Automated detection of intracranial artery stenosis and occlusion in magnetic resonance angiography: A preliminary study based on deep learning

Advancements in imaging of intracranial atherosclerotic disease: beyond the arterial lumen to the vessel wall

Intracranial atherosclerotic disease (ICAD) significantly increases the risk of ischemic stroke. It involves the accumulation of plaque within arterial walls and narrowing or blockage of blood vessel lumens. Accurate imaging is crucial for the diagnosis and management of ICAD at both acute and chronic stages. However, imaging the small, tortuous intracranial arterial walls amidst complex structures is challenging. Clinicians have employed diverse approaches to improve imaging quality, with a particular emphasis on optimizing the acquisition of images using new techniques, enhancing spatial and temporal resolution of images, and refining post-processing techniques. ICAD imaging has evolved from depicting lumen stenosis to assessing blood flow reserve and identifying plaque components. Advanced techniques such as fractional flow reserve (FFR), high-resolution vessel wall magnetic resonance (VW-MR), optical coherence tomography (OCT), and radial wall strain (RWS) now allow direct visualization of flow impairment, vulnerable plaques, and blood flow strain to plaque, aiding in the selection of high-risk stroke patients for intervention. This article reviews the progression of imaging modalities from lumen stenosis to vessel wall pathology and compares their diagnostic value for risk stratification in ICAD patients.

Machine Learning-Based Classification of Anterior Circulation Cerebral Infarction Using Computational Fluid Dynamics and CT Perfusion Metrics

Background: Intracranial atherosclerotic stenosis (ICAS) is a leading cause of ischemic stroke, particularly in the anterior circulation. Understanding the underlying stroke mechanisms is essential for guiding personalized treatment strategies. This study proposes an integrated framework that combines CT perfusion imaging, vascular anatomical features, computational fluid dynamics (CFD), and machine learning to classify stroke mechanisms based on the Chinese Ischemic Stroke Subclassification (CISS) system. Methods: A retrospective analysis was conducted on 118 patients with intracranial atherosclerotic stenosis. Key indicators were selected using one-way ANOVA with nested cross-validation and visualized through correlation heatmaps. Optimal thresholds were identified using decision trees. The classification performance of six machine learning models was evaluated using ROC and PR curves. Results: Time to Maximum (Tmax) > 4.0 s, wall shear stress ratio (WSSR), pressure ratio, and percent area stenosis were identified as the most predictive indicators. Thresholds such as Tmax > 4.0 s = 134.0 mL and WSSR = 86.51 effectively distinguished stroke subtypes. The Logistic Regression model demonstrated the best performance (AUC = 0.91, AP = 0.85), followed by Naive Bayes models. Conclusions: This multimodal approach effectively differentiates stroke mechanisms in anterior circulation ICAS and holds promise for supporting more precise diagnosis and personalized treatment in clinical practice.

Intracranial stenosis prediction using a small set of risk factors in the Tromsø Study

Intracranial atherosclerotic stenosis (ICAS) refers to a narrowing of intracranial arteries due to plaque buildup on the inside of the vessel walls restricting blood flow. Early detection of ICAS is crucial to prevent serious consequences such as stroke. Here we apply three different machine learning methods, such as support vector machines, multi-layer perceptrons and Kolmogorov-Arnold Networks to predict ICAS according to sparse risk factors from blood lipids and demographic data, including smoking habits, age, sex, diabetes, blood pressure lowering and cholesterol-lowering drugs and high-density lipoprotein. We achieved similar performance on classification compared to modern detection algorithms for ICAS in TOF-MRA (time-of-flight magnetic resonance angiography). The prevalence of ICAS in the population is relatively low, which is often case in medicine. While in the medical research community, the issue of low prevalence is established, machine learning-based research in medicine often does not take into account a critical viewpoint of the prevalence in clinical settings of their methods. We showed that with a balanced training/test set an accuracy up to 81% was achievable, while with the inclusion of prevalence, the positive predictive value was at 19% to the prevalence data, changes the performance metrics. Therefore, we highlighted the discrepancy that can arise between the results reported by the models and their clinical relevance. Furthermore, the results demonstrate the predictive potential of limited risk factors, highlighting its potential contribution to a multi-modular classification algorithm based on MRAs.

