Machine Learning for Onset Prediction of Patients with Intracerebral Hemorrhage.

OBJECTIVE: Intracerebral hemorrhage (ICH) has a high mortality and long-term morbidity and thus has a significant overall health-economic impact. Outcomes are especially poor if the exact onset is unknown, but reliable imaging-based methods for onset estimation have not been established. We hypothesized that onset prediction of patients with ICH using artificial intelligence (AI) may be more accurate than human readers. MATERIAL AND METHODS: A total of 7421 computed tomography (CT) datasets between January 2007-July 2021 from the University Hospital Basel with confirmed ICH were extracted and an ICH-segmentation algorithm as well as two classifiers (one with radiomics, one with convolutional neural networks) for onset estimation were trained. The classifiers were trained based on the gold standard of 644 datasets with a known onset of >1 and <48 h. The results of the classifiers were compared to the ratings of two radiologists. RESULTS: Both the AI-based classifiers and the radiologists had poor discrimination of the known onsets, with a mean absolute error (MAE) of 9.77 h (95% CI (confidence interval) = 8.52-11.03) for the convolutional neural network (CNN), 9.96 h (8.68-11.32) for the radiomics model, 13.38 h (11.21-15.74) for rater 1 and 11.21 h (9.61-12.90) for rater 2, respectively. The results of the CNN and radiomics model were both not significantly different to the mean of the known onsets (p = 0.705 and p = 0.423). CONCLUSIONS: In our study, the discriminatory power of AI-based classifiers and human readers for onset estimation of patients with ICH was poor. This indicates that accurate AI-based onset estimation of patients with ICH based only on CT-data may be unlikely to change clinical decision making in the near future. Perhaps multimodal AI-based approaches could improve ICH onset prediction and should be considered in future studies.

Prospective Assessment of Cerebral Microbleeds with Low-Field Magnetic Resonance Imaging (0.55 Tesla MRI).

PURPOSE: Accurate detection of cerebral microbleeds (CMBs) on susceptibility-weighted (SWI) magnetic resonance imaging (MRI) is crucial for the characterization of many neurological diseases. Low-field MRI offers greater access at lower costs and lower infrastructural requirements, but also reduced susceptibility artifacts. We therefore evaluated the diagnostic performance for the detection of CMBs of a whole-body low-field MRI in a prospective cohort of suspected stroke patients compared to an established 1.5 T MRI. METHODS: A prospective scanner comparison was performed including 27 patients, of whom 3 patients were excluded because the time interval was >1 h between acquisition of the 1.5 T and 0.55 T MRI. All SWI sequences were assessed for the presence, number, and localization of CMBs by two neuroradiologists and additionally underwent a Likert rating with respect to image impression, resolution, noise, contrast, and diagnostic quality. RESULTS: A total of 24 patients with a mean age of 74 years were included (11 female). Both readers detected the same number and localization of microbleeds in all 24 datasets (sensitivity and specificity 100%; interreader reliability Ï° = 1), with CMBs only being observed in 12 patients. Likert ratings of the sequences at both field strengths regarding overall image quality and diagnostic quality did not reveal significant differences between the 0.55 T and 1.5 T sequences (p = 0.942; p = 0.672). For resolution and contrast, the 0.55 T sequences were even significantly superior (p < 0.0001; p < 0.0003), whereas the 1.5 T sequences were significantly superior (p < 0.0001) regarding noise. CONCLUSION: Low-field MRI at 0.55 T may have similar accuracy as 1.5 T scanners for the detection of microbleeds and thus may have great potential as a resource-efficient alternative in the near future.

Image Quality of Lumbar Spine Imaging at 0.55T Low-Field MRI is Comparable to Conventional 1.5T MRI - Initial Observations in Healthy Volunteers.

