Non-contrast computed tomography features predict intraventricular hemorrhage growth.

OBJECTIVES: Non-contrast computed tomography (NCCT) markers are robust predictors of parenchymal hematoma expansion in intracerebral hemorrhage (ICH). We investigated whether NCCT features can also identify ICH patients at risk of intraventricular hemorrhage (IVH) growth. METHODS: Patients with acute spontaneous ICH admitted at four tertiary centers in Germany and Italy were retrospectively included from January 2017 to June 2020. NCCT markers were rated by two investigators for heterogeneous density, hypodensity, black hole sign, swirl sign, blend sign, fluid level, island sign, satellite sign, and irregular shape. ICH and IVH volumes were semi-manually segmented. IVH growth was defined as IVH expansion > 1 mL (eIVH) or any delayed IVH (dIVH) on follow-up imaging. Predictors of eIVH and dIVH were explored with multivariable logistic regression. Hypothesized moderators and mediators were independently assessed in PROCESS macro models. RESULTS: A total of 731 patients were included, of whom 185 (25.31%) suffered from IVH growth, 130 (17.78%) had eIVH, and 55 (7.52%) had dIVH. Irregular shape was significantly associated with IVH growth (OR 1.68; 95%CI [1.16-2.44]; p = 0.006). In the subgroup analysis stratified by the IVH growth type, hypodensities were significantly associated with eIVH (OR 2.06; 95%CI [1.48-2.64]; p = 0.015), whereas irregular shape (OR 2.72; 95%CI [1.91-3.53]; p = 0.016) in dIVH. The association between NCCT markers and IVH growth was not mediated by parenchymal hematoma expansion. CONCLUSIONS: NCCT features identified ICH patients at a high risk of IVH growth. Our findings suggest the possibility to stratify the risk of IVH growth with baseline NCCT and might inform ongoing and future studies. CLINICAL RELEVANCE STATEMENT: Non-contrast CT features identified ICH patients at a high risk of intraventricular hemorrhage growth with subtype-specific differences. Our findings may assist in the risk stratification of intraventricular hemorrhage growth with baseline CT and might inform ongoing and future clinical studies. KEY POINTS: • NCCT features identified ICH patients at a high risk of IVH growth with subtype-specific differences. • The effect of NCCT features was not moderated by time and location or indirectly mediated by hematoma expansion. • Our findings may assist in the risk stratification of IVH growth with baseline NCCT and might inform ongoing and future studies.

Evaluation of effectiveness and safety of the multizone NeVaTM stent retriever for mechanical thrombectomy in ischemic stroke.

PURPOSE: This study aimed to evaluate the effectiveness and safety of the NeVaTM stent retriever as first- and second-line device for mechanical thrombectomy in acute ischemic stroke. METHODS: In this retrospective single-center study, all consecutive patients that underwent mechanical thrombectomy with NeVaTM stent retriever as first- or second-line device due to intracranial vessel occlusion with acute ischemic stroke between March and November 2022 were included. RESULTS: Thirty-nine patients (m=18, f=21) with a mean age of 69.9 ± 13.3 years were treated with the NeVaTM stent retriever. NeVaTM stent retriever was used as first-line device in 24 (61.5%) of patients and in 15 (38.5%) as second-line device. First-pass rate (≥mTICI 2c) of NeVaTM stent retriever was both 66.7% when used as first- or second-line device. Final recanalization rate including rescue strategies was 92.3% for ≥mTICI2c and 94.9% for ≥mTICI2b. No device-related minor or major adverse events were observed. A hemorrhage was detected in 33.3% of patients at 24h post-thrombectomy dual-energy CT, of which none was classified as symptomatic intracerebral hemorrhage. NIHSS and mRS improved significantly at discharge compared to admission (p<0.05). CONCLUSION: The NeVaTM stent retriever has a high effectivity and good safety profile as first- and second-line device for mechanical thrombectomy in acute ischemic stroke.

Prognosis and histology of sporadic synchronous and metachronous meningiomas and comparative analyses with singular lesions.

