Current research trends on the effect of diabetes mellitus on rotator cuff tendon healing/tendinopathy.

Rotator cuff tendon tears are a leading cause of shoulder pain. They are challenging to treat, and tendon-bone healing has a high failure rate despite successful surgery. Tendons connect the muscles and bones, which make them important for the body's overall mobility and stability. Metabolic diseases, including diabetes or high blood pressure, can affect the healing process after repair of a damaged tendon. With a global incidence of 9.3%, diabetes is considered as a significant risk factor for rotator cuff tendon healing because it causes structural, inflammatory, and vascular changes in the tendon. However, the mechanisms of how diabetes affects tendon healing remain unknown. Several factors have been suggested, including glycation product accumulation, adipokine dysregulation, increased levels of reactive oxygen species, apoptosis, inflammatory cytokines, imbalanced matrix-metalloproteinase-to-tissue-inhibitor ratio, and impaired angiogenesis and differentiation of the tendon sheath. Despite the effects of diabetes on tendon function and healing, few treatments are available to improve recovery in these patients. This review summarizes the current literature on the pathophysiological changes of the tendon in diabetes and hyperlipidemia. Preclinical and clinical evidence regarding the association between diabetes and tendon healing is presented. Moreover, current approaches to improve tendon healing in patients with diabetes are reviewed.

Radiomics using non-contrast CT to predict hemorrhagic transformation risk in stroke patients undergoing revascularization.

OBJECTIVES: This study explores whether textural features from initial non-contrast CT scans of infarcted brain tissue are linked to hemorrhagic transformation susceptibility. MATERIALS AND METHODS: Stroke patients undergoing thrombolysis or thrombectomy from Jan 2012 to Jan 2022 were analyzed retrospectively. Hemorrhagic transformation was defined using follow-up magnetic resonance imaging. A total of 94 radiomic features were extracted from the infarcted tissue on initial NCCT scans. Patients were divided into training and test sets (7:3 ratio). Two models were developed with fivefold cross-validation: one incorporating first-order and textural radiomic features, and another using only textural radiomic features. A clinical model was also constructed using logistic regression with clinical variables, and test set validation was performed. RESULTS: Among 362 patients, 218 had hemorrhagic transformations. The LightGBM model with all radiomics features had the best performance, with an area under the receiver operating characteristic curve (AUROC) of 0.986 (95% confidence interval [CI], 0.971-1.000) on the test dataset. The ExtraTrees model performed best when textural features were employed, with an AUROC of 0.845 (95% CI, 0.774-0.916). Minimum, maximum, and ten percentile values were significant predictors of hemorrhagic transformation. The clinical model showed an AUROC of 0.544 (95% CI, 0.431-0.658). The performance of the radiomics models was significantly better than that of the clinical model on the test dataset (p < 0.001). CONCLUSIONS: The radiomics model can predict hemorrhagic transformation using NCCT in stroke patients. Low Hounsfield unit was a strong predictor of hemorrhagic transformation, while textural features alone can predict hemorrhagic transformation. CLINICAL RELEVANCE STATEMENT: Using radiomic features extracted from initial non-contrast computed tomography, early prediction of hemorrhagic transformation has the potential to improve patient care and outcomes by aiding in personalized treatment decision-making and early identification of at-risk patients. KEY POINTS: • Predicting hemorrhagic transformation following thrombolysis in stroke is challenging since multiple factors are associated. • Radiomics features of infarcted tissue on initial non-contrast CT are associated with hemorrhagic transformation. • Textural features on non-contrast CT are associated with the frailty of the infarcted tissue.

Natural language processing to predict isocitrate dehydrogenase genotype in diffuse glioma using MR radiology reports.

