GLORIA

GEOMAR Library Ocean Research Information Access

X

Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
  • 1
    Online Resource
    Online Resource
    Imaging-based outcome prediction in posterior circulation stroke
    Springer Science and Business Media LLC ; 2022
    In:  Journal of Neurology Vol. 269, No. 7 ( 2022-07), p. 3800-3809
    Details
    In: Journal of Neurology, Springer Science and Business Media LLC, Vol. 269, No. 7 ( 2022-07), p. 3800-3809
    Abstract: We developed a machine learning model to allow early functional outcome prediction for patients presenting with posterior circulation (pc)-stroke based on CT-imaging and clinical data at admission. The proposed algorithm utilizes quantitative information from automated multidimensional assessments of posterior circulation Acute Stroke Prognosis Early CT-Score (pc-ASPECTS) regions. Discriminatory power was compared to predictions based on conventional pc-ASPECTS ratings. Methods We retrospectively analyzed non-contrast CTs and clinical data of 172 pc-stroke patients. 90 days outcome was dichotomized into good and poor using modified Rankin Scale (mRS) cut-offs. Predictive performance was assessed for outcome differentiation at mRS 2, 3, 4 and survival prediction (mRS ≤ 5) using random forest algorithms. Results were compared to conventional pc-ASPECTS and clinical parameters. Models were evaluated in a nested fivefold cross-validation approach. Results Receiver operating characteristic areas under the curves (ROC-AUCs) of the test sets using conventionally rated pc-ASPECTS reached 0.63 for mRS ≤ 4 to 0.68 for mRS ≤ 5 and 0.73 for mRS ≤ 5 to 0.85 for mRS ≤ 2 if clinical data were considered. Pure imaging-based machine learning classifier ROC-AUCs were lowest for mRS ≤ 4 (0.81) and highest for mRS ≤ 5 (0.87). The combined clinical data and machine learning-based model had the highest predictive performance with ROC-AUCs reaching 0.90 for mRS ≤ 2. Conclusion Machine learning-based evaluation of pc-ASPECTS regions predicts functional outcome of pc-stroke patients with higher accuracy than conventional assessments. This could optimize triage for additional diagnostics and allocation of best possible medical care and might allow required arrangements of the social environment at an early point of time.
    Type of Medium: Online Resource
    ISSN: 0340-5354 , 1432-1459
    URL: Article
    DOI: 10.1007/s00415-022-11010-4
    RVK:
    XA 10000
    Language: English
    Publisher: Springer Science and Business Media LLC
    Publication Date: 2022
    detail.hit.zdb_id: 1421299-7
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 2
    Online Resource
    Online Resource
    Thrombectomy for M2 Occlusions: Predictors of Successful and Futile Recanalization
    Ovid Technologies (Wolters Kluwer Health) ; 2023
    In:  Stroke Vol. 54, No. 8 ( 2023-08), p. 2002-2012
    Details
    In: Stroke, Ovid Technologies (Wolters Kluwer Health), Vol. 54, No. 8 ( 2023-08), p. 2002-2012
    Abstract: Patient-specific factors associated with successful recanalization in mechanical thrombectomy (MT) have been evaluated for acute ischemic stroke with large vessel occlusion. However, MT for M2 occlusions is still a matter of debate, and predictors of successful and futile recanalization have not been assessed in detail. We sought to identify predictors of recanalization success in patients with M2 occlusions undergoing MT based on large-scale clinical data. METHODS: All patients prospectively enrolled in the German Stroke Registry (May, 2015 to December, 2021) were screened (N=13 082). Inclusion criteria for the complete case analysis were isolated M2 occlusions. Standard descriptive statistics and multivariable logistic regression analysis were used to identify factors associated with successful recanalization (Thrombolysis in Cerebral Infarction [TICI]≥2b), complete recanalization (TICI=3) and futile recanalization (TICI≥2b with 90-day modified Rankin Scale [mRS] score 〉 2). RESULTS: One thousand two hundred ninety-four patients were included, thereof 439 (33.9%) with TICI=2b and 643 (49.7%) with TICI=3. Five hundred sixty-nine (44%) patients had good functional outcome (90-day mRS score ≤2). In multivariable logistic regression, general anesthesia (adjusted odds ratio [aOR], 1.47 [95% CI, 1.05–2.09] ; P 〈 0.05) was associated with higher probability of TICI≥2b while intraprocedural change from