Machine Learning-Enabled Determination of Diffuseness of Brain Arteriovenous Malformations from Magnetic Resonance Angiography

Estimation of Ventricular and Intracranial Hemorrhage Volumes and Midline Shift on an External Validation Data Set Using a Convolutional Neural Network Algorithm

BACKGROUND AND OBJECTIVES

Noncontrast head computed tomography is the mainstay imaging modality to guide the management of intracranial hemorrhage (ICH); however, manual measurements can be time-consuming. In our study, we evaluate the performance of an artificial intelligence (AI) machine learning algorithm, Viz ICH-Plus, to automatically quantify ICH and bilateral lateral ventricular (BLV) volumes as well as midline shift (MLS).

METHODS

ICH patients considered for external ventricular drain with an initial noncontrast head computed tomography, and at least 1 follow-up scan within 48 hours was identified from a single center. Viz ICH-Plus estimations of ICH volume, BLV volume, and MLS were generated for each scan and compared with manually contoured and measured values. Median absolute errors and the ability of Viz ICH-Plus to detect clinically meaningful change from initial to follow-up scans (ICH volume growth ≥10 mL, BLV volume change ≥10 mL, or MLS increase ≥4 mm) were assessed.

RESULTS

Thirty patients were included for a total of 78 scans. The median absolute error was 2.9 mL (IQR 1.2 to 5.8) for ICH, 5.3 mL (IQR 2.5 to 7.9) for BLV volume, and 1.1 mm (IQR 0.7 to 2.0) for MLS. The ability of Viz ICH-Plus to detect a clinically significant change between scans was robust with sensitivity, specificity, positive predictive value, negative predictive value, and overall accuracy of 91.7%, 92.6%, 84.6%, 96.2%, and 92.3%, respectively.

CONCLUSION

The described Viz ICH-Plus algorithm performed moderately well at quantifying ICH, BLV volume, and MLS with satisfying spatial overlap of artificial intelligence and manual segmentations. The system demonstrated good predictive power when using predetermined thresholds to estimate clinically significant changes.

Comparison of Long-Term Outcomes in Ruptured Diffuse Brain Arteriovenous Malformations Between Interventional Therapy and Conservative Management

Brain arteriovenous malformations (AVMs) with a diffuse nidus structure present a therapeutic challenge due to their complexity and elevated risk of hemorrhagic events. This study examines the long-term effectiveness of interventional therapy versus conservative management in reducing hemorrhagic stroke or death in patients with ruptured diffuse AVMs. The analysis was conducted based on a multi-institutional database in China. Patients were divided into two groups: conservative management and interventional therapy. Using propensity score matching, patients were compared for the primary outcome of hemorrhagic stroke or death and the secondary outcomes of disability and neurofunctional decline. Out of 4286 consecutive AVMs in the registry, 901 patients were eligible. After matching, 70 pairs of patients remained with a median follow-up of 4.0 years. The conservative management group showed a trend toward higher rates of the primary outcome compared to the interventional group (4.15 vs. 1.87 per 100 patient-years, P = 0.090). While not statistically significant, intervention reduced the risk of hemorrhagic stroke or death by 55% (HR, 0.45 [95% CI 0.18-1.14], P = 0.094). No significant differences were observed in secondary outcomes of disability (OR, 0.89 [95% CI 0.35-2.26], P = 0.813) and neurofunctional decline (OR, 0.65 [95% CI 0.26 -1.63], P = 0.355). Subgroup analysis revealed particular benefits in interventional therapy for AVMs with a supplemented S-M grade of II-VI (HR, 0.10 [95% CI 0.01-0.79], P = 0.029). This study suggests a trend toward lower long-term hemorrhagic risks with intervention when compared to conservative management in ruptured diffuse AVMs, especially within supplemented S-M grade II-VI subgroups. No evidence indicated that interventional approaches worsen neurofunctional outcomes.

Artificial intelligence-based automatic nidus segmentation of cerebral arteriovenous malformation on time-of-flight magnetic resonance angiography

OBJECTIVE

Accurate nidus segmentation and quantification have long been challenging but important tasks in the clinical management of Cerebral Arteriovenous Malformation (CAVM). However, there are still dilemmas in nidus segmentation, such as difficulty defining the demarcation of the nidus, observer-dependent variation and time consumption. The aim of this study isto develop an artificial intelligence model to automatically segment the nidus on Time-Of-Flight Magnetic Resonance Angiography (TOF-MRA) images.

METHODS

A total of 92patients with CAVM who underwent both TOF-MRA and DSA examinations were enrolled. Two neurosurgeonsmanually segmented the nidusonTOF-MRA images,which were regarded as theground-truth reference. AU-Net-basedAImodelwascreatedfor automatic nidus detectionand segmentationonTOF-MRA images.