Synchronous or metachronous growth of multiple tumors (≥ 2) is found in up to 20% of meningioma patients. However, biological as well as histological features and prognosis are largely unexplored. Clinical and histological characteristics were retrospectively investigated in 95 patients harboring 226 multiple meningiomas (MMs) and compared with 135 cases of singular meningiomas (SM) using uni- and multivariate analyses. In MM, tumors occurred synchronously and metachronously in 62% and 38%, respectively. WHO grade was intra-individually constant in all but two MMs, and histological subtype varied in 13% of grade 1 tumors. MM occurred more commonly in convexity/parasagittal locations, while SM were more frequent at the skull base (p < .001). In univariate analyses, gross total resection (p = .014) and high-grade histology in MM were associated with a prolonged time to progression (p < .001). Most clinical characteristics and rates of high-grade histology were similar in both groups (p ≥ .05, each). Multivariate analyses showed synchronous/metachronous meningioma growth (HR 4.50, 95% CI 2.26-8.96; p < .001) as an independent predictor for progression. Compared to SM, risk of progression was similar in cases with two (HR 1.56, 95% CI .76-3.19; p = .224), but exponentially raised in patients with 3-4 (HR 3.25, 1.22-1.62; p = .018) and ≥ 5 tumors (HR 13.80, 4.06-46.96; p < .001). Clinical and histological characteristics and risk factors for progression do not relevantly differ between SM and MM. Although largely constant, histology and WHO grade occasionally intra-individually vary in MM. A distinctly higher risk of disease progression in MM as compared to SM might reflect different underlying molecular alterations.

Prediction of Seropositivity in Suspected Autoimmune Encephalitis by Use of Radiomics: A Radiological Proof-of-Concept Study.

In this study, we sought to evaluate the capabilities of radiomics and machine learning in predicting seropositivity in patients with suspected autoimmune encephalitis (AE) from MR images obtained at symptom onset. In 83 patients diagnosed with AE between 2011 and 2022, manual bilateral segmentation of the amygdala was performed on pre-contrast T2 images using 3D Slicer open-source software. Our sample of 83 patients contained 43 seropositive and 40 seronegative AE cases. Images were obtained at our tertiary care center and at various secondary care centers in North Rhine-Westphalia, Germany. The sample was randomly split into training data and independent test data. A total of 107 radiomic features were extracted from bilateral regions of interest (ROIs). Automated machine learning (AutoML) was used to identify the most promising machine learning algorithms. Feature selection was performed using recursive feature elimination (RFE) and based on the determination of the most important features. Selected features were used to train various machine learning algorithms on 100 different data partitions. Performance was subsequently evaluated on independent test data. Our radiomics approach was able to predict the presence of autoantibodies in the independent test samples with a mean AUC of 0.90, a mean accuracy of 0.83, a mean sensitivity of 0.84 and a mean specificity of 0.82, with Lasso regression models yielding the most promising results. These results indicate that radiomics-based machine learning could be a promising tool in predicting the presence of autoantibodies in suspected AE patients. Given the implications of seropositivity for definitive diagnosis of suspected AE cases, this may expedite diagnostic workup even before results from specialized laboratory testing can be obtained. Furthermore, in conjunction with recent publications, our results indicate that characterization of AE subtypes by use of radiomics may become possible in the future, potentially allowing physicians to tailor treatment in the spirit of personalized medicine even before laboratory workup is completed.

A Giant Stent for Giant Cerebral Aneurysms-The Accero®-Rex-Stent.

OBJECTIVE: Until now, giant intracranial aneurysms (GIAs) have in many cases been a vascular disease that was difficult or impossible to treat, not least due to the lack of availability of a large-format stent. In this multicentre study, we report on the first five clinical applications of the Accero®-Rex-Stents (Acandis, Pforzheim, Germany) in the successful treatment of fusiform cerebral giant aneurysms. MATERIAL AND METHODS: The Accero®-Rex-Stents are self-expanding, braided, fully radiopaque Nitinol stents designed for aneurysm treatment. The stent is available in three different sizes (diameter 7-10 mm, length 30-60 mm) and intended for endovascular implantation in vessels with diameters of 5.5-10 mm. RESULTS: Five patients (all male, age 54.4 ± 8.1 years) with large fusiform aneurysms of the posterior circulation were treated endovascularly using the Accero®-Rex-Stents. There were no technical complications. One major ischemic complication occurred. A significant remodeling and reduction in the size of the stent-covered aneurysms was already seen in the short-term post-interventional course. CONCLUSIONS: The Accero®-Rex-Stents were successfully and safely implanted in all five patients with fusiform giant aneurysms, showing technical feasibility with promising initial results and significant aneurysm size reduction in already available follow-up imaging. KEY POINT: With the Accero-Rex-Stents, a new device is available that offers another treatment option for rare cerebral fusiform giant aneurysms with very large parent vessels.

