Search

To develop a fully automatic radiomics model to differentiate adult pilocytic astrocytomas (PA) from high-grade gliomas (HGGs).This retrospective study included 302 adult patients with PA (n = 62) or HGG (n = 240). The patients were randomly divided into training (n = 211) and test (n = 91) sets. Clinical data were obtained, and radiomic features (n = 372) were extracted from multiparametric MRI with automatic tumour segmentation. After feature selection with F-score, a Light Gradient Boosting Machine classifier with subsampling was trained to develop three models: (1) clinical model, (2) radiomics model, and (3) combined clinical and radiomics model. Human performance was also assessed. The performance of the classifier was validated in the test set. SHapley Additive exPlanations (SHAP) was applied to explore the interpretability of the model.A total of 15 radiomic features were selected. In the test set, the combined clinical and radiomics model (area under the curve [AUC], 0.93) showed a significantly higher performance than the clinical model (AUC, 0.79, p = 0.037) and had a similar performance to the radiomics model (AUC, 0.92, p = 0.828). The combined clinical and radiomics model also showed a significantly higher performance than humans (AUC, 0.76-0.81, p0.05). The model explanation by SHAP suggested that lower intratumoural heterogeneity from T2-weighted images was highly associated with PA diagnosis.The fully automatic combined clinical and radiomics model may be helpful for differentiating adult PAs from HGGs.• Differentiating adult PAs from HGGs is challenging because PAs may manifest a large spectrum of imaging presentations, often including aggressive imaging features. • The fully automatic combined clinical and radiomics model showed a significantly higher performance than the clinical model or humans. • The model explanation by SHAP suggested that second-order features from T2-weighted imaging were important in diagnosis and might reflect the underlying pathophysiology that PAs have lesser tissue heterogeneity than HGGs.

Background and purpose Increasing evidence suggests that genomic and molecular markers need to be integrated in grading of meningioma. Telomerase reverse transcriptase promoter (TERTp) mutation is receiving attention due to its clinical relevance in the treatment of meningiomas. The predictive ability of conventional and diffusion MRI parameters for determining the TERTp mutation status in grade II meningiomas has yet been identified. Material and methods In this study, 63 patients with surgically confirmed grade II meningiomas (56 TERTp wildtype, 7 TERTp mutant) were included. Conventional imaging features were qualitatively assessed. The maximum diameter, volume of the tumors and histogram parameters from the apparent diffusion coefficient (ADC) were assessed. Independent clinical and imaging risk factors for TERTp mutation were investigated using multivariable logistic regression. The discriminative value of the prediction models with and without imaging features was evaluated. Results In the univariable regression, older age (odds ratio [OR] = 1.13, P = 0.005), larger maximum diameter (OR = 1.09, P = 0.023), larger volume (OR = 1.04, P = 0.014), lower mean ADC (OR = 0.02, P = 0.025), and lower ADC 10th percentile (OR = 0.01, P = 0.014) were predictors of TERTp mutation. In multivariable regression, age (OR = 1.13, P = 0.009) and ADC 10th percentile (OR = 0.01, P = 0.038) were independent predictors of variables for predicting the TERTp mutation status. The performance of the prediction model increased upon inclusion of imaging parameters (area under the curves of 0.86 and 0.91, respectively, without and with imaging parameters). Conclusion Older age and lower ADC 10th percentile may be useful parameters to predict TERTp mutation in grade II meningiomas.

Purpose In glioma, molecular alterations are closely associated with disease prognosis. This study aimed to develop a radiomics-based multiple gene prediction model incorporating mutual information of each genetic alteration in glioblastoma and grade 4 astrocytoma, IDH-mutant. Methods From December 2014 through January 2020, we enrolled 418 patients with pathologically confirmed glioblastoma (based on the 2016 WHO classification). All selected patients had preoperative MRI and isocitrate dehydrogenase (IDH) mutation, O-6-methylguanine-DNA methyltransferase (MGMT) promoter methylation, epidermal growth factor receptor amplification, and alpha-thalassemia/mental retardation syndrome X-linked (ATRX) loss status. Patients were randomly split into training and test sets (7:3 ratio). Enhancing tumor and peritumoral T2-hyperintensity were auto-segmented, and 660 radiomics features were extracted. We built binary relevance (BR) and ensemble classifier chain (ECC) models for multi-label classification and compared their performance. In the classifier chain, we calculated the mean absolute Shapley value of input features. Results The micro-averaged area under the curves (AUCs) for the test set were 0.804 and 0.842 in BR and ECC models, respectively. IDH mutation status was predicted with the highest AUCs of 0.964 (BR) and 0.967 (ECC). The ECC model showed higher AUCs than the BR model for ATRX (0.822 vs. 0.775) and MGMT promoter methylation (0.761 vs. 0.653) predictions. The mean absolute Shapley values suggested that predicted outcomes from the prior classifiers were important for better subsequent predictions along the classifier chains. Conclusion We built a radiomics-based multiple gene prediction chained model that incorporates mutual information of each genetic alteration in glioblastoma and grade 4 astrocytoma, IDH-mutant and performs better than a simple bundle of binary classifiers using prior classifiers’ prediction probability.

Purpose This study aimed to investigate whether a deep learning model for automated detection of unruptured intracranial aneurysms on time-of-flight (TOF) magnetic resonance angiography (MRA) can achieve a target diagnostic performance comparable to that of human radiologists for approval from the Korean Ministry of Food and Drug Safety as an artificial intelligence-applied software. Materials and methods In this single-center, retrospective, confirmatory clinical trial, the diagnostic performance of the model was evaluated in a predetermined test set. After sample size estimation, the test set consisted of 135 aneurysm-containing examinations with 168 intracranial aneurysms and 197 aneurysm-free examinations. The target sensitivity and specificity were set as 87% and 92%, respectively. The patient-wise sensitivity and specificity of the model were analyzed. Moreover, the lesion-wise sensitivity and false-positive detection rate per case were also investigated. Results The sensitivity and specificity of the model were 91.11% [95% confidence interval (CI): 84.99, 95.32] and 93.91% (95% CI: 89.60, 96.81), respectively, which met the target performance values. The lesion-wise sensitivity was 92.26%. The overall false-positive detection rate per case was 0.123. Of the 168 aneurysms, 13 aneurysms from 12 examinations were missed by the model. Conclusion The present deep learning model for automated detection of unruptured intracranial aneurysms on TOF MRA achieved the target diagnostic performance comparable to that of human radiologists. With high standalone performance, this model may be useful for accurate and efficient diagnosis of intracranial aneurysm.

Objective: To evaluate the quality of radiomics studies on pituitary adenoma according to the radiomics quality score (RQS) and Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD). Methods: PubMed MEDLINE and EMBASE were searched to identify radiomics studies on pituitary adenomas. From 138 articles, 20 relevant original research articles were included. Studies were scored based on RQS and TRIPOD guidelines. Results: Most included studies did not perform pre-processing; isovoxel resampling, signal intensity normalization, and N4 bias field correction were performed in only five (25%), eight (40%), and four (20%) studies, respectively. Only two (10%) studies performed external validation. The mean RQS and basic adherence rate were 2.8 (7.6%) and 26.6%, respectively. There was a low adherence rate for conducting comparison to “gold-standard” (20%), multiple segmentation (25%), and stating potential clinical utility (25%). No study stated the biological correlation, conducted a test–retest or phantom study, was a prospective study, conducted cost-effectiveness analysis, or provided open-source code and data, which resulted in low-level evidence. The overall adherence rate for TRIPOD was 54.6%, and it was low for reporting the title (5%), abstract (0%), explaining the sample size (10%), and suggesting a full prediction model (5%). Conclusion: The radiomics reporting quality for pituitary adenoma is insufficient. Pre-processing is required for feature reproducibility and external validation is necessary. Feature reproducibility, clinical utility demonstration, higher evidence levels, and open science are required. Titles, abstracts, and full prediction model suggestions should be improved for transparent reporting. Advances in knowledge: Despite the rapidly increasing number of radiomics researches on pituitary adenoma, the quality of science in these researches is unknown. Our study indicates that the overall quality needs to be significantly improved in radiomics studies on pituitary adenoma, and since the concept of RQS and IBSI is still unfamiliar to clinicians and radiologist researchers, our study may help to reach higher technical and clinical impact in the future study.

