Comparing methods of detecting and segmenting unruptured intracranial aneurysms on TOF-MRAS: The ADAM challenge

Multi-centric AI Model for Unruptured Intracranial Aneurysm Detection and Volumetric Segmentation in 3D TOF-MRI

The aim of this study was to develop an open-source nnU-Net-based AI model for combined detection and segmentation of unruptured intracranial aneurysms (UICA) in 3D TOF-MRI and compare models trained on datasets with aneurysm-like differential diagnoses. This retrospective study (2020–2023) included 385 anonymized 3D TOF-MRI images from 345 patients (mean age 59 years, 60% female) at multiple centers plus 113 subjects from the ADAM challenge. Images featured untreated or possible UICA and differential diagnoses. Four distinct training datasets were created, and the nnU-Net framework was used for model development. Performance was assessed on a separate test set using sensitivity and false positive (FP)/case rate for detection and DICE score and NSD (normalized surface distance, 0.5 mm threshold) for segmentation. Segmentation performance on the test set was also compared to a second human reader. The four models achieved overall sensitivity between 82 and 85% and an FP/case rate of 0.20 to 0.31, with no significant differences (p = 0.90 and p = 0.16) between them. The primary model showed 85% sensitivity and 0.23 FP/case rate, outperforming the ADAM-challenge winner (61%) and a nnU-Net trained on ADAM data (51%) in sensitivity (p < 0.05). Mean DICE (0.73) and NSD (0.84 for 0.5 mm threshold) for correctly detected UICA did not significantly differ from human reader performance. Our open-source, nnU-Net-based AI model (available at https://zenodo.org/records/13386859) demonstrates high sensitivity, low FP rates, and consistent segmentation accuracy for UICA detection and segmentation in 3D TOF-MRI, suggesting its potential to improve clinical diagnosis and monitoring of UICA.

Multi-centric AI Model for Unruptured Intracranial Aneurysm Detection and Volumetric Segmentation in 3D TOF-MRI

The aim of this study was to develop an open-source nnU-Net-based AI model for combined detection and segmentation of unruptured intracranial aneurysms (UICA) in 3D TOF-MRI and compare models trained on datasets with aneurysm-like differential diagnoses. This retrospective study (2020-2023) included 385 anonymized 3D TOF-MRI images from 345 patients (mean age 59 years, 60% female) at multiple centers plus 113 subjects from the ADAM challenge. Images featured untreated or possible UICA and differential diagnoses. Four distinct training datasets were created, and the nnU-Net framework was used for model development. Performance was assessed on a separate test set using sensitivity and false positive (FP)/case rate for detection and DICE score and NSD (normalized surface distance, 0.5 mm threshold) for segmentation. Segmentation performance on the test set was also compared to a second human reader. The four models achieved overall sensitivity between 82 and 85% and an FP/case rate of 0.20 to 0.31, with no significant differences (p = 0.90 and p = 0.16) between them. The primary model showed 85% sensitivity and 0.23 FP/case rate, outperforming the ADAM-challenge winner (61%) and a nnU-Net trained on ADAM data (51%) in sensitivity (p < 0.05). Mean DICE (0.73) and NSD (0.84 for 0.5 mm threshold) for correctly detected UICA did not significantly differ from human reader performance. Our open-source, nnU-Net-based AI model (available at https://zenodo.org/records/13386859 ) demonstrates high sensitivity, low FP rates, and consistent segmentation accuracy for UICA detection and segmentation in 3D TOF-MRI, suggesting its potential to improve clinical diagnosis and monitoring of UICA.

Accuracy of an nnUNet Neural Network for the Automatic Segmentation of Intracranial Aneurysms, Their Parent Vessels, and Major Cerebral Arteries from MRI-TOF

BACKGROUND AND PURPOSE

The automatic recognition of intracraial aneurysms by means of machine-learning algorithms represents a new frontier for diagnostic and therapeutic goals. Yet, the current algorithms focus solely on the aneurysms and not on the recognition of their parent vessels. The purpose of the present study is the development of a new machine-learning algorithm for fully automatic identification of cerebral arteries and intracranial aneurysms (IAs) based on a manually segmented MRA-TOF data set.

MATERIALS AND METHODS

In this retrospective single-center study, 62 MRA-TOF scans of a total of 73 untreated, unruptured IAs were manually color-labeled in 21 classes. A nnUNet architecture was trained on MRA-TOF images. The performance of the automatic segmentation was compared with the manual segmentation by using the Dice Similarity Coefficient (DSC), Centerline Dice (ClDice), and 95th percentile Hausdorff Distance (HD95). Sensitivity was computed for aneurysm detection.

RESULTS

Across all 21 classes, the median DSC was 0.86 [95% CI: 0.81-0.89], the median ClDice was 0.91 [0.85, 0.94], and the median HD95 was 2.9 [1.0, 14.9] mm. Sensitivity of the model for aneurysm detection was 0.8. For this class specifically, a median DSC of 0.88 [0.13, 0.92], median ClDice of 0.89 [0.06, 1.0], and median HD95 of 1.8 [0.58, 81] mm was achieved. The volume of the labeled anatomic structure was the most relevant determinant of accuracy in this model. Median time to predict was 130.6 [60.9, 284.1] seconds.

CONCLUSIONS

The nnUNet MRA-TOF-based algorithm provided a fast and adequate automatic extraction of unruptured IAs, their parent vessels, and the most relevant cerebral arteries. Future steps involve the expansion of the training set with the inclusion of more MRA-TOF studies with and without IAs and its incorporation in 3D imaging viewers and treatment prediction.

