Association of Mean Upper Cervical Spinal Cord Cross-Sectional Area With Cerebral Small Vessel Disease: A Community-Based Cohort Study.

BACKGROUND: The purpose of this study was to investigate the association between the mean upper cervical spinal cord cross-sectional area (MUCCA) and the risk and severity of cerebral small vessel disease (CSVD). METHODS: Community-dwelling residents in Lishui City, China, from the cross-sectional survey in the PRECISE cohort study (Polyvascular Evaluation for Cognitive Impairment and Vascular Events) conducted from 2017 to 2019. We included 1644 of 3067 community-dwelling adults in the PRECISE study after excluding those with incorrect, incomplete, insufficient, or missing clinical or imaging data. Total and modified total CSVD scores, as well as magnetic resonance imaging features, including white matter hyperintensity, lacunes, cerebral microbleeds, enlarged perivascular spaces, and brain atrophy, were assessed at the baseline. The Spinal Cord Toolbox was used to measure the upper cervical spinal cord cross-sectional area of the C1 to C3 segments of the spinal cord and its average value was taken as MUCCA. Participants were divided into 4 groups according to quartiles of MUCCA. Associations were analyzed using linear regression models adjusted for age, sex, current smoking and drinking, medical history, intracranial volume, and total cortical volume. RESULTS: The means±SD age of the participants was 61.4±6.5 years, and 635 of 1644 participants (38.6%) were men. The MUCCA was smaller in patients with CSVD than those without CSVD. Using the total CSVD score as a criterion, the MUCCA was 61.78±6.12 cm2 in 504 of 1644 participants with CSVD and 62.74±5.94 cm2 in 1140 of 1644 participants without CSVD. Using the modified total CSVD score, the MUCCA was 61.81±6.04 cm2 in 699 of 1644 participants with CSVD and 62.91±5.94 cm2 in 945 of 1644 without CSVD. There were statistical differences between the 2 groups after adjusting for covariates in 3 models. The MUCCA was negatively associated with the total and modified total CSVD scores (adjusted ß value, -0.009 [95% CI, -0.01 to -0.003] and -0.007 [95% CI, -0.01 to -0.0006]) after adjustment for covariates. Furthermore, the MUCCA was negatively associated with the white matter hyperintensity burden (adjusted ß value, -0.01 [95% CI, -0.02 to -0.003]), enlarged perivascular spaces in the basal ganglia (adjusted ß value, -0.005 [95% CI, -0.009 to -0.001]), lacunes (adjusted ß value, -0.004 [95% CI, -0.007 to -0.0007]), and brain atrophy (adjusted ß value, -0.009 [95% CI, -0.01 to -0.004]). CONCLUSIONS: The MUCCA and CSVD were correlated. Spinal cord atrophy may serve as an imaging marker for CSVD; thus, small vessel disease may involve the spinal cord in addition to being intracranial.

A Fully Automated Deep-Learning Model for Predicting the Molecular Subtypes of Posterior Fossa Ependymomas Using T2-Weighted Images.

PURPOSE: We aimed to develop and validate a deep learning (DL) model to automatically segment posterior fossa ependymoma (PF-EPN) and predict its molecular subtypes [Group A (PFA) and Group B (PFB)] from preoperative MR images. EXPERIMENTAL DESIGN: We retrospectively identified 227 PF-EPNs (development and internal test sets) with available preoperative T2-weighted (T2w) MR images and molecular status to develop and test a 3D nnU-Net (referred to as T2-nnU-Net) for tumor segmentation and molecular subtype prediction. The network was externally tested using an external independent set [n = 40; subset-1 (n = 31) and subset-2 (n =9)] and prospectively enrolled cases [prospective validation set (n = 27)]. The Dice similarity coefficient was used to evaluate the segmentation performance. Receiver operating characteristic analysis for molecular subtype prediction was performed. RESULTS: For tumor segmentation, the T2-nnU-Net achieved a Dice score of 0.94 ± 0.02 in the internal test set. For molecular subtype prediction, the T2-nnU-Net achieved an AUC of 0.93 and accuracy of 0.89 in the internal test set, an AUC of 0.99 and accuracy of 0.93 in the external test set. In the prospective validation set, the model achieved an AUC of 0.93 and an accuracy of 0.89. The predictive performance of T2-nnU-Net was superior or comparable to that of demographic and multiple radiologic features (AUCs ranging from 0.87 to 0.95). CONCLUSIONS: A fully automated DL model was developed and validated to accurately segment PF-EPNs and predict molecular subtypes using only T2w MR images, which could help in clinical decision-making.

Automated Determination of the H3 K27-Altered Status in Spinal Cord Diffuse Midline Glioma by Radiomics Based on T2-Weighted MR Images.