Background Group comparison results associating cortical thinning and Parkinson disease (PD) dementia (PDD) are limited in their application to clinical settings. Purpose To investigate whether cortical thickness from MRI can help predict conversion from mild cognitive impairment (MCI) to dementia in PD at an individual level using a machine learning-based model. Materials and Methods In this retrospective study, patients with PD and MCI who underwent MRI from September 2008 to November 2016 were included. Features were selected from clinical and cortical thickness variables in 10 000 randomly generated training sets. Features selected 5000 times or more were used to train random forest and support vector machine models. Each model was trained and tested in 10 000 randomly resampled data sets, and a median of 10 000 areas under the receiver operating characteristic curve (AUCs) was calculated for each. Model performances were validated in an external test set. Results Forty-two patients progressed to PDD (converters) (mean age, 71 years ± 6 [standard deviation]; 22 women), and 75 patients did not progress to PDD (nonconverters) (mean age, 68 years ± 6; 40 women). Four PDD converters (mean age, 74 years ± 10; four men) and 20 nonconverters (mean age, 67 years ± 7; 11 women) were included in the external test set. Models trained with cortical thickness variables (AUC range, 0.75-0.83) showed fair to good performances similar to those trained with clinical variables (AUC range, 0.70-0.81). Model performances improved when models were trained with both variables (AUC range, 0.80-0.88). In pair-wise comparisons, models trained with both variables more frequently showed better performance than others in all model types. The models trained with both variables were successfully validated in the external test set (AUC range, 0.69-0.84). Conclusion Cortical thickness from MRI helped predict conversion from mild cognitive impairment to dementia in Parkinson disease at an individual level, with improved performance when integrated with clinical variables. © RSNA, 2021

Brain atrophy is related to vascular risk factors and can increase cognitive dysfunction risk. This community-based, cross-sectional study investigated whether glucose metabolic disorders due to body fatness are linked to regional changes in brain structure and a decline in neuropsychological function in cognitively healthy older adults. From 2016 to 2019, 429 participants underwent measurements for cortical thickness and subcortical volume using 3 T magnetic resonance imaging and for cognitive function using the neuropsychological screening battery. The effects of body fatness mediated by impaired glucose metabolism on neuroimaging markers and cognitive function was investigated using partial least square structural equation modeling. Total grey matter volume (β = −0.020; bias-corrected (BC) 95% confidence interval (CI) = -0.047 to −0.006), frontal (β = −0.029; BC 95% CI = −0.063 to −0.005) and temporal (β = −0.022; BC 95% CI = −0.051 to −0.004) lobe cortical thickness, and hippocampal volume (β = −0.029; BC 95% CI = −0.058 to −0.008) were indirectly related to body fatness. Further, frontal/temporal lobe thinning was associated with recognition memory (β = −0.005; BC 95% CI = −0.012 to −0.001/β = −0.005; BC 95% CI = −0.013 to −0.001) and delayed recall for visual information (β = −0.005; BC 95% CI = −0.013 to −0.001/β = −0.005; BC 95% CI = −0.013 to −0.001). Additionally, the smaller the hippocampal volume, the lower the score in recognition memory (β = −0.005; BC 95% CI = −0.012 to −0.001), delayed recall for visual information (β = −0.005; BC 95% CI = −0.012 to −0.001), and verbal learning (β = −0.008; BC 95% CI = −0.017 to −0.002). Our findings indicate that impaired glucose metabolism caused by excess body fatness affects memory decline as well as regional grey matter atrophy in elderly individuals with no neurological disease.

To investigate whether type-specific sex differences in survival exist independently of clinical and molecular factors in adult-type diffuse gliomas according to the 2021 World Health Organization (WHO) classification.A retrospective chart and imaging review of 1325 patients (mean age, 54 ± 15 years; 569 females) with adult-type diffuse gliomas (oligodendroglioma, IDH-mutant, and 1p/19q-codeleted, n = 183; astrocytoma, IDH-mutant, n = 211; glioblastoma, IDH-wildtype, n = 800; IDH-wildtype diffuse glioma, NOS, n = 131) was performed. The demographic information, extent of resection, imaging data, and molecular data including OIn patients with glioblastoma, IDH-wildtype, female sex remained as an independent predictor of better overall survival (hazard ratio = 0.91, P = 0.031), along with age, histological grade 4, MGMT promoter methylation status, and gross total resection. Female sex showed a higher prevalence of MGMT promoter methylation (40.2% vs 32.0%, P = 0.017) but there was no interaction effect between female sex and MGMT promoter methylation status (P-interaction = 0.194), indicating independent role of female sex. The median OS for females were 19.2 months (12.3-35.0) and 16.2 months (10.5-30.6) for males. No sex difference in survival was seen in other types of adult-type diffuse gliomas.There was a female survival advantage in glioblastoma, IDH-wildtype, independently of clinical data or MGMT promoter methylation status. There was no sex difference in survival in other types of adult-type diffuse gliomas, suggesting type-specific sex effects solely in glioblastoma, IDH-wildtype.

This study investigated the empathic response of postpartum women to babies in pain and the underlying neural mechanism. Postpartum women responded with more empathy and speed to babies over other stimuli compared to controls. Brain scans taken 3 months after birth showed more elevated activation in the Middle cingulate cortex/middle frontal gyrus (MCC/MFG) than the controls regardless of the task condition. When compared to the adult and neutral conditions, the posterior cingulate cortex (PCC) region was consistently more activated when postpartum women saw babies than controls. In addition, higher activation levels in the PCC region for the baby condition significantly correlated with faster and more empathic responses to babies. Considering that PCC is a core region for the theory of mind or mentalizing which requires cognitive reasoning to understand others, these results suggest that PCC might be a pivotal neural locus facilitating cognitive efforts to empathize with babies during the postpartum period. In a follow‐up experiment at 12 months after birth, we were still able to observe higher activity in the MCC/MFG of postpartum women. However, previously observed PCC activation patterns disappeared 12 months after birth, despite the women's response patterns to babies still being maintained. These results suggest that the mentalizing process activated to empathize with babies in the early postpartum period becomes less cognitively demanding over time., This study investigated the empathic response of postpartum women to babies in pain and the underlying neural mechanism. Our results suggest that posterior cingulate cortex (PCC) might be a pivotal neural locus facilitating cognitive efforts to empathize with babies during the postpartum period.

The purpose of this study was to establish a high-performing radiomics strategy with machine learning from conventional and diffusion MRI to differentiate recurrent glioblastoma (GBM) from radiation necrosis (RN) after concurrent chemoradiotherapy (CCRT) or radiotherapy. Eighty-six patients with GBM were enrolled in the training set after they underwent CCRT or radiotherapy and presented with new or enlarging contrast enhancement within the radiation field on follow-up MRI. A diagnosis was established either pathologically or clinicoradiologically (63 recurrent GBM and 23 RN). Another 41 patients (23 recurrent GBM and 18 RN) from a different institution were enrolled in the test set. Conventional MRI sequences (T2-weighted and postcontrast T1-weighted images) and ADC were analyzed to extract 263 radiomic features. After feature selection, various machine learning models with oversampling methods were trained with combinations of MRI sequences and subsequently validated in the test set. In the independent test set, the model using ADC sequence showed the best diagnostic performance, with an AUC, accuracy, sensitivity, specificity of 0.80, 78%, 66.7%, and 87%, respectively. In conclusion, the radiomics models models using other MRI sequences showed AUCs ranging from 0.65 to 0.66 in the test set. The diffusion radiomics may be helpful in differentiating recurrent GBM from RN..

Background: Noninvasive identification of amyloid β (Aβ) is important in mild cognitive impairment (MCI) patients for better clinical management. This study aimed to evaluate whether radiomics features in the hippocampus in MCI improve the prediction of cerebrospinal fluid (CSF) Aβ 42 status when integrated with clinical and genetic profiles.Methods: A total of 407 MCI subjects from the Alzheimer’s Disease Neuroimaging Initiative were allocated to the training (n = 324) and test (n = 83) sets. Radiomics features (n = 214) from the bilateral hippocampi were extracted from T1-weighted images of magnetic resonance imaging (MRI). A previously defined cutoff (< 192 pg/mL) was applied for CSF Aβ 42 status. After feature selection, random forest with subsampling methods were trained to predict the CSF Aβ 42 with three models: 1) a radiomics model; 2) a clinical model based on clinical and genetic profiles including demographics, APOE ε4 genotype, and neuropsychological tests; and 3) a combined model based on radiomics and clinical profiles. The prediction performance of the classifier was validated in the test set using the area under the receiver operating characteristic curve (AUC). Results: The radiomics model identified 33 radiomics features to predict CSF Aβ 42 , which showed an AUC of 0.674 in the best performing radiomics model in the test set. The clinical model identified 6 clinical features to predict CSF Aβ 42 , which showed an AUC of 0.758 in the best performing clinical model in the test set. The combined model based on radiomics and clinical profiles identified a total of 37 features (32 from radiomics and 5 from clinical features), showing an AUC of 0.823 in the best performing combined model test set, which showed the highest performance among the three models. Conclusions: Radiomics model from MRI can help predict CSF Aβ 42 status in MCI patients and potentially triage the patients for the invasive and costly Aβ test.