OBJECTIVES: To evaluate the performance of natural language processing (NLP) models to predict isocitrate dehydrogenase (IDH) mutation status in diffuse glioma using routine MR radiology reports. MATERIALS AND METHODS: This retrospective, multi-center study included consecutive patients with diffuse glioma with known IDH mutation status from May 2009 to November 2021 whose initial MR radiology report was available prior to pathologic diagnosis. Five NLP models (long short-term memory [LSTM], bidirectional LSTM, bidirectional encoder representations from transformers [BERT], BERT graph convolutional network [GCN], BioBERT) were trained, and area under the receiver operating characteristic curve (AUC) was assessed to validate prediction of IDH mutation status in the internal and external validation sets. The performance of the best performing NLP model was compared with that of the human readers. RESULTS: A total of 1427 patients (mean age ± standard deviation, 54 ± 15; 779 men, 54.6%) with 720 patients in the training set, 180 patients in the internal validation set, and 527 patients in the external validation set were included. In the external validation set, BERT GCN showed the highest performance (AUC 0.85, 95% CI 0.81-0.89) in predicting IDH mutation status, which was higher than LSTM (AUC 0.77, 95% CI 0.72-0.81; p = .003) and BioBERT (AUC 0.81, 95% CI 0.76-0.85; p = .03). This was higher than that of a neuroradiologist (AUC 0.80, 95% CI 0.76-0.84; p = .005) and a neurosurgeon (AUC 0.79, 95% CI 0.76-0.84; p = .04). CONCLUSION: BERT GCN was externally validated to predict IDH mutation status in patients with diffuse glioma using routine MR radiology reports with superior or at least comparable performance to human reader. CLINICAL RELEVANCE STATEMENT: Natural language processing may be used to extract relevant information from routine radiology reports to predict cancer genotype and provide prognostic information that may aid in guiding treatment strategy and enabling personalized medicine. KEY POINTS: • A transformer-based natural language processing (NLP) model predicted isocitrate dehydrogenase mutation status in diffuse glioma with an AUC of 0.85 in the external validation set. • The best NLP models were superior or at least comparable to human readers in both internal and external validation sets. • Transformer-based models showed higher performance than conventional NLP model such as long short-term memory.

Association of partial T2-FLAIR mismatch sign and isocitrate dehydrogenase mutation in WHO grade 4 gliomas: results from the ReSPOND consortium.

PURPOSE: While the T2-FLAIR mismatch sign is highly specific for isocitrate dehydrogenase (IDH)-mutant, 1p/19q-noncodeleted astrocytomas among lower-grade gliomas, its utility in WHO grade 4 gliomas is not well-studied. We derived the partial T2-FLAIR mismatch sign as an imaging biomarker for IDH mutation in WHO grade 4 gliomas. METHODS: Preoperative MRI scans of adult WHO grade 4 glioma patients (n = 2165) from the multi-institutional ReSPOND (Radiomics Signatures for PrecisiON Diagnostics) consortium were analyzed. Diagnostic performance of the partial T2-FLAIR mismatch sign was evaluated. Subset analyses were performed to assess associations of imaging markers with overall survival (OS). RESULTS: One hundred twenty-one (5.6%) of 2165 grade 4 gliomas were IDH-mutant. Partial T2-FLAIR mismatch was present in 40 (1.8%) cases, 32 of which were IDH-mutant, yielding 26.4% sensitivity, 99.6% specificity, 80.0% positive predictive value, and 95.8% negative predictive value. Multivariate logistic regression demonstrated IDH mutation was significantly associated with partial T2-FLAIR mismatch (odds ratio [OR] 5.715, 95% CI [1.896, 17.221], p = 0.002), younger age (OR 0.911 [0.895, 0.927], p < 0.001), tumor centered in frontal lobe (OR 3.842, [2.361, 6.251], p < 0.001), absence of multicentricity (OR 0.173, [0.049, 0.612], p = 0.007), and presence of cystic (OR 6.596, [3.023, 14.391], p < 0.001) or non-enhancing solid components (OR 6.069, [3.371, 10.928], p < 0.001). Multivariate Cox analysis demonstrated cystic components (p = 0.024) and non-enhancing solid components (p = 0.003) were associated with longer OS, while older age (p < 0.001), frontal lobe center (p = 0.008), multifocality (p < 0.001), and multicentricity (p < 0.001) were associated with shorter OS. CONCLUSION: Partial T2-FLAIR mismatch sign is highly specific for IDH mutation in WHO grade 4 gliomas.

Causal Inference in Radiomics: Framework, Mechanisms, and Algorithms.

