Conditional generative adversarial network driven radiomic prediction of mutation status based on magnetic resonance imaging of breast cancer.

BACKGROUND: Breast Cancer (BC) is a highly heterogeneous and complex disease. Personalized treatment options require the integration of multi-omic data and consideration of phenotypic variability. Radiogenomics aims to merge medical images with genomic measurements but encounter challenges due to unpaired data consisting of imaging, genomic, or clinical outcome data. In this study, we propose the utilization of a well-trained conditional generative adversarial network (cGAN) to address the unpaired data issue in radiogenomic analysis of BC. The generated images will then be used to predict the mutations status of key driver genes and BC subtypes. METHODS: We integrated the paired MRI and multi-omic (mRNA gene expression, DNA methylation, and copy number variation) profiles of 61 BC patients from The Cancer Imaging Archive (TCIA) and The Cancer Genome Atlas (TCGA). To facilitate this integration, we employed a Bayesian Tensor Factorization approach to factorize the multi-omic data into 17 latent features. Subsequently, a cGAN model was trained based on the matched side-view patient MRIs and their corresponding latent features to predict MRIs for BC patients who lack MRIs. Model performance was evaluated by calculating the distance between real and generated images using the Fréchet Inception Distance (FID) metric. BC subtype and mutation status of driver genes were obtained from the cBioPortal platform, where 3 genes were selected based on the number of mutated patients. A convolutional neural network (CNN) was constructed and trained using the generated MRIs for mutation status prediction. Receiver operating characteristic area under curve (ROC-AUC) and precision-recall area under curve (PR-AUC) were used to evaluate the performance of the CNN models for mutation status prediction. Precision, recall and F1 score were used to evaluate the performance of the CNN model in subtype classification. RESULTS: The FID of the images from the well-trained cGAN model based on the test set is 1.31. The CNN for TP53, PIK3CA, and CDH1 mutation prediction yielded ROC-AUC values 0.9508, 0.7515, and 0.8136 and PR-AUC are 0.9009, 0.7184, and 0.5007, respectively for the three genes. Multi-class subtype prediction achieved precision, recall and F1 scores of 0.8444, 0.8435 and 0.8336 respectively. The source code and related data implemented the algorithms can be found in the project GitHub at https://github.com/mattthuang/BC_RadiogenomicGAN . CONCLUSION: Our study establishes cGAN as a viable tool for generating synthetic BC MRIs for mutation status prediction and subtype classification to better characterize the heterogeneity of BC in patients. The synthetic images also have the potential to significantly augment existing MRI data and circumvent issues surrounding data sharing and patient privacy for future BC machine learning studies.

Speed and efficiency: evaluating pulmonary nodule detection with AI-enhanced 3D gradient echo imaging.

OBJECTIVES: Evaluating the diagnostic feasibility of accelerated pulmonary MR imaging for detection and characterisation of pulmonary nodules with artificial intelligence-aided compressed sensing. MATERIALS AND METHODS: In this prospective trial, patients with benign and malignant lung nodules admitted between December 2021 and December 2022 underwent chest CT and pulmonary MRI. Pulmonary MRI used a respiratory-gated 3D gradient echo sequence, accelerated with a combination of parallel imaging, compressed sensing, and deep learning image reconstruction with three different acceleration factors (CS-AI-7, CS-AI-10, and CS-AI-15). Two readers evaluated image quality (5-point Likert scale), nodule detection and characterisation (size and morphology) of all sequences compared to CT in a blinded setting. Reader agreement was determined using the intraclass correlation coefficient (ICC). RESULTS: Thirty-seven patients with 64 pulmonary nodules (solid n = 57 [3-107 mm] part-solid n = 6 [ground glass/solid 8 mm/4-28 mm/16 mm] ground glass nodule n = 1 [20 mm]) were analysed. Nominal scan times were CS-AI-7 3:53 min; CS-AI-10 2:34 min; CS-AI-15 1:50 min. CS-AI-7 showed higher image quality, while quality remained diagnostic even for CS-AI-15. Detection rates of pulmonary nodules were 100%, 98.4%, and 96.8% for CS-AI factors 7, 10, and 15, respectively. Nodule morphology was best at the lowest acceleration and was inferior to CT in only 5% of cases, compared to 10% for CS-AI-10 and 23% for CS-AI-15. The nodule size was comparable for all sequences and deviated on average < 1 mm from the CT size. CONCLUSION: The combination of compressed sensing and AI enables a substantial reduction in the scan time of lung MRI while maintaining a high detection rate of pulmonary nodules. CLINICAL RELEVANCE STATEMENT: Incorporating compressed sensing and AI in pulmonary MRI achieves significant time savings without compromising nodule detection or characteristics. This advancement holds clinical promise, enhancing efficiency in lung cancer screening without sacrificing diagnostic quality. KEY POINTS: Lung cancer screening by MRI may be possible but would benefit from scan time optimisation. Significant scan time reduction, high detection rates, and preserved nodule characteristics were achieved across different acceleration factors. Integrating compressed sensing and AI in pulmonary MRI offers efficient lung cancer screening without compromising diagnostic quality.

