photoacoustic digital brain and deep-learning-assisted image reconstruction

Photoacoustic tomography (PAT) is a newly developed medical imaging modality, which combines the advantages of pure optical imaging and ultrasound imaging, owning both high optical contrast and deep penetration depth. Very recently, PAT is studied in human brain imaging. Nevertheless, while ultrasound waves are passing through the human skull tissues, the strong acoustic attenuation and aberration will happen, which causes photoacoustic signals' distortion. In this work, we use 180 T1 weighted magnetic resonance imaging (MRI) human brain volumes along with the corresponding magnetic resonance angiography (MRA) brain volumes, and segment them to generate the 2D human brain numerical phantoms for PAT. The numerical phantoms contain six kinds of tissues, which are scalp, skull, white matter, gray matter, blood vessel and cerebrospinal fluid. For every numerical phantom, Monte-Carlo based optical simulation is deployed to obtain the photoacoustic initial pressure based on optical properties of human brain. Then, two different k-wave models are used for the skull-involved acoustic simulation, which are fluid media model and viscoelastic media model. The former one only considers longitudinal wave propagation, and the latter model takes shear wave into consideration. Then, the PA sinograms with skull-induced aberration is taken as the input of U-net, and the skull-stripped ones are regarded as the supervision of U-net to train the network. Experimental result shows that the skull's acoustic aberration can be effectively alleviated after U-net correction, achieving conspicuous improvement in quality of PAT human brain images reconstructed from the corrected PA signals, which can clearly show the cerebral artery distribution inside the human skull.

Deformable image registration based on single or multi-atlas methods for automatic muscle segmentation and the generation of augmented imaging datasets

Muscle segmentation is a process relied upon to gather medical image-based muscle characterisation, useful in directly assessing muscle volume and geometry, that can be used as inputs to musculoskeletal modelling pipelines. Manual or semi-automatic techniques are typically employed to segment the muscles and quantify their properties, but they require significant manual labour and incur operator repeatability issues. In this study an automatic process is presented, aiming to segment all lower limb muscles from Magnetic Resonance (MR) imaging data simultaneously using three-dimensional (3D) deformable image registration (single inputs or multi-atlas). Twenty-three of the major lower limb skeletal muscles were segmented from five subjects, with an average Dice similarity coefficient of 0.72, and average absolute relative volume error (RVE) of 12.7% (average relative volume error of -2.2%) considering the optimal subject combinations. The multi-atlas approach showed slightly better accuracy (average DSC: 0.73; average RVE: 1.67%). Segmented MR imaging datasets of the lower limb are not widely available in the literature, limiting the potential of new, probabilistic methods such as deep learning to be used in the context of muscle segmentation. In this work, Non-linear deformable image registration is used to generate 69 manually checked, segmented, 3D, artificial datasets, allowing access for future studies to use these new methods, with a large amount of reliable reference data.

Effect of magnetic resonance imaging pre-processing on the performance of model-based prostate tumor probability mapping

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.

Jointly estimating bias field and reconstructing uniform MRI image by deep learning

Bias field is one of the main artifacts that degrade the quality of magnetic resonance images. It introduces intensity inhomogeneity and affects image analysis such as segmentation. In this work, we proposed a deep learning approach to jointly estimate bias field and reconstruct uniform image. By modeling the quality degradation process as the product of a spatially varying field and a uniform image, the network was trained on 800 images with true bias fields from 12 healthy subjects. A network structure of bias field estimation and uniform image reconstruction was designed to compensate for the intensity loss. To further evaluate the benefit of bias field correction, a quantitative analysis was made on image segmentation. Experimental results show that the proposed BFCNet improves the image uniformity by 8.3% and 10.1%, the segmentation accuracy by 4.1% and 6.8% on white and grey matter in T2-weighted brain images. Moreover, BFCNet outperforms the state-of-the-art traditional methods and deep learning methods on estimating bias field and preserving image structure, and BFCNet is robust to different levels of bias field and noise.