A survey of intracranial aneurysm detection and segmentation

Intracranial aneurysms (IAs) are a critical public health concern: they are asymptomatic and can lead to fatal subarachnoid hemorrhage in case of rupture. Neuroradiologists rely on advanced imaging techniques to identify aneurysms in a patient and consider the characteristics of IAs along with several other patient-related factors for rupture risk assessment and treatment decision-making. The process of diagnostic image reading is time-intensive and prone to inter- and intra-individual variations, so researchers have proposed many computer-aided diagnosis (CAD) systems for aneurysm detection and segmentation. This paper provides a comprehensive literature survey of semi-automated and automated approaches for IA detection and segmentation and proposes a taxonomy to classify the approaches. We also discuss the current issues and give some insight into the future direction of CAD systems for IA detection and segmentation.

Automation bias in AI-assisted detection of cerebral aneurysms on time-of-flight MR angiography

PURPOSE

To determine how automation bias (inclination of humans to overly trust-automated decision-making systems) can affect radiologists when interpreting AI-detected cerebral aneurysm findings in time-of-flight magnetic resonance angiography (TOF-MRA) studies.

MATERIAL AND METHODS

Nine radiologists with varying levels of experience evaluated twenty TOF-MRA examinations for the presence of cerebral aneurysms. Every case was evaluated with and without assistance by the AI software © mdbrain, with a washout period of at least four weeks in-between. Half of the cases included at least one false-positive AI finding. Aneurysm ratings, follow-up recommendations, and reading times were assessed using the Wilcoxon signed-rank test.

RESULTS

False-positive AI results led to significantly higher suspicion of aneurysm findings (p = 0.01). Inexperienced readers further recommended significantly more intense follow-up examinations when presented with false-positive AI findings (p = 0.005). Reading times were significantly shorter with AI assistance in inexperienced (164.1 vs 228.2 s; p < 0.001), moderately experienced (126.2 vs 156.5 s; p < 0.009), and very experienced (117.9 vs 153.5 s; p < 0.001) readers alike.

CONCLUSION

Our results demonstrate the susceptibility of radiology readers to automation bias in detecting cerebral aneurysms in TOF-MRA studies when encountering false-positive AI findings. While AI systems for cerebral aneurysm detection can provide benefits, challenges in human-AI interaction need to be mitigated to ensure safe and effective adoption.

Systematic review of artificial intelligence methods for detection and segmentation of unruptured intracranial aneurysms using medical imaging

Unruptured intracranial aneurysms are protuberances that appear in cerebral arteries, and their diagnostic evaluation can be a complex, time-consuming, and exhaustive task. In recent years, computer-aided systems have been developed to improve diagnostic processes. Although the proposed methods have already been reviewed to assess their suitability for clinical use, the segmentation methods have not been reviewed in detail, nor has there been a standardized way to compare segmentation and detection tasks. A systematic review was conducted to examine the technical and methodological factors contributing to this limitation. The analysis encompassed 49 studies conducted between 2019 and 2023 that utilized artificial intelligence methods and any medical imaging modality for the detection or segmentation of intracranial aneurysms. Most of the included studies focused exclusively on detection (57%), magnetic resonance angiography was the predominant imaging modality (47%), and the methodologies generally used 3D imaging as the input (71%). The reported sensitivities ranged from 0.68 to 0.90, specificities from 0.18 to 1.0, false positives per case from 0.18 to 13.8, and the Dice similarity coefficient from 0.53 to 0.98. Variations in aneurysm size were found to have a substantial impact on system performance. Studies were evaluated using a diagnostic accuracy study quality assessment tool, which revealed significant concerns regarding applicability. These concerns primarily stem from the poor reproducibility and inconsistent reporting of metrics. Recommendations for reporting outcomes were made to compare procedures across different types of imaging and tasks.

Building a Synthetic Vascular Model: Evaluation in an Intracranial Aneurysms Detection Scenario

We hereby present a full synthetic model, able to mimic the various constituents of the cerebral vascular tree, including the cerebral arteries, bifurcations and intracranial aneurysms. This model intends to provide a substantial dataset of brain arteries which could be used by a 3D convolutional neural network to efficiently detect Intra-Cranial Aneurysms. The cerebral aneurysms most often occur on a particular structure of the vascular tree named the Circle of Willis. Various studies have been conducted to detect and monitor the aneurysms and those based on Deep Learning achieve the best performance. Specifically, in this work, we propose a full synthetic 3D model able to mimic the brain vasculature as acquired by Magnetic Resonance Angiography, Time Of Flight principle. Among the various MRI modalities, this latter allows for a good rendering of the blood vessels and is non-invasive. Our model has been designed to simultaneously mimic the arteries' geometry, the aneurysm shape, and the background noise. The vascular tree geometry is modeled thanks to an interpolation with 3D Spline functions, and the statistical properties of the background noise is collected from angiography acquisitions and reproduced within the model. In this work, we thoroughly describe the synthetic vasculature model, we build up a neural network designed for aneurysm segmentation and detection, finally, we carry out an in-depth evaluation of the performance gap gained thanks to the synthetic model data augmentation.

Intracranial aneurysm CTA images and 3D models dataset with clinical morphological and hemodynamic data

Intracranial aneurysm is a cerebrovascular disease associated with a high rupture risk, often resulting in death or severe disability. Recent advances in AI enable the prediction of intracranial aneurysm initiation, progression, and rupture through medical image analysis. Despite growing research interest, there is a shortage of publicly available datasets for training and validating AI models. This paper presents a comprehensive dataset comprising high-resolution CTA images of 99 patients with 105 MCA aneurysms and 44 normal healthy controls, along with their respective clinical data and 3D models of aneurysms and the parent arteries derived from the CTA images. Furthermore, recognizing the significance of blood hemodynamics on aneurysm development, this dataset also included the morphological and hemodynamic parameters obtained by computational fluid dynamics (CFD) for each patient and healthy control, which can be utilized by researchers without prior CFD experience. This dataset will facilitate hypothesis-driven or data-driven research on intracranial aneurysms, and has the potential to deepen our understanding of this disease.