Comprehensive imaging analysis of intracranial atherosclerosis

Intracranial atherosclerotic disease (ICAD) involves the build-up of atherosclerotic plaques in cerebral arteries, significantly contributing to stroke worldwide. Diagnosing ICAD entails various techniques that measure arterial stenosis severity. Digital subtraction angiography, CT angiography, and magnetic resonance angiography are established methods for assessing stenosis. High-resolution MRI offers additional insights into plaque morphology including plaque burden, hemorrhage, remodeling, and contrast enhancement. These metrics and plaque traits help identify symptomatic plaques. Techniques like transcranial Doppler, CT perfusion, computational fluid dynamics, and quantitative MRA analyze blood flow restrictions due to ICAD. Intravascular ultrasound or optical coherence tomography have a very high spatial resolution and can assess the structure of the arterial wall and the plaque from the lumen of the target vascular territory. Positron emission tomography could further detect inflammation markers. This review aims to provide a comprehensive overview of the spectrum of current modalities for atherosclerotic plaque analysis and risk stratification.

Patch-Wise Deep Learning Method for Intracranial Stenosis and Aneurysm Detection-the Tromsø Study

Intracranial atherosclerotic stenosis (ICAS) and intracranial aneurysms are prevalent conditions in the cerebrovascular system. ICAS causes a narrowing of the arterial lumen, thereby restricting blood flow, while aneurysms involve the ballooning of blood vessels. Both conditions can lead to severe outcomes, such as stroke or vessel rupture, which can be fatal. Early detection is crucial for effective intervention. In this study, we introduced a method that combines classical computer vision techniques with deep learning to detect intracranial aneurysms and ICAS in time-of-flight magnetic resonance angiography images. The process began with skull-stripping, followed by an affine transformation to align the images to a common atlas space. We then focused on the region of interest, including the circle of Willis, by cropping the relevant area. A segmentation algorithm was used to isolate the arteries, after which a patch-wise residual neural network was applied across the image. A voting mechanism was then employed to identify the presence of atrophies. Our method achieved accuracies of 76.5% for aneurysms and 82.4% for ICAS. Notably, when occlusions were not considered, the accuracy for ICAS detection improved to 85.7%. While the algorithm performed well for localized pathological findings, it was less effective at detecting occlusions, which involved long-range dependencies in the MRIs. This limitation was due to the architectural design of the patch-wise deep learning approach. Regardless, this can, in the future, be mitigated in a multi-scale patch-wise algorithm.

Advancements in opportunistic intracranial aneurysm screening: The impact of a deep learning algorithm on radiologists' analysis of T2-weighted cranial MRI

(1) Background: Unruptured Intracranial Aneurysms (UIAs) are common blood vessel malformations, occurring in up to 3 % of healthy adults. Magnetic Resonance Angiography (MRA) is frequently used for the screening of UIAs due to its high resolution in vascular anatomy. However, T2-Weighted Magnetic Resonance Imaging (T2WI) is a standard sequence utilized for the majority of outpatient head scans. By employing a sequence such as T2WI, there is a possible shift towards early detection of UIAs through opportunistic screening. Here, we assess a Deep Learning Algorithm (DLA) developed to assist radiologists in identifying and reporting UIAs on T2WI in a routine clinical setting. (2) Methods: A DLA was trained on a set of 110 patients undergoing an MR head scan with the gold standard set by two radiology experts. Eight radiologists were given a cohort of 50 cranial T2WI studies and asked for a routine report. After a 10-day washout period, they reviewed the same cases randomized and supported by the DLA predictions. We assessed changes in sensitivity, specificity, accuracy, and false positives. (3) Results: During routine reporting, the models' assistance improved the sensitivity of the eight participants by an average of 36.19 and the accuracy by 10.00 percentage points. (4) Conclusion: Our results indicate the potential benefit of deep learning to improve radiologists' detection of UIAs during routine reporting. From this, we can infer that the combination of T2WI with our DLA supports opportunistic screening, suggesting potential approaches for future research and application.

Automated Detection of Steno-Occlusive Lesion on Time-of-Flight MR Angiography: An Observer Performance Study

BACKGROUND AND PURPOSE

Intracranial steno-occlusive lesions are responsible for acute ischemic stroke. However, the clinical benefits of artificial intelligence (AI)-based methods for detecting pathologic lesions in intracranial arteries have not been evaluated. We aimed to validate the clinical utility of an AI model for detecting steno-occlusive lesions in the intracranial arteries.

MATERIALS AND METHODS

Overall, 138 TOF-MRA images were collected from 2 institutions, which served as internal (n = 62) and external (n = 76) test sets, respectively. Each study was reviewed by 5 radiologists (2 neuroradiologists and 3 radiology residents) to compare the usage and nonusage of our proposed AI model for TOF-MRA interpretation. They identified the steno-occlusive lesions and recorded their reading time. Observer performance was assessed by using the area under the jackknife free-response receiver operating characteristic curve (AUFROC) and reading time for comparison.