The widespread use of machine learning algorithms in radiomics has led to a proliferation of flexible prognostic models for clinical outcomes. However, a limitation of these techniques is their black-box nature, which prevents the ability for increased mechanistic phenomenological understanding. In this article, we develop an inferential framework for estimating causal effects with radiomics data. A new challenge is that the exposure of interest is latent so that new estimation procedures are needed. We leverage a multivariate version of partial least squares for causal effect estimation. The methodology is illustrated with applications to two radiomics datasets, one in osteosarcoma and one in glioblastoma.

A Pipeline for the Implementation and Visualization of Explainable Machine Learning for Medical Imaging Using Radiomics Features.

Machine learning (ML) models have been shown to predict the presence of clinical factors from medical imaging with remarkable accuracy. However, these complex models can be difficult to interpret and are often criticized as "black boxes". Prediction models that provide no insight into how their predictions are obtained are difficult to trust for making important clinical decisions, such as medical diagnoses or treatment. Explainable machine learning (XML) methods, such as Shapley values, have made it possible to explain the behavior of ML algorithms and to identify which predictors contribute most to a prediction. Incorporating XML methods into medical software tools has the potential to increase trust in ML-powered predictions and aid physicians in making medical decisions. Specifically, in the field of medical imaging analysis the most used methods for explaining deep learning-based model predictions are saliency maps that highlight important areas of an image. However, they do not provide a straightforward interpretation of which qualities of an image area are important. Here, we describe a novel pipeline for XML imaging that uses radiomics data and Shapley values as tools to explain outcome predictions from complex prediction models built with medical imaging with well-defined predictors. We present a visualization of XML imaging results in a clinician-focused dashboard that can be generalized to various settings. We demonstrate the use of this workflow for developing and explaining a prediction model using MRI data from glioma patients to predict a genetic mutation.

A Tale of Two Organ Systems: Imaging review of diseases affecting the thoracic and neurological systems. Part 1.

In an era of rapidly expanding knowledge and sub-specialization, it is becoming increasingly common to focus on one organ system. However, the human body is intimately linked, and disease processes affecting one region of the body not uncommonly affect the other organ systems as well. Understanding diseases from a macroscopic perspective, rather than a narrow vantage point, enables efficient and accurate diagnosis. This tenet holds true for diseases affecting both the thoracic and neurological systems; in isolation, the radiologic appearance of disease in one organ system may be nonspecific, but viewing the pathophysiologic process in both organ systems may markedly narrow the differential considerations, and potentially lead to a definitive diagnosis. In this article, we discuss a variety of disease entities known to affect both the thoracic and neurological systems, either manifesting simultaneously or at different periods of time. Some of these conditions may show neither thoracic nor neurological manifestations. These diseases have been systematically classified into infectious, immune-mediated / inflammatory, vascular, syndromic / hereditary and neoplastic disorders. The underlying pathophysiological mechanisms linking both regions and radiologic appearances in both organ systems are discussed. When appropriate, brief clinical and diagnostic information is provided. Ultimately, accurate diagnosis will lead to expedited triage and prompt institution of potentially life-saving treatment for these groups of complex disorders.

Deep-learning-based cardiovascular risk stratification using coronary artery calcium scores predicted from retinal photographs.

