Deep learning-based quantification of brain atrophy using 2D T1-weighted MRI for Alzheimer's disease classification.

Background: Determining brain atrophy is crucial for the diagnosis of neurodegenerative diseases. Despite detailed brain atrophy assessments using three-dimensional (3D) T1-weighted magnetic resonance imaging, their practical utility is limited by cost and time. This study introduces deep learning algorithms for quantifying brain atrophy using a more accessible two-dimensional (2D) T1, aiming to achieve cost-effective differentiation of dementia of the Alzheimer's type (DAT) from cognitively unimpaired (CU), while maintaining or exceeding the performance obtained with T1-3D individuals and to accurately predict AD-specific atrophy similarity and atrophic changes [W-scores and Brain Age Index (BAI)]. Methods: Involving 924 participants (478 CU and 446 DAT), our deep learning models were trained on cerebrospinal fluid (CSF) volumes from 2D T1 images and compared with 3D T1 images. The performance of the models in differentiating DAT from CU was assessed using receiver operating characteristic analysis. Pearson's correlation analyses were used to evaluate the relations between 3D T1 and 2D T1 measurements of cortical thickness and CSF volumes, AD-specific atrophy similarity, W-scores, and BAIs. Results: Our deep learning models demonstrated strong correlations between 2D and 3D T1-derived CSF volumes, with correlation coefficients r ranging from 0.805 to 0.971. The algorithms based on 2D T1 accurately distinguished DAT from CU with high accuracy (area under the curve values of 0.873), which were comparable to those of algorithms based on 3D T1. Algorithms based on 2D T1 image-derived CSF volumes showed high correlations in AD-specific atrophy similarity (r = 0.915), W-scores for brain atrophy (0.732 ≤ r ≤ 0.976), and BAIs (r = 0.821) compared with those based on 3D T1 images. Conclusion: Deep learning-based analysis of 2D T1 images is a feasible and accurate alternative for assessing brain atrophy, offering diagnostic precision comparable to that of 3D T1 imaging. This approach offers the advantage of the availability of T1-2D imaging, as well as reduced time and cost, while maintaining diagnostic precision comparable to T1-3D.

A human brain atlas of χ-separation for normative iron and myelin distributions.

Iron and myelin are primary susceptibility sources in the human brain. These substances are essential for a healthy brain, and their abnormalities are often related to various neurological disorders. Recently, an advanced susceptibility mapping technique, which is referred to as χ-separation (pronounced as "chi"-separation), has been proposed, successfully disentangling paramagnetic iron from diamagnetic myelin. This method provided a new opportunity for generating high-resolution iron and myelin maps of the brain. Utilizing this technique, this study constructs a normative χ-separation atlas from 106 healthy human brains. The resulting atlas provides detailed anatomical structures associated with the distributions of iron and myelin, clearly delineating subcortical nuclei, thalamic nuclei, and white matter fiber bundles. Additionally, susceptibility values in a number of regions of interest are reported along with age-dependent changes. This atlas may have direct applications such as localization of subcortical structures for deep brain stimulation or high-intensity focused ultrasound and also serve as a valuable resource for future research.

Ethnic differences in the effects of apolipoprotein E ɛ4 and vascular risk factors on accelerated brain aging.

The frequency of the apolipoprotein E ɛ4 allele and vascular risk factors differs among ethnic groups. We aimed to assess the combined effects of apolipoprotein E ɛ4 and vascular risk factors on brain age in Korean and UK cognitively unimpaired populations. We also aimed to determine the differences in the combined effects between the two populations. We enrolled 2314 cognitively unimpaired individuals aged ≥45 years from Korea and 6942 cognitively unimpaired individuals from the UK, who were matched using propensity scores. Brain age was defined using the brain age index. The apolipoprotein E genotype (ɛ4 carriers, ɛ2 carriers and ɛ3/ɛ3 homozygotes) and vascular risk factors (age, hypertension and diabetes) were considered predictors. Apolipoprotein E ɛ4 carriers in the Korean (ß = 0.511, P = 0.012) and UK (ß = 0.302, P = 0.006) groups had higher brain age index values. The adverse effects of the apolipoprotein E genotype on brain age index values increased with age in the Korean group alone (ɛ2 carriers × age, ß = 0.085, P = 0.009; ɛ4 carriers × age, ß = 0.100, P < 0.001). The apolipoprotein E genotype, age and ethnicity showed a three-way interaction with the brain age index (ɛ2 carriers × age × ethnicity, ß = 0.091, P = 0.022; ɛ4 carriers × age × ethnicity, ß = 0.093, P = 0.003). The effects of apolipoprotein E on the brain age index values were more pronounced in individuals with hypertension in the Korean group alone (ɛ4 carriers × hypertension, ß = 0.777, P = 0.038). The apolipoprotein E genotype, age and ethnicity showed a three-way interaction with the brain age index (ɛ4 carriers × hypertension × ethnicity, ß=1.091, P = 0.014). We highlight the ethnic differences in the combined effects of the apolipoprotein E ɛ4 genotype and vascular risk factors on accelerated brain age. These findings emphasize the need for ethnicity-specific strategies to mitigate apolipoprotein E ɛ4-related brain aging in cognitively unimpaired individuals.