Confidence Region Identification and Contour Detection in MRI Image

Tumour region extraction (RE) method identifies the area of interest in MR imaging as it also highlights tumour boundaries. Some other intensities are existing, they are not visible but have their existence in region, and this region is called growing region. Such region is to be tumour region. Due to the variation of intensities in MRI images, tumour visibility becomes uncleared. Tumour intensity variations (tumour tissues) mix with normal brain tissues. In the light of above circumstance, tumour growing region becomes challenge. The goal of work is to extract the region of interest with confidence. The objective of the study is to develop the region of interest of brain tumour MRI image method by using confidence score for identifying the variation of intensity. The significance of work is based on identification of region of interest (tumour region). Confidence score is measured through pattern of intensities of MRI image. Similar patterns of brain tumour intensities are identified. Each pattern of intensities is adjusted with certain scale, and then biggest blob is analysed. Various biggest area blobs are combined, and resultant biggest blob is formed. In fact, resultant area blob is a combination of different patterns. Each pattern is assigned with particular colour. These colours highlight the growing region. Further, a contour is detected around the tumour boundaries. With combination of region scale fitting and contour detection (CD), tumour boundaries are further separated from normal tissues. Hence, the confidence score (CS) is formed from CD. CS is further converted to confidence region (CR). Conversion to CR is performed though confidence interval (CI). CI is based on defined conditions. In such conditions, different probabilities are considered. Probability identifies the region. Source of region formation is pixels; these pixels highlight tumour core significantly. This CR is obtained through checking standard deviation and statistical evaluation using confidence interval. Hence, region-of-interest pixels are identifying the CR. CR is evaluated through 97% Dice over index (DOI), 94% Jacquard, MSE 1.24, and PSNR 17.45. Value of testing parameter from benchmark study was JI, DOI, and MSE, PSNR : JI was 31.5%, DOI was 47.3%, MSE was 2.5 dB, and PSNR was 40 dB. The parameters are measured for the complex images; contribution parameter classifies the mean pixel values and deviating pixel values, and the classification of the pixel value is like to be termed as intensities. Mentioned classification extracts the variation of intensity pixels accurately; then, algorithm is highlighting the region as compared to the normal tumour cells.

Towards an Accurate MRI Acute Ischemic Stroke Lesion Segmentation Based on Bioheat Equation and U-Net Model

Acute ischemic stroke represents a cerebrovascular disease, for which it is practical, albeit challenging to segment and differentiate infarct core from salvageable penumbra brain tissue. Ischemic stroke causes the variation of cerebral blood flow and heat generation due to metabolism. Therefore, the temperature is modified in the ischemic stroke region. In this paper, we incorporate acute ischemic stroke temperature profile to reinforce segmentation accuracy in MRI. Pennes bioheat equation was used to generate brain thermal images that may provide rich information regarding the temperature change in acute ischemic stroke lesions. The thermal images were generated by calculating the temperature of the brain with acute ischemic stroke. Then, U-Net was used in this paper for the segmentation of acute ischemic stroke. A dataset of 3192 images was created to train U-Net using k-fold crossvalidation. The training time was about 10 hours and 35 minutes in NVIDIA GPU. Next, the obtained trained model was compared with recent methods to analyze the effect of the ischemic stroke temperature profile in segmentation. The obtained results show that significant parts of acute ischemic stroke and background areas are segmented only in thermal images, which proves the importance of using thermal information to improve the segmentation outcomes in MRI diagnosis.

Review on Hybrid Segmentation Methods for Identification of Brain Tumor in MRI

Modalities like MRI give information about organs and highlight diseases. Organ information is visualized in intensities. The segmentation method plays an important role in the identification of the region of interest (ROI). The ROI can be segmented from the image using clustering, features, and region extraction. Segmentation can be performed in steps; firstly, the region is extracted from the image. Secondly, feature extraction performed, and better features are selected. They can be shape, texture, or intensity. Thirdly, clustering segments the shape of tumor, tumor has specified shape, and shape is detected by feature. Clustering consists of FCM, K-means, FKM, and their hybrid. To support the segmentation, we conducted three studies (region extraction, feature, and clustering) which are discussed in the first line of this review paper. All these studies are targeting MRI as a modality. MRI visualization proved to be more accurate for the identification of diseases compared with other modalities. Information of the modality is compromised due to low pass image. In MRI Images, the tumor intensities are variable in tumor areas as well as in tumor boundaries.

Comparisons between skeletal muscle imaging techniques and histology in tracking midthigh hypertrophic adaptations following 10 weeks of resistance training