RESULTS

The average AUFROC for the 5 radiologists demonstrated an improvement from 0.70 without AI to 0.76 with AI (P = .027). Notably, this improvement was most pronounced among the 3 radiology residents, whose performance metrics increased from 0.68 to 0.76 (P = .002). Despite an increased reading time by using AI, there was no significant change among the readings by radiology residents. Moreover, the use of AI resulted in improved interobserver agreement among the reviewers (the intraclass correlation coefficient increased from 0.734 to 0.752).

CONCLUSIONS

Our proposed AI model offers a supportive tool for radiologists, potentially enhancing the accuracy of detecting intracranial steno-occlusion lesions on TOF-MRA. Less experienced readers may benefit the most from this model.

Predictors of the dynamics of changes in cognitive functions in patients 6 months after carotid endarterectomy

Background. Carotid atherosclerosis is one of the urgent problems due to the high risk of developing ischemic stroke and cognitive impairment. The dynamics of clinical disorders in patients with carotid stenosis is determined by a complex of neurophysiological, angiological, tissue and biomolecular reactions, the characteristics of which can act as predictors of the course of the pathology.The aim of the work. To determine the neurophysiological parameters and predictors of cognitive dysfunction in patients who underwent carotid endarterectomy.Materials and methods. The study included 59 people with carotid atherosclerotic disease. All included patients underwent carotid endarterectomy. We assessed the degree of stenosis of the internal carotid artery and cognitive status using the FAB (Frontal Assessment Battery) scale and MoCA (Montreal Cognitive Assessment) Test and recorded electroencephalogram (EEG), P300 cognitive evoked potentials and heart rate variability in patients at various terms (before surgery, 6 months after the surgery). Patients were divided into groups based on the dynamics of cognitive tests using cluster analysis (k-means) with identification of elements included in the clusters: patients of cluster 1 had a “preserved” profile of cognitive status; patients of cluster 2 – moderate cognitive dysfunction.Results. Patients of cluster 1 had a higher power of beta oscillations in the frontal lead, a higher amplitude of the P3 component of the P300 potential, and a greater variability of R-R intervals in terms of the total indicator and high-frequency power. We proposed a model that allows us to classify patients into groups according to the dynamics of cognitive function scores. According to the data obtained, the most significant predictors of the dynamics of cognitive status were the initial characteristics of the EEG and the P300 cognitive evoked potential.Conclusions. We determined the clinical and neurophysiological correlates of cognitive dysfunction: an association with greater preservation of activating effects on the EEG, processes of recognition and decision-making in the associative zones of the cortex, and less pronounced activity of stress-implementing mechanisms. Indicators of EEG spectral analysis and characteristics of the P300 cognitive evoked potential are predictors of the cognitive status dynamics.

Diagnostic value of high-resolution vessel wall imaging technique in intracranial arterial stenosis and occlusion: a comparative analysis with digital subtraction angiography

OBJECTIVE

To analyze the diagnostic value of HR-VWI in intracranial arterial stenosis and occlusion and compare it with DSA.

METHODS

A retrospective analysis of clinical data of 59 patients with intracranial arterial stenosis in our hospital was conducted to compare the diagnostic results of the two methods for different degrees of intracranial stenosis and various morphological plaques.

RESULTS

The diagnosis of stenosis and occlusion by both methods showed no significant difference (p > 0.05). Comparison of plaque morphology detected by HR-VWI with pathological examination results showed no significant difference (p > 0.05); however, there was a significant difference between plaque morphology detected by DSA and pathological examination results (p < 0.05). Additionally, there was a significant difference between plaque morphology detected by HR-VWI and DSA (p < 0.05).

CONCLUSION

HR-VWI technique is comparable to DSA technique in diagnosing intracranial arterial stenosis and occlusion, but it is superior to DSA in plaque morphology diagnosis.

Artificial intelligence for MRI stroke detection: a systematic review and meta-analysis

OBJECTIVES

This systematic review and meta-analysis aimed to assess the stroke detection performance of artificial intelligence (AI) in magnetic resonance imaging (MRI), and additionally to identify reporting insufficiencies.