RATIONALE AND OBJECTIVES: To assess the potential of 0.55T low-field MRI system in lumbar spine imaging with and without the use of additional advanced postprocessing techniques. MATERIALS AND METHODS: The lumbar spine of 14 volunteers (32.9 ± 3.6 years) was imaged both at 0.55T and 1.5T using sequences from clinical routine. On the 0.55T scanner system, additional sequences with simultaneous multi-slice acquisition and artificial intelligence-based postprocessing techniques were acquired. Image quality of all 28 examinations was assessed by three musculoskeletal radiologists with respect to signal/contrast, resolution, and assessability of the spinal canal and neuroforamina using a 5-point Likert scale (1 = non-diagnostic to 5 = perfect quality). Interrater agreement was evaluated with the Intraclass Correlation Coefficient and the Mann-Whitney U test (significance level: p < 0.05). RESULTS: Image quality at 0.55T was rated lower on the 5-point Likert scale compared to 1.5T regarding signal/contrast (mean: 4.16 ± 0.29 vs. 4.54 ± 0.29; p < 0.001), resolution (4.07 ± 0.31 vs. 4.49 ± 0.30; p < 0.001), assessability of the spinal canal (4.28 ± 0.13 vs. 4.73 ± 0.26; p < 0.001) and the neuroforamina (4.14 ± 0.28 vs. 4.70 ± 0.27; p < 0.001). Image quality for the AI-processed sagittal T1 TSE and T2 TSE at 0.55T was also rated slightly lower, but still good to perfect with a concomitant reduction in measurement time. Interrater agreement was good to excellent (range: 0.60-0.91). CONCLUSION: While lumbar spine image quality at 0.55T is perceived inferior to imaging at 1.5T by musculoskeletal radiologists, good overall examination quality was observed with high interrater agreement. Advanced postprocessing techniques may accelerate intrinsically longer acquisition times at 0.55T.

Impact of edema formation on functional outcome in pediatric stroke patients.

BACKGROUND: Quantitative lesion net water uptake (NWU) has been described as an imaging biomarker reflecting vasogenic edema as an early indicator of infarct progression. We hypothesized that edema formation measured by NWU is higher in children compared to adults but despite this functional outcome may be better in children. METHODS: This study analyzed children enrolled in the Save ChildS Study who had baseline and follow-up computed tomography available and the data were compared to adult patients. RESULTS: Some 207 patients, of whom 13 were children and 194 were adults, were analyzed. Median NWU at baseline was 7.8% (IQR: 4.3-11.3), and there were no significant differences between children and adults (7.5% vs. 7.8%; p = 0.87). The early edema progression rate was 3.0%/h in children and 2.3%/h in adults. Median ΔNWU was 15.1% in children and 10.5% in adults. Children had significantly more often excellent (mRS 0-1; children 10/13 = 77% vs. adults 28/196 = 14%; p < 0.0001) and favorable clinical outcomes (mRS 0-2, 12/13 = 92% vs. 39/196 = 20%; p < 0.0001). CONCLUSIONS: In this study, clinical outcomes in children with large vessel occlusion strokes were better than in adults despite similar clinical and imaging characteristics and similar edema formation. This may be impacted by the generally better outcomes of children after strokes but may demonstrate that the degree of early ischemic changes using Alberta Stroke Program Early Computed Tomography Score (ASPECTS) and edema progression rate may not be a reason for exclusion from endovascular thrombectomy.

More Space, Less Noise-New-generation Low-Field Magnetic Resonance Imaging Systems Can Improve Patient Comfort: A Prospective 0.55T-1.5T-Scanner Comparison.