This study had two aims. AIM1 was to determine the agreement between mid-thigh vastus lateralis (VL) cross-sectional area measured by ultrasound (mCSA_US) versus magnetic resonance imaging (mCSA_MRI) at a single time point, and the ability of each to detect hypertrophic changes. AIM2 was to assess the relationships between pre-to-post training changes in thigh lean mass determined by DXA, VL mCSA_US, ultrasound-determined VL thickness (VL_Thick), and VL mean myofiber cross-sectional area (fCSA) with changes in VL mCSA_MRI. Twelve untrained males (Age: 20±1 y, BMI: 26.9±5.4 kg/m²; n=12) engaged in a 10-week resistance training program (2x/week) where right mid-thigh images and VL biopsies were obtained prior to and 72-hours following the last training bout. Participants' VL mCSA_MRI (p=0.005), DXA thigh lean mass (p=0.015), and VL_Thick (p=0.001) increased following training, whereas VL mCSA_US and fCSA did not. For AIM1, mCSA_US demonstrated excellent concordance (CCC = 0.830) with mCSA_MRI, albeit mCSA_US values were systematically lower compared to mCSA_MRI (mean bias: -2.29 cm²). Additionally, PRE-to-POST VL mCSA changes between techniques exhibited good agreement (CCC = 0.700; mean bias: -1.08 cm²). For AIM2, moderate, positive correlations existed for PRE-to-POST changes in VL mCSA_MRI and DXA thigh lean mass (r=0.580, p=0.048), mCSA_US (r=0.622, p=0.031), and VL_Thick (r=0.520, p=0.080). A moderate, negative correlation existed between mCSA_MRI and fCSA (r=-0.569, p=0.054). Our findings have multiple implications: i) resistance training-induced hypertrophy was dependent on the quantification method, ii) ultrasound-determined mCSA shows good agreement with MRI, and iii) tissue-level changes poorly agreed with mean fCSA changes and this requires further research.

Automatic segmentation of glioblastoma multiform brain tumor in MRI images: Using Deeplabv3+ with pre-trained Resnet18 weights

PURPOSE

To assess the effectiveness of deep learning algorithms in automated segmentation of magnetic resonance brain images for determining the enhanced tumor, the peri-tumoral edema, the necrotic/ non-enhancing tumor, and Normal tissue volumes.

METHODS AND MATERIALS

A new deep neural network algorithm, Deep-Net, was developed for semantic segmentation of the glioblastoma tumors in MR images, using the Deeplabv3+ architecture, and the pre-trained Resnet18 initial weights. The MR image Dataset used for training the network was taken from the BraTS 2020 training set, with the ground truth labels for different tumor subregions manually drawn by a group of expert neuroradiologists. In this work, two multi-modal MRI scans, i.e., T₁ce and FLAIR of 293 patients with high-grade glioma (HGG), were used for deep network training (Deep-Net). The performance of the network was assessed for different hyper-parameters, to obtain the optimum set of parameters. The similarity scores were used for the evaluation of the optimized network.

RESULTS

According to the results of this study, epoch #37 is the optimum epoch giving the best global accuracy (97.53%), and loss function (0.14). The Deep-Net sensitivity in the delineation of the enhanced tumor is more than 90%.

CONCLUSIONS

The results indicate that the Deep-Net was able to segment GBM tumors with high accuracy.

Deep Learning for Reaction-Diffusion Glioma Growth Modeling: Towards a Fully Personalized Model?

Simple Summary

Mathematical tumor growth models have been proposed for decades to capture the growth of gliomas, an aggressive form of brain tumor. However, the estimation of the tumor cell-density distribution at diagnosis and model parameters from partial observations provided by magnetic resonance imaging are ill-posed problems. In this work, we propose a deep learning-based approach to address these problems. 1200 synthetic tumors are first generated using the mathematical model over brain geometries of 6 volunteers. Two deep convolutional neural networks are then trained to (i) reconstruct a whole tumor cell-density distribution and (ii) evaluate the model parameters from partial observations provided in the form of threshold-like imaging contours, with state-of-the-art results. From the estimated cell-density distribution and parameter values, the spatio-temporal evolution of the tumor can ultimately be accurately captured by the mathematical model. Such an approach could be of great interest for glioma characterization and therapy planning.

Abstract

Reaction-diffusion models have been proposed for decades to capture the growth of gliomas, the most common primary brain tumors. However, ill-posedness of the initialization at diagnosis time and parameter estimation of such models have restrained their clinical use as a personalized predictive tool. In this work, we investigate the ability of deep convolutional neural networks (DCNNs) to address commonly encountered pitfalls in the field. Based on 1200 synthetic tumors grown over real brain geometries derived from magnetic resonance (MR) data of six healthy subjects, we demonstrate the ability of DCNNs to reconstruct a whole tumor cell-density distribution from only two imaging contours at a single time point. With an additional imaging contour extracted at a prior time point, we also demonstrate the ability of DCNNs to accurately estimate the individual diffusivity and proliferation parameters of the model. From this knowledge, the spatio-temporal evolution of the tumor cell-density distribution at later time points can ultimately be precisely captured using the model. We finally show the applicability of our approach to MR data of a real glioblastoma patient. This approach may open the perspective of a clinical application of reaction-diffusion growth models for tumor prognosis and treatment planning.