Effects of current alcohol use on brain volume among older adults in the Gothenburg H70 Birth Cohort study 2014-16.

Brain gray- and white matter changes is well described in alcohol-dependent elderly subjects; however, the effect of lower levels of alcohol consumption on the brain is poorly understood. We investigated the impact of different amounts of weekly alcohol consumption on brain structure in a population-based sample of 70-year-olds living in Gothenburg, Sweden. Cross-sectional data from 676 participants from The Gothenburg H70 Birth Cohort Study 2014-16 were included. Current alcohol consumers were divided into seven groups based on self-reported weekly amounts of alcohol consumption in grams (g) (0-50 g/week, used as reference group, 51-100 g/week, 101-150 g/week, 151-200 g/week, 201-250 g/week, 251-300 g/week, and > 300 g/week). Subcortical volumes and cortical thickness were assessed on T1-weighted structural magnetic resonance images using FreeSurfer 5.3, and white matter integrity assessed on diffusion tensor images, using tract-based statistics in FSL. General linear models were carried out to estimate associations between alcohol consumption and gray- and white matter changes in the brain. Self-reported consumption above 250 g/week was associated with thinning in the bilateral superior frontal gyrus, the right precentral gyrus, and the right lateral occipital cortex, in addition to reduced fractional anisotropy (FA) and increased mean diffusivity (MD) diffusively spread in many tracts all over the brain. No changes were found in subcortical gray matter structures. These results suggest that there is a non-linear relationship between alcohol consumption and structural brain changes, in which loss of cortical thickness only occur in non-demented 70-year-olds who consume more than 250 g/week.

Cortical thickness differences are associated with cellular component morphogenesis of astrocytes and excitatory neurons in nonsuicidal self-injuring youth.

Nonsuicidal self-injury (NSSI) generally occurs in youth and probably progresses to suicide. An examination of cortical thickness differences (ΔCT) between NSSI individuals and controls is crucial to investigate potential neurobiological correlates. Notably, ΔCT are influenced by specific genetic factors, and a large proportion of cortical thinning is associated with the expression of genes that overlap in astrocytes and pyramidal cells. However, in NSSI youth, the mechanisms underlying the relations between the genetic and cell type-specific transcriptional signatures to ΔCT are unclear. Here, we studied the genetic association of ΔCT in NSSI youth by performing a partial least-squares regression (PLSR) analysis of gene expression data and 3D-T1 brain images of 45 NSSI youth and 75 controls. We extracted the top-10 Gene Ontology terms for the enrichment results of upregulated PLS component 1 genes related to ΔCT to conduct the cell-type classification and enrichment analysis. Enrichment of cell type-specific genes shows that cellular component morphogenesis of astrocytes and excitatory neurons accounts for the observed NSSI-specific ΔCT. We validated the main results in independent datasets to verify the robustness and specificity. We concluded that the brain ΔCT is associated with cellular component morphogenesis of astrocytes and excitatory neurons in NSSI youth.

An effective no-reference image quality index prediction with a hybrid Artificial Intelligence approach for denoised MRI images.