local to general anesthesia (aOR, 0.49 [0.26–0.95]; P 〈 0.05) and higher pre-mRS (aOR, 0.75 [0.67–0.85]; P 〈 0.001) lowered probability of successful recanalization. Futile recanalization was associated with higher age (aOR, 1.05 [1.04–1.07]; P 〈 0.001), higher prestroke mRS (aOR, 3.12 [2.49–3.91]; P 〈 0.001), higher NIHSS at admission (aOR, 1.11 [1.08–1.14]; P 〈 0.001), diabetes (aOR, 1.96 [1.38–2.8]; P 〈 0.001), higher number of passes (aOR, 1.29 [1.14–1.46]; P 〈 0.001), and adverse events (aOR, 1.82 [1.2–2.74]; P 〈 0.01). Higher Alberta Stroke Program Early CT Score (aOR, 0.85 [0.76–0.94]; P 〈 0.01) and IV thrombolysis (aOR, 0.71 [0.52–0.97]; P 〈 0.05) reduced risk of futile recanalization. CONCLUSIONS: In patients with M2 occlusions, successful recanalization was significantly associated with general anesthesia and low prestroke mRS, while intraprocedural change from conscious sedation to general anesthesia increased risk of unsuccessful recanalization, presumably caused by difficult anatomy and movement of patients in these cases. Futile recanalization was associated with severe prestroke mRS, comorbidity diabetes, number of passes and adverse events during treatment. IV thrombolysis reduced the risk of futile recanalization.
    Type of Medium: Online Resource
    ISSN: 0039-2499 , 1524-4628
    URL: Article
    DOI: 10.1161/STROKEAHA.123.043285
    RVK:
    XA 10000
    Language: English
    Publisher: Ovid Technologies (Wolters Kluwer Health)
    Publication Date: 2023
    detail.hit.zdb_id: 1467823-8
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 3
    Online Resource
    Online Resource
    Thrombectomy in M2 occlusion compared to M1 occlusion: treatment effects of Thrombolysis In Cerebral Infarction (TICI) 2b and TICI 3 recanalization on functional outcome
    BMJ ; 2023
    In:  Journal of NeuroInterventional Surgery
    Details
    In: Journal of NeuroInterventional Surgery, BMJ
    Abstract: Emerging data suggest that mechanical thrombectomy (MT) might also be safe and efficient for medium and distal occlusions. This study aims to compare average treatment effects on functional outcome of different degrees of recanalization after MT in patients with M2 occlusion and M1 occlusion. Methods All patients enrolled in the German Stroke Registry (GSR) between June 2015 and December 2021 were analyzed. Inclusion criteria were stroke with primary M1 occlusion or M2 occlusion, and availability of relevant clinical data. 4259 patients were included, thereof 1353 with M2 occlusion and 2906 with M1 occlusion. Treatment effects were analyzed using double-robust inverse-probability-weighted regression-adjustment (IPWRA) estimators to control for confounding covariates. Binarized endpoint metrics were defined as good outcome with modified Rankin Scale (mRS) ≤2 at 90 days, and linearized endpoint metrics were defined as mRS shift pre-stroke to 90 days. Effects were evaluated for near complete recanalization (Thrombolysis In Cerebral Infarction scale (TICI) 2b) and complete recanalization (TICI 3). Results Treatment effect estimation for TICI ≥2b versus TICI 〈 2b in M2 occlusions showed an increase in the probability of a good outcome from 27% to 47% with a number-needed-to-treat (NNT) of 5. For M1 occlusions the probability of a good outcome increased from 16% to 38% with NNT 4.5. TICI 3 versus TICI 2b increased the probability of a good outcome by 7 percentage points in M1 occlusions; for M2 occlusions the beneficial effect was not significant. Conclusions Results suggest that successful recanalization with TICI ≥2b versus TICI 〈 2b after MT in M2 occlusions provides significant patient benefit with treatment effects comparable to M1 occlusions. The probability of functional independence increased by 20 percentage points (NNT 5) and stroke-related mRS increase was reduced by 0.9 mRS points. In contrast to M1 occlusions, complete recanalization TICI 3 versus TICI 2b had lower additional beneficial effect.
    Type of Medium: Online Resource
    ISSN: 1759-8478 , 1759-8486
    URL: Article
    DOI: 10.1136/jnis-2022-019898
    Language: English
    Publisher: BMJ
    Publication Date: 2023
    detail.hit.zdb_id: 2506028-4
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 4
    Online Resource
    Online Resource
    How Much of the Thrombectomy Related Improvement in Functional Outcome Is Already Apparent at 24 Hours and at Hospital Discharge?