BACKGROUND: Coronary artery calcium (CAC) score is a clinically validated marker of cardiovascular disease risk. We developed and validated a novel cardiovascular risk stratification system based on deep-learning-predicted CAC from retinal photographs. METHODS: We used 216 152 retinal photographs from five datasets from South Korea, Singapore, and the UK to train and validate the algorithms. First, using one dataset from a South Korean health-screening centre, we trained a deep-learning algorithm to predict the probability of the presence of CAC (ie, deep-learning retinal CAC score, RetiCAC). We stratified RetiCAC scores into tertiles and used Cox proportional hazards models to evaluate the ability of RetiCAC to predict cardiovascular events based on external test sets from South Korea, Singapore, and the UK Biobank. We evaluated the incremental values of RetiCAC when added to the Pooled Cohort Equation (PCE) for participants in the UK Biobank. FINDINGS: RetiCAC outperformed all single clinical parameter models in predicting the presence of CAC (area under the receiver operating characteristic curve of 0·742, 95% CI 0·732-0·753). Among the 527 participants in the South Korean clinical cohort, 33 (6·3%) had cardiovascular events during the 5-year follow-up. When compared with the current CAC risk stratification (0, >0-100, and >100), the three-strata RetiCAC showed comparable prognostic performance with a concordance index of 0·71. In the Singapore population-based cohort (n=8551), 310 (3·6%) participants had fatal cardiovascular events over 10 years, and the three-strata RetiCAC was significantly associated with increased risk of fatal cardiovascular events (hazard ratio [HR] trend 1·33, 95% CI 1·04-1·71). In the UK Biobank (n=47 679), 337 (0·7%) participants had fatal cardiovascular events over 10 years. When added to the PCE, the three-strata RetiCAC improved cardiovascular risk stratification in the intermediate-risk group (HR trend 1·28, 95% CI 1·07-1·54) and borderline-risk group (1·62, 1·04-2·54), and the continuous net reclassification index was 0·261 (95% CI 0·124-0·364). INTERPRETATION: A deep learning and retinal photograph-derived CAC score is comparable to CT scan-measured CAC in predicting cardiovascular events, and improves on current risk stratification approaches for cardiovascular disease events. These data suggest retinal photograph-based deep learning has the potential to be used as an alternative measure of CAC, especially in low-resource settings. FUNDING: Yonsei University College of Medicine; Ministry of Health and Welfare, Korea Institute for Advancement of Technology, South Korea; Agency for Science, Technology, and Research; and National Medical Research Council, Singapore.

Machine Learning Based Radiomic HPV Phenotyping of Oropharyngeal SCC: A Feasibility Study Using MRI.

OBJECTIVES: To investigate whether a radiomic MRI feature-based prediction model can differentiate oropharyngeal squamous cell carcinoma (SCC) according to the human papillomavirus (HPV) status. STUDY DESIGN: Retrospective cohort study. METHODS: Pretreatment MRI data from 62 consecutive patients with oropharyngeal SCC were retrospectively reviewed, and chronologically allocated to training (n = 43) and test sets (n = 19). Enhancing tumors were semi-automatically segmented on each slice of the postcontrast T1WI to span the entire tumor volume, after registration of T2WI to postcontrast T1WI; 170 radiomic features were extracted from the entire tumor volume. Relevant features were selected and radiomics models were trained using least absolute shrinkage and selection operator (LASSO) logistic regression model with 10-fold cross-validation, after subsampling of training sets using synthetic minority over-sampling technique to mitigate data imbalance. The selected features, weighted by their respective coefficients, were combined linearly to yield a radiomics score. The diagnostic performance of the radiomic score was evaluated using the area under the receiver operating characteristic curve (AUC). RESULTS: Six radiomic features, which revealed strong association with HPV status of oropharyngeal SCC, were selected using LASSO. The radiomics model yielded excellent performance on the training set (AUC, 0.982 [95% CI, 0.942-1.000]) and moderate performance on the test set (AUC, 0.744 [95% CI, 0.496-0.991]) for differentiating oropharyngeal SCC according to HPV status. CONCLUSIONS: Radiomics-based MRI phenotyping differentiates oropharyngeal SCC according to HPV status, and thus, is a potential imaging biomarker. LEVEL OF EVIDENCE: 3 Laryngoscope, 131:E851-E856, 2021.

Fully automated hybrid approach to predict the IDH mutation status of gliomas via deep learning and radiomics.

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.

Squamous Cell Carcinoma and Lymphoma of the Oropharynx: Differentiation Using a Radiomics Approach.

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.

Radiomics risk score may be a potential imaging biomarker for predicting survival in isocitrate dehydrogenase wild-type lower-grade gliomas.