Central Vein Sign Profile of Newly Developing Lesions in Multiple Sclerosis: A 3-Year Longitudinal Study

BACKGROUND AND OBJECTIVES

The central vein sign (CVS), a central linear hypointensity within lesions on T2*-weighted imaging, has been established as a sensitive and specific biomarker for the diagnosis of multiple sclerosis (MS). However, the CVS has not yet been comprehensively studied in newly developing MS lesions. We aimed to identify the CVS profiles of new white matter lesions in patients with MS followed over time and investigate demographic and clinical risk factors associated with new CVS+ or CVS- lesion development.

METHODS

In this retrospective longitudinal cohort study, adults from the NIH MS Natural History Study were considered for inclusion. Participants with new T2 or enhancing lesions were identified through review of the radiology report and/or longitudinal subtraction imaging. Each new lesion was evaluated for the CVS. Clinical characteristics were identified through chart review.

RESULTS

A total of 153 adults (95 relapsing-remitting MS, 27 secondary progressive MS, 16 primary progressive MS, 5 clinically isolated syndrome, and 10 healthy; 67% female) were included. Of this cohort, 96 had at least 1 new T2 or contrast-enhancing lesion during median 3.1 years (Q1-Q3: 0.7-6.3) of follow-up; lesions eligible for CVS evaluation were found in 62 (65%). Of 233 new CVS-eligible lesions, 159 (68%) were CVS+, with 30 (48%) individuals having only CVS+, 12 (19%) only CVS-, and 20 (32%) both CVS+ and CVS- lesions. In gadolinium-enhancing (Gd+) lesions, the CVS+ percentage increased from 102/152 (67%) at the first time point where the lesion was observed, to 92/114 (82%) after a median follow-up of 2.8 years. Younger age (OR = 0.5 per 10-year increase, 95% CI = 0.3-0.8) and higher CVS+ percentage at baseline (OR = 1.4 per 10% increase, 95% CI = 1.1-1.9) were associated with increased likelihood of new CVS+ lesion development.

DISCUSSION

In a cohort of adults with MS followed over a median duration of 3 years, most newly developing T2 or enhancing lesions were CVS+ (68%), and nearly half (48%) developed new CVS+ lesions only. Importantly, the effects of edema and T2 signal changes can obscure small veins in Gd+ lesions; therefore, caution and follow-up is necessary when determining their CVS status.

TRIAL REGISTRATION INFORMATION

Clinical trial registration number NCT00001248.

CLASSIFICATION OF EVIDENCE

This study provides Class III evidence that younger age and higher CVS+ percentage at baseline are associated with new CVS+ lesion development.

Quantifying Retinal Microvascular Morphology in Schizophrenia Using Swept-Source Optical Coherence Tomography Angiography

BACKGROUND

Retinovascular changes are reported on fundus imaging in schizophrenia (SZ). This is the first study to use swept-source optical coherence tomography angiography (OCT-A) to comprehensively examine retinal microvascular changes in SZ.

METHODS

This study included 30 patients with SZ/schizoaffective disorder (8 early and 15 chronic) and 22 healthy controls (HCs). All assessments were performed at Beth Israel Deaconess Medical Center and Massachusetts Eye and Ear. All participants underwent swept-source OCT-A of right (oculus dextrus [OD]) and left (oculus sinister [OS]) eye, clinical, and cognitive assessments. Macular OCT-A images (6 × 6 mm) were collected with the DRI Topcon Triton for superficial, deep, and choriocapillaris vascular regions. Microvasculature was quantified using vessel density (VD), skeletonized vessel density (SVD), fractal dimension (FD), and vessel diameter index (VDI).

RESULTS

Twenty-one HCs and 26 SZ subjects were included. Compared to HCs, SZ patients demonstrated higher overall OD superficial SVD, OD choriocapillaris VD, and OD choriocapillaris SVD, which were primarily observed in the central, central and outer superior, and central and outer inferior/superior, respectively. Early-course SZ subjects had significantly higher OD superficial VD, OD choriocapillaris SVD, and OD choriocapillaris FD compared to matched HCs. Higher bilateral (OU) superficial VD correlated with lower Positive and Negative Syndrome Scale (PANSS) positive scores, and higher OU deep VDI was associated with higher PANSS negative scores.

CONCLUSIONS AND RELEVANCE

These results suggest the presence of microvascular dysfunction associated with early-stage SZ. Clinical associations with microvascular alterations further implicate this hypothesis, with higher measures being associated with worse symptom severity and functioning in early stages and with lower symptom severity and better functioning in later stages.