As the quantity and significance of digital pictures in the medical industry continue to increase, Image Quality Assessment (IQA) has recently become a prevalent subject in the research community. Due to the wide range of distortions that Magnetic Resonance Images (MRI) can experience and the wide variety of information they contain, No-Reference Image Quality Assessment (NR-IQA) has always been a challenging study issue. In an attempt to address this issue, a novel hybrid Artificial Intelligence (AI) is proposed to analyze NR-IQ in massive MRI data. First, the features from the denoised MRI images are extracted using the gray level run length matrix (GLRLM) and EfficientNet B7 algorithm. Next, the Multi-Objective Reptile Search Algorithm (MRSA) was proposed for optimal feature vector selection. Then, the Self-evolving Deep Belief Fuzzy Neural network (SDBFN) algorithm was proposed for the effective NR-IQ analysis. The implementation of this research is executed using MATLAB software. The simulation results are compared with the various conventional methods in terms of correlation coefficient (PLCC), Root Mean Square Error (RMSE), Spearman Rank Order Correlation Coefficient (SROCC) and Kendall Rank Order Correlation Coefficient (KROCC), and Mean Absolute Error (MAE). In addition, our proposed approach yielded a quality number approximately we achieved significant 20% improvement than existing methods, with the PLCC parameter showing a notable increase compared to current techniques. Moreover, the RMSE number decreased by 12% when compared to existing methods. Graphical representations indicated mean MAE values of 0.02 for MRI knee dataset, 0.09 for MRI brain dataset, and 0.098 for MRI breast dataset, showcasing significantly lower MAE values compared to the baseline models.

Tractography analysis results of the trigeminus nerve, which contains fibers responsible for proprioception sensation and motor control in Adolescent Idiopathic Scoliosis.

STUDY DESIGN: Cross-sectional Study. BACKGROUND: It is not yet clear whether the loss of proprioceptive sensation and muscle weakness seen in adolescent idiopathic scoliosis (AIS) is the result of central nervous system dysfunction or secondary to spinal deformity. In our study, in order to find an answer to this question, we examined the microarchitecture of the nervus trigeminus, which is least affected by spinal deformity and contains both proprioceptive sensory and motor fibers. METHODS: In this single-center, cross-sectional cohort study, 40 Lenke Type 3 (27 female, 13 male) AIS patients and 40 (25 female, 15 male) healthy individuals between the ages of 10-18 years. Tractography of the nervus trigenimus was performed using the "DSI Studio" program. The volumes of the targeted musculus pterygoideus lateralis and musculus pterygoideus medialis were measured using the Insight Segmentation and Registration Tool Kit (ITK -SNAP) program. The data were evaluated using the Statistical Package for the Social Sciences 22.0 program for Windows. RESULTS: There was no significant difference between the two groups in terms of baseline characteristics (p˃0.05). Left nervus trigeminus fiber number and fiber ratio were significantly higher in the control group compared to the scoliosis group p < 0.05. Right and left lateral pterygoid muscle showed lower volume and volume percentage in the scoliosis group compared to the control group (p < 0.05). CONCLUSION: According to the study data, proprioceptive sensory and motor control dysfunction in AIS is predicted to develop independently of spinal deformity.

Multi-parametric assessment of cardiac magnetic resonance images to distinguish myocardial infarctions: A tensor-based radiomics feature.