To investigate whether radiomic features from magnetic resonance image (MRI) can predict the granulation pattern of growth hormone (GH)-secreting pituitary adenoma patients. Sixty-nine pathologically proven acromegaly patients (densely granulated [DG] = 50, sparsely granulated [SG] = 19) were included. Radiomic features (n = 214) were extracted from contrast-enhancing and total tumor portions from T2-weighted (T2) MRIs. Imaging features were selected using a least absolute shrinkage and selection operator (LASSO) logistic regression model with fivefold cross-validation. Diagnostic performance for predicting granulation pattern was compared with that for qualitative T2 signal intensity assessment and T2 relative signal intensity (rSI) using the area under the receiver operating characteristics curve (AUC). Four significant radiomic features from the contrast-enhancing tumor (1 from shape, 1 from first order feature, and 2 from second order features) were selected by LASSO for model construction. The radiomics model showed an AUC, accuracy, sensitivity, and specificity of 0.834 (95% confidence interval [CI] 0.738–0.930), 73.7%, 74.0%, and 73.9%, respectively. The radiomics model showed significantly better performance than the model using qualitative T2 signal intensity assessment (AUC 0.597 [95% CI 0.447–0.747], P = 0.009) and T2 rSI (AUC 0.647 [95% CI 0.523–0.759], P = 0.037). Radiomic features may be useful biomarkers to differentiate granulation pattern of GH-secreting pituitary adenoma patients, and showed better performance than qualitative assessment or rSI evaluation.

To assess whether the radiomic features of diffusion tensor imaging (DTI) and conventional postcontrast T1-weighted (T1C) images can differentiate the epidermal growth factor receptor (EGFR) mutation status in brain metastases from non-small cell lung cancer (NSCLC). A total of 99 brain metastases in 51 patients who underwent surgery or biopsy with underlying NSCLC and known EGFR mutation statuses (57 from EGFR wild type, 42 from EGFR mutant) were allocated to the training (57 lesions in 31 patients) and test (42 lesions in 20 patients) sets. Radiomic features (n = 526) were extracted from preoperative MR images including T1C and DTI. Radiomics classifiers were constructed by combinations of five feature selectors and four machine learning algorithms. The trained classifiers were validated on the test set, and the classifier performance was assessed by determining the area under the curve (AUC). EGFR mutation status showed an overall discordance rate of 12% between the primary tumors and corresponding brain metastases. The best performing classifier was a combination of the tree-based feature selection and linear discriminant algorithm and 5 features were selected (1 from ADC, 2 from fractional anisotropy, and 2 from T1C images), resulting in an AUC, accuracy, sensitivity, and specificity of 0.73, 78.6%, 81.3%, and 76.9% in the test set, respectively. Radiomics classifiers integrating multiparametric MRI parameters may have potential in differentiating the EGFR mutation status in brain metastases from NSCLC.

We evaluated the diagnostic performance and generalizability of traditional machine learning and deep learning models for distinguishing glioblastoma from single brain metastasis using radiomics. The training and external validation cohorts comprised 166 (109 glioblastomas and 57 metastases) and 82 (50 glioblastomas and 32 metastases) patients, respectively. Two-hundred-and-sixty-five radiomic features were extracted from semiautomatically segmented regions on contrast-enhancing and peritumoral T2 hyperintense masks and used as input data. For each of a deep neural network (DNN) and seven traditional machine learning classifiers combined with one of five feature selection methods, hyperparameters were optimized through tenfold cross-validation in the training cohort. The diagnostic performance of the optimized models and two neuroradiologists was tested in the validation cohort for distinguishing glioblastoma from metastasis. In the external validation, DNN showed the highest diagnostic performance, with an area under receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy of 0.956 (95% confidence interval [CI], 0.918–0.990), 90.6% (95% CI, 80.5–100), 88.0% (95% CI, 79.0–97.0), and 89.0% (95% CI, 82.3–95.8), respectively, compared to the best-performing traditional machine learning model (adaptive boosting combined with tree-based feature selection; AUC, 0.890 (95% CI, 0.823–0.947)) and human readers (AUC, 0.774 [95% CI, 0.685–0.852] and 0.904 [95% CI, 0.852–0.951]). The results demonstrated deep learning using radiomic features can be useful for distinguishing glioblastoma from metastasis with good generalizability.

We report a rare case of oligodendroglioma with gangliocytic differentiation. A 31-year-old male without a past medical history was admitted with a sudden seizure. On magnetic resonance imaging, an approximately 7-cm mass with necrosis was noted in the right frontal lobe. The patient underwent surgical resection. On microscopy, two morphologically distinct areas with oligodendroglioma- and ganglioglioma-like features were found. Immunohistochemistry showed an absence of CD34 expression, whereas isocitrate dehydrogenase 1 (IDH1) was positive in the glial component. Moreover, IDH1 was positive in the ganglion-like cells as well as in the glial component. Subsequent 1p/19q co-deletion was confirmed by fluorescence in situ hybridization. Finally, a diagnosis of oligodendroglioma with gangliocytic differentiation was made. IDH1/2 molecular test would be basic and essential diagnostic tool in central nervous system tumor of young patients.

To develop a deep learning algorithm for automated detection and localization of intracranial aneurysms on time-of-flight MR angiography and evaluate its diagnostic performance. In a retrospective and multicenter study, MR images with aneurysms based on radiological reports were extracted. The examinations were randomly divided into two data sets: training set of 468 examinations and internal test set of 120 examinations. Additionally, 50 examinations without aneurysms were randomly selected and added to the internal test set. External test data set consisted of 56 examinations with intracranial aneurysms and 50 examinations without aneurysms, which were extracted based on radiological reports from a different institution. After manual ground truth segmentation of aneurysms, a deep learning algorithm based on 3D ResNet architecture was established with the training set. Its sensitivity, positive predictive value, and specificity were evaluated in the internal and external test sets. MR images included 551 aneurysms (mean diameter, 4.17 ± 2.49 mm) in the training, 147 aneurysms (mean diameter, 3.98 ± 2.11 mm) in the internal test, 63 aneurysms (mean diameter, 3.23 ± 1.69 mm) in the external test sets. The sensitivity, the positive predictive value, and the specificity were 87.1%, 92.8%, and 92.0% for the internal test set and 85.7%, 91.5%, and 98.0% for the external test set, respectively. A deep learning algorithm detected intracranial aneurysms with a high diagnostic performance which was validated using external data set. • A deep learning-based algorithm for the automated diagnosis of intracranial aneurysms demonstrated a high sensitivity, positive predictive value, and specificity. • The high diagnostic performance of the algorithm was validated using external test data set from a different institution with a different scanner. • The algorithm might be robust and effective for general use in real clinical settings.

BACKGROUND Clinicopathological studies have demonstrated that the neuropsychological profiles and outcomes are different between two dementia subtypes, namely Alzheimer's disease (AD) and Lewy bodies-related disease. OBJECTIVE We investigated the neural correlates of cognitive dysfunction in patients with AD-related cognitive impairment (ADCI) and those with Lewy bodies-related cognitive impairment (LBCI). METHODS We enrolled 216 ADCI patients, 183 LBCI patients, and 30 controls. Cortical thickness and diffusion tensor imaging analyses were performed to correlate gray matter and white matter (WM) abnormalities to cognitive composite scores for memory, visuospatial, and attention/executive domains in the ADCI spectrum (ADCI patients and controls) and the LBCI spectrum (LBCI patients and controls) separately. RESULTS Memory dysfunction correlated with cortical thinning and increased mean diffusivity in the AD-prone regions, particularly the medial temporal region, in ADCI. Meanwhile, it only correlated with increased mean diffusivity in the WM adjacent to the anteromedial temporal, insula, and basal frontal cortices in LBCI. Visuospatial dysfunction correlated with cortical thinning in posterior brain regions in ADCI, while it correlated with decreased fractional anisotropy in the corpus callosum and widespread WM regions in LBCI. Attention/executive dysfunction correlated with cortical thinning and WM abnormalities in widespread brain regions in both disease spectra; however, ADCI had more prominent correlation with cortical thickness and LBCI did with fractional anisotropy values. CONCLUSIONS Our study demonstrated that ADCI and LBCI have different neural correlates with respect to cognitive dysfunction. Cortical thinning had greater effects on cognitive dysfunction in the ADCI, while WM disruption did in the LBCI.