Comparison of MRI Sequences to Predict IDH Mutation Status in Gliomas Using Radiomics-Based Machine Learning.

OBJECTIVES: Regarding the 2021 World Health Organization (WHO) classification of central nervous system (CNS) tumors, the isocitrate dehydrogenase (IDH) mutation status is one of the most important factors for CNS tumor classification. The aim of our study is to analyze which of the commonly used magnetic resonance imaging (MRI) sequences is best suited to obtain this information non-invasively using radiomics-based machine learning models. We developed machine learning models based on different MRI sequences and determined which of the MRI sequences analyzed yields the highest discriminatory power in predicting the IDH mutation status. MATERIAL AND METHODS: In our retrospective IRB-approved study, we used the MRI images of 106 patients with histologically confirmed gliomas. The MRI images were acquired using the T1 sequence with and without administration of a contrast agent, the T2 sequence, and the Fluid-Attenuated Inversion Recovery (FLAIR) sequence. To objectively compare performance in predicting the IDH mutation status as a function of the MRI sequence used, we included only patients in our study cohort for whom MRI images of all four sequences were available. Seventy-one of the patients had an IDH mutation, and the remaining 35 patients did not have an IDH mutation (IDH wild-type). For each of the four MRI sequences used, 107 radiomic features were extracted from the corresponding MRI images by hand-delineated regions of interest. Data partitioning into training data and independent test data was repeated 100 times to avoid random effects associated with the data partitioning. Feature preselection and subsequent model development were performed using Random Forest, Lasso regression, LDA, and Naïve Bayes. The performance of all models was determined with independent test data. RESULTS: Among the different approaches we examined, the T1-weighted contrast-enhanced sequence was found to be the most suitable for predicting IDH mutations status using radiomics-based machine learning models. Using contrast-enhanced T1-weighted MRI images, our seven-feature model developed with Lasso regression achieved a mean area under the curve (AUC) of 0.846, a mean accuracy of 0.792, a mean sensitivity of 0.847, and a mean specificity of 0.681. The administration of contrast agents resulted in a significant increase in the achieved discriminatory power. CONCLUSIONS: Our analyses show that for the prediction of the IDH mutation status using radiomics-based machine learning models, among the MRI images acquired with the commonly used MRI sequences, the contrast-enhanced T1-weighted images are the most suitable.

How much of the variance in functional outcome related to intracerebral hemorrhage volume is already apparent in neurological status at admission?

BACKGROUND: Hematoma volume is a major pathophysiological hallmark of acute intracerebral hemorrhage (ICH). We investigated how the variance in functional outcome induced by the ICH volume is explained by neurological deficits at admission using a mediation model. METHODS: Patients with acute ICH treated in three tertiary stroke centers between January 2010 and April 2019 were retrospectively analyzed. Mediation analysis was performed to investigate the effect of ICH volume (0.8 ml (5% quantile) versus 130.6 ml (95% quantile)) on the risk of unfavorable functional outcome at discharge defined as modified Rankin Score (mRS) ≥ 3 with mediation through National Institutes of Health Stroke Scale (NIHSS) at admission. Multivariable regression was conducted to identify factors related to neurological improvement and deterioration. RESULTS: Three hundred thirty-eight patients were analyzed. One hundred twenty-one patients (36%) achieved mRS ≤ 3 at discharge. Mediation analysis showed that NIHSS on admission explained 30% [13%; 58%] of the ICH volume-induced variance in functional outcome at smaller ICH volume levels, and 14% [4%; 46%] at larger ICH volume levels. Higher ICH volume at admission and brainstem or intraventricular location of ICH were associated with neurological deterioration, while younger age, normotension, lower ICH volumes, and lobar location of ICH were predictors for neurological improvement. CONCLUSION: NIHSS at admission reflects 14% of the functional outcome at discharge for larger hematoma volumes and 30% for smaller hematoma volumes. These results underscore the importance of effects not reflected in NIHSS admission for the outcome of ICH patients such as secondary brain injury and early rehabilitation.