BACKGROUND AND PURPOSE: Conventional MR imaging is not sufficient to discern the H3 K27-altered status of spinal cord diffuse midline glioma. This study aimed to develop a radiomics-based model based on preoperative T2WI to determine the H3 K27-altered status of spinal cord diffuse midline glioma. MATERIALS AND METHODS: Ninety-seven patients with confirmed spinal cord diffuse midline gliomas were retrospectively recruited and randomly assigned to the training (n = 67) and test (n = 30) sets. One hundred seven radiomics features were initially extracted from automatically-segmented tumors on T2WI, then 11 features selected by the Pearson correlation coefficient and the Kruskal-Wallis test were used to train and test a logistic regression model for predicting the H3 K27-altered status. Sensitivity analysis was performed using additional random splits of the training and test sets, as well as applying other classifiers for comparison. The performance of the model was evaluated through its accuracy, sensitivity, specificity, and area under the curve. Finally, a prospective set including 28 patients with spinal cord diffuse midline gliomas was used to validate the logistic regression model independently. RESULTS: The logistic regression model accurately predicted the H3 K27-altered status with accuracies of 0.833 and 0.786, sensitivities of 0.813 and 0.750, specificities of 0.857 and 0.833, and areas under the curve of 0.839 and 0.818 in the test and prospective sets, respectively. Sensitivity analysis confirmed the robustness of the model, with predictive accuracies of 0.767-0.833. CONCLUSIONS: Radiomics signatures based on preoperative T2WI could accurately predict the H3 K27-altered status of spinal cord diffuse midline glioma, providing potential benefits for clinical management.

Amide proton transfer-weighted imaging and derived radiomics in the classification of adult-type diffuse gliomas.

OBJECTIVES: To evaluate the utility of amide proton transfer-weighted (APTw) MRI imaging and its derived radiomics in classifying adult-type diffuse glioma. MATERIALS AND METHODS: In this prospective study, APTw imaging was performed on 129 patients with adult-type diffuse gliomas. The mean APTw-related metrics (chemical exchange saturation transfer ratio (CESTR), CESTR normalized with the reference value (CESTRnr), and relaxation-compensated inverse magnetization transfer ratio (MTRRex)) and radiomic features within 3D tumor masks were extracted. APTw-radiomics models were developed using a support vector machine (SVM) classifier. Sensitivity analysis with tumor area of interest, different histogram cutoff values, and other classifiers were conducted. RESULTS: CESTR, CESTRnr, and MTRRex in glioblastomas were all significantly higher (p < 0.0003) than those of oligodendrogliomas and astrocytomas, with no significant difference between oligodendrogliomas and astrocytomas. The APTw-related metrics for IDH-wildtype and high-grade gliomas were significantly higher (p < 0.001) than those for the IDH-mutant and low-grade gliomas, with area under the curve (AUCs) of 0.88 for CESTR. The CESTR-radiomics models demonstrated accuracies of 84% (AUC 0.87), 83% (AUC 0.83), 90% (AUC 0.95), and 84% (AUC 0.86) in predicting the IDH mutation status, differentiating glioblastomas from astrocytomas, distinguishing glioblastomas from oligodendrogliomas, and determining high/low grade prediction, respectively, but showed poor performance in distinguishing oligodendrogliomas from astrocytomas (accuracy 63%, AUC 0.63). The sensitivity analysis affirmed the robustness of the APTw signal and APTw-derived radiomics prediction models. CONCLUSION: APTw imaging, along with its derived radiomics, presents a promising quantitative approach for prediction IDH mutation and grading adult-type diffuse glioma. CLINICAL RELEVANCE STATEMENT: Amide proton transfer-weighted imaging, a quantitative imaging biomarker, coupled with its derived radiomics, offers a promising non-invasive approach for predicting IDH mutation status and grading adult-type diffuse gliomas, thereby informing individualized clinical diagnostics and treatment strategies. KEY POINTS: • This study evaluates the differences of different amide proton transfer-weighted metrics across three molecular subtypes and their efficacy in classifying adult-type diffuse glioma. • Chemical exchange saturation transfer ratio normalized with the reference value and relaxation-compensated inverse magnetization transfer ratio effectively predicts IDH mutation/grading, notably the first one. • Amide proton transfer-weighted imaging and its derived radiomics holds potential to be used as a diagnostic tool in routine clinical characterizing adult-type diffuse glioma.

"Soap bubble" sign as an imaging marker for posterior fossa ependymoma Group B.