AIM: This study assessed the myocardial infarction (MI) using a novel fusion approach (multi-flavored or tensor-based) of multi-parametric cardiac magnetic resonance imaging (CMRI) at four sequences; T1-weighted (T1W) in the axial plane, sense-balanced turbo field echo (sBTFE) in the axial plane, late gadolinium enhancement of heart short axis (LGE-SA) in the sagittal plane, and four-chamber views of LGE (LGE-4CH) in the axial plane. METHODS: After considering the inclusion and exclusion criteria, 115 patients (83 with MI diagnosis and 32 as healthy control patients), were included in the present study. Radiomic features were extracted from the whole left ventricular myocardium (LVM). Feature selection methods were Least Absolute Shrinkage and Selection Operator (Lasso), Minimum Redundancy Maximum Relevance (MRMR), Chi-Square (Chi2), Analysis of Variance (Anova), Recursive Feature Elimination (RFE), and SelectPersentile. The classification methods were Support Vector Machine (SVM), Logistic Regression (LR), and Random Forest (RF). Different metrics, including receiver operating characteristic curve (AUC), accuracy, F1- score, precision, sensitivity, and specificity were calculated for radiomic features extracted from CMR images using stratified five-fold cross-validation. RESULTS: For the MI detection, Lasso (as the feature selection) and RF/LR (as the classifiers) in sBTFE sequences had the best performance (AUC: 0.97). All features and classifiers of T1 + sBTFE sequences with the weighted method (as the fused image), had a good performance (AUC: 0.97). In addition, the results of the evaluated metrics, especially mean AUC and accuracy for all models, determined that the T1 + sBTFE-weighted fused method had strong predictive performance (AUC: 0.93±0.05; accuracy: 0.93±0.04), followed by T1 + sBTFE-PCA fused method (AUC: 0.85±0.06; accuracy: 0.84±0.06). CONCLUSION: Our selected CMRI sequences demonstrated that radiomics analysis enables to detection of MI accurately. Among the investigated sequences, the T1 + sBTFE-weighted fused method with the highest AUC and accuracy values was chosen as the best technique for MI detection.

DMCA-GAN: Dual Multilevel Constrained Attention GAN for MRI-Based Hippocampus Segmentation.

Precise segmentation of the hippocampus is essential for various human brain activity and neurological disorder studies. To overcome the small size of the hippocampus and the low contrast of MR images, a dual multilevel constrained attention GAN for MRI-based hippocampus segmentation is proposed in this paper, which is used to provide a relatively effective balance between suppressing noise interference and enhancing feature learning. First, we design the dual-GAN backbone to effectively compensate for the spatial information damage caused by multiple pooling operations in the feature generation stage. Specifically, dual-GAN performs joint adversarial learning on the multiscale feature maps at the end of the generator, which yields an average Dice coefficient (DSC) gain of 5.95% over the baseline. Next, to suppress MRI high-frequency noise interference, a multilayer information constraint unit is introduced before feature decoding, which improves the sensitivity of the decoder to forecast features by 5.39% and effectively alleviates the network overfitting problem. Then, to refine the boundary segmentation effects, we construct a multiscale feature attention restraint mechanism, which forces the network to concentrate more on effective multiscale details, thus improving the robustness. Furthermore, the dual discriminators D1 and D2 also effectively prevent the negative migration phenomenon. The proposed DMCA-GAN obtained a DSC of 90.53% on the Medical Segmentation Decathlon (MSD) dataset with tenfold cross-validation, which is superior to the backbone by 3.78%.

Deep-Stacked Convolutional Neural Networks for Brain Abnormality Classification Based on MRI Images.

An automated diagnosis system is crucial for helping radiologists identify brain abnormalities efficiently. The convolutional neural network (CNN) algorithm of deep learning has the advantage of automated feature extraction beneficial for an automated diagnosis system. However, several challenges in the CNN-based classifiers of medical images, such as a lack of labeled data and class imbalance problems, can significantly hinder the performance. Meanwhile, the expertise of multiple clinicians may be required to achieve accurate diagnoses, which can be reflected in the use of multiple algorithms. In this paper, we present Deep-Stacked CNN, a deep heterogeneous model based on stacked generalization to harness the advantages of different CNN-based classifiers. The model aims to improve robustness in the task of multi-class brain disease classification when we have no opportunity to train single CNNs on sufficient data. We propose two levels of learning processes to obtain the desired model. At the first level, different pre-trained CNNs fine-tuned via transfer learning will be selected as the base classifiers through several procedures. Each base classifier has a unique expert-like character, which provides diversity to the diagnosis outcomes. At the second level, the base classifiers are stacked together through neural network, representing the meta-learner that best combines their outputs and generates the final prediction. The proposed Deep-Stacked CNN obtained an accuracy of 99.14% when evaluated on the untouched dataset. This model shows its superiority over existing methods in the same domain. It also requires fewer parameters and computations while maintaining outstanding performance.

