A deep learning algorithm for automatic detection and classification of acute intracranial hemorrhages in head CT scans

Intracranial hemorrhage segmentation and classification framework in computer tomography images using deep learning techniques

By helping the neurosurgeon create treatment strategies that increase the survival rate, automotive diagnosis and CT (Computed Tomography) hemorrhage segmentation (CT) could be beneficial. Owing to the significance of medical image segmentation and the difficulties in carrying out human operations, a wide variety of automated techniques for this purpose have been developed, with a primary focus on particular image modalities. In this paper, MUNet (Multiclass-UNet) based Intracranial Hemorrhage Segmentation and Classification Framework (IHSNet) is proposed to successfully segment multiple kinds of hemorrhages while the fully connected layers help in classifying the type of hemorrhages.The segmentation accuracy rates for hemorrhages are 98.53% with classification accuracy stands at 98.71% when using the suggested approach. There is potential for this suggested approach to be expanded in the future to handle further medical picture segmentation issues. Intraventricular hemorrhage (IVH), Epidural hemorrhage (EDH), Intraparenchymal hemorrhage (IPH), Subdural hemorrhage (SDH), Subarachnoid hemorrhage (SAH) are the subtypes involved in intracranial hemorrhage (ICH) whose DICE coefficients are 0.77, 0.84, 0.64, 0.80, and 0.92 respectively.The proposed method has great deal of clinical application potential for computer-aided diagnostics, which can be expanded in the future to handle further medical picture segmentation and to tackle with the involved issues.

Development of a deep-learning algorithm for etiological classification of subarachnoid hemorrhage using non-contrast CT scans

OBJECTIVES

This study aims to develop a deep learning algorithm for differentiating aneurysmal subarachnoid hemorrhage (aSAH) from non-aneurysmal subarachnoid hemorrhage (naSAH) using non-contrast computed tomography (NCCT) scans.

METHODS

This retrospective study included 618 patients diagnosed with SAH. The dataset was divided into a training and internal validation cohort (533 cases: aSAH = 305, naSAH = 228) and an external test cohort (85 cases: aSAH = 55, naSAH = 30). Hemorrhage regions were automatically segmented using a U-Net + + architecture. A ResNet-based deep learning model was trained to classify the etiology of SAH.

RESULTS

The model achieved robust performance in distinguishing aSAH from naSAH. In the internal validation cohort, it yielded an average sensitivity of 0.898, specificity of 0.877, accuracy of 0.889, Matthews correlation coefficient (MCC) of 0.777, and an area under the curve (AUC) of 0.948 (95% CI: 0.929-0.967). In the external test cohort, the model demonstrated an average sensitivity of 0.891, specificity of 0.880, accuracy of 0.887, MCC of 0.761, and AUC of 0.914 (95% CI: 0.889-0.940), outperforming junior radiologists (average accuracy: 0.836; MCC: 0.660).

CONCLUSION

The study presents a deep learning architecture capable of accurately identifying SAH etiology from NCCT scans. The model's high diagnostic performance highlights its potential to support rapid and precise clinical decision-making in emergency settings.

KEY POINTS

Question Differentiating aneurysmal from naSAH is crucial for timely treatment, yet existing imaging modalities are not universally accessible or convenient for rapid diagnosis. Findings A ResNet-variant-based deep learning model utilizing non-contrast CT scans demonstrated high accuracy in classifying SAH etiology and enhanced junior radiologists' diagnostic performance. Clinical relevance AI-driven analysis of non-contrast CT scans provides a fast, cost-effective, and non-invasive solution for preoperative SAH diagnosis. This approach facilitates early identification of patients needing aneurysm surgery while minimizing unnecessary angiography in non-aneurysmal cases, enhancing clinical workflow efficiency.

Label-efficient sequential model-based weakly supervised intracranial hemorrhage segmentation in low-data non-contrast CT imaging

BACKGROUND

In clinical settings, intracranial hemorrhages (ICH) are routinely diagnosed using non-contrast CT (NCCT) in emergency stroke imaging for severity assessment. However, compared to magnetic resonance imaging (MRI), ICH shows low contrast and poor signal-to-noise ratio on NCCT images. Accurate automated segmentation of ICH lesions using deep learning methods typically requires a large number of voxelwise annotated data with sufficient diversity to capture ICH characteristics.

PURPOSE

To reduce the requirement for voxelwise labeled data, in this study, we propose a weakly supervised (WS) method to segment ICH in NCCT images using image-level labels (presence/absence of ICH). Obtaining such image-level annotations is typically less time-consuming for clinicians. Hence, determining ICH segmentation from image-level labels provides highly time- and manually resource-efficient site-specific solutions in clinical emergency point-of-care (POC) settings. Moreover, because clinical datasets often consist of a limited amount of data, we show the utility of image-level annotated large datasets for training our proposed WS method to obtain a robust ICH segmentation in large as well as low-data regimes.