PURPOSE: To investigate the predictive value of the "soap bubble" sign on molecular subtypes (Group A [PFA] and Group B [PFB]) of posterior fossa ependymomas (PF-EPNs). METHODS: MRI scans of 227 PF-EPNs (internal retrospective discovery set) were evaluated by two independent neuroradiologists to assess the "soap bubble" sign, which was defined as clusters of cysts of various sizes that look like "soap bubbles" on T2-weighted images. Two independent cohorts (external validation set [n = 31] and prospective validation set [n = 27]) were collected to validate the "soap bubble" sign. RESULTS: Across three datasets, the "soap bubble" sign was observed in 21 PFB cases (7.4% [21/285] of PF-EPNs and 12.9% [21/163] of PFB); none in PFA. Analysis of the internal retrospective discovery set demonstrated substantial interrater agreement (1st Rating: κ = 0.71 [0.53-0.90], 2nd Rating: κ = 0.83 [0.68-0.98]) and intrarater agreement (Rater 1: κ = 0.73 [0.55-0.91], Rater 2: κ = 0.74 [0.55-0.92]) for the "soap bubble" sign; all 13 cases positive for the "soap bubble" sign were PFB (p = 0.002; positive predictive value [PPV] = 100%, negative predictive value [NPV] = 44%, sensitivity = 10%, specificity = 100%). The findings from the external validation set and the prospective validation set were similar, all cases positive for the "soap bubble" sign were PFB (p < 0.001; PPV = 100%). CONCLUSION: The "soap bubble" sign represents a highly specific imaging marker for the PFB molecular subtype of PF-EPNs.

Prediction of H3K27M Alteration Status in Brainstem Glioma Using Multi-Shell Diffusion MRI Metrics.

BACKGROUND: Multi-shell diffusion characteristics may help characterize brainstem gliomas (BSGs) and predict H3K27M status. PURPOSE: To identify the diffusion characteristics of BSG patients and investigate the predictive values of various diffusion metrics for H3K27M status in BSG. STUDY TYPE: Prospective. POPULATION: Eighty-four BSG patients (median age 10.5 years [IQR 6.8-30.0 years]) were included, of whom 56 were pediatric and 28 were adult patients. FIELD STRENGTH/SEQUENCE: 3 T, multi-shell diffusion imaging. ASSESSMENT: Diffusion kurtosis imaging and neurite orientation dispersion and density imaging analyses were performed. Age, gender, and diffusion metrics, including fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity, radial diffusivity (RD), mean kurtosis (MK), axial kurtosis (AK), radial kurtosis, intracellular volume fraction (ICVF), orientation dispersion index, and isotropic volume fraction (ISOVF), were compared between H3K27M-altered and wildtype BSG patients. STATISTICAL TESTS: Chi-square test, Mann-Whitney U test, multivariate analysis of variance (MANOVA), step-wise multivariable logistic regression. P-values <0.05 were considered significant. RESULTS: 82.4% pediatric and 57.1% adult patients carried H3K27M alteration. In the whole group, the H3K27M-altered BSGs demonstrated higher FA, AK and lower RD, ISOVF. The combination of age and median ISOVF showed fair performance for H3K27M prediction (AUC = 0.78). In the pediatric group, H3K27M-altered BSGs showed higher FA, AK, MK, ICVF and lower RD, MD, ISOVF. The combinations of median ISOVF, 5th percentile of FA, median MK and median MD showed excellent predictive power (AUC = 0.91). In the adult group, H3K27M-altered BSGs showed higher ICVF and lower RD, MD. The 75th percentile of RD demonstrated fair performance for H3K27M status prediction (AUC = 0.75). DATA CONCLUSION: Different alteration patterns of diffusion measures were identified between H3K27M-altered and wildtype BSGs, which collectively had fair to excellent predictive value for H3K27M alteration status, especially in pediatric patients. EVIDENCE LEVEL: 2 TECHNICAL EFFICACY: Stage 3.

Amide proton transfer-weighted imaging of pediatric brainstem glioma and its predicted value for H3 K27 alteration.

BACKGROUND: Non-invasive determination of H3 K27 alteration of pediatric brainstem glioma (pedBSG) remains a clinical challenge. PURPOSE: To predict H3 K27-altered pedBSG using amide proton transfer-weighted (APTw) imaging. MATERIAL AND METHODS: This retrospective study included patients with pedBSG who underwent APTw imaging and had the H3 K27 alteration status determined by immunohistochemical staining. The presence or absence of foci of markedly increased APTw signal in the lesion was visually assessed. Quantitative APTw histogram parameters within the entire solid portion of tumors were extracted and compared between H3 K27-altered and wild-type groups using Student's t-test. The ability of APTw for differential diagnosis was evaluated using logistic regression. RESULTS: Sixty pedBSG patients included 48 patients with H3 K27-altered tumor (aged 2-48 years) and 12 patients with wild-type tumor (aged 3-53 years). Visual assessment showed that the foci of markedly increased APTw signal intensity were more common in the H3 K27-altered group than in wild-type group (60% vs. 16%, P = 0.007). Histogram parameters of APTw signal intensity in the H3 K27-altered group were significantly higher than those in the wild-type group (median, 2.74% vs. 2.22%, P = 0.02). The maximum (area under the receiver operating characteristic curve [AUC] = 0.72, P = 0.01) showed the highest diagnostic performance among histogram analysis. A combination of age, median and maximum APTw signal intensity could predict H3 K27 alteration with a sensitivity of 81%, specificity of 75% and AUC of 0.80. CONCLUSION: APTw imaging may serve as an imaging biomarker for H3 K27 alteration of pedBSGs.