OBJECTIVES: The objectives of this study were to assess patient comfort when imaged on a newly introduced 0.55T low-field magnetic resonance (MR) scanner system with a wider bore opening compared to a conventional 1.5T MR scanner system. MATERIALS AND METHODS: In this prospective study, fifty patients (mean age: 66.2 ± 17.0 years, 22 females, 28 males) underwent subsequent magnetic resonance imaging (MRI) examinations with matched imaging protocols at 0.55T (MAGNETOM FreeMax, Siemens Healthineers; Erlangen, Germany) and 1.5T (MAGNETOM Avanto Fit, Siemens Healthineers; Erlangen, Germany) on the same day. MRI performed between 05/2021 and 07/2021 was included for analysis. The 0.55T MRI system had a bore opening of 80 cm, while the bore diameter of the 1.5T scanner system was 60 cm. Four patient groups were defined by imaged body regions: (1) cranial or cervical spine MRI using a head/neck coil (n = 27), (2) lumbar or thoracic spine MRI using only the in-table spine coils (n = 10), (3) hip MRI using a large flex coil (n = 8) and (4) upper- or lower-extremity MRI using small flex coils (n = 5). Following the MRI examinations, patients evaluated (1) sense of space, (2) noise level, (3) comfort, (4) coil comfort and (5) overall examination impression on a 5-point Likert-scale (range: 1= "much worse" to 5 = "much better") using a questionnaire. Maximum noise levels of all performed imaging studies were measured in decibels (dB) by a sound level meter placed in the bore center. RESULTS: Sense of space was perceived to be "better" or "much better" by 84% of patients for imaging examinations performed on the 0.55T MRI scanner system (mean score: 4.34 ± 0.75). Additionally, 84% of patients rated noise levels as "better" or "much better" when imaged on the low-field scanner system (mean score: 3.90 ± 0.61). Overall sensation during the imaging examination at 0.55T was rated as "better" or "much better" by 78% of patients (mean score: 3.96 ± 0.70). Quantitative assessment showed significantly reduced maximum noise levels for all 0.55T MRI studies, regardless of body region compared to 1.5T, i.e., brain MRI (83.8 ± 3.6 dB vs. 89.3 ± 5.4 dB; p = 0.04), spine MRI (83.7 ± 3.7 dB vs. 89.4 ± 2.6 dB; p = 0.004) and hip MRI (86.3 ± 5.0 dB vs. 89.1 ± 1.4 dB; p = 0.04). CONCLUSIONS: Patients perceived 0.55T new-generation low-field MRI to be more comfortable than conventional 1.5T MRI, given its larger bore opening and reduced noise levels during image acquisition. Therefore, new concepts regarding bore design and noise level reduction of MR scanner systems may help to reduce patient anxiety and improve well-being when undergoing MR imaging.

Clinical determinants and neural correlates of presbyphagia in community-dwelling older adults.

Background: "Presbyphagia" refers to characteristic age-related changes in the complex neuromuscular swallowing mechanism. It has been hypothesized that cumulative impairments in multiple domains affect functional reserve of swallowing with age, but the multifactorial etiology and postulated compensatory strategies of the brain are incompletely understood. This study investigates presbyphagia and its neural correlates, focusing on the clinical determinants associated with adaptive neuroplasticity. Materials and methods: 64 subjects over 70 years of age free of typical diseases explaining dysphagia received comprehensive workup including flexible endoscopic evaluation of swallowing (FEES), magnetoencephalography (MEG) during swallowing and pharyngeal stimulation, volumetry of swallowing muscles, laboratory analyzes, and assessment of hand-grip-strength, nutritional status, frailty, olfaction, cognition and mental health. Neural MEG activation was compared between participants with and without presbyphagia in FEES, and associated clinical influencing factors were analyzed. Presbyphagia was defined as the presence of oropharyngeal swallowing alterations e.g., penetration, aspiration, pharyngeal residue pooling or premature bolus spillage into the piriform sinus and/or laryngeal vestibule. Results: 32 of 64 participants showed swallowing alterations, mainly characterized by pharyngeal residue, whereas the airway was rarely compromised. In the MEG analysis, participants with presbyphagia activated an increased cortical sensorimotor network during swallowing. As major clinical determinant, participants with swallowing alterations exhibited reduced pharyngeal sensation. Presbyphagia was an independent predictor of a reduced nutritional status in a linear regression model. Conclusions: Swallowing alterations frequently occur in otherwise healthy older adults and are associated with decreased nutritional status. Increased sensorimotor cortical activation may constitute a compensation attempt to uphold swallowing function due to sensory decline. Further studies are needed to clarify whether the swallowing alterations observed can be considered physiological per se or whether the concept of presbyphagia may need to be extended to a theory with a continuous transition between presbyphagia and dysphagia.

Potential of Stroke Imaging Using a New Prototype of Low-Field MRI: A Prospective Direct 0.55 T/1.5 T Scanner Comparison.