Distinct effects of blood pressure parameters on Alzheimer's and vascular markers in 1,952 Asian individuals without dementia.

BACKGROUND: Risk factors for cardiovascular disease, including elevated blood pressure, are known to increase risk of Alzheimer's disease. There has been increasing awareness of the relationship between long-term blood pressure (BP) patterns and their effects on the brain. We aimed to investigate the association of repeated BP measurements with Alzheimer's and vascular disease markers. METHODS: We recruited 1,952 participants without dementia between August 2015 and February 2022. During serial clinic visits, we assessed both systolic BP (SBP) and diastolic BP (DBP), and visit-to-visit BP variability (BPV) was quantified from repeated measurements. In order to investigate the relationship of mean SBP (or DBP) with Alzheimer's and vascular markers and cognition, we performed multiple linear and logistic regression analyses after controlling for potential confounders (Model 1). Next, we investigated the relationship of with variation of SBP (or DBP) with the aforementioned variables by adding it into Model 1 (Model 2). In addition, mediation analyses were conducted to determine mediation effects of Alzheimer's and vascular makers on the relationship between BP parameters and cognitive impairment. RESULTS: High Aß uptake was associated with greater mean SBP (ß = 1.049, 95% confidence interval 1.016-1.083). High vascular burden was positively associated with mean SBP (odds ratio = 1.293, 95% CI 1.015-1.647) and mean DBP (1.390, 1.098-1.757). High tau uptake was related to greater systolic BPV (0.094, 0.001-0.187) and diastolic BPV (0.096, 0.007-0.184). High Aß uptake partially mediated the relationship between mean SBP and the Mini-Mental State Examination (MMSE) scores. Hippocampal atrophy mediated the relationship between diastolic BPV and MMSE scores. CONCLUSIONS: Each BP parameter affects Alzheimer's and vascular disease markers differently, which in turn leads to cognitive impairment. Therefore, it is necessary to appropriately control specific BP parameters to prevent the development of dementia. Furthermore, a better understanding of pathways from specific BP parameters to cognitive impairments might enable us to select the managements targeting the specific BP parameters to prevent dementia effectively.

Deep learning model for individualized trajectory prediction of clinical outcomes in mild cognitive impairment.

Objectives: Accurately predicting when patients with mild cognitive impairment (MCI) will progress to dementia is a formidable challenge. This work aims to develop a predictive deep learning model to accurately predict future cognitive decline and magnetic resonance imaging (MRI) marker changes over time at the individual level for patients with MCI. Methods: We recruited 657 amnestic patients with MCI from the Samsung Medical Center who underwent cognitive tests, brain MRI scans, and amyloid-ß (Aß) positron emission tomography (PET) scans. We devised a novel deep learning architecture by leveraging an attention mechanism in a recurrent neural network. We trained a predictive model by inputting age, gender, education, apolipoprotein E genotype, neuropsychological test scores, and brain MRI and amyloid PET features. Cognitive outcomes and MRI features of an MCI subject were predicted using the proposed network. Results: The proposed predictive model demonstrated good prediction performance (AUC = 0.814 ± 0.035) in five-fold cross-validation, along with reliable prediction in cognitive decline and MRI markers over time. Faster cognitive decline and brain atrophy in larger regions were forecasted in patients with Aß (+) than with Aß (-). Conclusion: The proposed method provides effective and accurate means for predicting the progression of individuals within a specific period. This model could assist clinicians in identifying subjects at a higher risk of rapid cognitive decline by predicting future cognitive decline and MRI marker changes over time for patients with MCI. Future studies should validate and refine the proposed predictive model further to improve clinical decision-making.