Left ventricular myocardial motion tracking in cardiac cine magnetic resonance images based on a biomechanical model.

BACKGROUND: Cardiac cine magnetic resonance (CCMR) imaging plays an important role in the clinical cardiovascular disease (CVD) examination and evaluation. OBJECTIVE: To accurately reconstruct the displacement field and describe the motion of the left ventricular myocardium (LVM), this study proposes and tests a new approach for tracking myocardial motion of the left ventricle based on a biomechanical model. METHODS: CCMR imaging data acquired from 103 patients are enrolled, including two simulated and 101 clinical data. A non-rigid image registration method with a combination of a thin-plate spline function and random sample consensus is used to recover the observed displacement field of LVM. Next, a biomechanical model and a material matrix are introduced to solve the dense displacement field of LVM using a finite element framework. Then, the tracking precision and error of results for the two groups are analyzed. RESULTS: Displacement results of the simulated data show correlation coefficient≥0.876 and mean square error≤0.159, while displacement results of the clinical data show Dice≥0.97 and mean contour distance≤0.464. Additionally, the strain results show correlation coefficient≥0.717. CONCLUSIONS: This study demonstrates that the proposed new method enables to accurately track the motion of the LVM and evaluate strain, which has clinical auxiliary value in the diagnosis of CVD.

[A meta-learning based method for segmentation of few-shot magnetic resonance images].

When applying deep learning algorithms to magnetic resonance (MR) image segmentation, a large number of annotated images are required as data support. However, the specificity of MR images makes it difficult and costly to acquire large amounts of annotated image data. To reduce the dependence of MR image segmentation on a large amount of annotated data, this paper proposes a meta-learning U-shaped network (Meta-UNet) for few-shot MR image segmentation. Meta-UNet can use a small amount of annotated image data to complete the task of MR image segmentation and obtain good segmentation results. Meta-UNet improves U-Net by introducing dilated convolution, which can increase the receptive field of the model to improve the sensitivity to targets of different scales. We introduce the attention mechanism to improve the adaptability of the model to different scales. We introduce the meta-learning mechanism, and employ a composite loss function for well-supervised and effective bootstrapping of model training. We use the proposed Meta-UNet model to train on different segmentation tasks, and then use the trained model to evaluate on a new segmentation task, where the Meta-UNet model achieves high-precision segmentation of target images. Meta-UNet has a certain improvement in mean Dice similarity coefficient (DSC) compared with voxel morph network (VoxelMorph), data augmentation using learned transformations (DataAug) and label transfer network (LT-Net). Experiments show that the proposed method can effectively perform MR image segmentation using a small number of samples. It provides a reliable aid for clinical diagnosis and treatment.

[Research on classification method of multimodal magnetic resonance images of Alzheimer's disease based on generalized convolutional neural networks].

Alzheimer's disease (AD) is a progressive and irreversible neurodegenerative disease. Neuroimaging based on magnetic resonance imaging (MRI) is one of the most intuitive and reliable methods to perform AD screening and diagnosis. Clinical head MRI detection generates multimodal image data, and to solve the problem of multimodal MRI processing and information fusion, this paper proposes a structural and functional MRI feature extraction and fusion method based on generalized convolutional neural networks (gCNN). The method includes a three-dimensional residual U-shaped network based on hybrid attention mechanism (3D HA-ResUNet) for feature representation and classification for structural MRI, and a U-shaped graph convolutional neural network (U-GCN) for node feature representation and classification of brain functional networks for functional MRI. Based on the fusion of the two types of image features, the optimal feature subset is selected based on discrete binary particle swarm optimization, and the prediction results are output by a machine learning classifier. The validation results of multimodal dataset from the AD Neuroimaging Initiative (ADNI) open-source database show that the proposed models have superior performance in their respective data domains. The gCNN framework combines the advantages of these two models and further improves the performance of the methods using single-modal MRI, improving the classification accuracy and sensitivity by 5.56% and 11.11%, respectively. In conclusion, the gCNN-based multimodal MRI classification method proposed in this paper can provide a technical basis for the auxiliary diagnosis of Alzheimer's disease.