Objectives: Ischemic stroke is a leading cause of mortality and acquired disability worldwide and thus plays an enormous health-economic role. Imaging of choice is computed-tomographic (CT) or magnetic resonance imaging (MRI), especially diffusion-weighted (DW) sequences. However, MR imaging is associated with high costs and therefore has a limited availability leading to low-field-MRI techniques increasingly coming into focus. Thus, the aim of our study was to assess the potential of stroke imaging with low-field MRI. Material and Methods: A scanner comparison was performed including 27 patients (17 stroke cohort, 10 control group). For each patient, a brain scan was performed first with a 1.5T scanner and afterwards with a 0.55T scanner. Scan protocols were as identical as possible and optimized. Data analysis was performed in three steps: All DWI/ADC (apparent diffusion coefficient) and FLAIR (fluid attenuated inversion recovery) sequences underwent Likert rating with respect to image impression, resolution, noise, contrast, and diagnostic quality and were evaluated by two radiologists regarding number and localization of DWI and FLAIR lesions in a blinded fashion. Then segmentation of lesion volumes was performed by two other radiologists on DWI/ADC and FLAIR. Results: DWI/ADC lesions could be diagnosed with the same reliability by the most experienced reader in the 0.55T and 1.5T sequences (specificity 100% and sensitivity 92.9%, respectively). False positive findings did not occur. Detection of number/location of FLAIR lesions was mostly equivalent between 0.55T and 1.5T sequences. No significant difference (p = 0.789−0.104) for FLAIR resolution and contrast was observed regarding Likert scaling. For DWI/ADC noise, the 0.55T sequences were significantly superior (p < 0.026). Otherwise, the 1.5T sequences were significantly superior (p < 0.029). There was no significant difference in infarct volume and volume of infarct demarcation between the 0.55T and 1.5T sequences, when detectable. Conclusions: Low-field MRI stroke imaging at 0.55T may not be inferior to scanners with higher field strengths and thus has great potential as a low-cost alternative in future stroke diagnostics. However, there are limitations in the detection of very small infarcts. Further technical developments with follow-up studies must show whether this problem can be solved.

New imaging score for outcome prediction in basilar artery occlusion stroke.

OBJECTIVE: In ischemic posterior circulation stroke, the utilization of standardized image scores is not established in daily clinical practice. We aimed to test a novel imaging score that combines the collateral status with the rating of the posterior circulation Acute Stroke Prognosis Early CT score (pcASPECTS). We hypothesized that this score (pcASCO) predicts functional outcome and malignant cerebellar edema (MCE). METHODS: Ischemic stroke patients with acute BAO who received multimodal-CT and underwent thrombectomy on admission at two comprehensive stroke centers were analyzed. The posterior circulation collateral score by van der Hoeven et al was added to the pcASPECTS to define pcASCO as a 20-point score. Multivariable logistic regression analyses were performed to predict functional independence at day 90, assessed using modified Rankin Scale scores, and occurrence of MCE in follow-up CT using the established Jauss scale score as endpoints. RESULTS: A total of 118 patients were included, of which 84 (71%) underwent successful thrombectomy. Based on receiver operating characteristic curve analysis, pcASCO ≥ 14 classified functional independence with higher discriminative power (AUC: 0.83, 95%CI: 0.71-0.91) than pcASPECTS (AUC: 0.74). In multivariable logistic regression analysis, pcASCO was significantly and independently associated with functional independence (aOR: 1.91, 95%CI: 1.25-2.92, p = 0.003), and MCE (aOR: 0.71, 95%CI: 0.53-0.95, p = 0.02). CONCLUSION: The pcASCO could serve as a simple and feasible imaging tool to assess BAO stroke patients on admission and might be tested as a complementary tool to select patients for thrombectomy in uncertain situations, or to predict clinical outcome. KEY POINTS: • The neurological assessment of basilar artery occlusion stroke patients can be challenging and there are yet no validated imaging scores established in daily clinical practice. • The pcASCO combines the rating of early ischemic changes with the status of the intracranial posterior circulation collaterals. • The pcASCO showed high diagnostic accuracy to predict functional outcome and malignant cerebellar edema and could serve as a simple and feasible imaging tool to support treatment selection in uncertain situations, or to predict clinical outcome.

Higher baseline blood glucose is associated with reduced likelihood for successful recanalization in patients with basilar artery occlusion.