Diffusion- and Perfusion-Weighted MRI Radiomics for Survival Prediction in Patients with Lower-Grade Gliomas.

PURPOSE: Lower-grade gliomas of histologic grades 2 and 3 follow heterogenous clinical outcomes, which necessitates risk stratification. This study aimed to evaluate whether diffusion-weighted and perfusion-weighted MRI radiomics allow overall survival (OS) prediction in patients with lower-grade gliomas and investigate its prognostic value. MATERIALS AND METHODS: In this retrospective study, radiomic features were extracted from apparent diffusion coefficient, relative cerebral blood volume map, and Ktrans map in patients with pathologically confirmed lower-grade gliomas (January 2012-February 2019). The radiomics risk score (RRS) calculated from selected features constituted a radiomics model. Multivariable Cox regression analysis, including clinical features and RRS, was performed. The models' integrated area under the receiver operating characteristic curves (iAUCs) were compared. The radiomics model combined with clinical features was presented as a nomogram. RESULTS: The study included 129 patients (median age, 44 years; interquartile range, 37-57 years; 63 female): 90 patients for training set and 39 patients for test set. The RRS was an independent risk factor for OS with a hazard ratio of 6.01. The combined clinical and radiomics model achieved superior performance for OS prediction compared to the clinical model in both training (iAUC, 0.82 vs. 0.72, p=0.002) and test sets (0.88 vs. 0.76, p=0.04). The radiomics nomogram combined with clinical features exhibited good agreement between the actual and predicted OS with C-index of 0.83 and 0.87 in the training and test sets, respectively. CONCLUSION: Adding diffusion- and perfusion-weighted MRI radiomics to clinical features improved survival prediction in lower-grade glioma.

Choroid Plexus Volume, Amyloid Burden, and Cognition in the Alzheimer's Disease Continuum.

As a part of the glymphatic system, the choroid plexus (CP) is involved in the clearance of harmful metabolites from the brain. We investigated the association between CP volume (CPV), amyloid-ß (Aß) burden, and cognition in patients on the Alzheimer's disease (AD) continuum. We retrospectively reviewed the records of 203 patients on the AD continuum and 82 healthy controls who underwent brain magnetic resonance imaging and 18F-florbetaben positron emission tomography. Automatic segmentation was performed, and the CPV was calculated. Cognitive function was assessed using detailed neuropsychological tests, and patients on the AD continuum were categorized into the non-dementia and dementia groups. The relationships between CPV, Aß burden, and cognitive function were assessed using multivariate linear regression and linear mixed model. CPV was greater in the AD group than in the healthy control group (1.50 vs. 1.30, P < 0.001), but was comparable between the AD non-dementia and dementia groups (1.50 vs. 1.48, P = 0.585). After adjusting for age and sex, a larger CPV was significantly associated with greater global Aß deposition (ß = 0.20, P = 0.002). Larger CPV was also associated with worse general cognitive function assessed using the sum of boxes of the clinical dementia rating scale (ß = 0.85, P = 0.034) and lower composite scores for memory (ß = -0.68, P = 0.002) and frontal/executive function domains (ß = -0.65, P < 0.001). In addition, a larger CPV was associated with a more rapid decline in Mini-Mental State Examination scores in the AD dementia group (ß = -0.58, P = 0.004). The present study demonstrated that CP enlargement was associated with increased Aß deposition and impaired memory and frontal/executive function in patients on the AD continuum.

MRI radiomics may predict early tumor recurrence in patients with sinonasal squamous cell carcinoma.