A magnetic resonance imaging based radiomics model to predict mitosis cycles in intracranial meningioma.

The aim of this study was to develop a magnetic resonance imaging (MRI) based radiomics model to predict mitosis cycles in intracranial meningioma grading prior to surgery. Preoperative contrast-enhanced T1-weighted (T1CE) cerebral MRI data of 167 meningioma patients between 2015 and 2020 were obtained, preprocessed and segmented using the 3D Slicer software and the PyRadiomics plugin. In total 145 radiomics features of the T1CE MRI images were computed. The criterion on the basis of which the feature selection was made is whether the number of mitoses per 10 high power field (HPF) is greater than or equal to zero. Our analyses show that machine learning algorithms can be used to make accurate predictions about whether the number of mitoses per 10 HPF is greater than or equal to zero. We obtained our best model using Ridge regression for feature pre-selection, followed by stepwise logistic regression for final model construction. Using independent test data, this model resulted in an AUC (Area under the Curve) of 0.8523, an accuracy of 0.7941, a sensitivity of 0.8182, a specificity of 0.7500 and a Cohen's Kappa of 0.5576. We analyzed the performance of this model as a function of the number of mitoses per 10 HPF. The model performs well for cases with zero mitoses as well as for cases with more than one mitosis per 10 HPF. The worst model performance (accuracy = 0.6250) is obtained for cases with one mitosis per 10 HPF. Our results show that MRI-based radiomics may be a promising approach to predict the mitosis cycles in intracranial meningioma prior to surgery. Specifically, our approach may offer a non-invasive means of detecting the early stages of a malignant process in meningiomas prior to the onset of clinical symptoms.

Comparison of MRI Sequences to Predict ATRX Status Using Radiomics-Based Machine Learning.

ATRX is an important molecular marker according to the 2021 WHO classification of adult-type diffuse glioma. We aim to predict the ATRX mutation status non-invasively using radiomics-based machine learning models on MRI and to determine which MRI sequence is best suited for this purpose. In this retrospective study, we used MRI images of patients with histologically confirmed glioma, including the sequences T1w without and with the administration of contrast agent, T2w, and the FLAIR. Radiomics features were extracted from the corresponding MRI images by hand-delineated regions of interest. Data partitioning into training data and independent test data was repeated 100 times to avoid random effects. Feature preselection and subsequent model development were performed using Lasso regression. The T2w sequence was found to be the most suitable and the FLAIR sequence the least suitable for predicting ATRX mutations using radiomics-based machine learning models. For the T2w sequence, our seven-feature model developed with Lasso regression achieved a mean AUC of 0.831, a mean accuracy of 0.746, a mean sensitivity of 0.772, and a mean specificity of 0.697. In conclusion, for the prediction of ATRX mutation using radiomics-based machine learning models, the T2w sequence is the most suitable among the commonly used MRI sequences.

Evaluation of effectiveness and safety of the large-format pRESET 6-50 thrombectomy stent-retriever in the endovascular treatment of ischemic stroke: real-world experiences from two tertiary comprehensive stroke centers.

