Evaluation of discrete orthogonal versus polar Stockwell Transform for local multi-resolution texture analysis using brain MRI of multiple sclerosis patients

The Stockwell Transform has the potential to perform multi-resolution texture analysis in magnetic resonance imaging (MRI). However, it is computationally intensive and memory demanding. The polar Stockwell Transform (PST) is rotation-invariant and relatively memory efficient, but still computationally demanding. The new Discrete Orthogonal Stockwell Transform (DOST) appears to have addressed both the computation and storage challenges; however, its utility in localized texture analysis remains unclear. Our goal was to investigate the theory and texture analysis ability of the DOST versus PST using both synthetic and MR images, and explore the relative importance of the associated texture features using a simple classification example based on clinical brain MRI of six multiple sclerosis patients. MRI texture analysis focused on FLAIR images, and the classification used a machine learning algorithm, random forest, that differentiated regions of interest (ROIs) into 2 classes: white matter lesions, and the contralateral normal-appearing white matter (control). Our results showed that the PST features had a greater ability in detecting subtle changes in image structure than the DOST and polar-index DOST (PDOST). Quantitatively, based on 187 lesion and 187 control ROIs, both the PST and the rotation-invariant radial PST performed better in the classification than the DOST and PDOST, where the latter were no better than guessing (p = 0.65 and 0.98). Further analysis using a hierarchical random forest showed that combining MRI signal intensity with the PST or DOST predictions increased the classification performance, with the accuracy, sensitivity, and specificity all improved to >85% in the tests. Collectively, the DOST is less competitive than the PST in localized image texture analysis. The PST features may help with texture-based lesion classification in MS based on clinical brain MRI scans following further verification.     

Spatial normalization of multiple sclerosis brain MRI data depends on analysis method and software package

BackgroundSpatially normalizing brain MRI data to a template is commonly performed to facilitate comparisons between individuals or groups. However, the presence of multiple sclerosis (MS) lesions and other MS-related brain pathologies may compromise the performance of automated spatial normalization procedures. We therefore aimed to systematically compare five commonly used spatial normalization methods for brain MRI – including linear (affine), and nonlinear MRIStudio (LDDMM), FSL (FNIRT), ANTs (SyN), and SPM (CAT12) algorithms – to evaluate their performance in the presence of MS-related pathologies.Methods3 Tesla MRI images (T1-weighted and T2-FLAIR) were obtained for 20 participants with MS from an ongoing cohort study (used to assess a real dataset) and 1 healthy control participant (used to create a simulated lesion dataset). Both raw and lesion-filled versions of each participant's T1-weighted brain images were warped to the Montreal Neurological Institute (MNI) template using all five normalization approaches for the real dataset, and the same procedure was then repeated using the simulated lesion dataset (i.e., total of 400 spatial normalizations). As an additional quality-assurance check, the resulting deformations were also applied to the corresponding lesion masks to evaluate how each processing pipeline handled focal white matter lesions. For each normalization approach, inter-subject variability (across normalized T1-weighted images) was quantified using both mutual information (MI) and coefficient of variation (COV), and the corresponding normalized lesion volumes were evaluated using paired-sample t-tests.ResultsAll four nonlinear warping methods outperformed conventional linear normalization, with SPM (CAT12) yielding the highest MI values, lowest COV values, and proportionately-scaled lesion volumes. Although lesion-filling improved spatial normalization accuracy for each of the methods tested, these effects were small compared to differences between normalization algorithms.ConclusionsSPM (CAT12) warping, ideally combined with lesion-filling, is recommended for use in future MS brain imaging studies requiring spatial normalization.     