OBJECTIVES: Isocitrate dehydrogenase wild-type (IDHwt) lower-grade gliomas of histologic grades II and III follow heterogeneous clinical outcomes, which necessitates risk stratification. We aimed to evaluate whether radiomics from MRI would allow prediction of overall survival in patients with IDHwt lower-grade gliomas and to investigate the added prognostic value of radiomics over clinical features. METHODS: Preoperative MRIs of 117 patients with IDHwt lower-grade gliomas from January 2007 to February 2018 were retrospectively analyzed. The external validation cohort consisted of 33 patients from The Cancer Genome Atlas. A total of 182 radiomic features were extracted. Radiomics risk scores (RRSs) for overall survival were derived from the least absolute shrinkage and selection operator (LASSO) and elastic net. Multivariable Cox regression analyses, including clinical features and RRSs, were performed. The integrated areas under the receiver operating characteristic curves (iAUCs) from models with and without RRSs were calculated for comparisons. The prognostic value of RRS was assessed in the validation cohort. RESULTS: The RRS derived from LASSO and elastic net independently predicted survival with hazard ratios of 9.479 (95% confidence interval [CI], 3.220-27.847) and 6.148 (95% CI, 3.009-12.563), respectively. Those RRSs enhanced model performance for predicting overall survival (iAUC increased to 0.780-0.797 from 0.726), which was externally validated. The RRSs stratified IDHwt lower-grade gliomas in the validation cohort with significantly different survival. CONCLUSION: Radiomics has the potential for noninvasive risk stratification and can improve prediction of overall survival in patients with IDHwt lower-grade gliomas when integrated with clinical features. KEY POINTS: • Isocitrate dehydrogenase wild-type lower-grade gliomas with histologic grades II and III follow heterogeneous clinical outcomes, which necessitates further risk stratification. • Radiomics risk scores derived from MRI independently predict survival even after incorporating strong clinical prognostic features (hazard ratios 6.148-9.479). • Radiomics risk scores derived from MRI have the potential to improve survival prediction when added to clinical features (integrated areas under the receiver operating characteristic curves increased from 0.726 to 0.780-0.797).

Machine learning and radiomic phenotyping of lower grade gliomas: improving survival prediction.

BACKGROUND AND PURPOSE: Recent studies have highlighted the importance of isocitrate dehydrogenase (IDH) mutational status in stratifying biologically distinct subgroups of gliomas. This study aimed to evaluate whether MRI-based radiomic features could improve the accuracy of survival predictions for lower grade gliomas over clinical and IDH status. MATERIALS AND METHODS: Radiomic features (n = 250) were extracted from preoperative MRI data of 296 lower grade glioma patients from databases at our institutional (n = 205) and The Cancer Genome Atlas (TCGA)/The Cancer Imaging Archive (TCIA) (n = 91) datasets. For predicting overall survival, random survival forest models were trained with radiomic features; non-imaging prognostic factors including age, resection extent, WHO grade, and IDH status on the institutional dataset, and validated on the TCGA/TCIA dataset. The performance of the random survival forest (RSF) model and incremental value of radiomic features were assessed by time-dependent receiver operating characteristics. RESULTS: The radiomics RSF model identified 71 radiomic features to predict overall survival, which were successfully validated on TCGA/TCIA dataset (iAUC, 0.620; 95% CI, 0.501-0.756). Relative to the RSF model from the non-imaging prognostic parameters, the addition of radiomic features significantly improved the overall survival prediction accuracy of the random survival forest model (iAUC, 0.627 vs. 0.709; difference, 0.097; 95% CI, 0.003-0.209). CONCLUSION: Radiomic phenotyping with machine learning can improve survival prediction over clinical profile and genomic data for lower grade gliomas. KEY POINTS: • Radiomics analysis with machine learning can improve survival prediction over the non-imaging factors (clinical and molecular profiles) for lower grade gliomas, across different institutions.

MR image phenotypes may add prognostic value to clinical features in IDH wild-type lower-grade gliomas.