Objective: Mechanical thrombectomy (MT) has become the standard treatment for acute ischemic stroke (AIS) with large vessel occlusion (LVO). First-pass (FP) reperfusion of the occluded vessel and fewer passes with stent retrievers show improvement in functional outcomes in stroke patients, while higher numbers of passes are associated with higher complication rates and worse outcomes. Studies indicate that a larger size of the stent-retriever is associated with a higher rate of first-pass reperfusion and improved clinical outcomes. In this retrospective study, we investigated the clinical performance of a recently developed and one of the largest stent-retrievers available in the treatment of LVO (pRESET 6-50, phenox GmbH, Bochum). Materials and methods: All consecutive patients with ischemic stroke due to proximal large vessel occlusion treated with MT using the pRESET 6-50 stent-retriever in two tertiary stroke centers between 09/2021 and 07/2022 were included in this study. The reperfusion rate after MT was quantified by the modified thrombolysis in cerebral infarction (mTICI) score, and functional neurological outcome was evaluated with the National Institutes of Health Stroke Scale (NIHSS) score and the major early neurological recovery (mENR) rate after 24 h. Successful FP reperfusion was defined as mTICI ≥ 2b. Successful and complete reperfusion were defined as mTICI ≥ 2b and mTICI ≥ 2c, respectively. Results: In total, 98 patients (52 men and 46 women) with a median age of 75 (range 25-95 years) were included. A total of 70 (72%) patients presented with an occlusion of the middle cerebral artery (MCA) in the M1 segment, 6 (6%) patients with an occlusion of the M2 segment, 17 (17%) patients with an occlusion of the internal carotid artery (ICA), and 5 (5%) patients with an occlusion of the obstructed basilar artery (BA). Successful FP reperfusion was achieved in 58 patients (62%). Successful and complete reperfusion were achieved in 95 (97%) and 82 (83%) patients, respectively. The median National Institutes of Health Stroke Scale (NIHSS) in all treated patients improved from 17 to 7.5. Major early neurological recovery (mENR) was observed in 34 patients (35.1%). Conclusion: MT with the pRESET 6-50 stent-retriever achieves high successful first-pass and final reperfusion rates in patients with AIS and LVO. The results of this study support the thesis to use large-format stent-retriever in proximal vessel occlusion MT whenever feasible in order to improve high FP and final reperfusion rate, which are known predictors of good clinical outcome.

Vasculitis and Ischemic Stroke in Lyme Neuroborreliosis-Interventional Management Approach and Literature Review.

OBJECTIVE: In rare cases, Lyme neuroborreliosis (LNB) can induce cerebral vasculitis leading to severe stenosis of the cerebral vasculature and consecutive ischemia. Therapy is based on anti-biotic treatment of the tick-borne disease, whereas interventional therapeutic options have not been assessed yet. MATERIAL AND METHODS: We report on a patient with LNB and concomitant stenoses and progressive and fatal vasculitis of the cerebral vessels despite all therapeutic efforts by the departments of neurology and interventional neuroradiology. In this context, we also conducted a literature review on endovascular treatment of LNB-associated cerebral ischemia. RESULTS: A 52-year-old female presented with transient neglect and psychomotor slowdown (initial NIHSS = 0). MRI and serology led to the diagnosis of basal meningitis due to LNB with vasculitis of cerebral arteries. Despite immediate treatment with antibiotics and steroids, neurologic deterioration (NIHSS 8) led to an emergency angiography on day 2 after admission. Hemodynamically relevant stenoses of the MCA were treated via spasmolysis and PTA, leading to almost complete neurological recovery. Despite intensified medical treatment, the vasculitis progressed and could only be transiently ameliorated via repetitive spasmolysis. On day 19, she again presented with significant neurologic deterioration (NIHSS 9), and PTA and stenting of the nearly occluded MCA were performed with a patent vessel, initially without hemorrhagic complications. Despite all therapeutic efforts and preserved stent perfusion, vasculitis worsened and the concurrent occurrence of subdural hemorrhage led to the death of the patient. CONCLUSION: Neuroradiological interventions, i.e., spasmolysis, PTA, and, if necessary, stenting, can and should be considered in cases of LNB-induced vasculitis and stroke that are refractory to best medical treatment alone. KEY POINT: Neuroradiological interventions can be considered in patients with vascular complications of Lyme neuroborreliosis as an additional extension of the primary drug therapy.

Protoporphyrin IX (PpIX) Fluorescence during Meningioma Surgery: Correlations with Histological Findings and Expression of Heme Pathway Molecules.