RESULTS

The meannidus volumes of the AI segmentationmodeland the ground truthwere 5.427 ± 4.996 and 4.824 ± 4.567 mL,respectively. The meandifference in the nidus volume between the two groups was0.603 ± 1.514 mL,which wasnot statisticallysignificant (P = 0.693). The DSC,precision and recallofthe testset were 0.754 ± 0.074, 0.713 ± 0.102 and 0.816 ± 0.098, respectively. The linear correlation coefficient of the nidus volume betweenthesetwo groupswas 0.988, p < 0.001.

CONCLUSION

The performance of the AI segmentationmodel is moderate consistent with that of manual segmentation. This AI model has great potential in clinical settings, such as preoperative planning, treatment efficacy evaluation, riskstratification and follow-up.

CT Angiography Radiomics Combining Traditional Risk Factors to Predict Brain Arteriovenous Malformation Rupture: a Machine Learning, Multicenter Study

This study aimed to develop a machine learning model for predicting brain arteriovenous malformation (bAVM) rupture using a combination of traditional risk factors and radiomics features. This multicenter retrospective study enrolled 586 patients with unruptured bAVMs from 2010 to 2020. All patients were grouped into the hemorrhage (n = 368) and non-hemorrhage (n = 218) groups. The bAVM nidus were segmented on CT angiography images using Slicer software, and radiomic features were extracted using Pyradiomics. The dataset included a training set and an independent testing set. The machine learning model was developed on the training set and validated on the testing set by merging numerous base estimators and a final estimator based on the stacking method. The area under the receiver operating characteristic (ROC) curve, precision, and the f1 score were evaluated to determine the performance of the model. A total of 1790 radiomics features and 8 traditional risk factors were contained in the original dataset, and 241 features remained for model training after L1 regularization filtering. The base estimator of the ensemble model was Logistic Regression, whereas the final estimator was Random Forest. In the training set, the area under the ROC curve of the model was 0.982 (0.967-0.996) and 0.893 (0.826-0.960) in the testing set. This study indicated that radiomics features are a valuable addition to traditional risk factors for predicting bAVM rupture. In the meantime, ensemble learning can effectively improve the performance of a prediction model.

The difference of functional MR imaging in evaluating outcome of patients with diffuse and compact brain arteriovenous malformation

Microsurgical resection is an effective method to treat brain arteriovenous malformations (BAVMs). Functional magnetic resonance imaging (fMRI) can evaluate the spatial relationship of nidus and eloquent. Diffuse BAVMs are related to poor outcomes postoperatively. The role of fMRI in evaluating outcomes in patients with different nidus types remains unclear. BAVM patients received microsurgical resection were included from a prospective, multicenter cohort study. All patients underwent fMRI evaluation preoperatively and were regularly followed up postoperatively. Diffuse BAVM is radiologically identified as nidus containing normal brain tissue interspersing between malformed vessels. Lesion-to-eloquent distance (LED) was calculated based on the relationship between nidus and eloquent. The primary outcome was 180-day unfavorable neurological status postoperatively. The risk of primary outcome was investigated within different BAVM nidus types. The LED's performance to predict poor outcome was evaluated using area under curve (AUC). 346 BAVM patients were included in this study. 93 (26.9%) patients were found to have a 180-day unfavorable outcome. Multivariate logistic analysis demonstrated LED (odd ratio [OR], 0.44; 0.34-0.57; P < 0.001) and mRS at admission (OR, 2.59; 1.90-3.54; P < 0.001) as factors of unfavorable outcome. Subgroup analysis showed LED and mRS at admission as factors of unfavorable outcome for patients with compact BAVMs (all P < 0.05), but not for patients with diffuse BAVMs. Subsequent analysis showed that LED performed poorly to predict the unfavorable outcome for patients with diffuse BAVMs, compared with patients with compact BAVMs (AUC as 0.69 vs. 0.86, P < 0.05). A larger cutoff value of LED to unfavorable outcome was found in patients with diffuse BAVMs (15 mm) compared with patients with compact BAVMs (4.7 mm). Usage of LED to evaluate postoperative outcome of patients with diffuse BAVMs differs from its use in patients with compact BAVMs. Specific assessment strategy considering BAVM nidus types could help improve patients' outcome. MITASREAVM cohort (unique identifier: NCT02868008, https://clinicaltrials.gov/study/NCT02868008?term=NCT02868008&rank=1 ).

The current landscape of machine learning-based radiomics in arteriovenous malformations: a systematic review and radiomics quality score assessment

Background

Arteriovenous malformations (AVMs) are rare vascular anomalies involving a disorganization of arteries and veins with no intervening capillaries. In the past 10 years, radiomics and machine learning (ML) models became increasingly popular for analyzing diagnostic medical images. The goal of this review was to provide a comprehensive summary of current radiomic models being employed for the diagnostic, therapeutic, prognostic, and predictive outcomes in AVM management.