Deep geometric learning for intracranial aneurysm detection: towards expert rater performance

BACKGROUND

Early detection of intracranial aneurysms (IAs) is crucial for patient outcomes. Typically identified on angiographic scans such as CT angiography (CTA) or MR angiography (MRA), the sensitivity of experts in studies on small IAs (diameter <3 mm) was moderate (64-74.1% for CTAs and 70-92.8% for MRAs), and these figures could be lower in a routine clinical setting. Recent research shows that the expert level of sensitivity might be achieved using deep learning approaches.

METHODS

A large multisite dataset including 1054 MRA and 2174 CTA scans with expert IA annotations was collected. A novel modality-agnostic two-step IA detection approach was proposed. The first step used nnU-Net for segmenting vascular structures, with model training performed separately for each modality. In the second step, segmentations were converted to vascular surface that was parcellated by sampling point clouds and, using a PointNet++ model, each point was labeled as an aneurysm or vessel class.

RESULTS

Quantitative validation of the test data from different sites than the training data showed that the proposed approach achieved pooled sensitivity of 85% and 90% on 157 MRA scans and 1338 CTA scans, respectively, while the sensitivity for small IAs was 72% and 83%, respectively. The corresponding number of false findings per image was low at 1.54 and 1.57, and 0.4 and 0.83 on healthy subject data.

CONCLUSIONS

The proposed approach achieved a state-of-the-art balance between the sensitivity and the number of false findings, matched the expert-level sensitivity to small (and other) IAs on external data, and therefore seems fit for computer-assisted detection of IAs in a clinical setting.

Morphology and Texture-Guided Deep Neural Network for Intracranial Aneurysm Segmentation in 3D TOF-MRA

This study concentrates on the segmentation of intracranial aneurysms, a pivotal aspect of diagnosis and treatment planning. We aim to overcome the inherent instance imbalance and morphological variability by introducing a novel morphology and texture loss reweighting approach. Our innovative method involves the incorporation of tailored weights within the loss function of deep neural networks. Specifically designed to account for aneurysm size, shape, and texture, this approach strategically guides the model to focus on capturing discriminative information from imbalanced features. The study conducted extensive experimentation utilizing ADAM and RENJI TOF-MRA datasets to validate the proposed approach. The results of our experimentation demonstrate the remarkable effectiveness of the introduced methodology in improving aneurysm segmentation accuracy. By dynamically adapting to the variances present in aneurysm features, our model showcases promising outcomes for accurate diagnostic insights. The nuanced consideration of morphological and textural nuances within the loss function proves instrumental in overcoming the challenge posed by instance imbalance. In conclusion, our study presents a nuanced solution to the intricate challenge of intracranial aneurysm segmentation. The proposed morphology and texture loss reweighting approach, with its tailored weights and dynamic adaptability, proves to be instrumental in enhancing segmentation precision. The promising outcomes from our experimentation suggest the potential for accurate diagnostic insights and informed treatment strategies, marking a significant advancement in this critical domain of medical imaging.

Intracranial aneurysm detection: an object detection perspective

PURPOSE

Intracranial aneurysm detection from 3D Time-Of-Flight Magnetic Resonance Angiography images is a problem of increasing clinical importance. Recently, a streak of methods have shown promising performance by using segmentation neural networks. However, these methods may be less relevant in a clinical settings where diagnostic decisions rely on detecting objects rather than their segmentation.

METHODS

We introduce a 3D single-stage object detection method tailored for small object detection such as aneurysms. Our anchor-free method incorporates fast data annotation, adapted data sampling and generation to address class imbalance problem, and spherical representations for improved detection.

RESULTS

A comprehensive evaluation was conducted, comparing our method with the state-of-the-art SCPM-Net, nnDetection and nnUNet baselines, using two datasets comprising 402 subjects. The evaluation used adapted object detection metrics. Our method exhibited comparable or superior performance, with an average precision of 78.96%, sensitivity of 86.78%, and 0.53 false positives per case.

CONCLUSION

Our method significantly reduces the detection complexity compared to existing methods and highlights the advantages of object detection over segmentation-based approaches for aneurysm detection. It also holds potential for application to other small object detection problems.

Quantifying irregular pulsation of intracranial aneurysms using 4D-CTA

Recent studies have suggested that irregular pulsation of intracranial aneurysm during the cardiac cycle may be potentially associated with aneurysm rupture risk. However, there is a lack of quantification method for irregular pulsations. This study aims to quantify irregular pulsations by the displacement and strain distribution of the intracranial aneurysm surface during the cardiac cycle using four-dimensional CT angiographic image data. Four-dimensional CT angiography was performed in 8 patients. The image data of a cardiac cycle was divided into approximately 20 phases, and irregular pulsations were detected in four intracranial aneurysms by visual observation, and then the displacement and strain of the intracranial aneurysm was quantified using coherent point drift and finite element method. The displacement and strain were compared between aneurysms with irregular and normal pulsations in two different ways (total and stepwise). The stepwise first principal strain was significantly higher in aneurysms with irregular than normal pulsations (0.20±0.01 vs 0.16±0.02, p=0.033). It was found that the irregular pulsations in intracranial aneurysms usually occur during the consecutive ascending or descending phase of volume changes during the cardiac cycle. In addition, no statistically significant difference was found in the aneurysm volume changes over the cardiac cycle between the two groups. Our method can successfully quantify the displacement and strain changes in the intracranial aneurysm during the cardiac cycle, which may be proven to be a useful tool to quantify intracranial aneurysm deformability and aid in aneurysm rupture risk assessment.

Deep learning-based platform performs high detection sensitivity of intracranial aneurysms in 3D brain TOF-MRA: An external clinical validation study

PURPOSE

To evaluate the diagnostic efficacy of a developed artificial intelligence (AI) platform incorporating deep learning algorithms for the automated detection of intracranial aneurysms in time-of-flight (TOF) magnetic resonance angiography (MRA).