    Ovid Technologies (Wolters Kluwer Health) ; 2022
    In:  Stroke Vol. 53, No. 9 ( 2022-09), p. 2828-2837
    Details
    In: Stroke, Ovid Technologies (Wolters Kluwer Health), Vol. 53, No. 9 ( 2022-09), p. 2828-2837
    Abstract: Early neurological status has been described as predictor of functional outcome in patients with anterior circulation stroke after mechanical thrombectomy. It remains unclear to what proportion the improvement of functional outcome at day 90 is already apparent at 24 hours and at hospital discharge and how later factors impact outcome. Methods: All patients enrolled in the German Stroke Registry (June 2015–December 2019) with anterior circulation stroke and availability of baseline data and neurological status were included. A mediation analysis was conducted to investigate the effect of successful recanalization (Thrombolysis in Cerebral Infarction scale score ≥2b) on good functional outcome (modified Rankin Scale score ≤2 at day 90) with mediation through neurological status (National Institutes of Health Stroke Scale [NIHSS] at 24 hours and at hospital discharge). Results: Three thousand fifty-seven patients fulfilled the inclusion criteria, thereof 2589 (85%) with successful recanalization and 1180 (39%) with good functional outcome. In a multivariate logistic regression analysis, probability of good outcome was significantly associated with age (odds ratio [95% CI], 0.95 [0.94–0.96] ), prestroke modified Rankin Scale (0.48 [0.42–0.55]), admission-NIHSS (0.96 [0.94–0.98] ), 24-hour NIHSS (0.83 [0.81–0.84]), diabetes (0.56 [0.43–0.72] ), proximal middle cerebral artery occlusions (0.78 [0.62–0.97]), passes (0.88 [0.82–0.95] ), Alberta Stroke Program Early CT Score (1.07 [1.00–1.14]), successful recanalization (2.39 [1.68–3.43] ), intracerebral hemorrhage (0.51 [0.35–0.73]), and recurrent strokes (0.54 [0.32–0.92] ). Mediation analysis showed a 20 percentage points (95% CI‚ 17–24 percentage points) increase of probability of good functional outcome after successful recanalization. Fifty-four percent (95% CI‚ 44%–66%) of the improvement in functional outcome was explained by 24-hour NIHSS and 75% (95% CI‚ 62%–90%) by NIHSS at hospital discharge. Conclusions: Fifty-four percent of the improvement in functional outcome after successful recanalization is apparent in NIHSS at 24 hours, 75% in NIHSS at hospital discharge. Other unknown factors not apparent in NIHSS at the 2 time points investigated account for the remaining effect on long term outcome, suggesting, among others, clinical relevance of delayed neurological improvement and deterioration. Registration: URL: https://www.clinicaltrials.gov ; Unique identifier: NCT03356392.
    Type of Medium: Online Resource
    ISSN: 0039-2499 , 1524-4628
    URL: Article
    DOI: 10.1161/STROKEAHA.121.037888
    RVK:
    XA 10000
    Language: English
    Publisher: Ovid Technologies (Wolters Kluwer Health)
    Publication Date: 2022
    detail.hit.zdb_id: 1467823-8
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 5
    Online Resource
    Online Resource
    Early surrogates of outcome after thrombectomy in posterior circulation stroke
    Wiley ; 2022
    In:  European Journal of Neurology Vol. 29, No. 11 ( 2022-11), p. 3296-3306
    Details
    In: European Journal of Neurology, Wiley, Vol. 29, No. 11 ( 2022-11), p. 3296-3306
    Abstract: Early surrogates for functional outcome in anterior circulation stroke have been described with the National Institute of Health Stroke Scale (NIHSS) at 24 h being reported as the most accurate metric. We compare discriminatory power of established definitions of early neurological improvement (ENI) and NIHSS scores at admission and 24 h to predict functional outcome at 90 days after thrombectomy in posterior circulation stroke (PCS). Methods All patients enrolled in the German Stroke Registry (June 2015–December 2019) with PCS and at least vertebral or basilar artery occlusions were included. NIHSS admission, 24 h and ENI definitions (improvement of 8/10 NIHSS points or 0/1 NIHSS points at 24 h) were compared for predicting functional outcome at 90 days. Favourable and good outcome were defined as modified Rankin Scale (mRS) 0–2 and 0–3. Multivariable logistic regression analysis was conducted to identify factors impairing predictive power. Results Three hundred and eighty‐seven patients were included. NIHSS 24 h had the highest discriminative power with receiver operator characteristics area under the curve of 0.87 (95% confidence interval: 0.83; 0.90) for good and 0.89 (0.85; 0.92) for favourable outcome; optimal cut‐off values were ≤9 and ≤5. Higher age (odds ratio = 1.10 [1.05; 1.16]), adverse events during treatment (9.46 [1.52; 72.5] ) and until discharge (18.34 [2.33; 172]) and high NIHSS scores at 24 h (1.29 [1.10; 1.53] ) were independent predictors for turning the outcome prognosis from good (mRS ≤3) to poor (mRS ≥4). Conclusions NIHSS 24 h ≤9 points serves best as surrogate for good functional outcome after thrombectomy in PCS. Advanced age, severe neurological symptoms at admission and adverse events decrease its predictive value.