METHODS

Our proposed WS method determines the location of ICH using class activation maps (CAMs) from image-level labels and further refines ICH pseudo-masks in an unsupervised manner to train a segmentation model. Unlike existing WS methods for ICH segmentation, we used interslice dependencies across contiguous slices in NCCT volumes to obtain robust activation maps from the classification step. Additionally, we showed the effect of a large dataset on low-data regimes by comparing the WS segmentation trained on a large dataset with the baseline performance in low-data regimes. We used the radiological society of North America (RSNA) dataset (21,784 subjects) as a large dataset and the INSTANCE (100 subjects) and PhysioNet (75 subjects) datasets as low-data regimes. In addition, we performed the first ever investigation of the minimum amount (lower bound) of training data (from a large dataset) required for robust ICH segmentation performance in low-data regimes. We also evaluated the performance of our model across different ICH subtypes. In RSNA, 541 2D slices were designated for annotation and held as test data. The remaining samples were divided, with training:testing of 90%:10%. For INSTANCE and PhysioNet, the data were divided into five-fold for cross validation.

RESULTS

Using only 50% of the ICH slices from a large data for training, our proposed method achieved a Dice overlap value (DSC) values of 0.583 and 0.64 on PhysioNet and INSTANCE datasets, respectively, representing low-data regimes, which was significantly better (p-value < $<$ 0.001) than their baseline fully supervised (FS) performances in the low-data regime. Moreover, the DSC on Physionet was better than the state-of-the-art WS method using 100% ICH slices for training (DSC of 0.44).

CONCLUSIONS

Our study presents a novel WS method for ICH segmentation in NCCT images using only image-level labels, offering a label-efficient solution for clinical emergency settings. By leveraging interslice dependencies and unsupervised refinement techniques, our results outperformed FS and existing WS methods using only a proportion of the large data. Our results underscore the importance of leveraging large datasets and WS methodologies to advance automated hemorrhage analysis.

Artificial intelligence in emergency neuroradiology: Current applications and perspectives

Emergency neuroradiology provides rapid diagnostic decision-making and guidance for management for a wide range of acute conditions involving the brain, head and neck, and spine. This narrative review aims at providing an up-to-date discussion about the state of the art of applications of artificial intelligence in emergency neuroradiology, which have substantially expanded in depth and scope in the past few years. A detailed analysis of machine learning and deep learning algorithms in several tasks related to acute ischemic stroke involving various imaging modalities, including a description of existing commercial products, is provided. The applications of artificial intelligence in acute intracranial hemorrhage and other vascular pathologies such as intracranial aneurysm and arteriovenous malformation are discussed. Other areas of emergency neuroradiology including infection, fracture, cord compression, and pediatric imaging are further discussed in turn. Based on these discussions, this article offers insight into practical considerations regarding the applications of artificial intelligence in emergency neuroradiology, calling for more development driven by clinical needs, attention to pediatric neuroimaging, and analysis of real-world performance.

Diagnostic Accuracy of Deep Learning for Intracranial Hemorrhage Detection in Non-Contrast Brain CT Scans: A Systematic Review and Meta-Analysis

Background: Intracranial hemorrhage (ICH) is a life-threatening medical condition that needs early detection and treatment. In this systematic review and meta-analysis, we aimed to update our knowledge of the performance of deep learning (DL) models in detecting ICH on non-contrast computed tomography (NCCT). Methods: The study protocol was registered with PROSPERO (CRD420250654071). PubMed/MEDLINE and Google Scholar databases and the reference section of included studies were searched for eligible studies. The risk of bias in the included studies was assessed using the QUADAS-2 tool. Required data was collected to calculate pooled sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) with the corresponding 95% CI using the random effects model. Results: Seventy-three studies were included in our qualitative synthesis, and fifty-eight studies were selected for our meta-analysis. A pooled sensitivity of 0.92 (95% CI 0.90-0.94) and a pooled specificity of 0.94 (95% CI 0.92-0.95) were achieved. Pooled PPV was 0.84 (95% CI 0.78-0.89) and pooled NPV was 0.97 (95% CI 0.96-0.98). A bivariate model showed a pooled AUC of 0.96 (95% CI 0.95-0.97). Conclusions: This meta-analysis demonstrates that DL performs well in detecting ICH from NCCTs, highlighting a promising potential for the use of AI tools in various practice settings. More prospective studies are needed to confirm the potential clinical benefit of implementing DL-based tools and reveal the limitations of such tools for automated ICH detection and their impact on clinical workflow and outcomes of patients.

Deep learning-assisted detection of intracranial hemorrhage: validation and impact on reader performance

PURPOSE

Intracranial hemorrhage (ICH) requires urgent treatment, and accurate and timely diagnosis is essential for improving outcomes. This pivotal clinical trial aimed to validate a deep learning algorithm for ICH detection and assess its clinical utility through a reader performance test.