OBJECTIVES: Sinonasal squamous cell carcinoma (SCC) follows a poor prognosis with high tendency for local recurrence. We aimed to evaluate whether MRI radiomics can predict early local failure in sinonasal SCC. METHODS: Sixty-eight consecutive patients with node-negative sinonasal SCC (January 2005-December 2020) were enrolled, allocated to the training (n = 47) and test sets (n = 21). Early local failure, which occurred within 12 months of completion of initial treatment, was the primary endpoint. For clinical features (age, location, treatment modality, and clinical T stage), binary logistic regression analysis was performed. For 186 extracted radiomic features, different feature selections and classifiers were combined to create two prediction models: (1) a pure radiomics model; and (2) a combined model with clinical features and radiomics. The areas under the receiver operating characteristic curves (AUCs) were calculated and compared using DeLong's method. RESULTS: Early local failure occurred in 38.3% (18/47) and 23.8% (5/21) in the training and test sets, respectively. We identified several radiomic features which were strongly associated with early local failure. In the test set, both the best-performing radiomics model and the combined model (clinical + radiomic features) yielded higher AUCs compared to the clinical model (AUC, 0.838 vs. 0.438, p = 0.020; 0.850 vs. 0.438, p = 0.016, respectively). The performances of the best-performing radiomics model and the combined model did not differ significantly (AUC, 0.838 vs. 0.850, p = 0.904). CONCLUSION: MRI radiomics integrated with a machine learning classifier may predict early local failure in patients with sinonasal SCC. CLINICAL RELEVANCE STATEMENT: MRI radiomics intergrated with machine learning classifiers may predict early local failure in sinonasal squamous cell carcinomas more accurately than the clinical model. KEY POINTS: • A subset of radiomic features which showed significant association with early local failure in patients with sinonasal squamous cell carcinomas was identified. • MRI radiomics integrated with machine learning classifiers can predict early local failure with high accuracy, which was validated in the test set (area under the curve = 0.838). • The combined clinical and radiomics model yielded superior performance for early local failure prediction compared to that of the radiomics (area under the curve 0.850 vs. 0.838 in the test set), without a statistically significant difference.

Evaluation of glymphatic system activity using diffusion tensor image analysis along the perivascular space and amyloid PET in older adults with objectively normal cognition: a preliminary study.

Objectives: Diffusion tensor image analysis along the perivascular space (DTI-ALPS) is a recently introduced method for the assessment of the glymphatic system without the need for contrast injection. The purpose of our study was to assess the glymphatic system in cognitively normal older adults with or without subjective cognitive decline (SCD) using DTI-ALPS, and correlating with amyloid PET. Design and participants: To evaluate the glymphatic system in cognitively normal older adults using DTI-ALPS, we built a prospective cohort including a total of 123 objectively cognitively normal older adults with or without SCD. The ALPS index was calculated from DTI MRI and was assessed by correlating it with standardized uptake value ratios (SUVRs) from amyloid PET and clinically relevant variables. The study subjects were also divided into amyloid "positive" and "negative" groups based on the result of amyloid PET, and the ALPS indices between those two groups were compared. Results: The ALPS index was not significantly different between the normal and SCD groups (P = 0.897). The mean ALPS index from the amyloid positive and amyloid negative group was 1.31 and 1.35, respectively, which showed no significant difference (P = 0.308). Among the SUVRs from variable cortices, that of the paracentral cortex was negatively correlated with the ALPS index (r = -0.218, P = 0.016). Multivariate linear regression revealed that older age (coefficient, -0.007) and higher SUVR from the paracentral cortex (coefficient, -0.101) were two independent variables with a significant association with a lower ALPS index (P = 0.015 and 0.045, respectively). Conclusion: DTI-ALPS may not be useful for evaluation of the glymphatic system in subjects with SCD. Older age was significantly associated with lower ALPS index. Greater amyloid deposition in the paracentral cortex was significantly associated with lower glymphatic activity in cognitively normal older adults. These results should be validated in future studies on the relationships between ALPS index and other fundamental compartments in glymphatic system, such as perivenous space and the meningeal lymphatic vessels.

An interpretable multiparametric radiomics model of basal ganglia to predict dementia conversion in Parkinson's disease.

Cognitive impairment in Parkinson's disease (PD) severely affects patients' prognosis, and early detection of patients at high risk of dementia conversion is important for establishing treatment strategies. We aimed to investigate whether multiparametric MRI radiomics from basal ganglia can improve the prediction of dementia development in PD when integrated with clinical profiles. In this retrospective study, 262 patients with newly diagnosed PD (June 2008-July 2017, follow-up >5 years) were included. MRI radiomic features (n = 1284) were extracted from bilateral caudate and putamen. Two models were developed to predict dementia development: (1) a clinical model-age, disease duration, and cognitive composite scores, and (2) a combined clinical and radiomics model. The area under the receiver operating characteristic curve (AUC) were calculated for each model. The models' interpretabilities were studied. Among total 262 PD patients (mean age, 68 years ± 8 [standard deviation]; 134 men), 51 (30.4%), and 24 (25.5%) patients developed dementia within 5 years of PD diagnosis in the training (n = 168) and test sets (n = 94), respectively. The combined model achieved superior predictive performance compared to the clinical model in training (AUCs 0.928 vs. 0.894, P = 0.284) and test set (AUCs 0.889 vs. 0.722, P = 0.016). The cognitive composite scores of the frontal/executive function domain contributed most to predicting dementia. Radiomics derived from the caudate were also highly associated with cognitive decline. Multiparametric MRI radiomics may have an incremental prognostic value when integrated with clinical profiles to predict future cognitive decline in PD.