Coordinatized lesion location analysis empowering ROI-based radiomics diagnosis on brain gliomas.

OBJECTIVES: To assess the value of coordinatized lesion location analysis (CLLA), in empowering ROI-based imaging diagnosis of gliomas by improving accuracy and generalization performances. METHODS: In this retrospective study, pre-operative contrasted T1-weighted and T2-weighted MR images were obtained from patients with gliomas from three centers: Jinling Hospital, Tiantan Hospital, and the Cancer Genome Atlas Program. Based on CLLA and ROI-based radiomic analyses, a fusion location-radiomics model was constructed to predict tumor grades, isocitrate dehydrogenase (IDH) status, and overall survival (OS). An inter-site cross-validation strategy was used for assessing the performances of the fusion model on accuracy and generalization with the value of area under the curve (AUC) and delta accuracy (ACC) (ACCtesting-ACCtraining). Comparisons of diagnostic performances were performed between the fusion model and the other two models constructed with location and radiomics analysis using DeLong's test and Wilcoxon signed ranks test. RESULTS: A total of 679 patients (mean age, 50 years ± 14 [standard deviation]; 388 men) were enrolled. Based on tumor location probabilistic maps, fusion location-radiomics models (averaged AUC values of grade/IDH/OS: 0.756/0.748/0.768) showed the highest accuracy in contrast to radiomics models (0.731/0.686/0.716) and location models (0.706/0.712/0.740). Notably, fusion models ([median Delta ACC: - 0.125, interquartile range: 0.130]) demonstrated improved generalization than that of radiomics model ([- 0.200, 0.195], p = 0.018). CONCLUSIONS: CLLA could empower ROI-based radiomics diagnosis of gliomas by improving the accuracy and generalization of the models. CLINICAL RELEVANCE STATEMENT: This study proposed a coordinatized lesion location analysis for glioma diagnosis, which could improve the performances of the conventional ROI-based radiomics model in accuracy and generalization. KEY POINTS: • Using coordinatized lesion location analysis, we mapped anatomic distribution patterns of gliomas with specific pathological and clinical features and constructed glioma prediction models. • We integrated coordinatized lesion location analysis into ROI-based analysis of radiomics to propose new fusion location-radiomics models. • Fusion location-radiomics models, with the advantages of being less influenced by variabilities, improved accuracy, and generalization performances of ROI-based radiomics models on predicting the diagnosis of gliomas.

CarveMix: A simple data augmentation method for brain lesion segmentation.

Brain lesion segmentation provides a valuable tool for clinical diagnosis and research, and convolutional neural networks (CNNs) have achieved unprecedented success in the segmentation task. Data augmentation is a widely used strategy to improve the training of CNNs. In particular, data augmentation approaches that mix pairs of annotated training images have been developed. These methods are easy to implement and have achieved promising results in various image processing tasks. However, existing data augmentation approaches based on image mixing are not designed for brain lesions and may not perform well for brain lesion segmentation. Thus, the design of this type of simple data augmentation method for brain lesion segmentation is still an open problem. In this work, we propose a simple yet effective data augmentation approach, dubbed as CarveMix, for CNN-based brain lesion segmentation. Like other mixing-based methods, CarveMix stochastically combines two existing annotated images (annotated for brain lesions only) to obtain new labeled samples. To make our method more suitable for brain lesion segmentation, CarveMix is lesion-aware, where the image combination is performed with a focus on the lesions and preserves the lesion information. Specifically, from one annotated image we carve a region of interest (ROI) according to the lesion location and geometry with a variable ROI size. The carved ROI then replaces the corresponding voxels in a second annotated image to synthesize new labeled images for network training, and additional harmonization steps are applied for heterogeneous data where the two annotated images can originate from different sources. Besides, we further propose to model the mass effect that is unique to whole brain tumor segmentation during image mixing. To evaluate the proposed method, experiments were performed on multiple publicly available or private datasets, and the results show that our method improves the accuracy of brain lesion segmentation. The code of the proposed method is available at https://github.com/ZhangxinruBIT/CarveMix.git.

Deep Learning for Noninvasive Assessment of H3 K27M Mutation Status in Diffuse Midline Gliomas Using MR Imaging.