Normal appearing brain white matter changes in relapsing multiple sclerosis: Texture image and classification analysis in serial MRI scans

ObjectiveThere is a clinical interest in identifying normal appearing white matter (NAWM) areas in brain T2-weighted (T₂W) MRI scans in multiple sclerosis (MS) subjects. These areas are susceptible to disease development and areas need to be studied in order to find potential associations between texture feature changes and disease progression.MethodsThe subjects investigated had a first demyelinating event (Clinically Isolated Syndrome-CIS) at baseline (Time₀), and the NAWM₀ (i.e. NAWM at Time₀) of the brain tissue was subsequently converted to demyelinating plaques (as evaluated in a follow up MRI at Time_6–12). 38 untreated subjects that had developed a CIS, had brain MRI scans within an interval of 6–12 months (Time_6–12 at follow-up). An experienced MS neurologist manually delineated the demyelinating lesions at Time₀ (L₀) and at Time_6–12 (L_6–12). Areas in the Time_6–12 MRI scans, where new lesions had been developed, were mapped back to their corresponding NAWM areas on the Time₀ MR scans (ROIS₀). In addition, contralateral ROIs of similar size and shape were segmented on the same images at Time₀ (ROIS_C0) to form an intra-subject control group. Following that, texture features were extracted from all prescribed areas and MS lesions.ResultsTexture features were used as input into Support Vector Machine (SVM) models to differentiate between the following: NAWM₀ vs ROIS_C0, NAWM₀ vs NAWM_6–12, NAWM₀ vs L₀, NAWM_6–12 vs L_6–12, ROIS₀ vs L₀, ROIS₀ vs L_6–12 and ROIS₀ vs ROIS_C0, where the corresponding % correct classifications scores were 89%, 95%, 98%, 92%, 85%, 90% and 65% respectively.ConclusionsTexture features may provide complementary information for following up the development and progression of MS disease. Future work will investigate the proposed method on more subjects.     

A multiparametric approach to diagnosing breast lesions using diffusion-weighted imaging and ultrafast dynamic contrast-enhanced MRI

PurposeTo evaluate the diagnostic performance of a multiparametric approach to breast lesions including apparent diffusion coefficient (ADC) from diffusion-weighted images (DWI), maximum slope (MS) from ultrafast dynamic contrast enhanced (UF-DCE) MRI, lesion size, and patient's age.Materials and methodsIn total, 96 lesions (73 malignant, 23 benign) were evaluated. UF-DCE MRI was acquired using a prototype 3D-gradient-echo volumetric interpolated breath-hold examination (VIBE) with compressed sensing. Images were obtained up to 1 min after gadolinium injection. MS was calculated as the percentage relative enhancement/s. An ADC map was automatically generated from DWI at b = 0 and b = 1000 s/mm². MS and ADC values were measured by two radiologists independently. Interrater agreement was evaluated using intraclass correlation coefficients. Univariate and multivariate logistic regression analyses were performed using MS, ADC, lesion size, and the patient's age. The parameters of the prediction model were generated from the results of the multivariate logistic regression analysis. Area under the curve (AUC) was used to compare diagnostic performance of the prediction model and each parameter.ResultsInterrater agreements on MS and ADC were excellent (ICC 0.99 and 0.88, respectively). MS, ADC, and patient's age remained as significant parameters after univariate and multivariate logistic regression analysis. The prediction model using these significant parameters yielded an AUC of 0.90, significantly higher than that of MS (AUC 0.74, p = 0.01). The AUCs of ADC, MS, patient's age were 0.87, 0.74 and 0.73, respectively.ConclusionsA multiparametric model using ADC from DWI, MS from UF-DCE MRI, and patient's age showed excellent diagnostic performance, with greater contribution of ADC. Combining DWI and UF-DCE MRI might reduce scanning time while preserving diagnostic performance.     