METHODS

Retrospective CT scans from patients with and without ICH were collected from a tertiary hospital. Two experts evaluated all scans, with a third expert reviewing disagreements for the final diagnosis. We analyzed the performance of the deep learning algorithm, JLK-ICH, for all cases and ICH subtypes. Additional external validation was performed using a multi-ethnic U.S.

DATASET

A reader performance study included six non-expert readers who evaluated 800 CT scans, with and without JLK-ICH assistance, following a washout period. ICH presence and five-point scale confidence level for decisions were rated.

RESULTS

A total of 1,370 CT scans were evaluated. The deep learning model showed 98.7% sensitivity (95% confidence interval [CI] 97.8-99.3%), 88.5% specificity (95% CI, 83.6-92.3%), and an area under the receiver operating characteristic curve (AUROC) of 0.936 (95% CI, 0.915-0.957). The model maintained high accuracy across all ICH subtypes, and additional external validation confirmed these results. In the reader performance study, AUROC with JLK-ICH assistance (0.967 [0.953-0.981]) surpassed that without assistance (0.953 [0.938-0.957]; P = 0.009). JLK-ICH particularly improved performance when readers were highly uncertain.

CONCLUSION

The JLK-ICH algorithm demonstrated high accuracy in detecting all ICH subtypes. Non-expert readers significantly improved diagnostic accuracy for brain CT scans with deep learning assistance.

Determining the optimal hematoma volume-based thresholds for surgical and medical strategies in basal ganglia hemorrhage

Hematoma volume is a significant concern in basal ganglia hemorrhage, with no clear cutoff to guide the choice between conservative and surgical management, particularly for larger hematomas where the optimal approach remains controversial. This study aimed to determine the maximum hematoma volume suitable for conservative treatment and the volume that necessitates surgical intervention in patients with basal ganglia hemorrhage. A total of 387 cases of basal ganglia hemorrhage from 2019 to 2021 were analyzed, evaluating patient demographics, medical history, and initial CT brain scans to assess hematoma volume. Outcomes of medical and surgical treatments were compared using multivariate logistic and Cox regression analysis. For patients treated with medical management alone, mortality rates did not differ significantly between hematoma volumes of 10-39.9 mL and those under 10 mL. Receiver operating characteristic (ROC) curve analysis identified a cutoff volume of 45.3 mL, with a sensitivity of 80.82% and specificity of 91.67% for predicting survival. Kaplan-Meier survival analysis revealed a reduced mortality hazard ratio (0.17) with surgical intervention for hematomas exceeding 45.3 mL. However, surgical treatment for volumes under 30 mL was associated with higher mortality compared to medical management. Surgical intervention showed a clear survival benefit for hematoma volumes of at least 60 mL, while conservative treatment remained appropriate for volumes up to 45.3 mL. For volumes between 45.3 mL and 59.9 mL, the decision to operate should be guided by the surgeon's judgment and patient-specific factors such as comorbidities, brain atrophy. In conclusion, conservative management is effective for hematomas up to 45.3 mL, while surgical intervention is absolutely indicated for volumes of 60 mL or more. These findings provide valuable guidance for optimizing treatment strategies in basal ganglia hemorrhage.

Machine Learning Approaches to Prognostication in Traumatic Brain Injury

PURPOSE OF REVIEW

This review investigates the use of machine learning (ML) in prognosticating outcomes for traumatic brain injury (TBI). It underscores the benefits of ML models in processing and integrating complex, multimodal data-including clinical, imaging, and physiological inputs-to identify intricate non-linear relationships that traditional methods might overlook.

RECENT FINDINGS

ML algorithms of clinical features, neuroimaging, and metrics from the autonomic nervous system enhance the early detection of clinical deterioration and improve outcome prediction. Challenges persist, including issues of data variability, model interpretability, and overfitting. However, advancements in model standardization and validation are key to enhancing their clinical applicability. ML-based, multimodal approaches offer transformative potential for personalized treatment planning and patient management. Future directions include integrating digital twins and real-time continuous data analysis, reinforcing the idea that comprehensive data amalgamation is essential for precise, adaptive prognostication and decision-making in neurocritical care, ultimately leading to better patient outcomes.

Automated detection of traumatic bleeding in CT images using 3D U-Net# and multi-organ segmentation

Traumatic injury remains a leading cause of death worldwide, with traumatic bleeding being one of its most critical and fatal consequences. The use of whole-body computed tomography (WBCT) in trauma management has rapidly expanded. However, interpreting WBCT images within the limited time available before treatment is particularly challenging for acute care physicians. Our group has previously developed an automated bleeding detection method in WBCT images. However, further reduction of false positives (FPs) is necessary for clinical application. To address this issue, we propose a novel automated detection for traumatic bleeding in CT images using deep learning and multi-organ segmentation; Methods: The proposed method integrates a three-dimensional U-Net# model for bleeding detection with an FP reduction approach based on multi-organ segmentation. The multi-organ segmentation method targets the bone, kidney, and vascular regions, where FPs are primarily found during the bleeding detection process. We evaluated the proposed method using a dataset of delayed-phase contrast-enhanced trauma CT images collected from four institutions; Results: Our method detected 70.0% of bleedings with 76.2 FPs/case. The processing time for our method was 6.3 ± 1.4 min. Compared with our previous ap-proach, the proposed method significantly reduced the number of FPs while maintaining detection sensitivity.