Association of choroid plexus volume with motor symptoms and dopaminergic degeneration in Parkinson's disease.

BACKGROUND: The choroid plexus (CP) is involved in the clearance of harmful metabolites from the brain, as a part of the glymphatic system. This study aimed to investigate the association between CP volume (CPV), nigrostriatal dopaminergic degeneration and motor outcomes in Parkinson's disease (PD). METHODS: We retrospectively searched drug-naïve patients with early-stage PD who underwent dopamine transporter (DAT) scanning and MRI. Automatic CP segmentation was performed, and the CPV was calculated. The relationship between CPV, DAT availability and Unified PD Rating Scale Part III (UPDRS-III) scores was assessed using multivariate linear regression. We performed longitudinal analyses to assess motor outcomes according to CPV. RESULTS: CPV was negatively associated with DAT availability in each striatal subregion (anterior caudate, ß=-0.134, p=0.012; posterior caudate, ß=-0.162, p=0.002; anterior putamen, ß=-0.133, p=0.024; posterior putamen, ß=-0.125, p=0.039; ventral putamen, ß=-0.125, p=0.035), except for the ventral striatum. CPV was positively associated with the UPDRS-III score even after adjusting for DAT availability in the posterior putamen (ß=0.121; p=0.035). A larger CPV was associated with the future development of freezing of gait in the Cox regression model (HR 1.539, p=0.027) and a more rapid increase in dopaminergic medication in the linear mixed model (CPV×time, p=0.037), but was not associated with the risk of developing levodopa-induced dyskinesia or wearing off. CONCLUSION: These findings suggest that CPV has the potential to serve as a biomarker for baseline and longitudinal motor disabilities in PD.

Association between choroid plexus volume and cognition in Parkinson disease.

BACKGROUND AND PURPOSE: The choroid plexus (CP) clears harmful metabolites from the central nervous system as part of the glymphatic system. We investigated the association of CP volume (CPV) with baseline and longitudinal cognitive decline in patients with Parkinson disease (PD). METHODS: We retrospectively reviewed the medical records of 240 patients with newly diagnosed PD who had undergone detailed neuropsychological tests and high-resolution T1-weighted structural magnetic resonance imaging during the initial assessment. The CPV of each patient was automatically segmented, and the intracranial volume ratio was used in subsequent analyses. The relationship between CPV and baseline composite scores of each cognitive domain was assessed using multivariate linear regression analyses. A Cox proportional hazards model was used to compare the risk of dementia conversion with CPV. RESULTS: CPV negatively correlated with composite scores of the frontal/executive function domain (ß = -0.375, p = 0.002) after adjusting for age, sex, years of education, and parkinsonian symptom duration. The Cox regression model revealed that a larger CPV was associated with a higher risk of dementia conversion (hazard ratio [HR] = 1.509, p = 0.038), which was no longer significant after adjusting for the composite scores of the frontal/executive function domain. A mediation analysis demonstrated that the effect of CPV on the risk of dementia conversion was completely mediated by frontal/executive function (direct effect: HR = 1.203, p = 0.396; indirect effect: HR = 1.400, p = 0.015). CONCLUSIONS: Baseline CPV is associated with baseline frontal/executive function, which subsequently influences dementia conversion risk in patients with PD.

Association of dynamic susceptibility contrast- and dynamic contrast-enhanced magnetic resonance imaging parameters with molecular marker status in lower-grade gliomas: A retrospective study.