Methods

A systematic literature review was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines, in which the PubMed and Embase databases were searched using the following terms: (cerebral OR brain OR intracranial OR central nervous system OR spine OR spinal) AND (AVM OR arteriovenous malformation OR arteriovenous malformations) AND (radiomics OR radiogenomics OR machine learning OR artificial intelligence OR deep learning OR computer-aided detection OR computer-aided prediction OR computer-aided treatment decision). A radiomics quality score (RQS) was calculated for all included studies.

Results

Thirteen studies were included, which were all retrospective in nature. Three studies (23%) dealt with AVM diagnosis and grading, 1 study (8%) gauged treatment response, 8 (62%) predicted outcomes, and the last one (8%) addressed prognosis. No radiomics model had undergone external validation. The mean RQS was 15.92 (range: 10-18).

Conclusion

We demonstrated that radiomics is currently being studied in different facets of AVM management. While not ready for clinical use, radiomics is a rapidly emerging field expected to play a significant future role in medical imaging. More prospective studies are warranted to determine the role of radiomics in the diagnosis, prediction of comorbidities, and treatment selection in AVM management.

The novel imaging methods in diagnosis and assessment of cerebrovascular diseases: an overview

Cerebrovascular diseases, including ischemic strokes, hemorrhagic strokes, and vascular malformations, are major causes of morbidity and mortality worldwide. The advancements in neuroimaging techniques have revolutionized the field of cerebrovascular disease diagnosis and assessment. This comprehensive review aims to provide a detailed analysis of the novel imaging methods used in the diagnosis and assessment of cerebrovascular diseases. We discuss the applications of various imaging modalities, such as computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET), and angiography, highlighting their strengths and limitations. Furthermore, we delve into the emerging imaging techniques, including perfusion imaging, diffusion tensor imaging (DTI), and molecular imaging, exploring their potential contributions to the field. Understanding these novel imaging methods is necessary for accurate diagnosis, effective treatment planning, and monitoring the progression of cerebrovascular diseases.

Application of artificial intelligence in brain arteriovenous malformations: Angioarchitectures, clinical symptoms and prognosis prediction

BACKGROUND

Artificial intelligence (AI) has rapidly advanced in the medical field, leveraging its intelligence and automation for the management of various diseases. Brain arteriovenous malformations (AVM) are particularly noteworthy, experiencing rapid development in recent years and yielding remarkable results. This paper aims to summarize the applications of AI in the management of AVMs management.

METHODS

Literatures published in PubMed during 1999-2022, discussing AI application in AVMs management were reviewed.

RESULTS

AI algorithms have been applied in various aspects of AVM management, particularly in machine learning and deep learning models. Automatic lesion segmentation or delineation is a promising application that can be further developed and verified. Prognosis prediction using machine learning algorithms with radiomic-based analysis is another meaningful application.

CONCLUSIONS

AI has been widely used in AVMs management. This article summarizes the current research progress, limitations and future research directions.

Deep Learning Detection and Segmentation of Brain Arteriovenous Malformation on Magnetic Resonance Angiography

BACKGROUND

The delineation of brain arteriovenous malformations (bAVMs) is crucial for subsequent treatment planning. Manual segmentation is time-consuming and labor-intensive. Applying deep learning to automatically detect and segment bAVM might help to improve clinical practice efficiency.

PURPOSE

To develop an approach for detecting bAVM and segmenting its nidus on Time-of-flight magnetic resonance angiography using deep learning methods.

STUDY TYPE

Retrospective.

SUBJECTS

221 bAVM patients aged 7-79 underwent radiosurgery from 2003 to 2020. They were split into 177 training, 22 validation, and 22 test data.

FIELD STRENGTH/SEQUENCE

1.5 T, Time-of-flight magnetic resonance angiography based on 3D gradient echo.

ASSESSMENT

The YOLOv5 and YOLOv8 algorithms were utilized to detect bAVM lesions and the U-Net and U-Net++ models to segment the nidus from the bounding boxes. The mean average precision, F1, precision, and recall were used to assess the model performance on the bAVM detection. To evaluate the model's performance on nidus segmentation, the Dice coefficient and balanced average Hausdorff distance (rbAHD) were employed.

STATISTICAL TESTS

The Student's t-test was used to test the cross-validation results (P < 0.05). The Wilcoxon rank test was applied to compare the median for the reference values and the model inference results (P < 0.05).