BACKGROUND: Determination of H3 K27M mutation in diffuse midline glioma (DMG) is key for prognostic assessment and stratifying patient subgroups for clinical trials. MRI can noninvasively depict morphological and metabolic characteristics of H3 K27M mutant DMG. PURPOSE: This study aimed to develop a deep learning (DL) approach to noninvasively predict H3 K27M mutation in DMG using T2-weighted images. STUDY TYPE: Retrospective and prospective. POPULATION: For diffuse midline brain gliomas, 341 patients from Center-1 (27 ± 19 years, 184 males), 42 patients from Center-2 (33 ± 19 years, 27 males) and 35 patients (37 ± 18 years, 24 males). For diffuse spinal cord gliomas, 133 patients from Center-1 (30 ± 15 years, 80 males). FIELD STRENGTH/SEQUENCE: 5T and 3T, T2-weighted turbo spin echo imaging. ASSESSMENT: Conventional radiological features were independently reviewed by two neuroradiologists. H3 K27M status was determined by histopathological examination. The Dice coefficient was used to evaluate segmentation performance. Classification performance was evaluated using accuracy, sensitivity, specificity, and area under the curve. STATISTICAL TESTS: Pearson's Chi-squared test, Fisher's exact test, two-sample Student's t-test and Mann-Whitney U test. A two-sided P value <0.05 was considered statistically significant. RESULTS: In the testing cohort, Dice coefficients of tumor segmentation using DL were 0.87 for diffuse midline brain and 0.81 for spinal cord gliomas. In the internal prospective testing dataset, the predictive accuracies, sensitivities, and specificities of H3 K27M mutation status were 92.1%, 98.2%, 82.9% in diffuse midline brain gliomas and 85.4%, 88.9%, 82.6% in spinal cord gliomas. Furthermore, this study showed that the performance generalizes to external institutions, with predictive accuracies of 85.7%-90.5%, sensitivities of 90.9%-96.0%, and specificities of 82.4%-83.3%. DATA CONCLUSION: In this study, an automatic DL framework was developed and validated for accurately predicting H3 K27M mutation using T2-weighted images, which could contribute to the noninvasive determination of H3 K27M status for clinical decision-making. EVIDENCE LEVEL: 2 Technical Efficacy: Stage 2.

Deep learning based on preoperative magnetic resonance (MR) images improves the predictive power of survival models in primary spinal cord astrocytomas.

BACKGROUND: Prognostic models for spinal cord astrocytoma patients are lacking due to the low incidence of the disease. Here, we aim to develop a fully automated deep learning (DL) pipeline for stratified overall survival (OS) prediction based on preoperative MR images. METHODS: A total of 587 patients diagnosed with intramedullary tumors were retrospectively enrolled in our hospital to develop an automated pipeline for tumor segmentation and OS prediction. The automated pipeline included a T2WI-based tumor segmentation model and 3 cascaded binary OS prediction models (1-year, 3-year, and 5-year models). For the tumor segmentation model, 439 cases of intramedullary tumors were used to model training and testing using a transfer learning strategy. A total of 138 patients diagnosed with astrocytomas were included to train and test the OS prediction models via 10 × 10-fold cross-validation using CNNs. RESULTS: The dice of the tumor segmentation model with the test set was 0.852. The results indicated that the best input of OS prediction models was a combination of T2W and T1C images and the tumor mask. The 1-year, 3-year, and 5-year automated OS prediction models achieved accuracies of 86.0%, 84.0%, and 88.0% and AUCs of 0.881 (95% CI 0.839-0.918), 0.862 (95% CI 0.827-0.901), and 0.905 (95% CI 0.867-0.942), respectively. The automated DL pipeline achieved 4-class OS prediction (<1 year, 1-3 years, 3-5 years, and >5 years) with 75.3% accuracy. CONCLUSIONS: We proposed an automated DL pipeline for segmenting spinal cord astrocytomas and stratifying OS based on preoperative MR images.

Automated Classification of Intramedullary Spinal Cord Tumors and Inflammatory Demyelinating Lesions Using Deep Learning.

Accurate differentiation of intramedullary spinal cord tumors and inflammatory demyelinating lesions and their subtypes are warranted because of their overlapping characteristics at MRI but with different treatments and prognosis. The authors aimed to develop a pipeline for spinal cord lesion segmentation and classification using two-dimensional MultiResUNet and DenseNet121 networks based on T2-weighted images. A retrospective cohort of 490 patients (118 patients with astrocytoma, 130 with ependymoma, 101 with multiple sclerosis [MS], and 141 with neuromyelitis optica spectrum disorders [NMOSD]) was used for model development, and a prospective cohort of 157 patients (34 patients with astrocytoma, 45 with ependymoma, 33 with MS, and 45 with NMOSD) was used for model testing. In the test cohort, the model achieved Dice scores of 0.77, 0.80, 0.50, and 0.58 for segmentation of astrocytoma, ependymoma, MS, and NMOSD, respectively, against manual labeling. Accuracies of 96% (area under the receiver operating characteristic curve [AUC], 0.99), 82% (AUC, 0.90), and 79% (AUC, 0.85) were achieved for the classifications of tumor versus demyelinating lesion, astrocytoma versus ependymoma, and MS versus NMOSD, respectively. In a subset of radiologically difficult cases, the classifier showed an accuracy of 79%-95% (AUC, 0.78-0.97). The established deep learning pipeline for segmentation and classification of spinal cord lesions can support an accurate radiologic diagnosis. Supplemental material is available for this article. © RSNA, 2022 Keywords: Spinal Cord MRI, Astrocytoma, Ependymoma, Multiple Sclerosis, Neuromyelitis Optica Spectrum Disorder, Deep Learning.