METHOD

This retrospective study encompassed 3D TOF MRA images acquired between January 2023 and June 2023, aiming to validate the presence of intracranial aneurysms via our developed AI platform. The manual segmentation results by experienced neuroradiologists served as the "gold standard". Following annotation of MRA images by neuroradiologists using InferScholar software, the AI platform conducted automatic segmentation of intracranial aneurysms. Various metrics including accuracy (ACC), balanced ACC, area under the curve (AUC), sensitivity (SE), specificity (SP), F1 score, Brier Score, and Net Benefit were utilized to evaluate the generalization of AI platform. Comparison of intracranial aneurysm identification performance was conducted between the AI platform and six radiologists with experience ranging from 3 to 12 years in interpreting MR images. Additionally, a comparative analysis was carried out between radiologists' detection performance based on independent visual diagnosis and AI-assisted diagnosis. Subgroup analyses were also performed based on the size and location of the aneurysms to explore factors impacting aneurysm detectability.

RESULTS

510 patients were enrolled including 215 patients (42.16 %) with intracranial aneurysms and 295 patients (57.84 %) without aneurysms. Compared with six radiologists, the AI platform showed competitive discrimination power (AUC, 0.96), acceptable calibration (Brier Score loss, 0.08), and clinical utility (Net Benefit, 86.96 %). The AI platform demonstrated superior performance in detecting aneurysms with an overall SE, SP, ACC, balanced ACC, and F1 score of 91.63 %, 92.20 %, 91.96 %, 91.92 %, and 90.57 % respectively, outperforming the detectability of the two resident radiologists. For subgroup analysis based on aneurysm size and location, we observed that the SE of the AI platform for identifying tiny (diameter＜3mm), small (3 mm ≤ diameter＜5mm), medium (5 mm ≤ diameter＜7mm) and large aneurysms (diameter ≥ 7 mm) was 87.80 %, 93.14 %, 95.45 %, and 100 %, respectively. Furthermore, the SE for detecting aneurysms in the anterior circulation was higher than that in the posterior circulation. Utilizing the AI assistance, six radiologists (i.e., two residents, two attendings and two professors) achieved statistically significant improvements in mean SE (residents: 71.40 % vs. 88.37 %; attendings: 82.79 % vs. 93.26 %; professors: 90.07 % vs. 97.44 %; P < 0.05) and ACC (residents: 85.29 % vs. 94.12 %; attendings: 91.76 % vs. 97.06 %; professors: 95.29 % vs. 98.82 %; P < 0.05) while no statistically significant change was observed in SP. Overall, radiologists' mean SE increased by 11.40 %, mean SP increased by 1.86 %, and mean ACC increased by 5.88 %, mean balanced ACC promoted by 6.63 %, mean F1 score grew by 7.89 %, and Net Benefit rose by 12.52 %, with a concurrent decrease in mean Brier score declined by 0.06.

CONCLUSIONS

The deep learning algorithms implemented in the AI platform effectively detected intracranial aneurysms on TOF-MRA and notably enhanced the diagnostic capabilities of radiologists. This indicates that the AI-based auxiliary diagnosis model can provide dependable and precise prediction to improve the diagnostic capacity of radiologists.

Classification, detection, and segmentation performance of image-based AI in intracranial aneurysm: a systematic review

BACKGROUND

The detection and management of intracranial aneurysms (IAs) are vital to prevent life-threatening complications like subarachnoid hemorrhage (SAH). Artificial Intelligence (AI) can analyze medical images, like CTA or MRA, spotting nuances possibly overlooked by humans. Early detection facilitates timely interventions and improved outcomes. Moreover, AI algorithms offer quantitative data on aneurysm attributes, aiding in long-term monitoring and assessing rupture risks.

METHODS

We screened four databases (PubMed, Web of Science, IEEE and Scopus) for studies using artificial intelligence algorithms to identify IA. Based on algorithmic methodologies, we categorized them into classification, segmentation, detection and combined, and then their merits and shortcomings are compared. Subsequently, we elucidate potential challenges that contemporary algorithms might encounter within real-world clinical diagnostic contexts. Then we outline prospective research trajectories and underscore key concerns in this evolving field.

RESULTS

Forty-seven studies of IA recognition based on AI were included based on search and screening criteria. The retrospective results represent that current studies can identify IA in different modal images and predict their risk of rupture and blockage. In clinical diagnosis, AI can effectively improve the diagnostic accuracy of IA and reduce missed detection and false positives.

CONCLUSIONS

The AI algorithm can detect unobtrusive IA more accurately in communicating arteries and cavernous sinus arteries to avoid further expansion. In addition, analyzing aneurysm rupture and blockage before and after surgery can help doctors plan treatment and reduce the uncertainties in the treatment process.

Multiple angle key points detection guided screening of unruptured intracranial aneurysms

Early screening of unruptured intracranial aneurysms is critical for disease control so as to attract a lot of attention. However, the extremly small size of lesions and large variance of appearances pose difficulties in algorithm modeling. To tackle this challenge, the paper proposes a multiple angle key points detection guided screening method for localization and segmentation of intracranial aneurysms. The proposed method consists of two modules, multiple angle key points detection and multi-task learning based segmentation. The key points detection is performed on multiple projection directions thus to localize aneurysms candidates. Once obtaining region of interest patches, segmentation models constrained by parallel multi downstream task headers perform the delineation accordingly. Validation has been performed on a dataset containing computational tomograhpic angiography scans of patients with intracranial aneurysms. Results have shown that the proposed method could significantly improve segmentation and detection performance from target-wise and voxel-wise point of views, which have also demonstrated its effectiveness and application prospects.