Brain tissue segmentation via non-local fuzzy c-means clustering combined with Markov random field

The segmentation and extraction of brain tissue in magnetic resonance imaging (MRI) is a meaningful task because it provides a diagnosis and treatment basis for observing brain tissue development, delineating lesions, and planning surgery. However, MRI images are often damaged by factors such as noise, low contrast and intensity brightness, which seriously affect the accuracy of segmentation. A non-local fuzzy c-means clustering framework incorporating the Markov random field for brain tissue segmentation is proposed in this paper. Firstly, according to the statistical characteristics that MRF can effectively describe the local spatial correlation of an image, a new distance metric with neighborhood constraints is constructed by combining probabilistic statistical information. Secondly, a non-local regularization term is integrated into the objective function to utilize the global structure feature of the image, so that both the local and global information of the image can be taken into account. In addition, a linear model of inhomogeneous intensity is also built to estimate the bias field in brain MRI, which has achieved the goal of overcoming the intensity inhomogeneity. The proposed model fully considers the randomness and fuzziness in the image segmentation problem, and obtains the prior knowledge of the image reasonably, which reduces the influence of low contrast in the MRI images. Then the experimental results demonstrate that the proposed method can eliminate the noise and intensity inhomogeneity of the MRI image and effectively improve the image segmentation accuracy.

AVLSM: Adaptive Variational Level Set Model for Image Segmentation in the Presence of Severe Intensity Inhomogeneity and High Noise

Intensity inhomogeneity and noise are two common issues in images but inevitably lead to significant challenges for image segmentation and is particularly pronounced when the two issues simultaneously appear in one image. As a result, most existing level set models yield poor performance when applied to this images. To this end, this paper proposes a novel hybrid level set model, named adaptive variational level set model (AVLSM) by integrating an adaptive scale bias field correction term and a denoising term into one level set framework, which can simultaneously correct the severe inhomogeneous intensity and denoise in segmentation. Specifically, an adaptive scale bias field correction term is first defined to correct the severe inhomogeneous intensity by adaptively adjusting the scale according to the degree of intensity inhomogeneity while segmentation. More importantly, the proposed adaptive scale truncation function in the term is model-agnostic, which can be applied to most off-the-shelf models and improves their performance for image segmentation with severe intensity inhomogeneity. Then, a denoising energy term is constructed based on the variational model, which can remove not only common additive noise but also multiplicative noise often occurred in medical image during segmentation. Finally, by integrating the two proposed energy terms into a variational level set framework, the AVLSM is proposed. The experimental results on synthetic and real images demonstrate the superiority of AVLSM over most state-of-the-art level set models in terms of accuracy, robustness and running time.

Autistic Spectrum Disorder Detection and Structural Biomarker Identification Using Self-Attention Model and Individual-Level Morphological Covariance Brain Networks

Autism spectrum disorder (ASD) is a range of neurodevelopmental disorders, which brings enormous burdens to the families of patients and society. However, due to the lack of representation of variance for diseases and the absence of biomarkers for diagnosis, the early detection and intervention of ASD are remarkably challenging. In this study, we proposed a self-attention deep learning framework based on the transformer model on structural MR images from the ABIDE consortium to classify ASD patients from normal controls and simultaneously identify the structural biomarkers. In our work, the individual structural covariance networks are used to perform ASD/NC classification via a self-attention deep learning framework, instead of the original structural MR data, to take full advantage of the coordination patterns of morphological features between brain regions. The self-attention deep learning framework based on the transformer model can extract both local and global information from the input data, making it more suitable for the brain network data than the CNN- structural model. Meanwhile, the potential diagnosis structural biomarkers are identified by the self-attention coefficients map. The experimental results showed that our proposed method outperforms most of the current methods for classifying ASD patients with the ABIDE data and achieves a classification accuracy of 72.5% across different sites. Furthermore, the potential diagnosis biomarkers were found mainly located in the prefrontal cortex, temporal cortex, and cerebellum, which may be treated as the early biomarkers for the ASD diagnosis. Our study demonstrated that the self-attention deep learning framework is an effective way to diagnose ASD and establish the potential biomarkers for ASD.