Background: The usefulness of 5-ALA-mediated fluorescence-guided resection (FGR) in meningiomas is controversial, and information on the molecular background of fluorescence is sparse. Methods: Specimens obtained during 44 FGRs of intracranial meningiomas were analyzed for the presence of tumor tissue and fluorescence. Protein/mRNA expression of key transmembrane transporters/enzymes involved in PpIX metabolism (ABCB6, ABCG2, FECH, CPOX) were investigated using immunohistochemistry/qPCR. Results: Intraoperative fluorescence was observed in 70 of 111 specimens (63%). No correlation was found between fluorescence and the WHO grade (p = 0.403). FGR enabled the identification of neoplastic tissue (sensitivity 84%, specificity 67%, positive and negative predictive value of 86% and 63%, respectively, AUC: 0.75, p < 0.001), and was improved in subgroup analyses excluding dura specimens (86%, 88%, 96%, 63% and 0.87, respectively; p < 0.001). No correlation was found between cortical fluorescence and tumor invasion (p = 0.351). Protein expression of ABCB6, ABCG2, FECH and CPOX was found in meningioma tissue and was correlated with fluorescence (p < 0.05, each), whereas this was not confirmed for mRNA expression. Aberrant expression was observed in the CNS. Conclusion: FGR enables the intraoperative identification of meningioma tissue with limitations concerning dura invasion and due to ectopic expression in the CNS. ABCB6, ABCG2, FECH and CPOX are expressed in meningioma tissue and are related to fluorescence.

Radiomics-Based Prediction of TERT Promotor Mutations in Intracranial High-Grade Meningiomas.

PURPOSE: In meningiomas, TERT promotor mutations are rare but qualify the diagnosis of anaplasia, directly impacting adjuvant therapy. Effective screening for patients at risk for promotor mutations could enable more targeted molecular analyses and improve diagnosis and treatment. METHODS: Semiautomatic segmentation of intracranial grade 2/3 meningiomas was performed on preoperative magnetic resonance imaging. Discriminatory power to predict TERT promoter mutations was analyzed using a random forest algorithm with an increasing number of radiomic features. Two final models with five and eight features with both fixed and differing radiomics features were developed and adjusted to eliminate random effects and to avoid overfitting. RESULTS: A total of 117 image sets including training (N = 94) and test data (N = 23) were analyzed. To eliminate random effects and demonstrate the robustness of our approach, data partitioning and subsequent model development and testing were repeated a total of 100 times (each time with repartitioned training and independent test data). The established five- and eight-feature models with both fixed and different radiomics features enabled the prediction of TERT with similar but excellent performance. The five-feature (different/fixed) model predicted TERT promotor mutation status with a mean AUC of 91.8%/94.3%, mean accuracy of 85.5%/88.9%, mean sensitivity of 88.6%/91.4%, mean specificity of 83.2%/87.0%, and a mean Cohen's Kappa of 71.0%/77.7%. The eight-feature (different/fixed) model predicted TERT promotor mutation status with a mean AUC of 92.7%/94.6%, mean accuracy of 87.3%/88.9%, mean sensitivity of 89.6%/90.6%, mean specificity of 85.5%/87.5%, and a mean Cohen's Kappa of 74.4%/77.6%. Of note, the addition of further features of up to N = 8 only slightly increased the performance. CONCLUSIONS: Radiomics-based machine learning enables prediction of TERT promotor mutation status in meningiomas with excellent discriminatory performance. Future analyses in larger cohorts should include grade 1 lesions as well as additional molecular alterations.

Assessing preoperative risk of STR in skull meningiomas using MR radiomics and machine learning.

Our aim is to predict possible gross total and subtotal resections of skull meningiomas from pre-treatment T1 post contrast MR-images using radiomics and machine learning in a representative patient cohort. We analyse the accuracy of our model predictions depending on the tumor location within the skull and the postoperative tumor volume. In this retrospective, IRB-approved study, image segmentation of the contrast enhancing parts of the tumor was semi-automatically performed using the 3D Slicer open-source software platform. Imaging data were split into training data and independent test data at random. We extracted a total of 107 radiomic features by hand-delineated regions of interest on T1 post contrast MR images. Feature preselection and model construction were performed with eight different machine learning algorithms. Each model was estimated 100 times on new training data and then tested on a previously unknown, independent test data set to avoid possible overfitting. Our cohort included 138 patients. A gross total resection of the meningioma was performed in 107 cases and a subtotal resection in the remaining 31 cases. Using the training data, the mean area under the curve (AUC), mean accuracy, mean kappa, mean sensitivity and mean specificity were 0.901, 0.875, 0.629, 0.675 and 0.933 respectively. We obtained very similar results with the independent test data: mean AUC = 0.900, mean accuracy = 0.881, mean kappa = 0.644, mean sensitivity = 0.692 and mean specificity = 0.936. Thus, our model exposes good and stable predictive performance with both training and test data. Our radiomics approach shows that with machine learning algorithms and comparatively few explanatory factors such as the location of the tumor within the skull as well as its shape, it is possible to make accurate predictions about whether a meningioma can be completely resected by surgery. Complete resections and resections with larger postoperative tumor volumes can be predicted with very high accuracy. However, cases with very small postoperative tumor volumes are comparatively difficult to predict correctly.