Accelerated simulation methodologies for computational vascular flow modelling

Vascular flow modelling can improve our understanding of vascular pathologies and aid in developing safe and effective medical devices. Vascular flow models typically involve solving the nonlinear Navier-Stokes equations in complex anatomies and using physiological boundary conditions, often presenting a multi-physics and multi-scale computational problem to be solved. This leads to highly complex and expensive models that require excessive computational time. This review explores accelerated simulation methodologies, specifically focusing on computational vascular flow modelling. We review reduced order modelling (ROM) techniques like zero-/one-dimensional and modal decomposition-based ROMs and machine learning (ML) methods including ML-augmented ROMs, ML-based ROMs and physics-informed ML models. We discuss the applicability of each method to vascular flow acceleration and the effectiveness of the method in addressing domain-specific challenges. When available, we provide statistics on accuracy and speed-up factors for various applications related to vascular flow simulation acceleration. Our findings indicate that each type of model has strengths and limitations depending on the context. To accelerate real-world vascular flow problems, we propose future research on developing multi-scale acceleration methods capable of handling the significant geometric variability inherent to such problems.

Where is VALDO? VAscular Lesions Detection and segmentatiOn challenge at MICCAI 2021

Imaging markers of cerebral small vessel disease provide valuable information on brain health, but their manual assessment is time-consuming and hampered by substantial intra- and interrater variability. Automated rating may benefit biomedical research, as well as clinical assessment, but diagnostic reliability of existing algorithms is unknown. Here, we present the results of the VAscular Lesions DetectiOn and Segmentation (Where is VALDO?) challenge that was run as a satellite event at the international conference on Medical Image Computing and Computer Aided Intervention (MICCAI) 2021. This challenge aimed to promote the development of methods for automated detection and segmentation of small and sparse imaging markers of cerebral small vessel disease, namely enlarged perivascular spaces (EPVS) (Task 1), cerebral microbleeds (Task 2) and lacunes of presumed vascular origin (Task 3) while leveraging weak and noisy labels. Overall, 12 teams participated in the challenge proposing solutions for one or more tasks (4 for Task 1-EPVS, 9 for Task 2-Microbleeds and 6 for Task 3-Lacunes). Multi-cohort data was used in both training and evaluation. Results showed a large variability in performance both across teams and across tasks, with promising results notably for Task 1-EPVS and Task 2-Microbleeds and not practically useful results yet for Task 3-Lacunes. It also highlighted the performance inconsistency across cases that may deter use at an individual level, while still proving useful at a population level.

Geometric Deep Learning Using Vascular Surface Meshes for Modality-Independent Unruptured Intracranial Aneurysm Detection

Early detection of unruptured intracranial aneurysms (UIAs) enables better rupture risk and preventative treatment assessment. UIAs are usually diagnosed on Time-of-Flight Magnetic Resonance Angiographs (TOF-MRA) or contrast-enhanced Computed Tomography Angiographs (CTA). Various automatic voxel-based deep learning UIA detection methods have been developed, but these are limited to a single modality. We propose a modality-independent UIA detection method using a geometric deep learning model with high resolution surface meshes of brain vessels. A mesh convolutional neural network with ResU-Net style architecture was used. UIA detection performance was investigated with different input and pooling mesh resolutions, and including additional edge input features (shape index and curvedness). Both a higher resolution mesh (15,000 edges) and additional curvature edge features improved performance (average sensitivity: 65.6%, false positive count/image (FPC/image): 1.61). UIAs were detected in an independent TOF-MRA test set and a CTA test set with average sensitivity of 52.0% and 48.3% and average FPC/image of 1.04 and 1.05 respectively. We provide modality-independent UIA detection using a deep-learning vascular surface mesh model with comparable performance to state-of-the-art UIA detection methods.

CFANet: Context Feature Fusion and Attention Mechanism Based Network for Small Target Segmentation in Medical Images

Medical image segmentation plays a crucial role in clinical diagnosis, treatment planning, and disease monitoring. The automatic segmentation method based on deep learning has developed rapidly, with segmentation results comparable to clinical experts for large objects, but the segmentation accuracy for small objects is still unsatisfactory. Current segmentation methods based on deep learning find it difficult to extract multiple scale features of medical images, leading to an insufficient detection capability for smaller objects. In this paper, we propose a context feature fusion and attention mechanism based network for small target segmentation in medical images called CFANet. CFANet is based on U-Net structure, including the encoder and the decoder, and incorporates two key modules, context feature fusion (CFF) and effective channel spatial attention (ECSA), in order to improve segmentation performance. The CFF module utilizes contextual information from different scales to enhance the representation of small targets. By fusing multi-scale features, the network captures local and global contextual cues, which are critical for accurate segmentation. The ECSA module further enhances the network's ability to capture long-range dependencies by incorporating attention mechanisms at the spatial and channel levels, which allows the network to focus on information-rich regions while suppressing irrelevant or noisy features. Extensive experiments are conducted on four challenging medical image datasets, namely ADAM, LUNA16, Thoracic OAR, and WORD. Experimental results show that CFANet outperforms state-of-the-art methods in terms of segmentation accuracy and robustness. The proposed method achieves excellent performance in segmenting small targets in medical images, demonstrating its potential in various clinical applications.

Using deep learning for an automatic detection and classification of the vascular bifurcations along the Circle of Willis

Most of the intracranial aneurysms (ICA) occur on a specific portion of the cerebral vascular tree named the Circle of Willis (CoW). More particularly, they mainly arise onto fifteen of the major arterial bifurcations constituting this circular structure. Hence, for an efficient and timely diagnosis it is critical to develop some methods being able to accurately recognize each Bifurcation of Interest (BoI). Indeed, an automatic extraction of the bifurcations presenting the higher risk of developing an ICA would offer the neuroradiologists a quick glance at the most alarming areas. Due to the recent efforts on Artificial Intelligence, Deep Learning turned out to be the best performing technology for many pattern recognition tasks. Moreover, various methods have been particularly designed for medical image analysis purposes. This study intends to assist the neuroradiologists to promptly locate any bifurcation presenting a high risk of ICA occurrence. It can be seen as a Computer Aided Diagnosis scheme, where the Artificial Intelligence facilitates the access to the regions of interest within the MRI. In this work, we propose a method for a fully automatic detection and recognition of the bifurcations of interest forming the Circle of Willis. Several neural networks architectures have been tested, and we thoroughly evaluate the bifurcation recognition rate.