PURPOSE: Evidence regarding the effect of mechanical thrombectomy (MT) of basilar artery occlusion (BAO) stroke is yet sparse. As successful recanalization has been suggested as major determinant of outcome, the early identification of modifiable factors associated with successful recanalization could be of importance to improve functional outcome. Hyperglycemia has been associated with enhanced thrombin generation and unfavorably altered clot features. OBJECTIVE: We hypothesized that serum baseline glucose is associated with likelihood of vessel recanalization mediated by collateral quality and clot burden in BAO stroke. METHODS: BAO stroke patients who received multimodal CT on admission were analyzed. The association of vessel recanalization defined using modified Thrombolysis in cerebral infarction scale (mTICI) scores 2b-3, and baseline imaging and clinical parameters were tested in logistic regression analyses. Collateral quality and clot burden were evaluated using the Basilar Artery on CT-Angiography (BATMAN) score. RESULTS: Out of 117 BAO patients, 91 patients (78%) underwent MT. In 70 patients (77%), successful recanalization could be achieved (mTICI 2b/3). In multivariable logistic regression analysis, only a higher BGL (aOR 0.97, 95% CI 0.96-0.99, p = 0.03) and higher BATMAN score (aOR 1.77, 95% CI 1.11-2.82, p = 0.02) were independently associated with vessel recanalization. Application of alteplase, or time from symptom onset-imaging revealed no independent association with recanalization status. CONCLUSION: Higher BGL was significantly associated with reduced likelihood for recanalization success besides BATMAN score as a measure of collateral quality and clot burden. BGL could be tested as a modifiable parameter to increase likelihood for recanalization in BAO stroke, aiming to improve functional outcome.

Posterior circulation collateral flow modifies the effect of thrombectomy on outcome in acute basilar artery occlusion.

BACKGROUND: In basilar artery occlusion stroke, the impact of the collateral circulation on infarct progression in the context of endovascular treatment is yet poorly studied. AIM: This study investigates the impact of the posterior circulation collateral score (PCCS) on functional outcome according to the extent of early ischemic changes and treatment. We hypothesized that the presence of collaterals, quantified by the PCCS, mediates the effect of endovascular treatment on functional outcome in patients with acute basilar artery occlusion. METHODS: In this multicenter observational study, patients with basilar artery occlusion and admission computed tomography were analyzed. At baseline, Posterior circulation Acute Stroke Prognosis Early Computed Tomography score (pcASPECTS) was assessed and PCCS was quantified using an established 10-point grading system. Logistic regression analyses were performed to identify factors associated with good functional outcome (modified Rankin Scale scores 0-2 at day 90). RESULTS: A total of 151 patients were included, of which 112 patients (74%) underwent endovascular treatment. In patients with a better PCCS (>5), the rate of good outcome was significantly higher (55% vs. 11%; p = 0.001). After adjusting for PCCS, vessel recanalization was significantly associated with improved functional outcome (aOR: 4.53, 95%CI: 1.25-16.4, p = 0.02), while there was no association between recanalization status and outcome in univariable analysis. Patients with low pcASPECTS generally showed very poor outcomes (mean modified Rankin Scale score 5.3, 95%CI: 4.9-5.8). CONCLUSION: PCCS modified the effect of recanalization on functional outcome, particularly in patients with less pronounced ischemic changes in admission computed tomography. These results should be validated to improve patient selection for endovascular treatment in basilar artery occlusion, particularly in uncertain indications, or to triage patients at risk for very poor outcomes.

Nucleus accumbens projections: Validity and reliability of fiber reconstructions based on high-resolution diffusion-weighted MRI.

Clinical effects of deep brain stimulation are largely mediated by the activation of myelinated axons. Hence, increasing attention has been paid in the past on targeting white matter tracts in addition to gray matter. Aims of the present study were: (i) visualization of discrete afferences and efferences of the nucleus accumbens (NAc), supposed to be a major hub of neural networks relating to mental disorders, using probabilistic fiber tractography and a data driven approach, and (ii) validation of the applied methodology for standardized routine clinical applications. MR-data from 11 healthy subjects and 7 measurement sessions each were acquired on a 3T MRI-scanner. For probabilistic fiber tracking the NAc as a seed region and the medial prefrontal cortex (mPFC), anterior cingulate cortex (ACC), amygdala (AMY), hippocampus (HPC), dorsomedial thalamus (dmT) and ventral tegmental area (VTA) as target regions were segmented for each subject and both hemispheres. To quantitatively assess the reliability and stability of the reconstructions, we filtered and clustered the individual fiber-tracts (NAc to target) for each session and subject and performed a point-by-point calculation of the maximum cluster distances for intra-subject comparison. The connectivity patterns formed by the obtained fibers were in good concordance with published data from tracer and/or fiber-dissection studies. Furthermore, the reliability assessment of the (NAc to target)-fiber-tracts yielded to high correlations between the obtained clustered-tracts. Using DBS with directional lead technology, the workflow elaborated in this study may guide selective electrical stimulation of NAc projections.