Initial Condition Assessment for Reaction-Diffusion Glioma Growth Models: A Translational MRI-Histology (In)Validation Study

Reaction-diffusion models have been proposed for decades to capture the growth of gliomas. Nevertheless, these models require an initial condition: the tumor cell density distribution over the whole brain at diagnosis time. Several works have proposed to relate this distribution to abnormalities visible on magnetic resonance imaging (MRI). In this work, we verify these hypotheses by stereotactic histological analysis of a non-operated brain with glioblastoma using a 3D-printed slicer. Cell density maps are computed from histological slides using a deep learning approach. The density maps are then registered to a postmortem MR image and related to an MR-derived geodesic distance map to the tumor core. The relation between the edema outlines visible on T2-FLAIR MRI and the distance to the core is also investigated. Our results suggest that (i) the previously proposed exponential decrease of the tumor cell density with the distance to the core is reasonable but (ii) the edema outlines would not correspond to a cell density iso-contour and (iii) the suggested tumor cell density at these outlines is likely overestimated. These findings highlight the limitations of conventional MRI to derive glioma cell density maps and the need for other initialization methods for reaction-diffusion models to be used in clinical practice.

Segmentation of Brain MR Image Using Modified Student’s t-Mixture Model

In conventional brain image analysis, it is a critical step to segment brain magnetic resonance (MR) image into three major tissues: Gray Matter (GM), White Matter (WM) and Cerebrospinal Fluid (CSF). The main difficulties for segmenting brain MR image are partial volume effect, intensity inhomogeneity and noise, which result in challenging segmentation task. In this paper, we propose a novel modified method based on the basis of the conventional Student’s t-Mixture Model (SMM), for segmentation of brain MR image and correction of bias field. The advantages of our model are introduced as follows. First, we take account of the influence on the probabilities of the pixels in the adjacent region and take full advantage of the local spatial information and class information. Second, our modified SMM is derived from the traditional finite mixture model (FMM) by adding the bias field correction model; the logarithmic likelihood function of traditional FMM is revised. Third, the noise and bias field can be easily extended to combine with the SMM model and EM algorithm. Last but not least, the exponential coefficients are employed to control the results of segmentation details. As a result, our effective and highly accurate method exhibits high robustness on both simulated and real MR image segmentation, compared to the state-of-the-art algorithms.

Association Between Obstructive Sleep Apnea and Brain White Matter Hyperintensities in a Population-Based Cohort in Germany

Importance

Underlying pathomechanisms of brain white matter hyperintensities (WMHs), commonly observed in older individuals and significantly associated with Alzheimer disease and brain aging, have not yet been fully elucidated. One potential contributing factor to WMH burden is chronic obstructive sleep apnea (OSA), a disorder highly prevalent in the general population with readily available treatment options.

Objective

To investigate potential associations between OSA and WMH burden.

Design, Setting, and Participants

Analyses were conducted in 529 study participants of the Study of Health in Pomerania-Trend baseline (SHIP-Trend-0) study with complete WMH, OSA, and important clinical data available. SHIP-Trend-0 is a general population-based, cross-sectional, observational study to facilitate the investigation of a large spectrum of common risk factors, subclinical disorders, and clinical diseases and their relationships among each other with patient recruitment from Western Pomerania, Germany, starting on September 1, 2008, with data collected until December 31, 2012. Data analysis was performed from February 1, 2019, to January 31, 2021.

Exposures

The apnea-hypopnea index (AHI) and oxygen desaturation index (ODI) were assessed during a single-night, laboratory-based polysomnography measurement.

Main Outcomes and Measures

The primary outcome was WMH data automatically segmented from 1.5-T magnetic resonance images.

Results

Of 529 study participants (mean [SD] age, 52.15 [13.58] years; 282 female [53%]), a total of 209 (40%) or 102 (19%) individuals were diagnosed with OSA according to AHI or ODI criteria (mean [SD] AHI, 7.98 [12.55] events per hour; mean [SD] ODI, 3.75 [8.43] events per hour). Both AHI (β = 0.024; 95% CI, 0.011-0.037; P <.001) and ODI (β = 0.033; 95% CI, 0.014-0.051; P <. 001) were significantly associated with brain WMH volumes. These associations remained even in the presence of additional vascular, metabolic, and lifestyle WMH risk factors. Region-specific WMH analyses found the strongest associations between periventricular frontal WMH volumes and both AHI (β = 0.0275; 95% CI, 0.013-0.042, P < .001) and ODI (β = 0.0381; 95% CI, 0.016-0.060, P < .001) as well as periventricular dorsal WMH volumes and AHI (β = 0.0165; 95% CI, 0.004-0.029, P = .008).

Conclusions and Relevance

This study found significant associations between OSA and brain WMHs, indicating a novel, potentially treatable WMH pathomechanism.

Volume and surface coil simultaneous reception (VSSR) method for intensity inhomogeneity correction in MRI

BACKGROUND

Addressing intensity inhomogeneity is critical in magnetic resonance imaging (MRI) because associated errors can adversely affect post-processing and quantitative analysis of images (i.e., segmentation, registration, etc.), as well as the accuracy of clinical diagnosis. Although several prior methods have been proposed to eliminate or correct intensity inhomogeneity, some significant disadvantages have remained, including alteration of tissue contrast, poor reliability and robustness of algorithms, and prolonged acquisition time.