Evaluation of multiple deep neural networks for detection of intracranial dural arteriovenous fistula on susceptibility weighted angiography imaging

BACKGROUND

The natural history of intracranial dural arteriovenous fistula (DAVF) is variable and early diagnosis is crucial in order to positively impact the clinical course of aggressive DAVF. Artificial intelligence (AI) based techniques can be promising in this regard, and in this study, we used various deep neural network (DNN) architectures to determine whether DAVF could be reliably identified on susceptibility-weighted angiography images (SWAN).

MATERIALS AND METHODS

A total of 3965 SWAN image slices from 30 digital subtraction angiographically proven DAVF patients and 4380 SWAN image slices from 40 age-matched patients with normal MRI findings as control group were included. The images were categorized as either DAVF or normal and the data was trained using various DNN such as VGG-16, EfficientNet-B0, and ResNet-50.

RESULTS

Various DNN architectures showed the accuracy of 95.96% (VGG-16), 91.75% (EfficientNet-B0), and 86.23% (ResNet-50) on the SWAN image dataset. ROC analysis yielded an area under the curve of 0.796 (p < .001), best for VGG-16 model. Criterion of seven consecutive positive slices for DAVF diagnosis yielded a sensitivity of 74.68% with a specificity of 69.15%, while setting eight slices improved the sensitivity to above 80.38%, with a decrease of specificity up to 56.38%. Based on seven consecutive positive slices criteria, EfficientNet-B0 yielded a sensitivity of 73.21% with a specificity of 45.92% and ResNet-50 yielded a sensitivity of 72.39% with a specificity of 67.42%.

CONCLUSION

This study shows that DNN can extract discriminative features of SWAN for the classification of DAVF from normal with good accuracy, reasonably good sensitivity and specificity.

Optimizing convolutional neural networks for Chronic Obstructive Pulmonary Disease detection in clinical computed tomography imaging

We aim to optimize the binary detection of Chronic Obstructive Pulmonary Disease (COPD) based on emphysema presence in the lung with convolutional neural networks (CNN) by exploring manually adjusted versus automated window-setting optimization (WSO) on computed tomography (CT) images. 7194 contrast-enhanced CT images (3597 with COPD; 3597 healthy controls) from 78 subjects were selected retrospectively (01.2018-12.2021) and preprocessed. For each image, intensity values were manually clipped to the emphysema window setting and a baseline 'full-range' window setting. Class-balanced train, validation, and test sets contained 3392, 1114, and 2688 images. The network backbone was optimized by comparing various CNN architectures. Furthermore, automated WSO was implemented by adding a customized layer to the model. The image-level area under the Receiver Operating Characteristics curve (AUC) [lower, upper limit 95% confidence] was utilized to compare model variations. Repeated inference (n = 7) on the test set showed that the DenseNet was the most efficient backbone and achieved a mean AUC of 0.80 [0.76, 0.85] without WSO. Comparably, with input images manually adjusted to the emphysema window, the DenseNet model predicted COPD with a mean AUC of 0.86 [0.82, 0.89]. By adding a customized WSO layer to the DenseNet, an optimal window in the proximity of the emphysema window setting was learned automatically, and a mean AUC of 0.82 [0.78, 0.86] was achieved. Detection of COPD with DenseNet models was improved by WSO of CT data to the emphysema window setting range.

Impact of Dataset Size on 3D CNN Performance in Intracranial Hemorrhage Classification

Background: This study aimed to evaluate the effect of sample size on the development of a three-dimensional convolutional neural network (3DCNN) model for predicting the binary classification of three types of intracranial hemorrhage (ICH): intraparenchymal, subarachnoid, and subdural (IPH, SAH, SDH, respectively). Methods: During the training, we compiled all images of each brain computed tomography scan into a single 3D image, which was then fed into the model to classify the presence of ICH. We divided the non-hemorrhage quantities into 20, 30, 40, 50, 100, and 150 and the ICH quantities into 20, 30, 40, and 50. Cross-validation was performed to compute the average area under the curve (AUC) over the last five iterations. The AUC and accuracy were used to evaluate the performance of the models. Results: Fifty patients, each with the three ICH types, and 150 non-hemorrhage cases were enrolled. Larger sample sizes achieved stable and acceptable performance in the artificial intelligence (AI) models, whereas training with a limited number of cases posed the risk of falsely high AUC values or accuracy. The overall trends and fluctuations in AUC values were similar between IPH and SDH but different for SAH. The accuracy of the results was relatively consistent among the three ICH types. Conclusions: The 3DCNN technique can be used to develop AI models capable of detecting ICH from limited case numbers. However, a minimal case number must be provided. The performance of AI models varies across different ICH types and is more stable with larger sample sizes.