Objectives This study investigated whether radiomic features can improve the prediction accuracy for tumor recurrence over clinicopathological features and if these features can be used to identify high-risk patients requiring adjuvant radiotherapy (ART) in WHO grade 2 meningiomas. Methods Preoperative magnetic resonance imaging (MRI) of 155 grade 2 meningioma patients with a median follow-up of 63.8 months were included and allocated to training (n = 92) and test sets (n = 63). After radiomic feature extraction (n = 200), least absolute shrinkage and selection operator feature selection with logistic regression classifier was performed to develop two models: (1) a clinicopathological model and (2) a combined clinicopathological and radiomic model. The probability of recurrence using the combined model was analyzed to identify candidates for ART. Results The combined clinicopathological and radiomics model exhibited superior performance for the prediction of recurrence compared with the clinicopathological model in the training set (area under the curve [AUC] 0.78 vs. 0.67, P = 0.042), which was also validated in the test set (AUC 0.77 vs. 0.61, P = 0.192). In patients with a high probability of recurrence by the combined model, the 5-year progression-free survival was significantly improved with ART (92% vs. 57%, P = 0.024), and the median time to recurrence was longer (54 vs. 17 months after surgery). Conclusions Radiomics significantly contributes added value in predicting recurrence when integrated with the clinicopathological features in patients with grade 2 meningiomas. Furthermore, the combined model can be applied to identify high-risk patients who require ART.

To assess whether radiomic features could improve the accuracy of survival predictions of IDH-wildtype (IDHwt) histological lower-grade gliomas (LGGs) over clinicopathological features.Preoperative MRI data of 61 patients with IDHwt histological LGGs were included as the institutional training set. The test set consisted of 32 patients from The Cancer Genome Atlas. Radiomic features (n = 186) were extracted using conventional MRIs. The radiomics risk score (RRS) for overall survival (OS) was derived from the elastic net. Multivariable Cox regression analyses with clinicopathological features (including epidermal growth factor receptor [EGFR] amplification and telomerase reverse transcriptase promoter [TERTp] mutation status) and the RRS were performed. The integrated area under the receiver operating curves (iAUCs) from the models with and without the RRS were compared. The net reclassification index (NRI) for 1-year OS was also calculated. The prognostic value of the RRS was evaluated using the external validation set.The RRS independently predicted OS (hazard ratio = 48.08; p = 0.001). Compared with the clinicopathological model alone, adding the RRS had a better OS prediction performance (iAUCs 0.775 vs. 0.910), which was internally validated (iAUCs 0.726 vs. 0.884, 1-year OS NRI = 0.497), and a similar trend was found on external validation (iAUCs 0.683 vs. 0.705, 1-year OS NRI = 0.733). The prognostic significance of the RRS was confirmed in the external validation set (p = 0.001).Integrating radiomics with clinicopathological features (including EGFR amplification and TERTp mutation status) can improve survival prediction in patients with IDHwt LGGs.• Radiomics risk score has the potential to improve survival prediction when added to clinicopathological features (iAUCs increased from 0.775 to 0.910). • NRIs for 1-year OS showed that the radiomics risk score had incremental value over the clinicopathological model. • The prognostic significance of the radiomics risk score was confirmed in the external validation set (p = 0.001).

Background While numerous neuroimaging studies have demonstrated that glaucoma is associated with smaller volumes of the visual cortices in the brain, only a few studies have linked glaucoma with brain structures beyond the visual cortices. Therefore, the objective of this study was to compare brain imaging markers and neuropsychological performance between individuals with and without glaucoma. Methods We identified 64 individuals with glaucoma and randomly selected 128 age-, sex-, and education level-matched individuals without glaucoma from a community-based cohort. The study participants underwent 3 T brain magnetic resonance imaging and neuropsychological assessment battery. Regional cortical thickness and subcortical volume were estimated from the brain images of the participants. We used a linear mixed model after adjusting for potential confounding variables. Results Cortical thickness in the occipital lobe was significantly smaller in individuals with glaucoma than in the matched individuals (β = − 0.04 mm, P = 0.014). This did not remain significant after adjusting for cardiovascular risk factors (β = − 0.02 mm, P = 0.67). Individuals with glaucoma had smaller volumes of the thalamus (β = − 212.8 mm3, P = 0.028), caudate (β = − 170.0 mm3, P = 0.029), putamen (β = − 151.4 mm3, P = 0.051), pallidum (β = − 103.6 mm3, P = 0.007), hippocampus (β = − 141.4 mm3, P = 0.026), and amygdala (β = − 87.9 mm3, P = 0.018) compared with those without glaucoma. Among neuropsychological battery tests, only the Stroop color reading test score was significantly lower in individuals with glaucoma compared with those without glaucoma (β = − 0.44, P = 0.038). Conclusions We found that glaucoma was associated with smaller volumes of the thalamus, caudate, putamen, pallidum, amygdala, and hippocampus.

To develop and test a machine learning model for classifying human papillomavirus (HPV) status of patients with oropharyngeal squamous cell carcinoma (OPSCC) usingThis retrospective study enrolled 126 patients (118 male; mean age, 60 years) with newly diagnosed, pathologically confirmed OPSCC, that underwentIn the external test set, ExtraTrees-based Model 3, which uses two PET-derived parameters and three clinical features, with a combination of MinMaxScaler, mutual information selection, and adaptive synthetic sampling approach, showed the best performance (AUC = 0.78; 95% confidence interval, 0.46-1). Model 3 outperformed Model 1 using PET parameters alone (AUC = 0.48,Using oversampling and mutual information selection, an ExtraTree-based HPV status classifier was developed by combining metabolic parameters derived from

Multiple burr hole surgery is considered to be an option for achieving indirect revascularization in patients with ischemic Moyamoya disease (MMD). We aimed to investigate the efficacy of stand-alone multiple burr hole surgery for salvage revascularization in patients with MMD by assessing the hemodynamic changes via normalized time-to-peak (nTTP) analysis and independent component analysis (ICA) of preoperative and postoperative dynamic susceptibility contrast (DSC) perfusion MRI data.The DSC perfusion MRI data of 25 hemispheres from 21 patients with MMD, who underwent multiple burr hole surgery for salvage revascularization due to persistent or recurrent symptoms after primary revascularization with modified encephaloduroarteriosynangiosis (mEDAS), were analyzed. The nTTP, which was measured using the region of interests covering the entire surgical hemisphere, was compared between the preoperative and postoperative images. ICA was used to compare the relative arterial and venous components of the surgical hemispheres between the respective preoperative and postoperative images.The median postoperative nTTP (1.80 s) was significantly shorter than the median preoperative nTTP (4.10 s) (P 0.001). The postoperative relative arterial component of the surgical hemisphere (median: 0.04) was significantly higher than the preoperative relative arterial component (median: - 0.02, P 0.001). In contrast, the postoperative relative venous component of the surgical hemisphere (median: - 0.05) was significantly lower than the preoperative value (median: 0.05, P 0.001).The improvement in cerebral perfusion parameters observed on postoperative DSC perfusion MRI demonstrated that stand-alone multiple burr hole surgery could be a favorable salvage revascularization technique after mEDAS failure in patients with ischemic MMD.

Pilocytic astrocytoma (PA) is rare in adults, and only limited knowledge on the clinical course and prognosis has been available. The combination of clinical information and comprehensive imaging parameters could be used for accurate prognostic stratification in adult PA patients. This study was conducted to predict the prognostic factors from clinical information and conventional magnetic resonance imaging (MRI) features in adult PAs.A total of 56 adult PA patients were enrolled in the institutional cohort. Clinical characteristics including age, sex, anaplastic PA, presence of neurofibromatosis type 1, Karnofsky performance status, extent of resection, and postoperative treatment were collected. MRI characteristics including major axis length, tumor location, presence of the typical 'cystic mass with enhancing mural nodule appearance', proportion of enhancing tumor, the proportion of edema, conspicuity of the nonenhancing margin, and presence of a cyst were evaluated. Univariable and multivariable Cox proportional hazard modeling were performed.The 5-year progression-free survival (PFS) and overall survival (OS) rates were 83.9% and 91.l%, respectively. On univariable analysis, older age, larger proportion of edema, and poor definition of nonenhancing margin were predictors of shorter PFS and OS, respectively (all Ps .05). On multivariable analysis, older age (hazard ratio [HR] = 1.04, P = .014; HR = 1.14, P = .030) and poor definition of nonenhancing margin (HR = 3.66, P = .027; HR = 24.30, P = .024) were independent variables for shorter PFS and OS, respectively.Age and the margin of the nonenhancing part of the tumor may be useful biomarkers for predicting the outcome in adult PAs.