StrokeNet: An automated approach for segmentation and rupture risk prediction of intracranial aneurysm

Intracranial Aneurysms (IA) present a complex challenge for neurosurgeons as the risks associated with surgical intervention, such as Subarachnoid Hemorrhage (SAH) mortality and morbidity, may outweigh the benefits of aneurysmal occlusion in some cases. Hence, there is a critical need for developing techniques that assist physicians in assessing the risk of aneurysm rupture to determine which aneurysms require treatment. However, a reliable IA rupture risk prediction technique is currently unavailable. To address this issue, this study proposes a novel approach for aneurysm segmentation and multidisciplinary rupture prediction using 2D Digital Subtraction Angiography (DSA) images. The proposed method involves training a fully connected convolutional neural network (CNN) to segment aneurysm regions in DSA images, followed by extracting and fusing different features using a multidisciplinary approach, including deep features, geometrical features, Fourier descriptor, and shear pressure on the aneurysm wall. The proposed method also adopts a fast correlation-based filter approach to drop highly correlated features from the set of fused features. Finally, the selected fused features are passed through a Decision Tree classifier to predict the rupture severity of the associated aneurysm into four classes: Mild, Moderate, Severe, and Critical. The proposed method is evaluated on a newly developed DSA image dataset and on public datasets to assess its generalizability. The system's performance is also evaluated on DSA images annotated by expert neurosurgeons for the rupture risk assessment of the segmented aneurysm. The proposed system outperforms existing state-of-the-art segmentation methods, achieving an 85 % accuracy against annotated DSA images for the risk assessment of aneurysmal rupture.

Automated detection of intracranial aneurysms using skeleton-based 3D patches, semantic segmentation, and auxiliary classification for overcoming data imbalance in brain TOF-MRA

Accurate and reliable detection of intracranial aneurysms is vital for subsequent treatment to prevent bleeding. However, the detection of intracranial aneurysms can be time-consuming and even challenging, and there is great variability among experts, especially in the case of small aneurysms. This study aimed to detect intracranial aneurysms accurately using a convolutional neural network (CNN) with 3D time-of-flight magnetic resonance angiography (TOF-MRA). A total of 154 3D TOF-MRA datasets with intracranial aneurysms were acquired, and the gold standards were manually drawn by neuroradiologists. We also obtained 113 subjects from a public dataset for external validation. These angiograms were pre-processed by using skull-stripping, signal intensity normalization, and N4 bias correction. The 3D patches along the vessel skeleton from MRA were extracted. Values of the ratio between the aneurysmal and the normal patches ranged from 1:1 to 1:5. The semantic segmentation on intracranial aneurysms was trained using a 3D U-Net with an auxiliary classifier to overcome the imbalance in patches. The proposed method achieved an accuracy of 0.910 in internal validation and external validation accuracy of 0.883 with a 2:1 ratio of normal to aneurysmal patches. This multi-task learning method showed that the aneurysm segmentation performance was sufficient to be helpful in an actual clinical setting.

Detection of cerebral aneurysms using artificial intelligence: a systematic review and meta-analysis

BACKGROUND

Subarachnoid hemorrhage from cerebral aneurysm rupture is a major cause of morbidity and mortality. Early aneurysm identification, aided by automated systems, may improve patient outcomes. Therefore, a systematic review and meta-analysis of the diagnostic accuracy of artificial intelligence (AI) algorithms in detecting cerebral aneurysms using CT, MRI or DSA was performed.

METHODS

MEDLINE, Embase, Cochrane Library and Web of Science were searched until August 2021. Eligibility criteria included studies using fully automated algorithms to detect cerebral aneurysms using MRI, CT or DSA. Following Preferred Reporting Items for Systematic Reviews and Meta-Analysis: Diagnostic Test Accuracy (PRISMA-DTA), articles were assessed using Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). Meta-analysis included a bivariate random-effect model to determine pooled sensitivity, specificity, and area under the receiver operator characteristic curve (ROC-AUC).

PROSPERO

CRD42021278454.

RESULTS

43 studies were included, and 41/43 (95%) were retrospective. 34/43 (79%) used AI as a standalone tool, while 9/43 (21%) used AI assisting a reader. 23/43 (53%) used deep learning. Most studies had high bias risk and applicability concerns, limiting conclusions. Six studies in the standalone AI meta-analysis gave (pooled) 91.2% (95% CI 82.2% to 95.8%) sensitivity; 16.5% (95% CI 9.4% to 27.1%) false-positive rate (1-specificity); 0.936 ROC-AUC. Five reader-assistive AI studies gave (pooled) 90.3% (95% CI 88.0% - 92.2%) sensitivity; 7.9% (95% CI 3.5% to 16.8%) false-positive rate; 0.910 ROC-AUC.

CONCLUSION

AI has the potential to support clinicians in detecting cerebral aneurysms. Interpretation is limited due to high risk of bias and poor generalizability. Multicenter, prospective studies are required to assess AI in clinical practice.

Towards Automated Brain Aneurysm Detection in TOF-MRA: Open Data, Weak Labels, and Anatomical Knowledge

Brain aneurysm detection in Time-Of-Flight Magnetic Resonance Angiography (TOF-MRA) has undergone drastic improvements with the advent of Deep Learning (DL). However, performances of supervised DL models heavily rely on the quantity of labeled samples, which are extremely costly to obtain. Here, we present a DL model for aneurysm detection that overcomes the issue with "weak" labels: oversized annotations which are considerably faster to create. Our weak labels resulted to be four times faster to generate than their voxel-wise counterparts. In addition, our model leverages prior anatomical knowledge by focusing only on plausible locations for aneurysm occurrence. We first train and evaluate our model through cross-validation on an in-house TOF-MRA dataset comprising 284 subjects (170 females / 127 healthy controls / 157 patients with 198 aneurysms). On this dataset, our best model achieved a sensitivity of 83%, with False Positive (FP) rate of 0.8 per patient. To assess model generalizability, we then participated in a challenge for aneurysm detection with TOF-MRA data (93 patients, 20 controls, 125 aneurysms). On the public challenge, sensitivity was 68% (FP rate = 2.5), ranking 4th/18 on the open leaderboard. We found no significant difference in sensitivity between aneurysm risk-of-rupture groups (p = 0.75), locations (p = 0.72), or sizes (p = 0.15). Data, code and model weights are released under permissive licenses. We demonstrate that weak labels and anatomical knowledge can alleviate the necessity for prohibitively expensive voxel-wise annotations.