Abdominal adipose tissue components quantification in MRI as a relevant biomarker of metabolic profile

IntroductionAbnormal accumulation of adipose tissue (AT) alters the metabolic profile and underlies cardiovascular complications. Conventional measures provide global measurements for the entire body. The purpose of this study was to propose a new approach to quantify the amount and type of truncal AT automatically from MRI in metabolic patients and controls.Materials and methodsDIXON acquisitions were performed at 1.5 T in 30 metabolic syndrome (MS) (59 ± 6 years), 12 obese (50 ± 11 years), 35 type 2 diabetes (T2DM) patients (56 ± 11 years) and 19 controls (52 ± 11 years). AT was segmented into: subcutaneous AT “SAT”, visceral AT “VAT”, deep VAT “dVAT”, peri-organ VAT “pVAT” using active contours and k-means clustering algorithms. Subsequently, organ AT infiltration index “oVAT” was calculated as the normalized fat signal magnitude in organs.ResultsExcellent intra- and inter-operator reproducibility was obtained for AT segmentation. MS and obese patients had the highest amount of total AT. SAT increased in MS (1144 ± 621 g) and T2DM patients (1024 ± 634 g), and twice the level of SAT in controls (505 ± 238 g), and further increased in obese patients (1429 ± 621 g). While VAT, pVAT and dVAT increased to a similar degree in the metabolic patients compared to controls, the oVAT index was able to differentiate controls from MS and T2DM patients and to discriminate the three metabolic patient groups (p < 0.01). Local AT sub-types were not related to BMI in all groups except for SAT in controls (p = 0.03).ConclusionReproducible truncal AT sub-types quantification using 3D MRI was able to characterize patients with metabolic diseases. It may serve in the future as a non-invasive predictor of cardiovascular complications in such patients.     

A knowledge-driven feature learning and integration method for breast cancer diagnosis on multi-sequence MRI

BackgroundThe classification of benign versus malignant breast lesions on multi-sequence Magnetic Resonance Imaging (MRI) is a challenging task since breast lesions are heterogeneous and complex. Recently, deep learning methods have been used for breast lesion diagnosis with raw image input. However, without the guidance of domain knowledge, these data-driven methods cannot ensure that the features extracted from images are comprehensive for breast cancer diagnosis. Specifically, these features are difficult to relate to clinically relevant phenomena.PurposeInspired by the cognition process of radiologists, we propose a Knowledge-driven Feature Learning and Integration (KFLI) framework, to discriminate between benign and malignant breast lesions using Multi-sequences MRI.MethodsStarting from sequence division based on characteristics, we use domain knowledge to guide the feature learning process so that the feature vectors of sub-sequence are constrained to lie in characteristic-related semantic space. Then, different deep networks are designed to extract various sub-sequence features. Furthermore, a weighting module is employed for the integration of the features extracted from different sub-sequence images adaptively.ResultsThe KFLI is a domain knowledge and deep network ensemble, which can extract sufficient and effective features from each sub-sequence for a comprehensive diagnosis of breast cancer. Experiments on 100 MRI studies have demonstrated that the KFLI achieves sensitivity, specificity, and accuracy of 84.6%, 85.7% and 85.0%, respectively, which outperforms other state-of-the-art algorithms.     

Texture analysis of multiple sclerosis: a comparative study

The difficulty of using magnetic resonance imaging (MRI) to support early diagnosis of multiple sclerosis (MS) stems from the subtle pathological changes in the central nervous system (CNS). In this study, texture analysis was performed on MR images of MS patients and normal controls and a combined set of texture features were explored in order to better discriminate tissues between MS lesions, normal appearing white matter (NAWM) and normal white matter (NWM). Features were extracted from gradient matrix, run-length (RL) matrix, gray level co-occurrence matrix (GLCM), autoregressive (AR) model and wavelet analysis, and were selected based on greatest difference between different tissue types. The results of the combined set of texture features were compared with our previous results of GLCM-based features alone. The results of this study demonstrated that (1) with the combined set of texture features, classification was perfect (100%) between MS lesions and NAWM (or NWM), less successful (88.89%) among the three tissue types and worst (58.33%) between NAWM and NWM; (2) compared with GLCM-based features, the combined set of texture features were better at discriminating MS lesions and NWM, equally good at discriminating MS lesions and NAWM and at all three tissue types, but less effective in classification between NAWM and NWM. This study suggested that texture analysis with the combined set of texture features may be equally good or more advantageous than the commonly used GLCM-based features alone in discriminating MS lesions and NWM/NAWM and in supporting early diagnosis of MS.     