Purpose The 2021 World Health Organization classification includes telomerase reverse transcriptase promoter (TERTp) mutation status as a factor for differentiating meningioma grades. Therefore, preoperative prediction of TERTp mutation may assist in clinical decision making. However, no previous study has applied fractal analysis for TERTp mutation status prediction in meningiomas. The purpose of this study was to assess the utility of three-dimensional (3D) fractal analysis for predicting the TERTp mutation status in grade 2 meningiomas. Methods Forty-eight patients with surgically confirmed grade 2 meningiomas (41 TERTp-wildtype and 7 TERTp-mutant) were included. 3D fractal dimension (FD) and lacunarity values were extracted from the fractal analysis. A predictive model combining clinical, conventional, and fractal parameters was built using logistic regression analysis. Receiver operating characteristic curve analysis was used to assess the ability of the model to predict TERTp mutation status. Results Patients with TERTp-mutant grade 2 meningiomas were older (P = 0.029) and had higher 3D FD (P = 0.026) and lacunarity (P = 0.004) values than patients with TERTp-wildtype grade 2 meningiomas. On multivariable logistic analysis, higher 3D FD values (odds ratio = 32.50, P = 0.039) and higher 3D lacunarity values (odds ratio = 20.54, P = 0.014) were significant predictors of TERTp mutation status. The area under the curve, accuracy, sensitivity, and specificity of the multivariable model were 0.84 (95% confidence interval 0.71–0.93), 83.3%, 71.4%, and 85.4%, respectively. Conclusion 3D FD and lacunarity may be useful imaging biomarkers for predicting TERTp mutation status in grade 2 meningiomas.

There is a growing need to develop novel strategies for the diagnosis of schizophrenia using neuroimaging biomarkers. We investigated the robustness of the diagnostic model for schizophrenia using radiomic features from T1-weighted and diffusion tensor images of the corpus callosum (CC). A total of 165 participants [86 schizophrenia and 79 healthy controls (HCs)] were allocated to training (N = 115) and test (N = 50) sets. Radiomic features of the CC subregions were extracted from T1-weighted, apparent diffusion coefficient (ADC), and fractional anisotropy (FA) images (N = 1605). Following feature selection, various combinations of classifiers were trained, and Bayesian optimization was adopted in the best performing classifier. Discrimination, calibration, and clinical utility of the model were assessed. An online calculator was constructed to offer the probability of having schizophrenia. SHapley Additive exPlanations (SHAP) was applied to explore the interpretability of the model. We identified 30 radiomic features to differentiate participants with schizophrenia from HCs. The Bayesian optimized model achieved the highest performance, with an area under the curve (AUC), accuracy, sensitivity, and specificity of 0.89 (95% confidence interval: 0.81–0.98), 80.0, 83.3, and 76.9%, respectively, in the test set. The final model offers clinical probability in an online calculator. The model explanation by SHAP suggested that second-order features from the posterior CC were highly associated with the risk of schizophrenia. The multiparametric radiomics model focusing on the CC shows its robustness for the diagnosis of schizophrenia. Radiomic features could be a potential source of biomarkers that support the biomarker-based diagnosis of schizophrenia and improve the understanding of its neurobiology.

Early and accurate diagnosis of panic disorder with or without agoraphobia (PDA) is crucial to reducing disease burden and individual suffering. However, its diagnosis is challenging for lack of validated biomarkers. This study aimed to investigate whether radiomic features extracted from T1-weighted images (T1) of major fear-circuit structures (amygdala, insula, and anterior cingulate cortex [ACC]) could differentiate patients with PDA from healthy controls (HCs).The 213 participants (93 PDA, 120 HCs) were allocated to training (n = 149) and test (n = 64) sets after undergoing magnetic resonance imaging. Radiomic features (n = 1498) were extracted from T1 of the studied structures. Machine learning models were trained after feature selection and then validated in the test set. SHapley Additive exPlanations (SHAP) explored the model interpretability.We identified 29 radiomic features to differentiate participants with PDA from HCs. The area under the curve, accuracy, sensitivity, and specificity of the best performing radiomics model in the test set were 0.84 (95% confidence interval: 0.74-0.95), 81.3%, 75.0%, and 86.1%, respectively. The SHAP model explanation suggested that the energy features extracted from the bilateral long insula gyrus and central sulcus of the insula and right ACC were highly associated with the risk of PDA.This was a cross-sectional study with a relatively small sample size, and the causality of changes in radiomic features and their biological and clinical meanings remained to be elucidated.Our findings suggest that radiomic features from the fear-circuit structures could unveil hidden microstructural aberrations underlying the pathogenesis of PDA that could help identify PDA.

Polycyclic aromatic hydrocarbons (PAHs) are formed during incomplete combustion of organic matter, and firefighters are highly exposed to these toxic compounds at fire sites. Exposure to PAHs can cause cognitive decline and neurodegeneration; however, to date, few studies have examined the potential effects of PAH exposure on structural changes in the brain. We aimed to investigate the association between the four types of PAH metabolites and the corresponding changes in neuroimaging markers based on smoking status and hypertension in male firefighters. For this, we utilized the 2-year follow-up data of 301 Korean male firefighters aged over 40 years. The concentrations of four PAH metabolites in urine were measured. Subcortical volume and cortical thickness were estimated using 3 T magnetic resonance imaging of the brain. A generalized linear model was used to investigate the effects of PAHs on changes in the subcortical volume and cortical thickness. We found an association between 1-hydroxyphenathrene (1-OHPHE) and 2-hydroxyfluorene (2-OHF) and changes in several brain regions in all the study participants. Individuals who had never smoked showed significantly thinner frontal (p < 0.001), parietal (p < 0.001), temporal (p < 0.001), and cingulate lobes (p < 0.001) with 1% increase each in the urinary concentration of 1-OHPHE. Hypertension interacted with the concentration of 1-OHPHE to reduce the volume of gray matter and cause cortical thinning in the frontal, parietal, and temporal lobes. Exposure to PAHs may reduce cortical thickness and subcortical volume, which are definitive markers of neurodegeneration. Notably, hypertension can accelerate the degenerative effects of PAHs.

Intracranial atherosclerotic stroke occurs through various mechanisms, mainly by artery-to-artery embolism (AA) or branch occlusive disease (BOD). This study evaluated the spatial relationship between middle cerebral artery (MCA) plaques and perforating arteries among different MCA territory infarction types using vessel wall magnetic resonance imaging (VW-MRI).We retrospectively enrolled patients with acute MCA infarction who underwent VW-MRI. Thirty-four patients were divided into three groups according to infarction pattern: 1) BOD, 2) both BOD and AA (BOD-AA), and 3) AA. To determine the factors related to BOD, the BOD and BOD-AA groups were combined into one group (with striatocapsular infarction [BOD+]) and compared with the AA group. To determine the factors related to AA, the BOD-AA and AA groups were combined into another group (with cortical infarction [AA+]) and compared with the BOD group. Plaque morphology and the spatial relationship between the perforating artery orifice and plaque were evaluated both quantitatively and qualitatively.The plaque margin in the BOD+ group was closer to the perforating artery orifice than that in the AA group (The spatial relationship between the perforating artery orifice and plaque varied among different types of MCA territory infarctions. In patients with BOD, the plaque margin was closer and blocked the perforating artery orifice, and stenosis degree and enhancement were less than those in patients with AA.

This study aims to determine how randomly splitting a dataset into training and test sets affects the estimated performance of a machine learning model and its gap from the test performance under different conditions, using real-world brain tumor radiomics data. We conducted two classification tasks of different difficulty levels with magnetic resonance imaging (MRI) radiomics features: (1) “Simple” task, glioblastomas [n = 109] vs. brain metastasis [n = 58] and (2) “difficult” task, low- [n = 163] vs. high-grade [n = 95] meningiomas. Additionally, two undersampled datasets were created by randomly sampling 50% from these datasets. We performed random training-test set splitting for each dataset repeatedly to create 1,000 different training-test set pairs. For each dataset pair, the least absolute shrinkage and selection operator model was trained and evaluated using various validation methods in the training set, and tested in the test set, using the area under the curve (AUC) as an evaluation metric. The AUCs in training and testing varied among different training-test set pairs, especially with the undersampled datasets and the difficult task. The mean (±standard deviation) AUC difference between training and testing was 0.039 (±0.032) for the simple task without undersampling and 0.092 (±0.071) for the difficult task with undersampling. In a training-test set pair with the difficult task without undersampling, for example, the AUC was high in training but much lower in testing (0.882 and 0.667, respectively); in another dataset pair with the same task, however, the AUC was low in training but much higher in testing (0.709 and 0.911, respectively). When the AUC discrepancy between training and test, or generalization gap, was large, none of the validation methods helped sufficiently reduce the generalization gap. Our results suggest that machine learning after a single random training-test set split may lead to unreliable results in radiomics studies especially with small sample sizes.