White matter alterations in pediatric brainstem glioma: An national brain tumor registry of China study.

Background: Previous studies have identified alterations in structural connectivity of patients with glioma. However, white matter (WM) integrity measured by diffusion kurtosis imaging (DKI) in pediatric patients with brainstem glioma (BSG) was lack of study. Here, the alterations in WM of patients with BSG were assessed through DKI analyses. Materials and methods: This study involved 100 patients with BSG from the National Brain Tumor Registry of China (NBTRC) and 50 age- and sex-matched healthy controls from social recruitment. WM tracts were segmented and reconstructed using U-Net and probabilistic bundle-specific tracking. Next, automatic fiber quantitative (AFQ) analyses of WM tracts were performed using tractometry module embedded in TractSeg. Results: WM quantitative analysis identified alterations in DKI-derived values in patients with BSG compared with healthy controls. WM abnormalities were detected in the projection fibers involved in the brainstem, including corticospinal tract (CST), superior cerebellar peduncle (SCP), middle cerebellar peduncle (MCP) and inferior cerebellar peduncle (ICP). Significant WM alterations were also identified in commissural fibers and association fibers, which were away from tumor location. Statistical analyses indicated the severity of WM abnormality was statistically correlated with the preoperative Karnofsky Performance Scale (KPS) and symptom duration of patients respectively. Conclusion: The results of this study indicated the widely distributed WM alterations in patients with BSG. DKI-derived quantitative assessment may provide additional information and insight into comprehensively understanding the neuropathological mechanisms of brainstem glioma.

Prediction of H3 K27M-mutant in midline gliomas by magnetic resonance imaging: a systematic review and meta-analysis.

PURPOSE: To summarize the predictive value of MRI for H3 K27M-mutant in midline gliomas using meta-analysis. METHODS: Systematic electronic searches of the PubMed, Embase, ISI Web of Science, and Cochrane Library up to Jun 31, 2021, were conducted by two experienced neuroradiologists with the keywords of "MRI," "Glioma," and "H3 K27M." The hierarchical summary receiver-operating characteristic (HSROC) model was used to calculate the pooled sensitivity, specificity, positive likelihood ratio (LR +), negative likelihood ratio (LR -), and diagnostic odds ratio (DOR). Coupled forest plots were used to evaluate the heterogeneity of the included studies. RESULTS: Of seven original studies with a total of 593 patients, 240 glioma patients were included, with 45.5-70.6% H3 K27M-mutant gliomas. Using MRI, a pooled sensitivity of 0.78 (95% CI, 0.66-0.87), specificity of 0.85 (95% CI, 0.76-0.91), LR + of 5.07 (95% CI, 3.19-8.08), LR - of 0.26 (95% CI, 0.16-0.42), and DOR of 19.80 (95% CI, 9.28-42.28) were achieved for H3 K27M-mutant prediction. Significant heterogeneity was observed among the studies in terms of sensitivity (Q = 16.83, df = 7, p = 0.02; I2 = 58.40 [95% CI, 25.83-90.97]), LR - (Q = 16.61, df = 7, p = 0.02; I2 = 57.87 [95% CI, 24.81-90.93]), and DOR (Q = 14.05, df = 7, p = 0.05; I2 = 50.18 [95% CI, 10.06-90.31]). CONCLUSIONS: This meta-analysis demonstrated a clinical value of MRI to predict H3 K27M-mutant in midline gliomas with a pooled sensitivity of 0.78 and specificity of 0.85.

Automatic multiclass intramedullary spinal cord tumor segmentation on MRI with deep learning.

Spinal cord tumors lead to neurological morbidity and mortality. Being able to obtain morphometric quantification (size, location, growth rate) of the tumor, edema, and cavity can result in improved monitoring and treatment planning. Such quantification requires the segmentation of these structures into three separate classes. However, manual segmentation of three-dimensional structures is time consuming, tedious and prone to intra- and inter-rater variability, motivating the development of automated methods. Here, we tailor a model adapted to the spinal cord tumor segmentation task. Data were obtained from 343 patients using gadolinium-enhanced T1-weighted and T2-weighted MRI scans with cervical, thoracic, and/or lumbar coverage. The dataset includes the three most common intramedullary spinal cord tumor types: astrocytomas, ependymomas, and hemangioblastomas. The proposed approach is a cascaded architecture with U-Net-based models that segments tumors in a two-stage process: locate and label. The model first finds the spinal cord and generates bounding box coordinates. The images are cropped according to this output, leading to a reduced field of view, which mitigates class imbalance. The tumor is then segmented. The segmentation of the tumor, cavity, and edema (as a single class) reached 76.7 ± 1.5% of Dice score and the segmentation of tumors alone reached 61.8 ± 4.0% Dice score. The true positive detection rate was above 87% for tumor, edema, and cavity. To the best of our knowledge, this is the first fully automatic deep learning model for spinal cord tumor segmentation. The multiclass segmentation pipeline is available in the Spinal Cord Toolbox (https://spinalcordtoolbox.com/). It can be run with custom data on a regular computer within seconds.