PURPOSE: To identify significant prognostic magnetic resonance imaging (MRI) features and their prognostic value when added to clinical features in patients with isocitrate dehydrogenase wild-type (IDHwt) lower-grade gliomas. MATERIALS AND METHODS: Preoperative MR images of 158 patients (discovery set = 112, external validation set = 46) with IDHwt lower-grade gliomas (WHO grade II or III) were retrospectively analyzed using the Visually Accessible Rembrandt Images feature set. Radiologic risk scores (RRSs) for overall survival were derived from the least absolute shrinkage and selection operator and elastic net. Multivariable Cox regression analysis, including age, Karnofsky Performance score, extent of resection, WHO grade, and RRS, was performed. The added prognostic value of RRS was calculated by comparing the integrated area under the receiver operating characteristic curve (iAUC) between models with and without RRS. RESULTS: The presence of cysts, pial invasion, and cortical involvement were favorable prognostic factors, while ependymal extension, multifocal or multicentric distribution, nonlobar location, proportion of necrosis > 33%, satellites, and eloquent cortex involvement were significantly associated with worse prognosis. RRS independently predicted survival and significantly enhanced model performance for survival prediction when integrated to clinical features (iAUC increased to 0.773-0.777 from 0.737), which was successfully validated on the validation set (iAUC increased to 0.805-0.830 from 0.735). CONCLUSION: MRI features associated with prognosis in patients with IDHwt lower-grade gliomas were identified. RRSs derived from MRI features independently predicted survival and significantly improved performance of survival prediction models when integrated into clinical features. KEY POINTS: • Comprehensive analysis of MRI features conveys prognostic information in patients with isocitrate dehydrogenase wild-type lower-grade gliomas. • Presence of cysts, pial invasion, and cortical involvement of the tumor were favorable prognostic factors. • Radiological phenotypes derived from MRI independently predict survival and have the potential to improve survival prediction when added to clinical features.

Diffusion tensor imaging radiomics in lower-grade glioma: improving subtyping of isocitrate dehydrogenase mutation status.

PURPOSE: To evaluate whether diffusion tensor imaging (DTI) radiomics with machine learning improves the prediction of isocitrate dehydrogenase (IDH) mutation status of lower-grade gliomas beyond radiomic features from conventional MRI and DTI histogram parameters. METHODS: A total of 168 patients with pathologically confirmed lower-grade gliomas were retrospectively enrolled. A total of 158 and 253 radiomic features were extracted from DTI (DTI radiomics) and conventional MRI (T1-weighted image with contrast enhancement, T2-weighted image, and FLAIR [conventional radiomics]), respectively. The random forest models for predicting IDH status were trained with variable combinations as follows: (1) DTI radiomics, (2) conventional radiomics, (3) conventional radiomics + DTI radiomics, and (4) conventional radiomics + DTI histogram. The models were validated with nested cross-validation. The predictive performances of those models were compared by using area under the curve (AUC) from receiver operating characteristic analysis, and 95% confidence interval (CI) was calculated. RESULTS: Adding DTI radiomics to conventional radiomics significantly improved the accuracy of IDH status subtyping (AUC, 0.900 [95% CI, 0.855-0.945], p = 0.006), whereas adding DTI histogram parameters yielded nonsignificant trend toward improvement (0.869 [95% CI, 0.816-0.922], p = 0.150) compared with the model with conventional radiomics alone (0.835 [95% CI, 0.773-0.896]). The performance of the model consisting of both DTI and conventional radiomics was significantly superior than that of model consisting of both DTI histogram parameters and conventional radiomics (0.900 vs 0.869, p = 0.040). CONCLUSION: DTI radiomics with machine learning can help improve the subtyping of IDH status beyond conventional radiomics and DTI histogram parameters in patients with lower-grade gliomas.

Radiomics MRI Phenotyping with Machine Learning to Predict the Grade of Lower-Grade Gliomas: A Study Focused on Nonenhancing Tumors.

OBJECTIVE: To assess whether radiomics features derived from multiparametric MRI can predict the tumor grade of lower-grade gliomas (LGGs; World Health Organization grade II and grade III) and the nonenhancing LGG subgroup. MATERIALS AND METHODS: Two-hundred four patients with LGGs from our institutional cohort were allocated to training (n = 136) and test (n = 68) sets. Postcontrast T1-weighted images, T2-weighted images, and fluid-attenuated inversion recovery images were analyzed to extract 250 radiomics features. Various machine learning classifiers were trained using the radiomics features to predict the glioma grade. The trained classifiers were internally validated on the institutional test set and externally validated on a separate cohort (n = 99) from The Cancer Genome Atlas (TCGA). Classifier performance was assessed by determining the area under the curve (AUC) from receiver operating characteristic curve analysis. An identical process was performed in the nonenhancing LGG subgroup (institutional training set, n = 73; institutional test set, n = 37; and TCGA cohort, n = 37) to predict the glioma grade. RESULTS: The performance of the best classifier was good in the internal validation set (AUC, 0.85) and fair in the external validation set (AUC, 0.72) to predict the LGG grade. For the nonenhancing LGG subgroup, the performance of the best classifier was good in the internal validation set (AUC, 0.82), but poor in the external validation set (AUC, 0.68). CONCLUSION: Radiomics feature-based classifiers may be useful to predict LGG grades. However, radiomics classifiers may have a limited value when applied to the nonenhancing LGG subgroup in a TCGA cohort.