OBJECTIVE. The prognosis of tongue squamous cell carcinoma (SCC) with cervical lymph node metastases is poor, and a subset of patients with aggressive disease experiences treatment failure. The current study evaluated the prognostic value of cervical nodal necrosis (CNN) observed on preoperative imaging studies of patients with tongue SCC and cervical node metastases. MATERIALS AND METHODS. We identified patients with tongue SCC who had undergone preoperative neck CT or MRI (or both) and retrospectively reviewed their demographic and clinical data. Patients with metastatic cervical lymph nodes were divided into two groups according to the presence (CNN group) or absence (non-CNN group) of necrosis, and radiologic extranodal extension (ENE) was assessed for all patients. Follow-up biopsy, imaging, and clinical examinations were used to determine survival and treatment failure. Cox proportional hazard regression analyses were performed to determine clinical, demographic, and pathologic factors for survival. RESULTS. Seventy-two patients with a mean follow-up period of 28.4 months were included. The incidence of CNN was 55.6% (40/72). In univariate analysis, patient age, evidence of CNN on preoperative imaging, radiologic ENE, clinical N classification, and overall stage were significantly associated with survival. The multivariate Cox proportional hazard model showed that patient age and CNN on preoperative imaging were independent negative prognostic factors. CONCLUSION. CNN observed on preoperative imaging studies is an independent predictor of a poor prognosis for patients with tongue SCC, and it may serve as a useful imaging biomarker for tailoring individual treatment regimens.

Negative symptoms are recognized as a fundamental feature of schizophrenia throughout the disease course. Epigenetic alterations in the oxytocin receptor gene (OXTR) may be a key mechanism involved in social-emotional disturbances of schizophrenia. Here, we investigated OXTR methylation and its association with clinical and brain network connectivity phenotypes of negative symptoms, particularly anhedonia-asociality, in individuals with recent-onset schizophrenia (ROS) and at ultrahigh risk (UHR) for psychosis. Sixty-four ROS (39 women), 46 UHR (19 women), and 98 healthy individuals (52 women) participated in this study. OXTR methylation was quantified using the pyrosequencing method. A subset of participants (16 ROS, 23 UHR, and 33 healthy controls [HCs]) underwent a 5.5-minute resting-state functional magnetic resonance imaging to determine the relationship between OXTR methylation and the striatal-amygdala network functional connectivity (FC) underlying anhedonia-asociality. Both men and women with ROS and UHR showed significantly decreased OXTR methylation compared to HCs. In women with ROS and UHR, decreased OXTR methylation showed a significant correlation with increased anhedonia-asociality. FC of the striatal-amygdala network, positively associated with the severity of anhedonia-asociality, showed an inverse correlation with OXTR methylation. This study suggests that epigenetic alterations of OXTR, which can be detected before the development of full-blown psychosis, confer susceptibility to schizophrenia and play a crucial role in the manifestation of anhedonia-asociality, particularly in women.

ObjectiveTo investigate whether the presence of autonomic dysfunction is associated with white matter and functional connectivities and the level of cognitive performance in patients with de novo Parkinson disease (PD).MethodsSeventy-five patients with de novo PD underwent a comprehensive autonomic function test and were classified into 2 groups according to the Composite Autonomic Severity Score (CASS; 30 with moderate to severe autonomic dysfunction [CASS 4–10, PD-AUT+] and 45 without significant autonomic dysfunction [CASS 0–3, PD-AUT−]). Network-based statistics and a graph theoretical analysis were performed to assess the interregional white matter connectivity using diffusion tensor imaging. We also performed analyses of resting-state functional connectivity and compared cognitive performance between the 2 groups.ResultsThere were no significant differences in demographic characteristics and vascular risk factors between the PD-AUT+ and PD-AUT− groups. The PD-AUT+ group showed poorer cognitive performance on frontal/executive function than the PD-AUT− group. The PD-AUT+ group exhibited severely disrupted white matter connectivity in both fronto-subcortical and posterior cortical regions, which was well correlated with the severity of autonomic dysfunction assessed by the CASS. In addition, functional connectivity within the executive control network and dorsal attention network negatively correlated with the CASS.ConclusionsOur results suggest that autonomic dysfunction is associated with disrupted white matter and functional brain connectivity as well as cognitive impairment in de novo patients with PD.

To determine whether radiological phenotype can improve the predictive performance of the risk model based on molecular subtype and clinical risk factors in anaplastic glioma patients. This retrospective study was approved by our institutional review board with waiver of informed consent. MR images of 86 patients with pathologically diagnosed anaplastic glioma (WHO grade III) between January 2007 and February 2016 were analyzed according to the Visually Accessible Rembrandt Images (VASARI) features set. Significant imaging findings were selected to generate a radiological risk score (RRS) for overall survival (OS) and progression-free survival (PFS) using the least absolute shrinkage and selection operator (LASSO) Cox regression model. The prognostic value of RRS was evaluated with multivariate Cox regression including molecular subtype and clinical risk factors. The C-indices of multivariate models with and without RRS were compared by bootstrapping. Eight VASARI features contributed to RRS for OS and six contributed to PFS. Multifocality or multicentricity was the most influential feature, followed by restricted diffusion. RRS was significantly associated with OS and PFS (P

Firefighters are exposed to physical and mental threats in the working environment that put them at risk for occupational stress and burnout. Stress responses can impact the functional interactions between brain regions involved in emotional and cognitive regulation. The objective of this study was to investigate brain functional connectivity (FC) related to occupational stress in firefighters. Male firefighters (n = 77) completed the Korean Occupational Stress Scale questionnaire on occupational stress and underwent brain magnetic resonance imaging. Seed-based FC analyses were conducted by setting core regions of the large-scale functional networks as seeds. Subsequent correlational analyses detected relationships between occupational stress scale scores and brain FC. The results showed that occupational stress was negatively correlated with FC between the central executive network (CEN)-related brain regions and seed regions of other networks. Additionally, occupational stress was negatively correlated with FC within the default mode network (DMN), but positively correlated with FC between the salience network (SN) and the DMN. Changes in FC in large-scale neural networks are likely involved in occupational stress responses. Taken together, these results suggest that proper management of occupational stress may help prevent the occurrence of clinical problems caused by changes in brain functional networks.

We predicted molecular profiles in newly diagnosed glioblastoma patients using magnetic resonance (MR) imaging features and explored the associations between imaging features and major molecular alterations. This retrospective study included patients with newly diagnosed glioblastoma and available next-generation sequencing results. From preoperative MR imaging, Visually AcceSAble Rembrandt Images (VASARI) features, volumetric parameters, and apparent diffusion coefficient (ADC) values were obtained. First, univariate random forest was performed to identify gene abnormalities that could be predicted by imaging features with high accuracy and stability. Next, multivariate random forest was trained to predict the selected genes in the discovery cohort and was validated in the external cohort. Univariable logistic regression was performed to further explore the associations between imaging features and genes. Univariate random forest identified nine genes predicted by imaging features, with high accuracy and stability. The multivariate random forest model showed excellent performance in predicting IDH and PTPN11 mutations in the discovery cohort, which were validated in the external validation cohorts (areas under the receiver operator characteristic curve [AUCs] of 0.855 for IDH and 0.88 for PTPN11). ATRX loss and EGFR mutation were predicted with AUCs of 0.753 and 0.739, respectively, whereas PTEN could not be reliably predicted. Based on univariable logistic regression analyses, IDH, ATRX, and TP53 were clustered according to their shared imaging features, whereas EGFR and CDKN2A/B were clustered in the opposite direction. MR imaging features are related to specific molecular alterations and can be used to predict molecular profiles in patients with newly diagnosed glioblastoma.

Alcohol, a known addictive substance, affects the structural properties of the brain. In this study, we explored associations between alcohol use and gray matter properties among firefighters, who are often exposed to significant occupational stress.Gray matter volume (GMV) was evaluated using voxel-based morphometry in 287 male firefighters (mean age: 48.8 ± 7.7 years). Firefighters were classified into 32 never-drinkers, 162 non-heavy alcohol users, and 93 heavy alcohol users according to their alcohol consumption. GMV was compared between groups, and the correlations between GMV and alcohol use were investigated. A voxel-wise height threshold of p 0.001 (uncorrected) was used, with small volume correction applied on cluster level.Heavy alcohol users had lower GMV in the bilateral thalamus than non-heavy alcohol users or never-drinkers. Heavy alcohol users also showed lower GMV in the left insula, compared to other groups. The higher the alcohol consumption among firefighters, the lower the GMV of the right thalamus.The results of this study show that heavy alcohol use has an association with lower GMV in several core regions, including the thalamus. When considering the impact of these brain regions on cognitive and behavioral control, our findings suggest a need for concern about heavy alcohol use among firefighters.