METHODS

PRISMA guidelines were followed. MEDLINE, Embase, Cochrane Central, and IEEE Xplore were searched for studies utilising MRI and AI for stroke detection. The protocol was prospectively registered with PROSPERO (CRD42021289748). Sensitivity, specificity, accuracy, and area under the receiver operating characteristic (ROC) curve were the primary outcomes. Only studies using MRI in adults were included. The intervention was AI for stroke detection with ischaemic and haemorrhagic stroke in separate categories. Any manual labelling was used as a comparator. A modified QUADAS-2 tool was used for bias assessment. The minimum information about clinical artificial intelligence modelling (MI-CLAIM) checklist was used to assess reporting insufficiencies. Meta-analyses were performed for sensitivity, specificity, and hierarchical summary ROC (HSROC) on low risk of bias studies.

RESULTS

Thirty-three studies were eligible for inclusion. Fifteen studies had a low risk of bias. Low-risk studies were better for reporting MI-CLAIM items. Only one study examined a CE-approved AI algorithm. Forest plots revealed detection sensitivity and specificity of 93% and 93% with identical performance in the HSROC analysis and positive and negative likelihood ratios of 12.6 and 0.079.

CONCLUSION

Current AI technology can detect ischaemic stroke in MRI. There is a need for further validation of haemorrhagic detection. The clinical usability of AI stroke detection in MRI is yet to be investigated.

CRITICAL RELEVANCE STATEMENT

This first meta-analysis concludes that AI, utilising diffusion-weighted MRI sequences, can accurately aid the detection of ischaemic brain lesions and its clinical utility is ready to be uncovered in clinical trials.

KEY POINTS

There is a growing interest in AI solutions for detection aid. The performance is unknown for MRI stroke assessment. AI detection sensitivity and specificity were 93% and 93% for ischaemic lesions. There is limited evidence for the detection of patients with haemorrhagic lesions. AI can accurately detect patients with ischaemic stroke in MRI.

GravityNet for end-to-end small lesion detection

This paper introduces a novel one-stage end-to-end detector specifically designed to detect small lesions in medical images. Precise localization of small lesions presents challenges due to their appearance and the diverse contextual backgrounds in which they are found. To address this, our approach introduces a new type of pixel-based anchor that dynamically moves towards the targeted lesion for detection. We refer to this new architecture as GravityNet, and the novel anchors as gravity points since they appear to be "attracted" by the lesions. We conducted experiments on two well-established medical problems involving small lesions to evaluate the performance of the proposed approach: microcalcifications detection in digital mammograms and microaneurysms detection in digital fundus images. Our method demonstrates promising results in effectively detecting small lesions in these medical imaging tasks.

CASMatching strategy for automated detection and quantification of carotid artery stenosis based on digital subtraction angiography

BACKGROUND AND OBJECTIVE

Automated detection and quantification of carotid artery stenosis is a crucial task in establishing a computer-aided diagnostic system for brain diseases. Digital subtraction angiography (DSA) is known as the "gold standard" for carotid stenosis diagnosis. It is commonly used to identify carotid artery stenosis and measure morphological indices of the stenosis. However, using deep learning to detect stenosis based on DSA images and further quantitatively predicting the morphological indices remain a challenge due the absence of prior work. In this paper, we propose a quantitative method for predicting morphological indices of carotid stenosis.

METHODS

Our method adopts a two-stage pipeline, first locating regions suitable for predicting morphological indices by object detection model, and then using a regression model to predict indices. A novel Carotid Artery Stenosis Matching (CASMatching) strategy is introduced into the object detection to model the matching relationship between a stenosis and multiple normal vessel segments. The proposed Match-ness branch predicts a Match-ness score for each normal vessel segment to indicate the degree of matching to the stenosis. A novel Direction Distance-IoU (2DIoU) loss based on the Distance-IoU loss is proposed to make the model focused more on the bounding box regression in the direction of vessel extension. After detection, the normal vessel segment with the highest Match-ness score and the stenosis are intercepted from the original image, then fed into a regression model to predict morphological indices and calculate the degree of stenosis.

RESULTS

Our method is trained and evaluated on a dataset collected from three different manufacturers' monoplane X-ray systems. The results show that the proposed components in the object detector substantially improve the detection performance of normal vascular segments. For the prediction of morphological indices, our model achieves Mean Absolute Error of 0.378, 0.221, 4.9 on reference vessel diameter (RVD), minimum lumen diameter (MLD) and stenosis degree.

CONCLUSIONS

Our method can precisely localize the carotid stenosis and the normal vessel segment suitable for predicting RVD of the stenosis, and further achieve accurate quantification, providing a novel solution for the quantification of carotid artery stenosis.