    Type of Medium: Online Resource
    ISSN: 1351-5101 , 1468-1331
    URL: Issue
    URL: Article
    DOI: 10.1111/ene.v29.11
    DOI: 10.1111/ene.15519
    Language: English
    Publisher: Wiley
    Publication Date: 2022
    detail.hit.zdb_id: 2020241-6
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 6
    Online Resource
    Online Resource
    Discordant and Converting Receptor Expressions in Brain Metastases from Breast Cancer: MRI-Based Non-Invasive Receptor Status Tracking
    MDPI AG ; 2023
    In:  Cancers Vol. 15, No. 11 ( 2023-05-23), p. 2880-
    Details
    In: Cancers, MDPI AG, Vol. 15, No. 11 ( 2023-05-23), p. 2880-
    Abstract: Discordance and conversion of receptor expressions in metastatic lesions and primary tumors is often observed in patients with brain metastases from breast cancer. Therefore, personalized therapy requires continuous monitoring of receptor expressions and dynamic adaptation of applied targeted treatment options. Radiological in vivo techniques may allow receptor status tracking at high frequencies at low risk and cost. The present study aims to investigate the potential of receptor status prediction through machine-learning-based analysis of radiomic MR image features. The analysis is based on 412 brain metastases samples from 106 patients acquired between 09/2007 and 09/2021. Inclusion criteria were as follows: diagnosed cerebral metastases from breast cancer; histopathology reports on progesterone (PR), estrogen (ER), and human epidermal growth factor 2 (HER2) receptor status; and availability of MR imaging data. In total, 3367 quantitative features of T1 contrast-enhanced, T1 non-enhanced, and FLAIR images and corresponding patient age were evaluated utilizing random forest algorithms. Feature importance was assessed using Gini impurity measures. Predictive performance was tested using 10 permuted 5-fold cross-validation sets employing the 30 most important features of each training set. Receiver operating characteristic areas under the curves of the validation sets were 0.82 (95% confidence interval [0.78; 0.85] ) for ER+, 0.73 [0.69; 0.77] for PR+, and 0.74 [0.70; 0.78] for HER2+. Observations indicate that MR image features employed in a machine learning classifier could provide high discriminatory accuracy in predicting the receptor status of brain metastases from breast cancer.
    Type of Medium: Online Resource
    ISSN: 2072-6694
    URL: Article
    DOI: 10.3390/cancers15112880
    Language: English
    Publisher: MDPI AG
    Publication Date: 2023
    detail.hit.zdb_id: 2527080-1
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 7
    Online Resource
    Online Resource
    How much of the outcome improvement after successful recanalization is explained by follow-up infarct volume reduction?