Purpose To evaluate the quality of radiomics studies on meningiomas, using a radiomics quality score (RQS), Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD), and the Image Biomarker Standardization Initiative (IBSI). Methods PubMed MEDLINE and Embase were searched to identify radiomics studies on meningiomas. Of 138 identified articles, 25 relevant original research articles were included. Studies were scored according to the RQS, TRIPOD guidelines, and items in IBSI. Results Only four studies (16 %) performed external validation. The mean RQS was 5.6 out of 36 (15.4 %), and the basic adherence rate was 26.8 %. The adherence rate was low for stating biological correlation (4%), conducting calibration statistics (12 %), multiple segmentation (16 %), and stating potential clinical utility (16 %). None of the studies conducted a test‒retest or phantom study, stated a comparison to a ‘gold standard’, conducted prospective studies or cost-effectivity analysis, or opened code and data to the public, resulting in low RQS. The overall adherence rate for TRIPOD was 54.1 %, with low scores for reporting the title (4%), abstract (0%), blind assessment of the outcome (8%), and explaining the sample size (0%). According to IBSI items, only 6 (24 %), 6 (24 %), and 3 (12 %) studies performed N4 bias-field correction, isovoxel resampling, and grey-level discretization, respectively. No study performed skull stripping. Conclusion The quality of radiomics studies for meningioma is insufficient. Acknowledgement of RQS, TRIPOD, and IBSI reporting guidelines may improve the quality of meningioma radiomics studies and enable their clinical application.

We aimed to evaluate the utility of diffusion tensor imaging (DTI), dynamic contrast-enhanced (DCE), and dynamic susceptibility contrast (DSC) imaging for stratifying bevacizumab treatment outcomes in patients with recurrent high-grade glioma. Fifty-three patients with recurrent high-grade glioma who underwent baseline magnetic resonance imaging including DTI, DCE, and DSC before bevacizumab treatment were included. The mean apparent diffusion coefficient, fractional anisotropy, normalized cerebral blood volume, normalized cerebral blood flow, volume transfer constant, rate transfer coefficient (Kep), extravascular extracellular volume fraction, and plasma volume fraction were assessed. Predictors of response status, progression-free survival (PFS), and overall survival (OS) were determined using logistic regression and Cox proportional hazard modeling. Responders (n = 16) showed significantly longer PFS and OS (P < 0.001) compared with nonresponders (n = 37). Multivariable analysis revealed that lower mean Kep (odds ratio = 0.01, P = 0.008) was the only independent predictor of favorable response after adjustment for age, isocitrate dehydrogenase (IDH) mutation status, and O6-methylguanine-DNA methyltransferase (MGMT) promoter methylation status. Multivariable Cox proportional hazard modeling showed that a higher mean Kep was the only variable associated with shorter PFS (hazard ratio [HR] = 7.90, P = 0.006) and OS (HR = 9.71, P = 0.020) after adjustment for age, IDH mutation status, and MGMT promoter methylation status. Baseline mean Kep may be a useful biomarker for predicting response and stratifying patient outcomes following bevacizumab treatment in patients with recurrent high-grade glioma.

Background Firefighters inevitably encounter emotionally and physically stressful situations at work. Even firefighters without diagnosed post-traumatic stress disorder receive clinical attention because the nature of the profession exposes them to repetitive trauma and high occupational stress. This study investigated gray matter abnormalities related to high occupational stress in firefighters using voxel-based morphometry (VBM) and surface-based morphometry (SBM). Methods We assessed 115 subjects (112 males and 3 females) using magnetic resonance imaging and evaluated occupational stress by the Korean Occupational Stress Scale-26 (KOSS-26). Subjects were classified into highly or lowly stressed groups based on the median value of the KOSS-26. Results In VBM analysis, we found that firefighters with high occupational stress had lower gray matter volume (GMV) in both sides of the insula, the left amygdala, the right medial prefrontal cortex (mPFC), and the anterior cingulate cortex than firefighters with low occupational stress. In SBM analysis based on regions of interest, the GMV of the bilateral insula and right mPFC were also lower in the highly stressed group. Within the highly stressed group, low GMV of the insula was significantly correlated with the length of service (left: r = −0.347, P = 0.009; right: r = −0.333, P = 0.012). Conclusion Our findings suggest that regional GMV abnormalities are related to occupational stress. Regional gray matter abnormalities and related emotional dysregulation may contribute to firefighter susceptibility to burnout., Graphical Abstract

Context Early identification of the response of prolactinoma patients to dopamine agonists (DA) is crucial in treatment planning. Objective To develop a radiomics model using an ensemble machine learning classifier with conventional magnetic resonance images (MRIs) to predict the DA response in prolactinoma patients. Design Retrospective study. Setting Severance Hospital, Seoul, Korea. Patients A total of 177 prolactinoma patients who underwent baseline MRI (109 DA responders and 68 DA nonresponders) were allocated to the training (n = 141) and test (n = 36) sets. Radiomic features (n = 107) were extracted from coronal T2-weighed MRIs. After feature selection, single models (random forest, light gradient boosting machine, extra-trees, quadratic discrimination analysis, and linear discrimination analysis) with oversampling methods were trained to predict the DA response. A soft voting ensemble classifier was used to achieve the final performance. The performance of the classifier was validated in the test set. Results The ensemble classifier showed an area under the curve (AUC) of 0.81 [95% confidence interval (CI), 0.74–0.87] in the training set. In the test set, the ensemble classifier showed an AUC, accuracy, sensitivity, and specificity of 0.81 (95% CI, 0.67-0.96), 77.8%, 78.6%, and 77.3%, respectively. The ensemble classifier achieved the highest performance among all the individual models in the test set. Conclusions Radiomic features may be useful biomarkers to predict the DA response in prolactinoma patients.

Background: Only a limited number of neuroimaging studies have explored the effects of ambient air pollution in adults. The prior studies have investigated only cortical volume, and they have reported mixed findings, particularly for gray matter. Furthermore, the association between nitrogen dioxide (NO2) and neuroimaging markers has been little studied in adults. Objectives: We investigated the association between long-term exposure to air pollutants (NO2, particulate matter (PM) with aerodynamic diameters of ≤10μm (PM10) and ≤2.5μm (PM2.5), and neuroimaging markers. Methods: The study included 427 men and 530 women dwelling in four cities in the Republic of Korea. Long-term concentrations of PM10, NO2, and PM2.5 at residential addresses were estimated. Neuroimaging markers (cortical thickness and subcortical volume) were obtained from brain magnetic resonance images. A generalized linear model was used, adjusting for potential confounders. Results: A 10-μg/m3 increase in PM10 was associated with reduced thicknesses in the frontal [–0.02mm (95% CI: –0.03, –0.01)] and temporal lobes [–0.06mm (95% CI: –0.07, –0.04)]. A 10-μg/m3 increase in PM2.5 was associated with a thinner temporal cortex [–0.18mm (95% CI: –0.27, –0.08)]. A 10-ppb increase in NO2 was associated with reduced thicknesses in the global [–0.01mm (95% CI: –0.01, 0.00)], frontal [–0.02mm (95% CI: –0.03, –0.01)], parietal [–0.02mm (95% CI: –0.03, –0.01)], temporal [–0.04mm (95% CI: –0.05, –0.03)], and insular lobes [–0.01mm (95% CI: –0.02, 0.00)]. The air pollutants were also associated with increased thicknesses in the occipital and cingulate lobes. Subcortical structures associated with the air pollutants included the thalamus, caudate, pallidum, hippocampus, amygdala, and nucleus accumbens. Discussion: The findings suggest that long-term exposure to high ambient air pollution may lead to cortical thinning and reduced subcortical volume in adults. https://doi.org/10.1289/EHP7133

Introduction For the diagnosis of Parkinson's disease (PD) and atypical parkinsonism (AP) using neuroimaging, structural measures have been largely employed since structural abnormalities are most noticeable in the diseases. Functional abnormalities have been known as well, though less clearly seen, and thus, the addition of functional measures to structural measures is expected to be more informative for the diagnosis. Here, we aimed to assess whether multimodal neuroimaging measures of structural and functional alterations could have potential for enhancing performance in diverse diagnostic classification problems. Methods For 77 patients with PD, 86 patients with AP comprising multiple system atrophy and progressive supranuclear palsy, and 53 healthy controls (HC), structural and functional MRI data were collected. Gray matter (GM) volume was acquired as a structural measure, and GM regional homogeneity and degree centrality were acquired as functional measures. The measures were used as predictors individually or in combination in support vector machine classifiers for different problems of distinguishing between HC and each diagnostic type and between different diagnostic types. Results In statistical comparisons of the measures, structural alterations were extensively seen in all diagnostic types, whereas functional alterations were limited to specific diagnostic types. The addition of functional measures to the structural measure generally yielded statistically significant improvements to classification accuracy, compared to the use of the structural measure alone. Conclusion We suggest the fusion of multimodal neuroimaging measures as an effective strategy that could generally cope with diverse prediction problems of clinical concerns., The addition of functional measures (ReHo and DegCen) to the structural measure (Vol) generally yielded statistically significant improvements to classification accuracy, compared to the use of the structural measure alone, across different problems of distinguishing between healthy controls (HC) and each diagnostic type of parkinsonism (PD, MSA, and PSP) and between different diagnostic types of parkinsonism.