Prediction of H3K27M-mutant brainstem glioma by amide proton transfer-weighted imaging and its derived radiomics.

PURPOSE: H3K27M-mutant associated brainstem glioma (BSG) carries a very poor prognosis. We aimed to predict H3K27M mutation status by amide proton transfer-weighted (APTw) imaging and radiomic features. METHODS: Eighty-one BSG patients with APTw imaging at 3T MR and known H3K27M status were retrospectively studied. APTw values (mean, median, and max) and radiomic features within manually delineated 3D tumor masks were extracted. Comparison of APTw measures between H3K27M-mutant and wildtype groups was conducted by two-sample Student's T/Mann-Whitney U test and receiver operating characteristic curve (ROC) analysis. H3K27M-mutant prediction using APTw-derived radiomics was conducted using a machine learning algorithm (support vector machine) in randomly selected train (n = 64) and test (n = 17) sets. Sensitivity analysis with additional random splits of train and test sets, 2D tumor masks, and other classifiers were conducted. Finally, a prospective cohort including 29 BSG patients was acquired for validation of the radiomics algorithm. RESULTS: BSG patients with H3K27M-mutant were younger and had higher max APTw values than those with wildtype. APTw-derived radiomic measures reflecting tumor heterogeneity could predict H3K27M mutation status with an accuracy of 0.88, sensitivity of 0.92, and specificity of 0.80 in the test set. Sensitivity analysis confirmed the predictive ability (accuracy range: 0.71-0.94). In the independent prospective validation cohort, the algorithm reached an accuracy of 0.86, sensitivity of 0.88, and specificity of 0.85 for predicting H3K27M-mutation status. CONCLUSION: BSG patients with H3K27M-mutant had higher max APTw values than those with wildtype. APTw-derived radiomics could accurately predict a H3K27M-mutant status in BSG patients.

Feasibility evaluation of amide proton transfer-weighted imaging in the parotid glands: a strategy to recognize artifacts and measure APT value.

BACKGROUND: The feasibility and image quality of three-dimensional (3D) amide proton transfer (APT)-weighted (APTw) in parotid tumor lesions have not been well established in previous studies. This study aimed to evaluate the utility of APT imaging in parotid lesions and glands. METHODS: Patients with parotid lesions received 3D turbo spin echo (TSE) APTw on a 3.0T scanner. Two radiologists, who were blinded to the clinical data, independently evaluated the APTw image quality using 4-point Likert scales (1= poor, 4= excellent) in terms of integrity and hyperintensity artifacts. An image quality selection protocol was built based on the two scores. Evaluable images (integrity score >1) and trustable images (integrity score >3 and hyperintensity artifacts score >2) were then enrolled for APTw value comparison between parotid lesions and glands. RESULTS: Forty consecutive patients were included in this study. Four patients were excluded due to severe motion (n=3) or dental (n=1) artifacts, and 36 patients received the APT sequence. Among these, more parotid tumor lesions (34/36, 94.4%) than normal parotid glands (23/31, 74.2%) revealed excellent integrity scores (score =4) (P=0.034). Most parotid tumor lesions (24/34, 70.6%) and glands (16/28, 57.1%) revealed no or little hyperintensity artifacts for diagnosis (scores 3 and 4). APT values of parotid lesions and glands in the evaluable groups were 2.11%±1.15% and 1.60%±1.56%, respectively, and the difference was not significant (P=0.197). APT values of parotid lesions and glands in the trustable groups were 1.99%±1.18% and 1.03%±1.09%, respectively, and the difference was statistically significant (P=0.018). CONCLUSIONS: 3D APTw could be used to differentiate parotid tumors and normal parotid glands; however, the technology still needs to be improved to remove artifacts. In our study, most APTw images of tumor lesions in parotid glands had acceptable image quality, and these APTw images are feasible for diagnostic use.

The application value of ultra-short echo time MRI in the quantification of liver iron overload in a rat model.