Recent and future advances in intracerebral hemorrhage

Spontaneous intracerebral hemorrhage (ICH) is defined by the rupture of a cerebral blood vessel and the entry of blood into the brain parenchyma. With a global incidence of around 3.5 million, ICH accounts for almost 30 % of all new strokes worldwide. It is also the deadliest form of acute stroke and survivors are at risk of poor functional outcome. The pathophysiology of ICH is a dynamic process with key stages occurring at successive times: vessel rupture and initial bleeding; hematoma expansion, mechanical mass effect and secondary brain injury (peri-hematomal edema). While deep perforating vasculopathy and cerebral amyloid angiopathy are responsible for 80 % of ICH, a prompt diagnostic work-up, including advanced imaging is require to exclude a treatable cause. ICH is a neurological emergency and simple therapeutic measures such as blood pressure lowering and anticoagulant reversal should be implemented as early as possible as part of a bundle of care. Although ICH is still devoided of specific treatment, recent advances give hope for a cautious optimism. Therapeutic approaches under the scope are focusing on fighting against hemorrhage expansion, promoting hematoma evacuation by minimally invasive surgery, and reducing secondary brain injury. Among survivors, the global vascular risk is now better established, but optimal secondary prevention is still unclear and is based on an individual benefit-risk balance evaluation.

Deep learning to predict risk of lateral skull base cerebrospinal fluid leak or encephalocele

PURPOSE

Skull base features, including increased foramen ovale (FO) cross-sectional area, are associated with lateral skull base spontaneous cerebrospinal fluid (sCSF) leak and encephalocele. Manual measurement requires skill in interpreting imaging studies and is time consuming. The goal of this study was to develop a fully automated deep learning method for FO segmentation and to determine the predictive value in identifying patients with sCSF leak or encephalocele.

METHODS

A retrospective cohort study at a tertiary care academic hospital of 34 adults with lateral skull base sCSF leak or encephalocele were compared with 815 control patients from 2013-2021. A convolutional neural network (CNN) was constructed for image segmentation of axial computed tomography (CT) studies. Predicted FO segmentations were compared to manual segmentations, and receiver operating characteristic (ROC) curves were constructed.

RESULTS

295 CTs were used for training and validation of the CNN. A separate dataset of 554 control CTs was matched 5:1 on age and sex with the sCSF leak/encephalocele group. The mean Dice score was 0.81. The sCSF leak/encephalocele group had greater mean (SD) FO cross-sectional area compared to the control group, 29.0 (7.7) mm2 versus 24.3 (7.6) mm2 (P = .002, 95% confidence interval 0.02-0.08). The area under the ROC curve was 0.69.

CONCLUSION

CNNs can be used to segment the cross-sectional area of the FO accurately and efficiently. Used together with other predictors, this method could be used as part of a clinical tool to predict the risk of sCSF leak or encephalocele.

External validation and performance analysis of a deep learning-based model for the detection of intracranial hemorrhage

PURPOSE

We aimed to investigate the external validation and performance of an FDA-approved deep learning model in labeling intracranial hemorrhage (ICH) cases on a real-world heterogeneous clinical dataset. Furthermore, we delved deeper into evaluating how patients' risk factors influenced the model's performance and gathered feedback on satisfaction from radiologists of varying ranks.

METHODS

This prospective IRB approved study included 5600 non-contrast CT scans of the head in various clinical settings, that is, emergency, inpatient, and outpatient units. The patients' risk factors were collected and tested for impacting the performance of DL model utilizing univariate and multivariate regression analyses. The performance of DL model was contrasted to the radiologists' interpretation to determine the presence or absence of ICH with subsequent classification into subcategories of ICH. Key metrics, including accuracy, sensitivity, specificity, positive predictive value, and negative predictive value, were calculated. Receiver operating characteristics curve, along with the area under the curve, were determined. Additionally, a questionnaire was conducted with radiologists of varying ranks to assess their experience with the model.

RESULTS

The model exhibited outstanding performance, achieving a high sensitivity of 89% and specificity of 96%. Additional performance metrics, including positive predictive value (82%), negative predictive value (97%), and overall accuracy (94%), underscore its robust capabilities. The area under the ROC curve further demonstrated the model's efficacy, reaching 0.954. Multivariate logistic regression revealed statistical significance for age, sex, history of trauma, operative intervention, HTN, and smoking.

CONCLUSION

Our study highlights the satisfactory performance of the DL model on a diverse real-world dataset, garnering positive feedback from radiology trainees.