Testing the applicability and performance of Auto ML for potential applications in diagnostic neuroradiology.

To investigate the applicability and performance of automated machine learning (AutoML) for potential applications in diagnostic neuroradiology. In the medical sector, there is a rapidly growing demand for machine learning methods, but only a limited number of corresponding experts. The comparatively simple handling of AutoML should enable even non-experts to develop adequate machine learning models with manageable effort. We aim to investigate the feasibility as well as the advantages and disadvantages of developing AutoML models compared to developing conventional machine learning models. We discuss the results in relation to a concrete example of a medical prediction application. In this retrospective IRB-approved study, a cohort of 107 patients who underwent gross total meningioma resection and a second cohort of 31 patients who underwent subtotal resection were included. Image segmentation of the contrast enhancing parts of the tumor was performed semi-automatically using the open-source software platform 3D Slicer. A total of 107 radiomic features were extracted by hand-delineated regions of interest from the pre-treatment MRI images of each patient. Within the AutoML approach, 20 different machine learning algorithms were trained and tested simultaneously. For comparison, a neural network and different conventional machine learning algorithms were trained and tested. With respect to the exemplary medical prediction application used in this study to evaluate the performance of Auto ML, namely the pre-treatment prediction of the achievable resection status of meningioma, AutoML achieved remarkable performance nearly equivalent to that of a feed-forward neural network with a single hidden layer. However, in the clinical case study considered here, logistic regression outperformed the AutoML algorithm. Using independent test data, we observed the following classification results (AutoML/neural network/logistic regression): mean area under the curve = 0.849/0.879/0.900, mean accuracy = 0.821/0.839/0.881, mean kappa = 0.465/0.491/0.644, mean sensitivity = 0.578/0.577/0.692 and mean specificity = 0.891/0.914/0.936. The results obtained with AutoML are therefore very promising. However, the AutoML models in our study did not yet show the corresponding performance of the best models obtained with conventional machine learning methods. While AutoML may facilitate and simplify the task of training and testing machine learning algorithms as applied in the field of neuroradiology and medical imaging, a considerable amount of expert knowledge may still be needed to develop models with the highest possible discriminatory power for diagnostic neuroradiology.

Pseudoprogression prediction in high grade primary CNS tumors by use of radiomics.

Our aim is to define the capabilities of radiomics and machine learning in predicting pseudoprogression development from pre-treatment MR images in a patient cohort diagnosed with high grade gliomas. In this retrospective analysis, we analysed 131 patients with high grade gliomas. Segmentation of the contrast enhancing parts of the tumor before administration of radio-chemotherapy was semi-automatically performed using the 3D Slicer open-source software platform (version 4.10) on T1 post contrast MR images. Imaging data was split into training data, test data and an independent validation sample at random. We extracted a total of 107 radiomic features by hand-delineated regions of interest (ROI). Feature selection and model construction were performed using Generalized Boosted Regression Models (GBM). 131 patients were included, of which 64 patients had a histopathologically proven progressive disease and 67 were diagnosed with mixed or pure pseudoprogression after initial treatment. Our Radiomics approach is able to predict the occurrence of pseudoprogression with an AUC, mean sensitivity, mean specificity and mean accuracy of 91.49% [86.27%, 95.89%], 79.92% [73.08%, 87.55%], 88.61% [85.19%, 94.44%] and 84.35% [80.19%, 90.57%] in the full development group, 78.51% [75.27%, 82.46%], 66.26% [57.95%, 73.02%], 78.31% [70.48%, 84.19%] and 72.40% [68.06%, 76.85%] in the testing group and finally 72.87% [70.18%, 76.28%], 71.75% [62.29%, 75.00%], 80.00% [69.23%, 84.62%] and 76.04% [69.90%, 80.00%] in the independent validation sample, respectively. Our results indicate that radiomics is a promising tool to predict pseudo-progression, thus potentially allowing to reduce the use of biopsies and invasive histopathology.