BACKGROUND: The quantitative evaluation of liver iron concentration (LIC) is important in guiding the treatment of blood transfusion-dependent patients. Conventionally, LIC is assessed through R2*or R2 values using magnetic resonance imaging (MRI). However, most of the studies using MRI to determine iron overload were restricted by the minimum echo time, so that severe iron overload could hardly be quantified. In our study, we demonstrate a new approach to overcome the limitation of the shortest echo time using ultra-short echo time (UTE) MRI to quantify liver iron overload of varying degrees in a rat model. METHODS: Sixty female Sprague-Dawley rats were included and randomly assigned into 10 equal groups. Group 1 was not injected with iron dextran. Groups 2 to 10 were intraperitoneally injected with iron dextran at a dose of 15 mg/kg every 3 days. On every 6th day, one group was randomly selected from groups 2 to 10 for MRI scanning and liver iron concentration (LIC) detection. For groups 1 to 10, images were acquired by UTE sequence using a 3.0T MR scanner, and the T2* value and R2* value were obtained (R2* =1/T2*). In addition, LIC was measured using an atomic absorption photometer. The correlation analysis between R2* value and LIC was performed and the regression equation of R2* and LIC was established and its reliability verified. RESULTS: For groups 1 to 10, R2* values and LIC ranged from 60.16±4.76 to 1,306.90±42.26 Hz and from 0.84±0.11 to 5.89±2.64 mg/g dry, respectively. The R2* value was linearly correlated to the LIC (r=0.897, P<0.001), and the linear regression equation was LIC = 0.005 × R2* + 1.783. The validation analysis results showed that the intragroup correlation coefficient (ICC) between the predicted and measured LIC was 89.5%. CONCLUSIONS: The UTE sequence could be used for quantification of varying degrees of hepatic iron overload in the rat model, and the LIC could be predicted by using the R2* value on an MR 3.0T scanner.

Diffusion kurtosis imaging-derived histogram metrics for prediction of KRAS mutation in rectal adenocarcinoma: Preliminary findings.

BACKGROUND: Although histological examination is the standard method for assessing genetic status, the development of a noninvasive method, which can display the heterogeneity of the whole tumor to supplement genotype analysis, might be important for personalized treatment strategies. PURPOSE: To evaluate the potential role of diffusion kurtosis imaging (DKI)-derived parameters using histogram analysis derived from whole-tumor volumes for prediction of the status of KRAS mutations in patients with rectal adenocarcinoma. STUDY TYPE: Retrospective. SUBJECTS: In all, 148 consecutive patients with histologically confirmed rectal adenocarcinoma who were treated at our institution. SEQUENCE: DKI was performed with a 3.0 T MRI system using a single-shot echo-planar imaging sequence with b values of 0, 700, 1400, and 2100 sec/mm2 . ASSESSMENT: D, K, and apparent diffusion coefficient (ADC) values were measured using whole-tumor volume histogram analysis and were compared between different KRAS mutations status. STATISTICAL TESTS: Student's t-test or Mann-Whitney U-test, and receiver operating characteristic (ROC) curves were used for statistical analysis. RESULTS: All the percentile metrics of ADC and D values were significantly lower in the mutated group than those in the wildtype group (all P < 0.05), except for the minimum value of ADC and D (both P > 0.05), while K-related percentile metrics were higher in the mutated group compared with those in the wildtype group (all P < 0.05). Regarding the comparison of the diagnostic performance of all the histogram metrics, K75th showed the highest AUC value of 0.871, and the corresponding values for sensitivity, specificity, positive predictive value, and negative predictive value were 81.43%, 78.21%, 77.03%, and 82.43%, respectively. DATA CONCLUSION: DKI metrics with whole-tumor volume histogram analysis is associated with KRAS mutations, and thus may be useful for predicting the KRAS status of rectal cancers for guiding targeted therapy. LEVEL OF EVIDENCE: 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;50:930-939.

Whole-tumour diffusion kurtosis MR imaging histogram analysis of rectal adenocarcinoma: Correlation with clinical pathologic prognostic factors.

OBJECTIVE: To investigate potential relationships between diffusion kurtosis imaging (DKI)-derived parameters using whole-tumour volume histogram analysis and clinicopathological prognostic factors in patients with rectal adenocarcinoma. MATERIAL AND METHODS: 79 consecutive patients who underwent MRI examination with rectal adenocarcinoma were retrospectively evaluated. Parameters D, K and conventional ADC were measured using whole-tumour volume histogram analysis. Student's t-test or Mann-Whitney U-test, receiver operating characteristic curves and Spearman's correlation were used for statistical analysis. RESULTS: Almost all the percentile metrics of K were correlated positively with nodal involvement, higher histological grades, the presence of lymphangiovascular invasion (LVI) and circumferential margin (CRM) (p<0.05), with the exception of between K10th, K90th and histological grades. In contrast, significant negative correlations were observed between 25th, 50th percentiles and mean values of ADC and D, as well as ADC10th, with tumour T stages (p< 0.05). Meanwhile, lower 75th and 90th percentiles of ADC and D values were also correlated inversely with nodal involvement (p< 0.05). Kmean showed a relatively higher area under the curve (AUC) and higher specificity than other percentiles for differentiation of lesions with nodal involvement. CONCLUSION: DKI metrics with whole-tumour volume histogram analysis, especially K parameters, were associated with important prognostic factors of rectal cancer. KEY POINTS: • K correlated positively with some important prognostic factors of rectal cancer. • K mean showed higher AUC and specificity for differentiation of nodal involvement. • DKI metrics with whole-tumour volume histogram analysis depicted tumour heterogeneity.