SenseCare: a research platform for medical image informatics and interactive 3D visualization

Introduction

Clinical research on smart health has an increasing demand for intelligent and clinic-oriented medical image computing algorithms and platforms that support various applications. However, existing research platforms for medical image informatics have limited support for Artificial Intelligence (AI) algorithms and clinical applications.

Methods

To this end, we have developed SenseCare research platform, which is designed to facilitate translational research on intelligent diagnosis and treatment planning in various clinical scenarios. It has several appealing functions and features such as advanced 3D visualization, concurrent and efficient web-based access, fast data synchronization and high data security, multi-center deployment, support for collaborative research, etc.

Results and discussion

SenseCare provides a range of AI toolkits for different tasks, including image segmentation, registration, lesion and landmark detection from various image modalities ranging from radiology to pathology. It also facilitates the data annotation and model training processes, which makes it easier for clinical researchers to develop and deploy customized AI models. In addition, it is clinic-oriented and supports various clinical applications such as diagnosis and surgical planning for lung cancer, liver tumor, coronary artery disease, etc. By simplifying AI-based medical image analysis, SenseCare has a potential to promote clinical research in a wide range of disease diagnosis and treatment applications.

Precise Image-level Localization of Intracranial Hemorrhage on Head CT Scans with Deep Learning Models Trained on Study-level Labels

Purpose To develop a highly generalizable weakly supervised model to automatically detect and localize image-level intracranial hemorrhage (ICH) by using study-level labels. Materials and Methods In this retrospective study, the proposed model was pretrained on the image-level Radiological Society of North America dataset and fine-tuned on a local dataset by using attention-based bidirectional long short-term memory networks. This local training dataset included 10 699 noncontrast head CT scans in 7469 patients, with ICH study-level labels extracted from radiology reports. Model performance was compared with that of two senior neuroradiologists on 100 random test scans using the McNemar test, and its generalizability was evaluated on an external independent dataset. Results The model achieved a positive predictive value (PPV) of 85.7% (95% CI: 84.0, 87.4) and an area under the receiver operating characteristic curve of 0.96 (95% CI: 0.96, 0.97) on the held-out local test set (n = 7243, 3721 female) and 89.3% (95% CI: 87.8, 90.7) and 0.96 (95% CI: 0.96, 0.97), respectively, on the external test set (n = 491, 178 female). For 100 randomly selected samples, the model achieved performance on par with two neuroradiologists, but with a significantly faster (P < .05) diagnostic time of 5.04 seconds per scan (vs 86 seconds and 22.2 seconds for the two neuroradiologists, respectively). The model's attention weights and heatmaps visually aligned with neuroradiologists' interpretations. Conclusion The proposed model demonstrated high generalizability and high PPVs, offering a valuable tool for expedited ICH detection and prioritization while reducing false-positive interruptions in radiologists' workflows. Keywords: Computer-Aided Diagnosis (CAD), Brain/Brain Stem, Hemorrhage, Convolutional Neural Network (CNN), Transfer Learning Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Akinci D'Antonoli and Rudie in this issue.

Spatial attention-based CSR-Unet framework for subdural and epidural hemorrhage segmentation and classification using CT images

BACKGROUND

Automatic diagnosis and brain hemorrhage segmentation in Computed Tomography (CT) may be helpful in assisting the neurosurgeon in developing treatment plans that improve the patient's chances of survival. Because medical segmentation of images is important and performing operations manually is challenging, many automated algorithms have been developed for this purpose, primarily focusing on certain image modalities. Whenever a blood vessel bursts, a dangerous medical condition known as intracranial hemorrhage (ICH) occurs. For best results, quick action is required. That being said, identifying subdural (SDH) and epidural haemorrhages (EDH) is a difficult task in this field and calls for a new, more precise detection method.

METHODS

This work uses a head CT scan to detect cerebral bleeding and distinguish between two types of dural hemorrhages using deep learning techniques. This paper proposes a rich segmentation approach to segment both SDH and EDH by enhancing segmentation efficiency with a better feature extraction procedure. This method incorporates Spatial attention- based CSR (convolution-SE-residual) Unet, for rich segmentation and precise feature extraction.

RESULTS

According to the study's findings, the CSR based Spatial network performs better than the other models, exhibiting impressive metrics for all assessed parameters with a mean dice coefficient of 0.970 and mean IoU of 0.718, while EDH and SDH dice scores are 0.983 and 0.969 respectively.

CONCLUSIONS

The CSR Spatial network experiment results show that it can perform well regarding dice coefficient. Furthermore, Spatial Unet based on CSR may effectively model the complicated in segmentations and rich feature extraction and improve the representation learning compared to alternative deep learning techniques, of illness and medical treatment, to enhance the meticulousness in predicting the fatality.