PURPOSE: Molecular marker status is clinically relevant for treatment planning and predicting the prognosis of gliomas. This study aimed to assess whether quantitative imaging parameters from dynamic susceptibility contrast- (DSC-) and dynamic contrast-enhanced (DCE)-magnetic resonance imaging (MRI) can predict the molecular marker status of lower-grade gliomas (LGGs). MATERIALS AND METHODS: Overall, 132 patients with LGGs who underwent DSC- and DCE-MRI were retrospectively enrolled. Statuses of relevant molecular markers including isocitrate dehydrogenase isoenzyme (IDH), 1p19q codeletion, epidermal growth factor receptor (EGFR), O6-methylguanine-DNA methyltransferase (MGMT), and telomerase reverse transcriptase (TERT) were collected. For each molecular marker, age, tumor diameter and location, and DSC- and DCE-MRI parameters, including the normalized cerebral blood volume (nCBV), volume transfer constant (Ktrans), rate transfer coefficient (Kep), extravascular extracellular volume fraction (Ve), and plasma volume fraction (Vp), were compared. Multivariable logistic regression analyses were performed. RESULTS: The nCBV was significantly lower in LGGs with IDH mutation (p = .001) and TERT mutation (p = .027) than those without these mutations. Ktrans (p = .034), Ve (p = .023), and Vp (p = .044) values were significantly lower in MGMT methylated LGGs than in MGMT unmethylated LGGs. Perfusion parameters were not significantly associated with EGFR amplification and 1p19q codeletion. Young age (p < .001) and small diameter (p = .001) were significantly associated with IDH mutation. The nCBV was independently associated with IDH status (AUC, 0.817; 95% CI: 0.739-0.894). CONCLUSIONS: DSC- and DCE-MRI parameters demonstrated correlations with molecular markers of LGGs. Especially, the nCBV can be helpful in predicting the IDH mutation status.

Predicting conversion of brain ß-amyloid positivity in amyloid-negative individuals.

BACKGROUND: Cortical deposition of ß-amyloid (Aß) plaque is one of the main hallmarks of Alzheimer's disease (AD). While Aß positivity has been the main concern so far, predicting whether Aß (-) individuals will convert to Aß (+) has become crucial in clinical and research aspects. In this study, we aimed to develop a classifier that predicts the conversion from Aß (-) to Aß (+) using artificial intelligence. METHODS: Data were obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort regarding patients who were initially Aß (-). We developed an artificial neural network-based classifier with baseline age, gender, APOE ε4 genotype, and global and regional standardized uptake value ratios (SUVRs) from positron emission tomography. Ten times repeated 10-fold cross-validation was performed for model measurement, and the feature importance was assessed. To validate the prediction model, we recruited subjects at the Samsung Medical Center (SMC). RESULTS: A total of 229 participants (53 converters) from the ADNI dataset and a total of 40 subjects (10 converters) from the SMC dataset were included. The average area under the receiver operating characteristic values of three developed models are as follows: Model 1 (age, gender, APOE ε4) of 0.674, Model 2 (age, gender, APOE ε4, global SUVR) of 0.814, and Model 3 (age, gender, APOE ε4, global and regional SUVR) of 0.841. External validation result showed an AUROC of 0.900. CONCLUSION: We developed prediction models regarding Aß positivity conversion. With the growing recognition of the need for earlier intervention in AD, the results of this study are expected to contribute to the screening of early treatment candidates.

Prediction of conversion to dementia using interpretable machine learning in patients with amnestic mild cognitive impairment.

Purpose: Amnestic mild cognitive impairment (aMCI) is a transitional state between normal aging and Alzheimer's disease (AD). However, not all aMCI patients are observed to convert to AD dementia. Therefore, developing a predictive algorithm for the conversion of aMCI to AD dementia is important. Parametric methods, such as logistic regression, have been developed; however, it is difficult to reflect complex patterns, such as non-linear relationships and interactions between variables. Therefore, this study aimed to improve the predictive power of aMCI patients' conversion to dementia by using an interpretable machine learning (IML) algorithm and to identify the factors that increase the risk of individual conversion to dementia in each patient. Methods: We prospectively recruited 705 patients with aMCI who had been followed-up for at least 3 years after undergoing baseline neuropsychological tests at the Samsung Medical Center between 2007 and 2019. We used neuropsychological tests and apolipoprotein E (APOE) genotype data to develop a predictive algorithm. The model-building and validation datasets were composed of data of 565 and 140 patients, respectively. For global interpretation, four algorithms (logistic regression, random forest, support vector machine, and extreme gradient boosting) were compared. For local interpretation, individual conditional expectations (ICE) and SHapley Additive exPlanations (SHAP) were used to analyze individual patients. Results: Among the four algorithms, the extreme gradient boost model showed the best performance, with an area under the receiver operating characteristic curve of 0.852 and an accuracy of 0.807. Variables, such as age, education, the scores of visuospatial and memory domains, the sum of boxes of the Clinical Dementia Rating scale, Mini-Mental State Examination, and APOE genotype were important features for creating the algorithm. Through ICE and SHAP analyses, it was also possible to interpret which variables acted as strong factors for each patient. Conclusion: We were able to propose a predictive algorithm for each aMCI individual's conversion to dementia using the IML technique. This algorithm is expected to be useful in clinical practice and the research field, as it can suggest conversion with high accuracy and identify the degree of influence of risk factors for each patient.