OBJECTIVE

In this study, we propose an intensity inhomogeneity correction method based on volume and surface coils simultaneous reception (VSSR).

METHODS

The VSSR method comprises of two major steps: 1) simultaneous image acquisition from both volume and surface coils and 2) denoising of volume coil images and polynomial surface fitting of bias field. Extensive in vivo experiments were performed considering various anatomical structures, acquisition sequences, imaging resolutions, and orientations. In terms of correction performance, the proposed VSSR method was comparatively evaluated against several popular methods, including multiplicative intrinsic component optimization and improved nonparametric nonuniform intensity normalization bias correction methods.

RESULTS

Experimental results show that VSSR is more robust and reliable and does not require prolonged acquisition time with the volume coil.

CONCLUSION

The VSSR may be considered suitable for general implementation.

Magnetic Resonance Imaging Segmentation via Weighted Level Set Model Based on Local Kernel Metric and Spatial Constraint

Magnetic resonance imaging (MRI) segmentation is a fundamental and significant task since it can guide subsequent clinic diagnosis and treatment. However, images are often corrupted by defects such as low-contrast, noise, intensity inhomogeneity, and so on. Therefore, a weighted level set model (WLSM) is proposed in this study to segment inhomogeneous intensity MRI destroyed by noise and weak boundaries. First, in order to segment the intertwined regions of brain tissue accurately, a weighted neighborhood information measure scheme based on local multi information and kernel function is designed. Then, the membership function of fuzzy c-means clustering is used as the spatial constraint of level set model to overcome the sensitivity of level set to initialization, and the evolution of level set function can be adaptively changed according to different tissue information. Finally, the distance regularization term in level set function is replaced by a double potential function to ensure the stability of the energy function in the evolution process. Both real and synthetic MRI images can show the effectiveness and performance of WLSM. In addition, compared with several state-of-the-art models, segmentation accuracy and Jaccard similarity coefficient obtained by WLSM are increased by 0.0586, 0.0362 and 0.1087, 0.0703, respectively.

Comparison of Five Conductivity Tensor Models and Image Reconstruction Methods Using MRI

Imaging of the electrical conductivity distribution inside the human body has been investigated for numerous clinical applications. The conductivity tensors of biological tissue have been obtained from water diffusion tensors by applying several models, which may not cover the entire phenomenon. Recently, a new conductivity tensor imaging (CTI) method was developed through a combination of B1 mapping, and multi-b diffusion weighted imaging. In this study, we compared the most recent CTI method with the four existing models of conductivity tensors reconstruction. Two conductivity phantoms were designed to evaluate the accuracy of the models. Applied to five human brains, the conductivity tensors using the four existing models and CTI were imaged and compared with the values from the literature. The conductivity image of the phantoms by the CTI method showed relative errors between 1.10% and 5.26%. The images by the four models using DTI could not measure the effects of different ion concentrations subsequently due to prior information of the mean conductivity values. The conductivity tensor images obtained from five human brains through the CTI method were comparable to previously reported literature values. The images by the four methods using DTI were highly correlated with the diffusion tensor images, showing a coefficient of determination (R2) value of 0.65 to 1.00. However, the images by the CTI method were less correlated with the diffusion tensor images and exhibited an averaged R2 value of 0.51. The CTI method could handle the effects of different ion concentrations as well as mobilities and extracellular volume fractions by collecting and processing additional B1 map data. It is necessary to select an application-specific model taking into account the pros and cons of each model. Future studies are essential to confirm the usefulness of these conductivity tensor imaging methods in clinical applications, such as tumor characterization, EEG source imaging, and treatment planning for electrical stimulation.

An efficient brain tumor image classifier by combining multi-pathway cascaded deep neural network and handcrafted features in MR images