Amide proton transfer imaging might predict survival and IDH mutation status in high-grade glioma.

OBJECTIVES: To assess the utility of amide proton transfer (APT) imaging as an imaging biomarker to predict prognosis and molecular marker status in high-grade glioma (HGG, WHO grade III/IV). METHODS: We included 71 patients with pathologically diagnosed HGG who underwent preoperative MRI with APT imaging. Overall survival (OS) and progression-free survival (PFS) according to APT signal, clinical factors, MGMT methylation status, and IDH mutation status were analyzed. Multivariate Cox regression models with and without APT signal data were constructed. Model performance was compared using the integrated AUC (iAUC). Associations between APT signals and molecular markers were assessed using the Mann-Whitney test. RESULTS: High APT signal was a significant predictor for poor OS (HR = 3.21, 95% CI = 1.62-6.34) and PFS (HR = 2.22, 95% CI = 1.33-3.72) on univariate analysis. On multivariate analysis, high APT signals were an independent predictor of poor OS and PFS when clinical factors alone (OS: HR = 2.89; PFS: HR = 2.13), or in combination with molecular markers (OS: HR = 2.85; PFS: HR = 2.00), were included as covariates. The incremental prognostic value of APT signals was significant for OS and PFS. IDH-wild type was significantly associated with high APT signals (p = 0.001) when compared to IDH-mutant; however, there was no difference based on MGMT methylation status (p = 0.208). CONCLUSION: High APT signal was a significant predictor of poor prognosis in HGG. APT data showed significant incremental prognostic value over clinical prognostic factors and molecular markers and may also predict IDH mutation status. KEY POINTS: • Amide proton transfer (APT) imaging is a promising prognostic marker of high-grade glioma. • APT signals were significantly higher in IDH-wild type compared to IDH-mutant high-grade glioma. • APT imaging may be valuable for preoperative screening and treatment guidance.

Differentiation between spinal cord diffuse midline glioma with histone H3 K27M mutation and wild type: comparative magnetic resonance imaging.

PURPOSE: Diffuse midline glioma with histone H3 K27M mutation is a new entity described in the 2016 update of the World Health Organization Classification of Tumors of the Central Nervous System. The purpose of this study was to evaluate the clinical and imaging characteristics to predict the presence of H3 K27M mutation in spinal cord glioma using a machine learning-based classification model. METHODS: A total of 41 spinal cord glioma patients consisting of 24 H3 K27M mutants and 17 wild types were enrolled in this retrospective study. A total of 17 clinical and radiological features were evaluated. The random forest (RF) model was trained with the clinical and radiological features to predict the presence of H3 K27M mutation. The diagnostic ability of the RF model was evaluated using receiver operating characteristic (ROC) analysis. Area under the ROC curves (AUC) was calculated. RESULTS: MR imaging features of spinal cord diffuse midline gliomas were heterogeneous. Hemorrhage was the only variable that was able to differentiate H3 K27M mutated tumors from wild-type tumors in univariate analysis (p = 0.033). RF classifier yielded 0.632 classification AUC (95% CI, 0.456-0.808), 63.4% accuracy, 45.8% sensitivity, and 88.2% specificity. CONCLUSION: Our findings indicate that clinical and radiological features are associated with H3 K27M mutation status in spinal cord glioma.

The added prognostic value of radiological phenotype combined with clinical features and molecular subtype in anaplastic gliomas.

PURPOSE: 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. METHODS: 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. RESULTS: 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 < .001), as well as age and molecular subtype. The multivariate model with RRS demonstrated a significantly higher predictive performance than the model without (C-index difference: 0.074, 95% confidence interval [CI]: 0.031, 0.148 for OS; C-index difference: 0.054, 95% CI: 0.014, 0.123 for PFS). CONCLUSION: RRS derived from VASARI features was an independent predictor of survival in patients with anaplastic gliomas. The addition of RRS significantly improved the predictive performance of the molecular feature based model.