Automated thalamic nuclei segmentation using multi-planar cascaded convolutional neural networks

PurposeTo develop a fast and accurate convolutional neural network based method for segmentation of thalamic nuclei.MethodsA cascaded multi-planar scheme with a modified residual U-Net architecture was used to segment thalamic nuclei on conventional and white-matter-nulled (WMn) magnetization prepared rapid gradient echo (MPRAGE) data. A single network was optimized to work with images from healthy controls and patients with multiple sclerosis (MS) and essential tremor (ET), acquired at both 3 T and 7 T field strengths. WMn-MPRAGE images were manually delineated by a trained neuroradiologist using the Morel histological atlas as a guide to generate reference ground truth labels. Dice similarity coefficient and volume similarity index (VSI) were used to evaluate performance. Clinical utility was demonstrated by applying this method to study the effect of MS on thalamic nuclei atrophy.ResultsSegmentation of each thalamus into twelve nuclei was achieved in under a minute. For 7 T WMn-MPRAGE, the proposed method outperforms current state-of-the-art on patients with ET with statistically significant improvements in Dice for five nuclei (increase in the range of 0.05–0.18) and VSI for four nuclei (increase in the range of 0.05–0.19), while performing comparably for healthy and MS subjects. Dice and VSI achieved using 7 T WMn-MPRAGE data are comparable to those using 3 T WMn-MPRAGE data. For conventional MPRAGE, the proposed method shows a statistically significant Dice improvement in the range of 0.14–0.63 over FreeSurfer for all nuclei and disease types. Effect of noise on network performance shows robustness to images with SNR as low as half the baseline SNR. Atrophy of four thalamic nuclei and whole thalamus was observed for MS patients compared to healthy control subjects, after controlling for the effect of parallel imaging, intracranial volume, gender, and age (p < 0.004).ConclusionThe proposed segmentation method is fast, accurate, performs well across disease types and field strengths, and shows great potential for improving our understanding of thalamic nuclei involvement in neurological diseases.     

Computer-aided diagnosis of breast DCE-MRI using pharmacokinetic model and 3-D morphology analysis

Three-dimensional (3-D) dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) consists of a large number of images in different enhancement phases which are used to identify and characterize breast lesions. The purpose of this study was to develop a computer-assisted algorithm for tumor segmentation and characterization using both kinetic information and morphological features of 3-D breast DCE-MRI. An integrated color map created by intersecting kinetic and area under the curve (AUC) color maps was used to detect potential breast lesions, followed by the application of a region growing algorithm to segment the tumor. Modified fuzzy c-means clustering was used to identify the most representative kinetic curve of the whole segmented tumor, which was then characterized by using conventional curve analysis or pharmacokinetic model. The 3-D morphological features including shape features (compactness, margin, and ellipsoid fitting) and texture features (based on the grey level co-occurrence matrix) of the segmented tumor were obtained to characterize the lesion. One hundred and thirty-two biopsy-proven lesions (63 benign and 69 malignant) were used to evaluate the performance of the proposed computer-aided system for breast MRI. Five combined features including rate constant (k_ep), volume of plasma (v_p), energy (G₁), entropy (G₂), and compactness (C₁), had the best performance with an accuracy of 91.67% (121/132), sensitivity of 91.30% (63/69), specificity of 92.06% (58/63), and A_z value of 0.9427. Combining the kinetic and morphological features of 3-D breast MRI is a potentially useful and robust algorithm when attempting to differentiate benign and malignant lesions.     