Guideline-concordant utilization of magnetic resonance imaging in adults receiving chiropractic manipulative therapy vs other care for radicular low back pain: a retrospective cohort study.

BACKGROUND: Lumbar magnetic resonance imaging (LMRI) is often performed early in the course of care, which can be discordant with guidelines for non-serious low back pain. Our primary hypothesis was that adults receiving chiropractic spinal manipulative therapy (CSMT) for incident radicular low back pain (rLBP) would have reduced odds of early LMRI over 6-weeks' follow-up compared to those receiving other care (a range of medical care, excluding CSMT). As a secondary hypothesis, CSMT recipients were also expected to have reduced odds of LMRI over 6-months' and 1-years' follow-up. METHODS: A national 84-million-patient health records database including large academic healthcare organizations (TriNetX) was queried for adults age 20-70 with rLBP newly-diagnosed between January 31, 2012 and January 31, 2022. Receipt or non-receipt of CSMT determined cohort allocation. Patients with prior lumbar imaging and serious pathology within 90 days of diagnosis were excluded. Propensity score matching controlled for variables associated with LMRI utilization (e.g., demographics). Odds ratios (ORs) of LMRI over 6-weeks', 6-months', and 1-years' follow-up after rLBP diagnosis were calculated. RESULTS: After matching, there were 12,353 patients per cohort (mean age 50 years, 56% female), with a small but statistically significant reduction in odds of early LMRI in the CSMT compared to other care cohort over 6-weeks' follow-up (9%, 10%, OR [95% CI] 0.88 [0.81-0.96] P = 0.0046). There was a small but statistically significant increase in odds of LMRI among patients in the CSMT relative to the other care cohort over 6-months' (12%, 11%, OR [95% CI] 1.10 [1.02-1.19], P < 0.0174) and 1-years' follow-up (14%, 12%, OR [95% CI] 1.21 [1.13-1.31], P < 0.0001). CONCLUSIONS: These results suggest that patients receiving CSMT for newly-diagnosed rLBP are less likely to receive early LMRI than patients receiving other care. However, CSMT recipients have a small increase in odds of LMRI over the long-term. Both cohorts in this study had a relatively low rate of early LMRI, possibly because the data were derived from academic healthcare organizations. The relationship of these findings to other patient care outcomes and cost should be explored in a future randomized controlled trial. REGISTRATION: Open Science Framework ( https://osf.io/t9myp ).

Efficient Segmentation for Left Atrium With Convolution Neural Network Based on Active Learning in Late Gadolinium Enhancement Magnetic Resonance Imaging.

BACKGROUND: To propose fully automatic segmentation of left atrium using active learning with limited dataset in late gadolinium enhancement in cardiac magnetic resonance imaging (LGE-CMRI). METHODS: An active learning framework was developed to segment the left atrium in cardiac LGE-CMRI. Patients (n = 98) with atrial fibrillation from the Korea University Anam Hospital were enrolled. First, 20 cases were delineated for ground truths by two experts and used for training a draft model. Second, the 20 cases from the first step and 50 new cases, corrected in a human-in-the-loop manner after predicting using the draft model, were used to train the next model; all 98 cases (70 cases from the second step and 28 new cases) were trained. An additional 20 LGE-CMRI were evaluated in each step. RESULTS: The Dice coefficients for the three steps were 0.85 ± 0.06, 0.89 ± 0.02, and 0.90 ± 0.02, respectively. The biases (95% confidence interval) in the Bland-Altman plots of each step were 6.36% (-14.90-27.61), 6.21% (-9.62-22.03), and 2.68% (-8.57-13.93). Deep active learning-based annotation times were 218 ± 31 seconds, 36.70 ± 18 seconds, and 36.56 ± 15 seconds, respectively. CONCLUSION: Deep active learning reduced annotation time and enabled efficient training on limited LGE-CMRI.

Evaluation of clinical findings and neurofibromatosis type 1 bright objects on brain magnetic resonance images of 60 Turkish patients with NF1 gene variants.