Improving Automated Hemorrhage Detection at Sparse-View CT via U-Net-based Artifact Reduction

Purpose To explore the potential benefits of deep learning-based artifact reduction in sparse-view cranial CT scans and its impact on automated hemorrhage detection. Materials and Methods In this retrospective study, a U-Net was trained for artifact reduction on simulated sparse-view cranial CT scans in 3000 patients, obtained from a public dataset and reconstructed with varying sparse-view levels. Additionally, EfficientNet-B2 was trained on full-view CT data from 17 545 patients for automated hemorrhage detection. Detection performance was evaluated using the area under the receiver operating characteristic curve (AUC), with differences assessed using the DeLong test, along with confusion matrices. A total variation (TV) postprocessing approach, commonly applied to sparse-view CT, served as the basis for comparison. A Bonferroni-corrected significance level of .001/6 = .00017 was used to accommodate for multiple hypotheses testing. Results Images with U-Net postprocessing were better than unprocessed and TV-processed images with respect to image quality and automated hemorrhage detection. With U-Net postprocessing, the number of views could be reduced from 4096 (AUC: 0.97 [95% CI: 0.97, 0.98]) to 512 (0.97 [95% CI: 0.97, 0.98], P < .00017) and to 256 views (0.97 [95% CI: 0.96, 0.97], P < .00017) with a minimal decrease in hemorrhage detection performance. This was accompanied by mean structural similarity index measure increases of 0.0210 (95% CI: 0.0210, 0.0211) and 0.0560 (95% CI: 0.0559, 0.0560) relative to unprocessed images. Conclusion U-Net-based artifact reduction substantially enhanced automated hemorrhage detection in sparse-view cranial CT scans. Keywords: CT, Head/Neck, Hemorrhage, Diagnosis, Supervised Learning Supplemental material is available for this article. © RSNA, 2024.

Deep learning-assisted detection and segmentation of intracranial hemorrhage in noncontrast computed tomography scans of acute stroke patients: a systematic review and meta-analysis

BACKGROUND

Deep learning (DL)-assisted detection and segmentation of intracranial hemorrhage stroke in noncontrast computed tomography (NCCT) scans are well-established, but evidence on this topic is lacking.

MATERIALS AND METHODS

PubMed and Embase databases were searched from their inception to November 2023 to identify related studies. The primary outcomes included sensitivity, specificity, and the Dice Similarity Coefficient (DSC); while the secondary outcomes were positive predictive value (PPV), negative predictive value (NPV), precision, area under the receiver operating characteristic curve (AUROC), processing time, and volume of bleeding. Random-effect model and bivariate model were used to pooled independent effect size and diagnostic meta-analysis data, respectively.

RESULTS

A total of 36 original studies were included in this meta-analysis. Pooled results indicated that DL technologies have a comparable performance in intracranial hemorrhage detection and segmentation with high values of sensitivity (0.89, 95% CI: 0.88-0.90), specificity (0.91, 95% CI: 0.89-0.93), AUROC (0.94, 95% CI: 0.93-0.95), PPV (0.92, 95% CI: 0.91-0.93), NPV (0.94, 95% CI: 0.91-0.96), precision (0.83, 95% CI: 0.77-0.90), DSC (0.84, 95% CI: 0.82-0.87). There is no significant difference between manual labeling and DL technologies in hemorrhage quantification (MD 0.08, 95% CI: -5.45-5.60, P =0.98), but the latter takes less process time than manual labeling (WMD 2.26, 95% CI: 1.96-2.56, P =0.001).

CONCLUSION

This systematic review has identified a range of DL algorithms that the performance was comparable to experienced clinicians in hemorrhage lesions identification, segmentation, and quantification but with greater efficiency and reduced cost. It is highly emphasized that multicenter randomized controlled clinical trials will be needed to validate the performance of these tools in the future, paving the way for fast and efficient decision-making during clinical procedure in patients with acute hemorrhagic stroke.

Improved differentiation of cavernous malformation and acute intraparenchymal hemorrhage on CT using an AI algorithm

This study aimed to evaluate the utility of an artificial intelligence (AI) algorithm in differentiating between cerebral cavernous malformation (CCM) and acute intraparenchymal hemorrhage (AIH) on brain computed tomography (CT). A retrospective, multireader, randomized study was conducted to validate the performance of an AI algorithm in differentiating AIH from CCM on brain CT. CT images of CM and AIH (< 3 cm) were identified from the database. Six blinded reviewers, including two neuroradiologists, two radiology residents, and two emergency department physicians, evaluated CT images from 288 patients (CCM, n = 173; AIH, n = 115) with and without AI assistance, comparing diagnostic performance. Brain CT interpretation with AI assistance resulted in significantly higher diagnostic accuracy than without (86.92% vs. 79.86%, p < 0.001). Radiology residents and emergency department physicians showed significantly improved accuracy of CT interpretation with AI assistance than without (84.21% vs. 75.35%, 80.73% vs. 72.57%; respectively, p < 0.05). Neuroradiologists showed a trend of higher accuracy with AI assistance in the interpretation but lacked statistical significance (95.83% vs. 91.67%, p = 0.56). The use of an AI algorithm can enhance the differentiation of AIH from CCM in brain CT interpretation, particularly for nonexperts in neuroradiology.