Are multi-contrast magnetic resonance images necessary for segmenting multiple sclerosis brains? A large cohort study based on deep learning

BackgroundMagnetic resonance images with multiple contrasts or sequences are commonly used for segmenting brain tissues, including lesions, in multiple sclerosis (MS). However, acquisition of images with multiple contrasts increases the scan time and complexity of the analysis, possibly introducing factors that could compromise segmentation quality.ObjectiveTo investigate the effect of various combinations of multi-contrast images as input on the segmented volumes of gray (GM) and white matter (WM), cerebrospinal fluid (CSF), and lesions using a deep neural network.MethodsU-net, a fully convolutional neural network was used to automatically segment GM, WM, CSF, and lesions in 1000 MS patients. The input to the network consisted of 15 combinations of FLAIR, T1-, T2-, and proton density-weighted images. The Dice similarity coefficient (DSC) was evaluated to assess the segmentation performance. For lesions, true positive rate (TPR) and false positive rate (FPR) were also evaluated. In addition, the effect of lesion size on lesion segmentation was investigated.ResultsHighest DSC was observed for all the tissue volumes, including lesions, when the input was combination of all four image contrasts. All other input combinations that included FLAIR also provided high DSC for all tissue classes. However, the quality of lesion segmentation showed strong dependence on the input images. The DSC and TPR values for inputs with the four contrast combination and FLAIR alone were very similar, but FLAIR showed a moderately higher FPR for lesion size <100 μl. For lesions smaller than 20 μl all image combinations resulted in poor performance. The segmentation quality improved with lesion size.ConclusionsBest performance for segmented tissue volumes was obtained with all four image contrasts as the input, and comparable performance was attainable with FLAIR only as the input, albeit with a moderate increase in FPR for small lesions. This implies that acquisition of only FLAIR images provides satisfactory tissue segmentation. Lesion segmentation was poor for very small lesions and improved rapidly with lesion size.     

Distinct patterns of active and non-active plaques using texture analysis on brain NMR images in multiple sclerosis patients: preliminary results

The benefits of texture analysis of magnetic resonance images have been assessed in multiple sclerosis (MS) patients. Out of thirty-two lesions identified in eight MS patients, nine were considered active, judging from their gadolinium uptake. Texture analysis allowed to obtain forty-two characterizing parameters for each lesion. Using discriminant analysis as a statistical method allowed to classify the lesions into two groups: active or non-active. An attempt to classify their level of activity by using only co-occurrence matrices was unsuccessful. Alternately, the same type of analysis performed on runlength analysis criteria allowed the accurate classification of 88% of active lesions and 96% of non-active lesions. Using incremental discriminate analysis can reduce the number of useful parameters. This method showed that among the 42 parameters, 8 only were highly significant and permitted an accurate classification. Five of these parameters are runlength parameters, and three others are more directly related to the global distribution. The main interest of runlength parameters is that they allowed to demonstrate that the lesion structure was different in active and non-active plaques. This preliminary work suggests that using texture analysis could be of interest in the follow-up of MS patients because it provides an opportunity to identify active lesions without frequent gadolinium injections.     

Optimization and numerical evaluation of multi-compartment diffusion MRI using the spherical mean technique for practical multiple sclerosis imaging

BackgroundThe multi-compartment diffusion MRI using the spherical mean technique (SMT) has been suggested to enhance the pathological specificity to tissue injury in multiple sclerosis (MS) imaging, but its accuracy and precision have not been comprehensively evaluated.MethodsA Cramer-Rao Lower Bound method was used to optimize an SMT protocol for MS imaging. Finite difference computer simulations of spins in packed cylinders were then performed to evaluate the influences of five realistic pathological features in MS lesions: axon diameter, axon density, free water fraction, axonal crossing, dispersion, and undulation.ResultsSMT derived metrics can be biased by some confounds of pathological variations, such as axon size and free water fraction. However, SMT in general provides valuable information to characterize pathological features in MS lesions with a clinically feasible protocol.ConclusionSMT may be used as a practical MS imaging method and should be further improved in clinical MS imaging.     