Neurofibromatosis type 1 (NF1) is caused by mutations in the NF1 gene. This retrospective study aims to evaluate the clinical manifestations and brain magnetic resonance images (MRI) analysis in 60 genetically confirmed NF1 patients. The results of next-generation sequencing (NGS), Sanger sequencing, and MLPA of NF1 gene were evaluated. A total of 54 different variants were identified. Fourteen out of them were novel variants (25.9%). Patients who complied with NIH criteria had most frequently frameshift variants (11/32 patients), and those with only CALMs had missense variants (9/28 patients). Neurofibromatosis type 1 bright objects (NBOs) on T2-weighted MRI were detected in 42 patients (42/56; 75%). These brain lesions were detected mostly in basal ganglia and in cerebellar vermis. NBOs were detected more in the patients who complied with NIH criteria (80.6%) compared to those who were only CALMs (68%). While frameshift variants (33.3%) were the most common type variants in the patients who had NBOs, the most common variants were splicing (35.7%) and missense (35.7%) variants in the patients whose MRIs were normal. Frameshift variants (11/28 patients; 39.3%) were the most common in the patients with more than one brain locus involvement. Therefore, we consider that frameshift variants may be associated with increased incidence of NBOs and involvement of more than one brain locus. In addition, NBOs may occur less frequently in the patients with splicing variants. To our knowledge, this is the first study evaluated the relationship between NF1 gene variants and NBOs. Future studies may help us understand the etiology of NBOs.

Distinguishing brain abscess from necrotic glioblastoma using MRI-based intranodular radiomic features and peritumoral edema/tumor volume ratio.

A correct preoperative diagnosis is essential for the treatment and prognosis of necrotic glioblastoma and brain abscess, but the differentiation between them remains challenging. We constructed a diagnostic prediction model with good performance and enhanced clinical applicability based on data from 86 patients with necrotic glioblastoma and 32 patients with brain abscess that were diagnosed between January 2012 and January 2020. The diagnostic values of three regions of interest based on contrast-enhanced T1 weighted images (including whole tumor, brain-tumor interface, and an amalgamation of both regions) were compared using Logistics Regression and Random Forest. Feature reduction based on the optimal regions of interest was performed using principal component analysis with varimax rotation. The performance of the classifiers was assessed by receiver operator curves. Finally, clinical predictors were utilized to detect the diagnostic power. The mean area under curve (AUC) values of the whole tumor model was significantly higher than other two models obtained from Brain-Tumor Interface (BTI) and combine regions both in training (AUC mean = 0.850) and test/validation set (AUC mean = 0.896) calculated by Logistics Regression and in the testing set (AUC mean = 0.876) calculated by Random Forest. Among these three diagnostic prediction models, the combined model provided superior discrimination performance and yielded an AUC of 0.993, 0.907, and 0.974 in training, testing, and combined datasets, respectively. Compared with the brain-tumor interface and the combined regions, features obtained from the whole tumor showed the best differential value. The radiomic features combined with the peritumoral edema/tumor volume ratio provided the prediction model with the greatest diagnostic performance.

Fusion of Deep Convolutional Neural Networks for No-Reference Magnetic Resonance Image Quality Assessment.

The quality of magnetic resonance images may influence the diagnosis and subsequent treatment. Therefore, in this paper, a novel no-reference (NR) magnetic resonance image quality assessment (MRIQA) method is proposed. In the approach, deep convolutional neural network architectures are fused and jointly trained to better capture the characteristics of MR images. Then, to improve the quality prediction performance, the support vector machine regression (SVR) technique is employed on the features generated by fused networks. In the paper, several promising network architectures are introduced, investigated, and experimentally compared with state-of-the-art NR-IQA methods on two representative MRIQA benchmark datasets. One of the datasets is introduced in this work. As the experimental validation reveals, the proposed fusion of networks outperforms related approaches in terms of correlation with subjective opinions of a large number of experienced radiologists.

Learning U-Net Based Multi-Scale Features in Encoding-Decoding for MR Image Brain Tissue Segmentation.