Imaging-Based Outcome Prediction of Acute Intracerebral Hemorrhage.

We hypothesized that imaging-only-based machine learning algorithms can analyze non-enhanced CT scans of patients with acute intracerebral hemorrhage (ICH). This retrospective multicenter cohort study analyzed 520 non-enhanced CT scans and clinical data of patients with acute spontaneous ICH. Clinical outcome at hospital discharge was dichotomized into good outcome and poor outcome using different modified Rankin Scale (mRS) cut-off values. Predictive performance of a random forest machine learning approach based on filter- and texture-derived high-end image features was evaluated for differentiation of functional outcome at mRS 2, 3, and 4. Prediction of survival (mRS ≤ 5) was compared to results of the ICH Score. All models were tuned, validated, and tested in a nested 5-fold cross-validation approach. Receiver-operating-characteristic area under the curve (ROC AUC) of the machine learning classifier using image features only was 0.80 (95% CI [0.77; 0.82]) for predicting mRS ≤ 2, 0.80 (95% CI [0.78; 0.81]) for mRS ≤ 3, and 0.79 (95% CI [0.77; 0.80]) for mRS ≤ 4. Trained on survival prediction (mRS ≤ 5), the classifier reached an AUC of 0.80 (95% CI [0.78; 0.82]) which was equivalent to results of the ICH Score. If combined, the integrated model showed a significantly higher AUC of 0.84 (95% CI [0.83; 0.86], P value <0.05). Accordingly, sensitivities were significantly higher at Youden Index maximum cut-offs (77% vs. 74% sensitivity at 76% specificity, P value <0.05). Machine learning-based evaluation of quantitative high-end image features provided the same discriminatory power in predicting functional outcome as multidimensional clinical scoring systems. The integration of conventional scores and image features had synergistic effects with a statistically significant increase in AUC.

Early Prediction of Malignant Cerebellar Edema in Posterior Circulation Stroke Using Quantitative Lesion Water Uptake.

BACKGROUND: Malignant cerebellar edema (MCE) is a life-threatening complication of ischemic posterior circulation stroke that requires timely diagnosis and management. Yet, there is no established imaging biomarker that may serve as predictor of MCE. Early edematous water uptake can be determined using quantitative lesion water uptake, but this biomarker has only been applied in anterior circulation strokes. OBJECTIVE: To test the hypothesis that lesion water uptake in early posterior circulation stroke predicts MCE. METHODS: A total 179 patients with posterior circulation stroke and multimodal admission CT were included. A total of 35 (19.5%) patients developed MCE defined by using an established 10-point scale in follow-up CT, of which ≥4 points are considered malignant. Posterior circulation net water uptake (pcNWU) was quantified in admission CT based on CT densitometry and compared with posterior circulation Acute Stroke Prognosis Early CT Score (pc-ASPECTS) as predictor of MCE using receiver operating curve (ROC) analysis and logistic regression analysis. RESULTS: Acute pcNWU within the early ischemic lesion was 24.6% (±8.4) for malignant and 7.2% (±7.4) for nonmalignant infarctions, respectively (P < .0001). Based on ROC analysis, pcNWU above 14.9% identified MCE with high discriminative power (area under the curve: 0.94; 95% CI: 0.89-0.97). Early pcNWU (odds ratio [OR]: 1.28; 95% CI: 1.15-1.42, P < .0001) and pc-ASPECTS (OR: 0.71, 95% CI: 0.53-0.95, P = .02) were associated with MCE, adjusted for age and recanalization status. CONCLUSION: Quantitative pcNWU in early posterior circulation stroke is an important marker for MCE. Besides pc-ASPECTS, lesion water uptake measurements may further support identifying patients at risk for MCE at an early stage indicating stricter monitoring and consideration for further therapeutic measures.

Predictors of Successful First-Pass Thrombectomy with a Balloon Guide Catheter: Results of a Decision Tree Analysis.