Prognosticating brain tumor patient survival after laser thermotherapy: Comparison between neuroradiological reading and semi-quantitative analysis of MRI data

Background and purposeGiven increasing interest in laser interstitial thermotherapy (LITT) to treat brain tumor patients, we explored if examining multiple MRI contrasts per brain tumor patient undergoing surgery can impact predictive accuracy of survival post-LITT.Materials and methodsMRI contrasts included fluid-attenuated inversion recovery (FLAIR), T1 pre-gadolinium (T1pre), T1 post-gadolinium (T1Gd), T2, diffusion-weighted imaging (DWI), apparent diffusion coefficient (ADC), susceptibility weighted images (SWI), and magnetization-prepared rapid gradient-echo (MPRAGE). The latter was used for MRI data registration across preoperative to postoperative scans. Two ROIs were identified by thresholding preoperative FLAIR (large ROI) and T1Gd (small ROI) images. For each MRI contrast, a numerical score was assigned based on changing image intensity of both ROIs (vs. a normal ROI) from preoperative to postoperative stages. The fully-quantitative method was based on changing image intensity across scans at different stages without any human intervention, whereas the semi-quantitative method was based on subjective criteria of cumulative trends across scans at different stages. A fully-quantitative/semi-quantitative score per patient was obtained by averaging scores for each MRI contrast. A standard neuroradiological reading score per patient was obtained from radiological interpretation of MRI data. Scores from all 3 methods per patient were compared against patient survival, and re-examined for comorbidity and pathology effects.ResultsPatient survival correlated best with semi-quantitative scores obtained from T1Gd, ADC, and T2 data, and these correlations improved when biopsy and comorbidity were included.ConclusionThese results suggest interfacing neuroradiological readings with semi-quantitative image analysis can improve predictive accuracy of patient survival.     

Cavernous hemangiomas in patients with chronic liver disease: MR imaging findings

The purpose of our study was to assess the difference in magnetic resonance imaging (MRI) features of cavernous hemangiomas in patients with chronic liver disease compared them with hemangiomas in normal livers. We retrospectively searched our records of MRI of the liver between October 1998 and June 2002, and identified 76 hemangiomas in 49 patients (18 men and 31 women; age range 29-81 years [mean, 57 years]). Hemangiomas were classified into 3 groups: patients with cirrhosis [group 1, 8 lesions in 8 patients], patients with chronic hepatitis [group 2, 6 lesions in 5 patients], and patients without underlying liver disease [group 3, 62 lesions in 36 patients]. Four radiologists, blinded to clinical information, retrospectively reviewed in consensus the MRI findings of hemangiomas for number, size, signal intensities on T1- and T2-weighted images, and enhancement patterns on early- and late-phase postcontrast images. The mean lesion numbers and sizes were 1.0 and 16.2 +/- 9.6 mm, 1.2 and 15.3 +/- 7.1 mm, and 1.7 and 26.1 +/- 24.7 mm in groups 1-3, respectively. There was a correlation (p < 0.05, coefficient: 0.35) between lesion number and severity of liver disease. Although there was no significant difference in lesion size among the 3 groups, all of 11 lesions larger than 4 cm in diameter belonged to group 3. Almost all lesions appeared moderately hypointense on T1-weighted images and moderately hyperintense on T2-weighted images. Twenty-seven lesions showed immediate homogeneous enhancement (pattern 1), and 49 showed peripheral nodular enhancement with centripetal enhancement progression (pattern 2). There was no difference in frequency of enhancement patterns among the 3 groups. Hemangiomas were more often solitary in livers with chronic liver disease, large lesions were exclusively seen in livers without chronic liver disease, and there was a trend for small lesions in patients with chronic liver disease.     