Accurate brain tissue segmentation of MRI is vital to diagnosis aiding, treatment planning, and neurologic condition monitoring. As an excellent convolutional neural network (CNN), U-Net is widely used in MR image segmentation as it usually generates high-precision features. However, the performance of U-Net is considerably restricted due to the variable shapes of the segmented targets in MRI and the information loss of down-sampling and up-sampling operations. Therefore, we propose a novel network by introducing spatial and channel dimensions-based multi-scale feature information extractors into its encoding-decoding framework, which is helpful in extracting rich multi-scale features while highlighting the details of higher-level features in the encoding part, and recovering the corresponding localization to a higher resolution layer in the decoding part. Concretely, we propose two information extractors, multi-branch pooling, called MP, in the encoding part, and multi-branch dense prediction, called MDP, in the decoding part, to extract multi-scale features. Additionally, we designed a new multi-branch output structure with MDP in the decoding part to form more accurate edge-preserving predicting maps by integrating the dense adjacent prediction features at different scales. Finally, the proposed method is tested on datasets MRbrainS13, IBSR18, and ISeg2017. We find that the proposed network performs higher accuracy in segmenting MRI brain tissues and it is better than the leading method of 2018 at the segmentation of GM and CSF. Therefore, it can be a useful tool for diagnostic applications, such as brain MRI segmentation and diagnosing.

No-reference image quality assessment of magnetic resonance images with high-boost filtering and local features.

PURPOSE: Subjective quality assessment of displayed magnetic resonance (MR) images plays a key role in diagnosis and the resultant treatment. Therefore, this study aims to introduce a new no-reference (NR) image quality assessment (IQA) method for the objective, automatic evaluation of MR images and compare its judgments with those of similar techniques. METHODS: A novel NR-IQA method was developed. The method uses a sequence of scaled images filtered to enhance high-frequency components and preserve low-frequency parts. Since the human visual system (HVS) is sensitive to local image variations and local features often mimic the attraction of the HVS to high-frequency image regions, they were detected in the filtered images and described. Then, the statistics of obtained descriptors were used to build a quality model via the Support Vector Regression method. RESULTS: The method was compared with 21 state-of-the-art techniques for NR-IQA on a new dataset of 70 distorted MR images assessed by 31 experienced radiologists, using typical evaluation criteria for the comparison of NR measures. The introduced method significantly outperforms the compared approaches, in terms of the correlation with human judgments. CONCLUSIONS: It is demonstrated that the presented NR-IQA method for the assessment of MR images is superior to the state-of-the-art NR techniques. The method would be beneficial for a wide range of image processing applications, assessing their outputs and affecting the directions of their development.

Vestibular nuclear infarction: Case series and review of the literature.

BACKGROUND AND PURPOSE: Acute vestibular syndrome (AVS) is a common cause of emergency admittance and has very rarely been reported due to a vestibular nucleus infarction. Initial magnetic resonance imaging studies (MRIs) including diffusion-weighted images may reveal normal results and even bedside examination tests like HINTS battery which involves head impulse test (HIT), nystagmus and test of skew can be challenging in differing a peripheral vestibulopathy from a central lesion. METHODS: Four patients seen in the emergency department with AVS and evaluated with HINTS battery, cervical vestibular-evoked myogenic potentials (cVEMP) and cranial MRI revealing infarcts restricted to vestibular nuclei were evaluated. RESULTS: In two patients spontaneous nystagmus beating towards the unaffected side was present. In one patient spontaneous nystagmus changed direction on looking to the affected side. In the fourth gaze evoked nystagmus was present without any spontaneous nystagmus. In all, HIT was positive to the affected side. In three cVEMPs was studied revealing delayed latency, reduced amplitude p13/n23 potentials on the lesioned side in two of them. Initial MRIs including diffusion-weighted images disclosed acute infarction in the area of the vestibular nuclei in two patients, with normal results in the other two. Follow-up MRI's performed 48 hours later revealed vestibular nuclear infarction. CONCLUSION: It is not always easy to differentiate small lesions restricted to central vestibular structures from peripheral vestibular lesions both on clinical and radiological grounds. Follow-up cranial MRI is necessary in patients with known vascular risk factors.