Accurate segmentation and delineation of the sub-tumor regions are very challenging tasks due to the nature of the tumor. Traditionally, convolutional neural networks (CNNs) have succeeded in achieving most promising performance for the segmentation of brain tumor; however, handcrafted features remain very important in identification of tumor's boundary regions accurately. The present work proposes a robust deep learning-based model with three different CNN architectures along with pre-defined handcrafted features for brain tumor segmentation, mainly to find out more prominent boundaries of the core and enhanced tumor regions. Generally, automatic CNN architecture does not use the pre-defined handcrafted features because it extracts the features automatically. In this present work, several pre-defined handcrafted features are computed from four MRI modalities (T2, FLAIR, T1c, and T1) with the help of additional handcrafted masks according to user interest and fed to the convolutional features (automatic features) to improve the overall performance of the proposed CNN model for tumor segmentation. Multi-pathway CNN is explored in this present work along with single-pathway CNN, which extracts simultaneously both local and global features to identify the accurate sub-regions of the tumor with the help of handcrafted features. The present work uses a cascaded CNN architecture, where the outcome of a CNN is considered as an additional input information to next subsequent CNNs. To extract the handcrafted features, convolutional operation was applied on the four MRI modalities with the help of several pre-defined masks to produce a predefined set of handcrafted features. The present work also investigates the usefulness of intensity normalization and data augmentation in pre-processing stage in order to handle the difficulties related to the imbalance of tumor labels. The proposed method is experimented on the BraST 2018 datasets and achieved promising results than the existing (currently published) methods with respect to different metrics such as specificity, sensitivity, and dice similarity coefficient (DSC) for complete, core, and enhanced tumor regions. Quantitatively, a notable gain is achieved around the boundaries of the sub-tumor regions using the proposed two-pathway CNN along with the handcrafted features. Graphical Abstract This data is mandatory. Please provide.

Segmentation of MRI Brain Tumor Image using Optimization based Deep Convolutional Neural networks (DCNN)

Segmentation of brain image should be done accurately as it can help to predict deadly brain tumor disease so that it can be possible to control the malicious segments of brain image if known beforehand. The accuracy of the brain tumor analysis can be enhanced through the brain tumor segmentation procedure. Earlier DCNN models do not consider the weights as of learning instances which may decrease accuracy levels of the segmentation procedure. Considering the above point, we have suggested a framework for optimizing the network parameters such as weight and bias vector of DCNN models using swarm intelligent based algorithms like Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Gray Wolf Optimization (GWO) and Whale Optimization Algorithm (WOA). The simulation results reveals that the WOA optimized DCNN segmentation model is outperformed than other three optimization based DCNN models i.e., GA-DCNN, PSO-DCNN, GWO-DCNN.

Sleep Quality Detection Based on EEG Signals Using Transfer Support Vector Machine Algorithm

BACKGROUND

In recent years, with the acceleration of life rhythm and increased pressure, the problem of sleep disorders has become more and more serious. It affects people's quality of life and reduces work efficiency, so the monitoring and evaluation of sleep quality is of great significance. Sleep staging has an important reference value in sleep quality assessment. This article starts with the study of sleep staging to detect and analyze sleep quality. For the purpose of sleep quality detection, this article proposes a sleep quality detection method based on electroencephalography (EEG) signals.

MATERIALS AND METHODS

This method first preprocesses the EEG signals and then uses the discrete wavelet transform (DWT) for feature extraction. Finally, the transfer support vector machine (TSVM) algorithm is used to classify the feature data.

RESULTS

The proposed algorithm was tested using 60 pieces of data from the National Sleep Research Resource Library of the United States, and sleep quality was evaluated using three indicators: sensitivity, specificity, and accuracy. Experimental results show that the classification performance of the TSVM classifier is significantly higher than those of other comparison algorithms. This further validated the effectiveness of the proposed sleep quality detection method.

Investigating DWI changes in white matter of meningioma patients treated with proton therapy

PURPOSE

To evaluate changes in diffusion and perfusion-related properties of white matter (WM) induced by proton therapy, which is capable of a greater dose sparing to organs at risk with respect to conventional X-ray radiotherapy, and to eventually expose early manifestations of delayed neuro-toxicities.

METHODS

Apparent diffusion coefficient (ADC) and IVIM parameters (D, D* and f) were estimated from diffusion-weighted MRI (DWI) in 46 patients affected by meningioma and treated with proton therapy. The impact on changes in diffusion and perfusion-related WM properties of dose and time, as well as the influence of demographic and pre-treatment clinical information, were investigated through linear mixed-effects models.

RESULTS

Decreasing trends in ADC and D were found for WM regions hit by medium-high (30-40 Gy(RBE)) and high (>40 Gy(RBE)) doses, which are compatible with diffusion restriction due to radiation-induced cellular injury. Significant influence of dose and time on median ADC changes were observed. Also, D* showed a significant dependency on dose, whereas f consistently showed no dependency on dose and time. Age, gender and surgery extent were also found to affect changes in ADC.

CONCLUSIONS

These results overall agree with those from studies conducted on cohorts of mixed proton and X-ray radiotherapy patients. Future work should focus on relating our findings with clinical information of co-morbidities and thus exploiting such or more advanced imaging data to build normal tissue complication probability models to better integrate clinical and dose information.