RESULTS

The detection results demonstrated that the model with pretraining and augmentation performed optimally. The U-Net++ with random dilation mechanism resulted in higher Dice and lower rbAHD, compared to that without that mechanism, across varying dilated bounding box conditions (P < 0.05). When combining detection and segmentation, the Dice and rbAHD were statistically different from the references calculated using the detected bounding boxes (P < 0.05). For the detected lesions in the test dataset, it showed the highest Dice of 0.82 and the lowest rbAHD of 5.3%.

DATA CONCLUSION

This study showed that pretraining and data augmentation improved YOLO detection performance. Properly limiting lesion ranges allows for adequate bAVM segmentation.

LEVEL OF EVIDENCE

4 TECHNICAL EFFICACY STAGE: 1.

Quantitative image signature and machine learning-based prediction of outcomes in cerebral cavernous malformations

PURPOSE

There is increasing interest in novel prognostic tools and predictive biomarkers to help identify, with more certainty, cerebral cavernous malformations (CCM) susceptible of bleeding if left untreated. We developed explainable quantitative-based machine learning models from magnetic resonance imaging (MRI) in a large CCM cohort to demonstrate the value of artificial intelligence and radiomics in complementing natural history studies for hemorrhage and functional outcome prediction.

MATERIALS AND METHODS

One-hundred-eighty-one patients from a prospectively registered cohort of 366 adults with CCM were included. Fluid attenuated inversion recovery (FLAIR) T2-weighted brain images were preprocessed, and CCM and surrounding edema were segmented before radiomic feature computation. Minority class oversampling, dimensionality reduction and feature selection methods were applied. With prospective hemorrhage as primary outcome, machine learning models were built, cross-validated, and compared using clinico-radiologic, radiomic, and combined features. SHapley Additive exPlanations (SHAP) was used for interpretation to determine the radiomic features with most contribution to hemorrhage prediction.

RESULTS

The highest performances in hemorrhage predictions on the test set were combining radiomic and clinico-radiological features with an area under the curve (AUC) of 83% using linear regression and selected features, and an F1 score of 61% and 85% sensitivity using K-nearest neighbors with principal component analysis (PCA). Multilayer perceptron had the best performance predicting modified Rankin Scale ≥ 2 with an AUC of 74% using PCA derived features. For interpretation of the selected radiomic signature XGBoost model, Shapley additive explanations highlighted 6 radiomic features contributing the most to hemorrhage prediction.

CONCLUSION

Quantitative image-based modeling using machine learning has the potential to highlight novel imaging biomarkers that predict hemorrhagic and functional outcomes, ensuring more precise and personalized care for CCM patients.

Artificial Intelligence-Assisted Evaluation of the Spatial Relationship between Brain Arteriovenous Malformations and the Corticospinal Tract to Predict Postsurgical Motor Defects

BACKGROUND AND PURPOSE

Preoperative evaluation of brain AVMs is crucial for the selection of surgical candidates. Our goal was to use artificial intelligence to predict postsurgical motor defects in patients with brain AVMs involving motor-related areas.

MATERIALS AND METHODS

Eighty-three patients who underwent microsurgical resection of brain AVMs involving motor-related areas were retrospectively reviewed. Four artificial intelligence-based indicators were calculated with artificial intelligence on TOF-MRA and DTI, including FN5mm/50mm (the proportion of fiber numbers within 5-50mm from the lesion border), FN10mm/50mm (the same but within 10-50mm), FP5mm/50mm (the proportion of fiber voxel points within 5-50mm from the lesion border), and FP10mm/50mm (the same but within 10-50mm). The association between the variables and long-term postsurgical motor defects was analyzed using univariate and multivariate analyses. Least absolute shrinkage and selection operator regression with the Pearson correlation coefficient was used to select the optimal features to develop the machine learning model to predict postsurgical motor defects. The area under the curve was calculated to evaluate the predictive performance.

RESULTS

In patients with and without postsurgical motor defects, the mean FN5mm/50mm, FN10mm/50mm, FP5mm/50mm, and FP10mm/50mm were 0.24 (SD, 0.24) and 0.03 (SD, 0.06), 0.37 (SD, 0.27) and 0.06 (SD, 0.08), 0.06 (SD, 0.10) and 0.01 (SD, 0.02), and 0.10 (SD, 0.12) and 0.02 (SD, 0.05), respectively. Univariate and multivariate logistic analyses identified FN10mm/50mm as an independent risk factor for long-term postsurgical motor defects (P = .002). FN10mm/50mm achieved a mean area under the curve of 0.86 (SD, 0.08). The mean area under the curve of the machine learning model consisting of FN10mm/50mm, diffuseness, and the Spetzler-Martin score was 0.88 (SD, 0.07).

CONCLUSIONS

The artificial intelligence-based indicator, FN10mm/50mm, can reflect the lesion-fiber spatial relationship and act as a dominant predictor for postsurgical motor defects in patients with brain AVMs involving motor-related areas.