Fast and Low-GPU-memory abdomen CT organ segmentation: The FLARE challenge

Automatic segmentation of abdominal organs in CT scans plays an important role in clinical practice. However, most existing benchmarks and datasets only focus on segmentation accuracy, while the model efficiency and its accuracy on the testing cases from different medical centers have not been evaluated. To comprehensively benchmark abdominal organ segmentation methods, we organized the first Fast and Low GPU memory Abdominal oRgan sEgmentation (FLARE) challenge, where the segmentation methods were encouraged to achieve high accuracy on the testing cases from different medical centers, fast inference speed, and low GPU memory consumption, simultaneously. The winning method surpassed the existing state-of-the-art method, achieving a 19× faster inference speed and reducing the GPU memory consumption by 60% with comparable accuracy. We provide a summary of the top methods, make their code and Docker containers publicly available, and give practical suggestions on building accurate and efficient abdominal organ segmentation models. The FLARE challenge remains open for future submissions through a live platform for benchmarking further methodology developments at https://flare.grand-challenge.org/.

A coarse-to-fine cascade deep learning neural network for segmenting cerebral aneurysms in time-of-flight magnetic resonance angiography

BACKGROUND

Accurate segmentation of unruptured cerebral aneurysms (UCAs) is essential to treatment planning and rupture risk assessment. Currently, three-dimensional time-of-flight magnetic resonance angiography (3D TOF-MRA) has been the most commonly used method for screening aneurysms due to its noninvasiveness. The methods based on deep learning technologies can assist radiologists in achieving accurate and reliable analysis of the size and shape of aneurysms, which may be helpful in rupture risk prediction models. However, the existing methods did not accomplish accurate segmentation of cerebral aneurysms in 3D TOF-MRA.

METHODS

This paper proposed a CCDU-Net for segmenting UCAs of 3D TOF-MRA images. The CCDU-Net was a cascade of a convolutional neural network for coarse segmentation and the proposed DU-Net for fine segmentation. Especially, the dual-channel inputs of DU-Net were composed of the vessel image and its contour image which can augment the vascular morphological information. Furthermore, a newly designed weighted loss function was used in the training process of DU-Net to promote the segmentation performance.

RESULTS

A total of 270 patients with UCAs were enrolled in this study. The images were divided into the training (N = 174), validation (N = 43), and testing (N = 53) cohorts. The CCDU-Net achieved a dice similarity coefficient (DSC) of 0.616 ± 0.167, Hausdorff distance (HD) of 5.686 ± 7.020 mm, and volumetric similarity (VS) of 0.752 ± 0.226 in the testing cohort. Compared with the existing best method, the DSC and VS increased by 18% and 5%, respectively, while the HD decreased by one-tenth.

CONCLUSIONS

We proposed a CCDU-Net for segmenting UCAs in 3D TOF-MRA, and the obtained results show that the proposed method outperformed other existing methods.

A domain adaptation benchmark for T1-weighted brain magnetic resonance image segmentation

Accurate brain segmentation is critical for magnetic resonance imaging (MRI) analysis pipelines. Machine-learning-based brain MR image segmentation methods are among the state-of-the-art techniques for this task. Nevertheless, the segmentations produced by machine learning models often degrade in the presence of expected domain shifts between the test and train sets data distributions. These domain shifts are expected due to several factors, such as scanner hardware and software differences, technology updates, and differences in MRI acquisition parameters. Domain adaptation (DA) methods can make machine learning models more resilient to these domain shifts. This paper proposes a benchmark for investigating DA techniques for brain MR image segmentation using data collected across sites with scanners from different vendors (Philips, Siemens, and General Electric). Our work provides labeled data, publicly available source code for a set of baseline and DA models, and a benchmark for assessing different brain MR image segmentation techniques. We applied the proposed benchmark to evaluate two segmentation tasks: skull-stripping; and white-matter, gray-matter, and cerebrospinal fluid segmentation, but the benchmark can be extended to other brain structures. Our main findings during the development of this benchmark are that there is not a single DA technique that consistently outperforms others, and hyperparameter tuning and computational times for these methods still pose a challenge before broader adoption of these methods in the clinical practice.

Automatic quantification of perivascular spaces in T2-weighted images at 7 T MRI

Perivascular spaces (PVS) are believed to be involved in brain waste disposal. PVS are associated with cerebral small vessel disease. At higher field strengths more PVS can be observed, challenging manual assessment. We developed a method to automatically detect and quantify PVS. A machine learning approach identified PVS in an automatically positioned ROI in the centrum semiovale (CSO), based on -resolution T2-weighted TSE scans. Next, 3D PVS tracking was performed in 50 subjects (mean age 62.9 years (range 27-78), 19 male), and quantitative measures were extracted. Maps of PVS density, length, and tortuosity were created. Manual PVS annotations were available to train and validate the automatic method. Good correlation was found between the automatic and manual PVS count: ICC (absolute/consistency) is 0.64/0.75, and Dice similarity coefficient (DSC) is 0.61. The automatic method counts fewer PVS than the manual count, because it ignores the smallest PVS (length <2 mm). For 20 subjects manual PVS annotations of a second observer were available. Compared with the correlation between the automatic and manual PVS, higher inter-observer ICC was observed (0.85/0.88), but DSC was lower (0.49 in 4 persons). Longer PVS are observed posterior in the CSO compared with anterior in the CSO. Higher PVS tortuosity are observed in the center of the CSO compared with the periphery of the CSO. Our fully automatic method can detect PVS in a 2D slab in the CSO, and extract quantitative PVS parameters by performing 3D tracking. This method enables automated quantitative analysis of PVS.