    BMJ ; 2023
    In:  Journal of NeuroInterventional Surgery
    Details
    In: Journal of NeuroInterventional Surgery, BMJ
    Abstract: Follow-up infarct volume (FIV) is used as surrogate for treatment efficiency in mechanical thrombectomy (MT). However, previous works suggest that MT-related FIV reduction has only limited association with outcome comparing MT independently of recanalization success versus medical care. It remains unclear to what extent the relationship between successful recanalization versus persistent occlusion and functional outcome is explained by FIV reduction. Objective To determine whether FIV mediates the relationship between successful recanalization and functional outcome. Methods All patients from our institution enrolled in the German Stroke Registry (May 2015–December 2019) with anterior circulation stroke; availability of the relevant clinical data, and follow-up-CT were analyzed. The effect of FIV reduction on functional outcome (90-day modified Rankin Scale (mRS) score ≤2) after successful recanalization (Thrombolysis in Cerebral Infarction ≥2b) was quantified using mediation analysis. Results 429 patients were included, of whom, 309 (72 %) had successful recanalization and 127 (39%) had good functional outcome. Good outcome was associated with age (OR=0.89, P 〈 0.001), pre-stroke mRS score (OR=0.38, P 〈 0.001), FIV (OR=0.98, P 〈 0.001), hypertension (OR=2.08, P 〈 0.05), and successful recanalization (OR=3.57, P 〈 0.01). Using linear regression in the mediator pathway, FIV was associated with Alberta Stroke program Early CT Score (coefficient (Co)=−26.13, P 〈 0.001), admission National Institutes of Health Stroke Scale score (Co=3.69, P 〈 0.001), age (Co=−1.18, P 〈 0.05), and successful recanalization (Co=−85.22, P 〈 0.001). Successful recanalization increased the probability of good outcome by 23 percentage points (pp) (95% CI 16pp to 29pp). 56% (95% CI 38% to 78%) of the improvement in good outcome was explained by FIV reduction. Conclusion 56% (95% CI 38% to 78%) of outcome improvement after successful recanalization was explained by FIV reduction. Results corroborate pathophysiological assumptions and confirm the value of FIV as an imaging endpoint in clinical trials. 44% (95% CI 22% to 62%) of the improvement in outcome was not explained by FIV reduction and reflects the remaining mismatch between radiological and clinical outcome measures.
    Type of Medium: Online Resource
    ISSN: 1759-8478 , 1759-8486
    URL: Article
    DOI: 10.1136/jnis-2023-020296
    Language: English
    Publisher: BMJ
    Publication Date: 2023
    detail.hit.zdb_id: 2506028-4
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 8
    Online Resource
    Online Resource
    Predictors of aneurysm occlusion after treatment with flow diverters: a systematic literature review
    BMJ ; 2023
    In:  Journal of NeuroInterventional Surgery
    Details
    In: Journal of NeuroInterventional Surgery, BMJ
    Abstract: Flow diverters (FDs) have become an integral part of treatment for brain aneurysms. Aim To summarize available evidence of factors associated with aneurysm occlusion (AO) after treatment with a FD. Methods References were identified using the Nested Knowledge AutoLit semi-automated review platform between January 1, 2008 and August 26, 2022. The review focuses on preprocedural and postprocedural factors associated with AO identified in logistic regression analysis. Studies were included if they met the inclusion criteria of study details (ie, study design, sample size, location, (pre)treatment aneurysm details). Evidence levels were classified by variability and significancy across studies (eg, low variability ≥5 studies and significance in ≥60% throughout reports). Results Overall, 2.03% (95% CI 1.22 to 2.82; 24/1184) of screened studies met the inclusion criteria for predictors of AO based on logistic regression analysis. Predictors of AO with low variability in multivariable logistic regression analysis included aneurysm characteristics (aneurysm diameter), particularly complexity (absence of branch involvement) and younger patient age. Predictors of moderate evidence for AO included aneurysm characteristics (neck width), patient characteristics (absence of hypertension), procedural (adjunctive coiling) and post-deployment variables (longer follow-up; direct postprocedural satisfactory occlusion). Variables with a high variability in predicting AO following FD treatment were gender, FD as re-treatment strategy, and aneurysm morphology (eg, fusiform or blister). Conclusion Evidence of predictors for AO after FD treatment is sparse. Current literature suggests that absence of branch involvement, younger age, and aneurysm diameter have the highest impact on AO following FD treatment. Large studies investigating high-quality data with well-defined inclusion criteria are needed for greater insight into FD effectiveness.