An interpretable radiomics model to select patients for radiotherapy after surgery for WHO grade 2 meningiomas.

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.

Adding radiomics to the 2021 WHO updates may improve prognostic prediction for current IDH-wildtype histological lower-grade gliomas with known EGFR amplification and TERT promoter mutation status.

OBJECTIVES: To assess whether radiomic features could improve the accuracy of survival predictions of IDH-wildtype (IDHwt) histological lower-grade gliomas (LGGs) over clinicopathological features. METHODS: 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. RESULTS: 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). CONCLUSIONS: Integrating radiomics with clinicopathological features (including EGFR amplification and TERTp mutation status) can improve survival prediction in patients with IDHwt LGGs. KEY POINTS: • 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).

Automatic Prediction of Conductive Hearing Loss Using Video Pneumatic Otoscopy and Deep Learning Algorithm.

OBJECTIVES: Diseases of the middle ear can interfere with normal sound transmission, which results in conductive hearing loss. Since video pneumatic otoscopy (VPO) findings reveal not only the presence of middle ear effusions but also dynamic movements of the tympanic membrane and part of the ossicles, analyzing VPO images was expected to be useful in predicting the presence of middle ear transmission problems. Using a convolutional neural network (CNN), a deep neural network implementing computer vision, this preliminary study aimed to create a deep learning model that detects the presence of an air-bone gap, conductive component of hearing loss, by analyzing VPO findings. DESIGN: The medical records of adult patients who underwent VPO tests and pure-tone audiometry (PTA) on the same day were reviewed for enrollment. Conductive hearing loss was defined as an average air-bone gap of more than 10 dB at 0.5, 1, 2, and 4 kHz on PTA. Two significant images from the original VPO videos, at the most medial position on positive pressure and the most laterally displaced position on negative pressure, were used for the analysis. Applying multi-column CNN architectures with individual backbones of pretrained CNN versions, the performance of each model was evaluated and compared for Inception-v3, VGG-16 or ResNet-50. The diagnostic accuracy predicting the presence of conductive component of hearing loss of the selected deep learning algorithm used was compared with experienced otologists. RESULTS: The conductive hearing loss group consisted of 57 cases (mean air-bone gap = 25 ± 8 dB): 21 ears with effusion, 14 ears with malleus-incus fixation, 15 ears with stapes fixation including otosclerosis, one ear with a loose incus-stapes joint, 3 cases with adhesive otitis media, and 3 ears with middle ear masses including congenital cholesteatoma. The control group consisted of 76 cases with normal hearing thresholds without air-bone gaps. A total of 1130 original images including repeated measurements were obtained for the analysis. Of the various network architectures designed, the best was to feed each of the images into the individual backbones of Inception-v3 (three-column architecture) and concatenate the feature maps after the last convolutional layer from each column. In the selected model, the average performance of 10-fold cross-validation in predicting conductive hearing loss was 0.972 mean areas under the curve (mAUC), 91.6% sensitivity, 96.0% specificity, 94.4% positive predictive value, 93.9% negative predictive value, and 94.1% accuracy, which was superior to that of experienced otologists, whose performance had 0.773 mAUC and 79.0% accuracy on average. The algorithm detected over 85% of cases with stapes fixations or ossicular chain problems other than malleus-incus fixations. Visualization of the region of interest in the deep learning model revealed that the algorithm made decisions generally based on findings in the malleus and nearby tympanic membrane. CONCLUSIONS: In this preliminary study, the deep learning algorithm created to analyze VPO images successfully detected the presence of conductive hearing losses caused by middle ear effusion, ossicular fixation, otosclerosis, and adhesive otitis media. Interpretation of VPO using the deep learning algorithm showed promise as a diagnostic tool to differentiate conductive hearing loss from sensorineural hearing loss, which would be especially useful for patients with poor cooperation.