Detection and analysis of cerebral aneurysms based on X-ray rotational angiography - the CADA 2020 challenge

The Cerebral Aneurysm Detection and Analysis (CADA) challenge was organized to support the development and benchmarking of algorithms for detecting, analyzing, and risk assessment of cerebral aneurysms in X-ray rotational angiography (3DRA) images. 109 anonymized 3DRA datasets were provided for training, and 22 additional datasets were used to test the algorithmic solutions. Cerebral aneurysm detection was assessed using the F2 score based on recall and precision, and the fit of the delivered bounding box was assessed using the distance to the aneurysm. The segmentation quality was measured using the Jaccard index and a combination of different surface distance measures. Systematic errors were analyzed using volume correlation and bias. Rupture risk assessment was evaluated using the F2 score. 158 participants from 22 countries registered for the CADA challenge. The U-Net-based detection solutions presented by the community show similar accuracy compared to experts (F2 score 0.92), with a small number of missed aneurysms with diameters smaller than 3.5 mm. In addition, the delineation of these structures, based on U-Net variations, is excellent, with a Jaccard score of 0.92. The rupture risk estimation methods achieved an F2 score of 0.71. The performance of the detection and segmentation solutions is equivalent to that of human experts. The best results are obtained in rupture risk estimation by combining different image-based, morphological, and computational fluid dynamic parameters using machine learning methods. Furthermore, we evaluated the best methods pipeline, from detecting and delineating the vessel dilations to estimating the risk of rupture. The chain of these methods achieves an F2-score of 0.70, which is comparable to applying the risk prediction to the ground-truth delineation (0.71).

Relationship between 3D Morphologic Change and 2D and 3D Growth of Unruptured Intracranial Aneurysms

BACKGROUND AND PURPOSE

Untreated unruptured intracranial aneurysms are usually followed radiologically to detect aneurysm growth, which is associated with increased rupture risk. The ideal aneurysm size cutoff for defining growth remains unclear and also whether change in morphology should be part of the definition. We investigated the relationship between change in aneurysm size and 3D quantified morphologic changes during follow-up.

MATERIALS AND METHODS

We performed 3D morphology measurements of unruptured intracranial aneurysms on baseline and follow-up TOF-MRAs. Morphology measurements included surface area, compactness, elongation, flatness, sphericity, shape index, and curvedness. We investigated the relation between morphologic change between baseline and follow-up scans and unruptured intracranial aneurysm growth, with 2D and 3D growth defined as a continuous variable (correlation statistics) and a categoric variable (t test statistics). Categoric growth was defined as ≥1-mm increase in 2D length or width. We assessed unruptured intracranial aneurysms that changed in morphology and the proportion of growing and nongrowing unruptured intracranial aneurysms with statistically significant morphologic change.

RESULTS

We included 113 patients with 127 unruptured intracranial aneurysms. Continuous growth of unruptured intracranial aneurysms was related to an increase in surface area and flatness and a decrease in the shape index and curvedness. In 15 growing unruptured intracranial aneurysms (12%), curvedness changed significantly compared with nongrowing unruptured intracranial aneurysms. Of the 112 nongrowing unruptured intracranial aneurysms, 10 (9%) changed significantly in morphology (flatness, shape index, and curvedness).

CONCLUSIONS

Growing unruptured intracranial aneurysms show morphologic change. However, nearly 10% of nongrowing unruptured intracranial aneurysms change in morphology, suggesting that they could be unstable. Future studies should investigate the best growth definition including morphologic change and size to predict aneurysm rupture.

Morphology-aware multi-source fusion-based intracranial aneurysms rupture prediction

OBJECTIVES

We proposed a new approach to train deep learning model for aneurysm rupture prediction which only uses a limited amount of labeled data.

METHOD

Using segmented aneurysm mask as input, a backbone model was pretrained using a self-supervised method to learn deep embeddings of aneurysm morphology from 947 unlabeled cases of angiographic images. Subsequently, the backbone model was finetuned using 120 labeled cases with known rupture status. Clinical information was integrated with deep embeddings to further improve prediction performance. The proposed model was compared with radiomics and conventional morphology models in prediction performance. An assistive diagnosis system was also developed based on the model and was tested with five neurosurgeons.

RESULT

Our method achieved an area under the receiver operating characteristic curve (AUC) of 0.823, outperforming deep learning model trained from scratch (0.787). By integrating with clinical information, the proposed model's performance was further improved to AUC = 0.853, making the results significantly better than model based on radiomics (AUC = 0.805, p = 0.007) or model based on conventional morphology parameters (AUC = 0.766, p = 0.001). Our model also achieved the highest sensitivity, PPV, NPV, and accuracy among the others. Neurosurgeons' prediction performance was improved from AUC=0.877 to 0.945 (p = 0.037) with the assistive diagnosis system.

CONCLUSION

Our proposed method could develop competitive deep learning model for rupture prediction using only a limited amount of data. The assistive diagnosis system could be useful for neurosurgeons to predict rupture.

KEY POINTS

• A self-supervised learning method was proposed to mitigate the data-hungry issue of deep learning, enabling training deep neural network with a limited amount of data. • Using the proposed method, deep embeddings were extracted to represent intracranial aneurysm morphology. Prediction model based on deep embeddings was significantly better than conventional morphology model and radiomics model. • An assistive diagnosis system was developed using deep embeddings for case-based reasoning, which was shown to significantly improve neurosurgeons' performance to predict rupture.