    Type of Medium: Online Resource
    ISSN: 1759-8478 , 1759-8486
    URL: Article
    DOI: 10.1136/jnis-2022-019993
    Language: English
    Publisher: BMJ
    Publication Date: 2023
    detail.hit.zdb_id: 2506028-4
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 9
    Online Resource
    Online Resource
    Value of Dual-Energy Dual-Layer CT After Mechanical Recanalization for the Quantification of Ischemic Brain Edema
    Frontiers Media SA ; 2021
    In:  Frontiers in Neurology Vol. 12 ( 2021-7-19)
    Details
    In: Frontiers in Neurology, Frontiers Media SA, Vol. 12 ( 2021-7-19)
    Abstract: Background and Purpose: Ischemic brain edema can be measured in computed tomography (CT) using quantitative net water uptake (NWU), a recently established imaging biomarker. NWU determined in follow-up CT after mechanical thrombectomy (MT) has shown to be a strong predictor of functional outcome. However, disruption of the blood–brain barrier after MT may also lead to contrast staining, increasing the density on CT scans, and hence, directly impairing measurements of NWU. The purpose of this study was to determine whether dual-energy dual-layer CT (DDCT) after MT can improve the quantification of NWU by measuring NWU in conventional polychromatic CT images (CP-I) and virtual non-contrast images (VNC-I). We hypothesized that VNC-based NWU (vNWU) differs from NWU in conventional CT (cNWU). Methods: Ten patients with middle cerebral artery occlusion who received a DDCT follow-up scan after MT were included. NWU was quantified in conventional and VNC images as previously published and was compared using paired sample t -tests. Results: The mean cNWU was 3.3% (95%CI: 0–0.41%), and vNWU was 11% (95%CI: 1.3–23.4), which was not statistically different ( p = 0.09). Two patients showed significant differences between cNWU and vNWU (Δ = 24% and Δ = 36%), while the agreement of cNWU/vNWU in 8/10 patients was high (difference 2.3%, p = 0.23). Conclusion: NWU may be quantified precisely on conventional CT images, as the underestimation of ischemic edema due to contrast staining was low. However, a proportion of patients after MT might show significant contrast leakage resulting in edema underestimation. Further research is needed to validate these findings and investigate clinical implications.
    Type of Medium: Online Resource
    ISSN: 1664-2295
    URL: Article
    DOI: 10.3389/fneur.2021.668030
    Language: Unknown
    Publisher: Frontiers Media SA
    Publication Date: 2021
    detail.hit.zdb_id: 2564214-5
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 10
    Online Resource
    Online Resource
    Prediction of tissue outcome in acute ischemic stroke based on single-phase CT angiography at admission
    Frontiers Media SA ; 2024
    In:  Frontiers in Neurology Vol. 15 ( 2024-3-19)
    Details
    In: Frontiers in Neurology, Frontiers Media SA, Vol. 15 ( 2024-3-19)
    Abstract: In acute ischemic stroke, prediction of the tissue outcome after reperfusion can be used to identify patients that might benefit from mechanical thrombectomy (MT). The aim of this work was to develop a deep learning model that can predict the follow-up infarct location and extent exclusively based on acute single-phase computed tomography angiography (CTA) datasets. In comparison to CT perfusion (CTP), CTA imaging is more widely available, less prone to artifacts, and the established standard of care in acute stroke imaging protocols. Furthermore, recent RCTs have shown that also patients with large established infarctions benefit from MT, which might not have been selected for MT based on CTP core/penumbra mismatch analysis. Methods All patients with acute large vessel occlusion of the anterior circulation treated at our institution between 12/2015 and 12/2020 were screened ( N = 404) and 238 patients undergoing MT with successful reperfusion were included for final analysis. Ground truth infarct lesions were segmented on 24 h follow-up CT scans. Pre-processed CTA images were used as input for a U-Net-based convolutional neural network trained for lesion prediction, enhanced with a spatial and channel-wise squeeze-and-excitation block. Post-processing was applied to remove small predicted lesion components. The model was evaluated using a 5-fold cross-validation and a separate test set with Dice similarity coefficient (DSC) as the primary metric and average volume error as the secondary metric. Results The mean ± standard deviation test set DSC over all folds after post-processing was 0.35 ± 0.2 and the mean test set average volume error was 11.5 mL. The performance was relatively uniform across models with the best model according to the DSC achieved a score of 0.37 ± 0.2 after post-processing and the best model in terms of average volume error yielded 3.9 mL. Conclusion 24 h follow-up infarct prediction using acute CTA imaging exclusively is feasible with DSC measures comparable to results of CTP-based algorithms reported in other studies. The proposed method might pave the way to a wider acceptance, feasibility, and applicability of follow-up infarct prediction based on artificial intelligence.
    Type of Medium: Online Resource
    ISSN: 1664-2295
    URL: Article
    DOI: 10.3389/fneur.2024.1330497
    Language: Unknown
    Publisher: Frontiers Media SA
    Publication Date: 2024
    detail.hit.zdb_id: 2564214-5
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...