Triple-negative breast cancer: Pretreatment magnetic resonance imaging features and clinicopathological factors associated with recurrence

PurposeWe aimed to investigate the magnetic resonance imaging (MRI) features and clinicopathologic factors with recurrence of triple-negative breast cancer (TNBC).Patients and methodsWe identified 281 patients with 288 surgically confirmed TNBC lesions who underwent pretreatment MRI between 2009 and 2015. The presence of intratumoral high signal on T2-weighted images, high-signal rim on diffusion-weighted images (DWI), and rim enhancement on the dynamic contrast-enhanced MRI and clinicopathological data were collected. Cox proportional analysis was performed.ResultsOf the 288 lesions, 36 (12.5%) recurred after a median follow-up of 18 months (range, 3.6–68.3 months). Rim enhancement (hazard ratio [HR] = 3.15; 95% confidence interval [CI] = 1.01, 9.88; p = .048), and lymphovascular invasion (HR = 2.73, 95% CI = 1.20, 6.23; p = .016) were independently associated with disease recurrence. While fibroglandular volume, background parenchymal enhancement, intratumoral T2 high signal, and high-signal rim on DWI, were not found to be risk factors for recurrence.ConclusionPretreatment MRI features may help predict a high risk of recurrence in patients with TNBC.     

Active inflammation increases the heterogeneity of MRI texture in mice with relapsing experimental allergic encephalomyelitis

Inflammation modulates tissue damage in relapsing-remitting multiple sclerosis (MS) both acutely and chronically, but its severity is difficult to evaluate with conventional MRI analysis. In mice with experimental allergic encephalomyelitis (EAE, a model of MS), we administered ultra small particles of iron oxide to track macrophage-mediated inflammation during the onset (relapse) and recovery (remission) of disease activity using high field MRI. We performed MRI texture analysis, a sensitive measure of tissue regularity, and T2 assessment both in EAE lesions and the control tissue, and measured spinal cord volume. We found that inflammation was 3 times more remarkable at onset than at recovery of EAE in histology yet demyelination appeared similar across animals and disease course. In MRI, lesion texture was more heterogeneous; T2 was lower; and spinal cord volume was greater in EAE than in controls, but only MRI texture was worse at relapse than at remission of EAE. Moreover, MRI texture correlated with spinal cord volume and tended to correlate with the extent of disability in EAE. While subject to further confirmation, our findings may suggest the sensitivity of MRI texture analysis for accessing inflammation.     

Meningiomas: Preoperative predictive histopathological grading based on radiomics of MRI

PurposeWe aimed to develop a radiomics model to predict the histopathological grading of meningiomas by magnetic resonance imaging (MRI) before surgery.MethodsWe recruited 131 patients with pathological diagnosis of meningiomas. All the patients had undergone MRI before surgery on a 3.0 T MRI scanner to obtain T1 fluid- attenuated inversion recovery (T1 FLAIR) images, T2-weighted images (T2WI) and T1 FLAIR with contrast enhancement (CE-T1 FLAIR) images covering the whole brain. The removing features with low variance, univariate feature selection, and least absolute shrinkage and selection operator (LASSO) were used to select radiomics features. Six classifiers were used to train the models (logistic regression (LR), k-nearest neighbor (KNN), decision tree (DT), support vector machine (SVM), random forests (RF), and XGBoost), and then 24 models were established using a random verification method to differentiate low-grade from high-grade meningiomas. The performance was assessed by receiver-operating characteristic (ROC) analysis, the f1-score, sensitivity, and specificity.ResultsThe radiomics features were significantly associated with the histopathological grading. Quantitative imaging features (n = 1409) were extracted, and nine features were selected to predict the grades of meningiomas. The best performance of the radiomics model for the degree of differentiation was obtained by SVM (area under the curve (AUC), 0.956; 95% confidence interval (CI), 0.83–1.00; sensitivity, 0.87; specificity, 0.92; f1-score, 0.90).ConclusionThe radiomics models are of great value in predicting the histopathological grades of meningiomas, and have broad prospects in radiology and clinics.     