Quality of Radiomics Research on Brain Metastasis: A Roadmap to Promote Clinical Translation.

OBJECTIVE: Our study aimed to evaluate the quality of radiomics studies on brain metastases based on the radiomics quality score (RQS), Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) checklist, and the Image Biomarker Standardization Initiative (IBSI) guidelines. MATERIALS AND METHODS: PubMed MEDLINE, and EMBASE were searched for articles on radiomics for evaluating brain metastases, published until February 2021. Of the 572 articles, 29 relevant original research articles were included and evaluated according to the RQS, TRIPOD checklist, and IBSI guidelines. RESULTS: External validation was performed in only three studies (10.3%). The median RQS was 3.0 (range, -6 to 12), with a low basic adherence rate of 50.0%. The adherence rate was low in comparison to the "gold standard" (10.3%), stating the potential clinical utility (10.3%), performing the cut-off analysis (3.4%), reporting calibration statistics (6.9%), and providing open science and data (3.4%). None of the studies involved test-retest or phantom studies, prospective studies, or cost-effectiveness analyses. The overall rate of adherence to the TRIPOD checklist was 60.3% and low for reporting title (3.4%), blind assessment of outcome (0%), description of the handling of missing data (0%), and presentation of the full prediction model (0%). The majority of studies lacked pre-processing steps, with bias-field correction, isovoxel resampling, skull stripping, and gray-level discretization performed in only six (20.7%), nine (31.0%), four (3.8%), and four (13.8%) studies, respectively. CONCLUSION: The overall scientific and reporting quality of radiomics studies on brain metastases published during the study period was insufficient. Radiomics studies should adhere to the RQS, TRIPOD, and IBSI guidelines to facilitate the translation of radiomics into the clinical field.

A Fully Automated Analytic System for Measuring Endolymphatic Hydrops Ratios in Patients With Ménière Disease via Magnetic Resonance Imaging: Deep Learning Model Development Study.

BACKGROUND: Recently, the analysis of endolymphatic hydropses (EHs) via inner ear magnetic resonance imaging (MRI) for patients with Ménière disease has been attempted in various studies. In addition, artificial intelligence has rapidly been incorporated into the medical field. In our previous studies, an automated algorithm for EH analysis was developed by using a convolutional neural network. However, several limitations existed, and further studies were conducted to compensate for these limitations. OBJECTIVE: The aim of this study is to develop a fully automated analytic system for measuring EH ratios that enhances EH analysis accuracy and clinical usability when studying Ménière disease via MRI. METHODS: We proposed the 3into3Inception and 3intoUNet networks. Their network architectures were based on those of the Inception-v3 and U-Net networks, respectively. The developed networks were trained for inner ear segmentation by using the magnetic resonance images of 124 people and were embedded in a new, automated EH analysis system-inner-ear hydrops estimation via artificial intelligence (INHEARIT)-version 2 (INHEARIT-v2). After fivefold cross-validation, an additional test was performed by using 60 new, unseen magnetic resonance images to evaluate the performance of our system. The INHEARIT-v2 system has a new function that automatically selects representative images from a full MRI stack. RESULTS: The average segmentation performance of the fivefold cross-validation was measured via the intersection of union method, resulting in performance values of 0.743 (SD 0.030) for the 3into3Inception network and 0.811 (SD 0.032) for the 3intoUNet network. The representative magnetic resonance slices (ie, from a data set of unseen magnetic resonance images) that were automatically selected by the INHEARIT-v2 system only differed from a maximum of 2 expert-selected slices. After comparing the ratios calculated by experienced physicians and those calculated by the INHEARIT-v2 system, we found that the average intraclass correlation coefficient for all cases was 0.941; the average intraclass correlation coefficient of the vestibules was 0.968, and that of the cochleae was 0.914. The time required for the fully automated system to accurately analyze EH ratios based on a patient's MRI stack was approximately 3.5 seconds. CONCLUSIONS: In this study, a fully automated full-stack magnetic resonance analysis system for measuring EH ratios was developed (named INHEARIT-v2), and the results showed that there was a high correlation between the expert-calculated EH ratio values and those calculated by the INHEARIT-v2 system. The system is an upgraded version of the INHEARIT system; it has higher segmentation performance and automatically selects representative images from an MRI stack. The new model can help clinicians by providing objective analysis results and reducing the workload for interpreting magnetic resonance images.