Complete recanalization after a single retrieval maneuver is an interventional goal in acute ischemic stroke and an independent factor for good clinical outcome. Anatomical biomarkers for predicting clot removal difficulties have not been comprehensively analyzed and await unused. We retrospectively evaluated 200 consecutive patients who suffered acute stroke and occlusion of the anterior circulation and were treated with mechanical thrombectomy through a balloon guide catheter (BGC). The primary objective was to evaluate the influence of carotid tortuosity and BGC positioning on the one-pass Modified Thrombolysis in Cerebral Infarction Scale (mTICI) 3 rate, and secondarily, the influence of communicating arteries on the angiographic results. After the first-pass mTICI 3, recanalization fell from 51 to 13%. The regression models and decision tree (supervised machine learning) results concurred: carotid tortuosity was the main constraint on efficacy, reducing the likelihood of mTICI 3 after one pass to 30%. BGC positioning was relevant only in carotid arteries without elongation: BGCs located in the distal internal carotid artery (ICA) had a 70% probability of complete recanalization after one pass, dropping to 43% if located in the proximal ICA. These findings demonstrate that first-pass mTICI 3 is influenced by anatomical and interventional factors capable of being anticipated, enabling the BGC technique to be adapted to patient's anatomy to enhance effectivity.

Posterior circulation stroke: machine learning-based detection of early ischemic changes in acute non-contrast CT scans.

OBJECTIVES: Triage of patients with basilar artery occlusion for additional imaging diagnostics, therapy planning, and initial outcome prediction requires assessment of early ischemic changes in early hyperacute non-contrast computed tomography (NCCT) scans. However, accuracy of visual evaluation is impaired by inter- and intra-reader variability, artifacts in the posterior fossa and limited sensitivity for subtle density shifts. We propose a machine learning approach for detecting early ischemic changes in pc-ASPECTS regions (Posterior circulation Alberta Stroke Program Early CT Score) based on admission NCCTs. METHODS: The retrospective study includes 552 pc-ASPECTS regions (144 with infarctions in follow-up NCCTs) extracted from pre-therapeutic early hyperacute scans of 69 patients with basilar artery occlusion that later underwent successful recanalization. We evaluated 1218 quantitative image features utilizing random forest algorithms with fivefold cross-validation for the ability to detect early ischemic changes in hyperacute images that lead to definitive infarctions in follow-up imaging. Classifier performance was compared to conventional readings of two neuroradiologists. RESULTS: Receiver operating characteristic area under the curves for detection of early ischemic changes were 0.70 (95% CI [0.64; 0.75]) for cerebellum to 0.82 (95% CI [0.77; 0.86]) for thalamus. Predictive performance of the classifier was significantly higher compared to visual reading for thalamus, midbrain, and pons (P value < 0.05). CONCLUSIONS: Quantitative features of early hyperacute NCCTs can be used to detect early ischemic changes in pc-ASPECTS regions. The classifier performance was higher or equal to results of human raters. The proposed approach could facilitate reproducible analysis in research and may allow standardized assessments for outcome prediction and therapy planning in clinical routine.

Clot Analog Attenuation in Non-contrast CT Predicts Histology: an Experimental Study Using Machine Learning.

Exact histological clot composition remains unknown. The purpose of this study was to identify the best imaging variables to be extrapolated on clot composition and clarify variability in the imaging of thrombi by non-contrast CT. Using a CT-phantom and covering a wide range of histologies, we analyzed 80 clot analogs with respect to X-ray attenuation at 24 and 48 h after production. The mean, maximum, and minimum HU values for the axial and coronal reconstructions were recorded. Each thrombus underwent a corresponding histological analysis, together with a laboratory analysis of water and iron contents. Decision trees, a type of supervised machine learning, were used to select the primary variable altering attenuation and the best parameter for predicting histology. The decision trees selected red blood cells (RBCs) for correlation with all attenuation parameters (p < 0.001). Conversely, maximum attenuation on axial CT offered the greatest accuracy for discriminating up to four groups of clot histology (p < 0.001). Similar RBC-rich thrombi displayed variable imaging associated with different iron (p = 0.023) and white blood cell contents (p = 0.019). Water content varied among the different histologies but did not in itself account for the differences in attenuation. Independent factors determining clot attenuation were the RBCs (ß = 0.33, CI = 0.219-0.441, p < 0.001) followed by the iron content (ß = 0.005, CI = 0.0002-0.009, p = 0.042). Our findings suggest that it is possible to extract more and valuable information from NCCT that can be extrapolated to provide insights into clot histological and chemical composition.