A 3D densely connected convolution neural network with connection-wise attention mechanism for Alzheimer's disease classification

PurposeAlzheimer's disease (AD) is a progressive and irreversible neurodegenerative disease. In recent years, machine learning methods have been widely used on analysis of neuroimage for quantitative evaluation and computer-aided diagnosis of AD or prediction on the conversion from mild cognitive impairment (MCI) to AD. In this study, we aimed to develop a new deep learning method to detect or predict AD in an efficient way.Materials and methodsWe proposed a densely connected convolution neural network with connection-wise attention mechanism to learn the multi-level features of brain MR images for AD classification. We used the densely connected neural network to extract multi-scale features from pre-processed images, and connection-wise attention mechanism was applied to combine connections among features from different layers to hierarchically transform the MR images into more compact high-level features. Furthermore, we extended the convolution operation to 3D to capture the spatial information of MRI. The features extracted from each 3D convolution layer were integrated with features from all preceding layers with different attention, and were finally used for classification. Our method was evaluated on the baseline MRI of 968 subjects from ADNI database to discriminate (1) AD versus healthy subjects, (2) MCI converters versus healthy subjects, and (3) MCI converters versus non-converters.ResultsThe proposed method achieved 97.35% accuracy for distinguishing AD patients from healthy control, 87.82% for MCI converters against healthy control, and 78.79% for MCI converters against non-converters. Compared with some neural networks and methods reported in recent studies, the classification performance of our proposed algorithm was among the top ranks and improved in discriminating MCI subjects who were in high risks of conversion to AD.ConclusionsDeep learning techniques provide a powerful tool to explore minute but intricate characteristics in MR images which may facilitate early diagnosis and prediction of AD.     

Correlation between spinal cord diffusion tensor imaging and postural response latencies in persons with multiple sclerosis: A pilot study

PurposeLonger latency of postural response in multiple sclerosis (MS) may be linked to imbalance and increased likelihood of falls. It may be caused by the compromised microstructural integrity in the spinal cord, as evidenced by slowed somatosensory conduction in the spinal cord. Thus, the purpose of this study is to investigate the correlation between latency of postural responses and microstructural integrity of the cervical spinal cord, the region particularly related to the disease severity in MS, using diffusion tensor imaging (DTI) metrics.MethodsSeventeen persons with MS with mild-to-moderate disease severity were enrolled in this study. Postural response latencies of each patient were measured using electromyography of the tibialis anterior muscle (TA) and gastrocnemius muscle (GN) in response to surface perturbations. Cervical spinal cord DTI images were obtained from each patient. DTI mean, radial, axial diffusivity, and fractional anisotropy (FA) were measured between segments C4 and C6. Correlations of DTI metrics with postural response latencies, expanded disability status scale (EDSS) scores, and 25-foot walk (T25FW) were assessed using the Spearman's rank correlation coefficient at α = 0.05.ResultsLower FA was significantly correlated with longer latencies measured on right TA in response to forward postural perturbations (r = −0.51, p = .04). DTI metrics showed no significant correlations with EDSS scores (r = −0.06–0.09, p = .73–0.95) or T25FW (r = −0.1–0.14, p = .6–0.94). DTI metrics showed no significant differences between subjects with and without spinal cord lesions (p = .2–0.7).ConclusionsOur results showed a significant correlation between lower FA in the cervical spinal cord and longer latencies measured on right TA in response to forward postural perturbations in persons with MS, suggesting that impaired cervical spinal cord microstructure assessed by DTI may be associated with the delayed postural responses.     

MRI-guided breast vacuum biopsy: Localization of the lesion without contrast-agent application using diffusion-weighted imaging

ObjectiveIn magnetic resonance-guided breast vacuum biopsies, the contrast agent for targeting suspicious lesions can typically be applied only once during an intervention, due to the slow elimination of the gadolinium chelate from the extracellular fluid space. This study evaluated the feasibility of diffusion-weighted imaging (DWI) for lesion targeting in vacuum assisted magnetic resonance imaging (MRI) biopsies.ConclusionDWI may be used as an alternative to dynamic contrast-enhanced MRI with the advantage of reproducibility. However, the targeted lesion requires the characteristics of a mass-like lesion, substantial diffusion restriction, and a minimum size of approximately 1 cm.