To evaluate whether a deep learning (DL) model using both three-dimensional (3D) black-blood (BB) imaging and 3D gradient echo (GRE) imaging may improve the detection and segmentation performance of brain metastases compared to that using only 3D GRE imaging. A total of 188 patients with brain metastases (917 lesions) who underwent a brain metastasis MRI protocol including contrast-enhanced 3D BB and 3D GRE were included in the training set. DL models based on 3D U-net were constructed. The models were validated in the test set consisting of 45 patients with brain metastases (203 lesions) and 49 patients without brain metastases. The combined 3D BB and 3D GRE model yielded better performance than the 3D GRE model (sensitivities of 93.1% vs 76.8%, p < 0.001), and this effect was significantly stronger in subgroups with small metastases (p interaction < 0.001). For metastases < 3 mm, ≥ 3 mm and < 10 mm, and ≥ 10 mm, the sensitivities were 82.4%, 93.2%, and 100%, respectively. The combined 3D BB and 3D GRE model showed a false-positive per case of 0.59 in the test set. The combined 3D BB and 3D GRE model showed a Dice coefficient of 0.822, while 3D GRE model showed a lower Dice coefficient of 0.756. The combined 3D BB and 3D GRE DL model may improve the detection and segmentation performance of brain metastases, especially in detecting small metastases. • The combined 3D BB and 3D GRE model yielded better performance for the detection of brain metastases than the 3D GRE model (p < 0.001), with sensitivities of 93.1% and 76.8%, respectively. • The combined 3D BB and 3D GRE model showed a false-positive rate per case of 0.59 in the test set. • The combined 3D BB and 3D GRE model showed a Dice coefficient of 0.822, while the 3D GRE model showed a lower Dice coefficient of 0.756.

Background Glioma prognosis depends on isocitrate dehydrogenase (IDH) mutation status. We aimed to predict the IDH status of gliomas from preoperative MR images using a fully automated hybrid approach with convolutional neural networks (CNNs) and radiomics. Methods We reviewed 1166 preoperative MR images of gliomas (grades II–IV) from Severance Hospital (n = 856), Seoul National University Hospital (SNUH; n = 107), and The Cancer Imaging Archive (TCIA; n = 203). The Severance set was subdivided into the development (n = 727) and internal test (n = 129) sets. Based on T1 postcontrast, T2, and fluid-attenuated inversion recovery images, a fully automated model was developed that comprised a CNN for tumor segmentation (Model 1) and CNN-based classifier for IDH status prediction (Model 2) that uses a hybrid approach based on 2D tumor images and radiomic features from 3D tumor shape and loci guided by Model 1. The trained model was tested on internal (a subset of the Severance set) and external (SNUH and TCIA) test sets. Results The CNN for tumor segmentation (Model 1) achieved a dice coefficient of 0.86–0.92 across datasets. Our hybrid model achieved accuracies of 93.8%, 87.9%, and 78.8%, with areas under the receiver operating characteristic curves of 0.96, 0.94, and 0.86 and areas under the precision-recall curves of 0.88, 0.82, and 0.81 in the internal test, SNUH, and TCIA sets, respectively. Conclusions Our fully automated hybrid model demonstrated the potential to be a highly reproducible and generalizable tool across different datasets for the noninvasive prediction of the IDH status of gliomas.

While drug-induced parkinsonism (DIP) is mainly caused by blockage of the dopaminergic pathway, multiple neurotransmitter systems besides the dopaminergic system are involved in Parkinson’s disease (PD). Therefore, alterations found in both DIP and PD might be manifestations of dopaminergic dysfunction. To prove this hypothesis, we aimed to define the areas commonly involved in DIP and PD and determine whether the overlapping areas were associated with the dopaminergic system. 68 PD patients, 69 DIP patients and 70 age-and sex-matched controls underwent resting-state functional MRI (rsfMRI). Regional homogeneity (ReHo), amplitude of low-frequency fluctuation (ALFF) and fractional ALFF were calculated and compared. Afterwards, we compared mean rsfMRI values extracted from the overlapping areas with uptake quantitatively measured on dopamine transporter (DAT) images and neuropsychological test results. Compared to the controls, both PD and DIP patients revealed altered rsfMRI values in the right insular cortex, right temporo-occipital cortex, and cerebellum. Among them, decreased ALFF in the right insular cortex and decreased ReHo in the right occipital cortex were correlated with decreased DAT uptake in the caudate as well as executive, visuospatial, and language function. Increased ReHo in the cerebellum was also correlated with decrease DAT uptake in the posterior and ventral anterior putamen, but not with cognitive function. In conclusion, the insular cortex, occipital cortex, and cerebellum were commonly affected in both PD and DIP patients and might be associated with altered dopaminergic modulation.

Postpartum working memory decline has been investigated mostly with neuropsychological tests, but neural evidence is almost unknown. Here we investigated task-related neural alterations during working memory task (n-back) and intrinsic alterations during resting-state (rs) in postpartum women using functional MRI (fMRI). Behaviorally, postpartum women showed comparable working memory performances to the controls although there was a tendency of prolonged response time. fMRI analysis results showed hyper-activation in regions belong to the task positive network (TPN) during the task and hypo-rsfMRI values in the default mode network (DMN) regions during rest in postpartum women. Based on these results, we performed network connectivity analysis using nodes of the TPN and DMN. As a result, the DMN showed a tendency of decreased connectivity in postpartum women during the working memory process compared to the controls. Our results suggest that postpartum women might have functional alterations in the DMN, and that hyper-activation in the TPN during a task might be a compensatory mechanism to maintain working memory performance in postpartum women.

The purpose of this study was to evaluate the diagnostic performance of magnetic resonance (MR) radiomics-based machine learning algorithms in differentiating squamous cell carcinoma (SCC) from lymphoma in the oropharynx. MR images from 87 patients with oropharyngeal SCC (n=68) and lymphoma (n=19) were reviewed retrospectively. Tumors were semi-automatically segmented on contrast-enhanced T1-weighted images registered to T2-weighted images, and radiomic features (n=202) were extracted from contrast-enhanced T1- and T2-weighted images. The radiomics classifier was built using elastic-net regularized generalized linear model analyses with nested five-fold cross-validation. The diagnostic abilities of the radiomics classifier and visual assessment by two head and neck radiologists were evaluated using receiver operating characteristic (ROC) analyses for distinguishing SCC from lymphoma. Nineteen radiomics features were selected at least twice during the five-fold cross-validation. The mean area under the ROC curve (AUC) of the radiomics classifier was 0.750 [95% confidence interval (CI), 0.613-0.887], with a sensitivity of 84.2%, specificity of 60.3%, and an accuracy of 65.5%. Two human readers yielded AUCs of 0.613 (95% CI, 0.467-0.759) and 0.663 (95% CI, 0.531-0.795), respectively. The radiomics-based machine learning model can be useful for differentiating SCC from lymphoma of the oropharynx.

Background Accurately diagnosing schizophrenia is still challenging due to the lack of validated biomarkers. Here, we aimed to investigate whether radiomic features in bilateral hippocampal subfields from magnetic resonance images (MRIs) can differentiate patients with schizophrenia from healthy controls (HCs). Methods A total of 152 participants with MRI (86 schizophrenia and 66 HCs) were allocated to training (n = 106) and test (n = 46) sets. Radiomic features (n = 642) from the bilateral hippocampal subfields processed with automatic segmentation techniques were extracted from T1-weighted MRIs. After feature selection, various combinations of classifiers (logistic regression, extra-trees, AdaBoost, XGBoost, or support vector machine) and subsampling were trained. The performance of the classifier was validated in the test set by determining the area under the curve (AUC). Furthermore, the association between selected radiomic features and clinical symptoms in schizophrenia was assessed. Results Thirty radiomic features were identified to differentiate participants with schizophrenia from HCs. In the training set, the AUC exhibited poor to good performance (range: 0.683–0.861). The best performing radiomics model in the test set was achieved by the mutual information feature selection and logistic regression with an AUC, accuracy, sensitivity, and specificity of 0.821 (95% confidence interval 0.681–0.961), 82.1%, 76.9%, and 70%, respectively. Greater maximum values in the left cornu ammonis 1–3 subfield were associated with a higher severity of positive symptoms and general psychopathology in participants with schizophrenia. Conclusion Radiomic features from hippocampal subfields may be useful biomarkers for identifying schizophrenia.