Radiomics for pseudoprogression prediction in high grade gliomas: added value of MR contrast agent.

Objective: Our aim is to define the capabilities of radiomics in predicting pseudoprogression from pre-treatment MR images in patients diagnosed with high-grade gliomas using T1 non-contrast-enhanced and contrast-enhanced images. Material & methods: In this retrospective IRB-approved study, image segmentation of high-grade gliomas was semi-automatically performed using 3D Slicer. Non-contrast-enhanced T1-weighted images and contrast-enhanced T1-weighted images were used prior to surgical therapy or radio-chemotherapy. Imaging data was split into a training sample and an independent test sample at random. We extracted 107 radiomic features by use of PyRadiomics. Feature selection and model construction were performed using Generalized Boosted Regression Models (GBM). Results: Our cohort included 124 patients (female: n = 53), diagnosed with progressive (n = 61) and pseudoprogressive disease (n = 63) of primary high-grade gliomas. Based on non-contrast-enhanced T1-weighted images of the independent test sample, the mean area under the curve (AUC), mean sensitivity, mean specificity and mean accuracy of our model were 0.651 [0.576, 0.761], 0.616 [0.417, 0.833], 0.578 [0.417, 0.750] and 0.597 [0.500, 0.708] to predict the development of pseudoprogression. In comparison, the independent test data of contrast-enhanced T1-weighted images yielded significantly higher values of AUC = 0.819 [0.760, 0.872], sensitivity = 0.817 [0.750, 0.833], specificity = 0.723 [0.583, 0.833] and accuracy = 0.770 [0.687, 0.833]. Conclusion: Our findings show that it is possible to predict pseudoprogression of high-grade gliomas with a Radiomics model using contrast-enhanced T1-weighted images with comparatively good discriminatory power. The use of a contrast agent results in a clear added value.

Diagnostic Accuracy and Reliability of Noncontrast Computed Tomography Markers for Acute Hematoma Expansion among Radiologists.

BACKGROUND: Noncontrast Computed Tomography (NCCT) features are promising markers for acute hematoma expansion (HE) in patients with intracerebral hemorrhage (ICH). It remains unclear whether accurate identification of these markers is also reliable in raters with different levels of experience. METHODS: Patients with acute spontaneous ICH admitted at four tertiary centers in Germany and Italy were retrospectively included from January 2017 to June 2020. In total, nine NCCT markers were rated by one radiology resident, one radiology fellow, and one neuroradiology fellow with different levels experience in ICH imaging. Interrater reliabilities of the resident and radiology fellow were evaluated by calculated Cohen's kappa (κ) statistics in reference to the neuroradiology fellow who was referred as the gold standard. Gold-standard ratings were evaluated by calculated interrater κ statistics. Global interrater reliabilities were evaluated by calculated Fleiss kappa statistics across all three readers. A comparison of receiver operating characteristics (ROCs) was used to evaluate differences in the diagnostic accuracy for predicting acute hematoma expansion (HE) among the raters. RESULTS: Substantial-to-almost-perfect interrater concordance was found for the resident with interrater Cohen's kappa from 0.70 (95% CI 0.65-0.81) to 0.96 (95% CI 0.94-0.98). The interrater Cohen's kappa for the radiology fellow was moderate to almost perfect and ranged from 0.58 (95% CI 0.52-0.65) to 94 (95% CI 92-0.97). The intrarater gold-standard Cohen's kappa was almost perfect and ranged from 0.79 (95% CI 0.78-0.90) to 0.98 (95% CI 0.78-0.90). The global interrater Fleiss kappa ranged from 0.62 (95%CI 0.57-0.66) to 0.93 (95%CI 0.89-0.97). The diagnostic accuracy for the prediction of acute hematoma expansion (HE) was different for the island sign and fluid sign, with p-values < 0.05. CONCLUSION: The NCCT markers had a substantial-to-almost-perfect interrater agreement among raters with different levels of experience. Differences in the diagnostic accuracy for the prediction of acute HE were found in two out of nine NCCT markers. The study highlights the promising utility of NCCT markers for acute HE prediction.