Data Liberation and Crowdsourcing in Medical Research: The Intersection of Collective and Artificial Intelligence

In spite of an exponential increase in the volume of medical data produced globally, much of these data are inaccessible to those who might best use them to develop improved health care solutions through the application of advanced analytics such as artificial intelligence. Data liberation and crowdsourcing represent two distinct but interrelated approaches to bridging existing data silos and accelerating the pace of innovation internationally. In this article, we examine these concepts in the context of medical artificial intelligence research, summarizing their potential benefits, identifying potential pitfalls, and ultimately making a case for their expanded use going forward. A practical example of a crowdsourced competition using an international medical imaging dataset is provided. Keywords: Artificial Intelligence, Data Liberation, Crowdsourcing © RSNA, 2023.

Strengthening deep-learning models for intracranial hemorrhage detection: strongly annotated computed tomography images and model ensembles

Background and purpose

Multiple attempts at intracranial hemorrhage (ICH) detection using deep-learning techniques have been plagued by clinical failures. We aimed to compare the performance of a deep-learning algorithm for ICH detection trained on strongly and weakly annotated datasets, and to assess whether a weighted ensemble model that integrates separate models trained using datasets with different ICH improves performance.

Methods

We used brain CT scans from the Radiological Society of North America (27,861 CT scans, 3,528 ICHs) and AI-Hub (53,045 CT scans, 7,013 ICHs) for training. DenseNet121, InceptionResNetV2, MobileNetV2, and VGG19 were trained on strongly and weakly annotated datasets and compared using independent external test datasets. We then developed a weighted ensemble model combining separate models trained on all ICH, subdural hemorrhage (SDH), subarachnoid hemorrhage (SAH), and small-lesion ICH cases. The final weighted ensemble model was compared to four well-known deep-learning models. After external testing, six neurologists reviewed 91 ICH cases difficult for AI and humans.

Results

InceptionResNetV2, MobileNetV2, and VGG19 models outperformed when trained on strongly annotated datasets. A weighted ensemble model combining models trained on SDH, SAH, and small-lesion ICH had a higher AUC, compared with a model trained on all ICH cases only. This model outperformed four deep-learning models (AUC [95% C.I.]: Ensemble model, 0.953[0.938-0.965]; InceptionResNetV2, 0.852[0.828-0.873]; DenseNet121, 0.875[0.852-0.895]; VGG19, 0.796[0.770-0.821]; MobileNetV2, 0.650[0.620-0.680]; p < 0.0001). In addition, the case review showed that a better understanding and management of difficult cases may facilitate clinical use of ICH detection algorithms.

Conclusion

We propose a weighted ensemble model for ICH detection, trained on large-scale, strongly annotated CT scans, as no model can capture all aspects of complex tasks.

Diagnostic test accuracy of machine learning algorithms for the detection intracranial hemorrhage: a systematic review and meta-analysis study

BACKGROUND

This systematic review and meta-analysis were conducted to objectively evaluate the evidence of machine learning (ML) in the patient diagnosis of Intracranial Hemorrhage (ICH) on computed tomography (CT) scans.

METHODS

Until May 2023, systematic searches were conducted in ISI Web of Science, PubMed, Scopus, Cochrane Library, IEEE Xplore Digital Library, CINAHL, Science Direct, PROSPERO, and EMBASE for studies that evaluated the diagnostic precision of ML model-assisted ICH detection. Patients with and without ICH as the target condition who were receiving CT-Scan were eligible for the research, which used ML algorithms based on radiologists' reports as the gold reference standard. For meta-analysis, pooled sensitivities, specificities, and a summary receiver operating characteristics curve (SROC) were used.

RESULTS

At last, after screening the title, abstract, and full paper, twenty-six retrospective and three prospective, and two retrospective/prospective studies were included. The overall (Diagnostic Test Accuracy) DTA of retrospective studies with a pooled sensitivity was 0.917 (95% CI 0.88-0.943, I2 = 99%). The pooled specificity was 0.945 (95% CI 0.918-0.964, I2 = 100%). The pooled diagnostic odds ratio (DOR) was 219.47 (95% CI 104.78-459.66, I2 = 100%). These results were significant for the specificity of the different network architecture models (p-value = 0.0289). However, the results for sensitivity (p-value = 0.6417) and DOR (p-value = 0.2187) were not significant. The ResNet algorithm has higher pooled specificity than other algorithms with 0.935 (95% CI 0.854-0.973, I2 = 93%).

CONCLUSION

This meta-analysis on DTA of ML algorithms for detecting ICH by assessing non-contrast CT-Scans shows the ML has an acceptable performance in diagnosing ICH. Using ResNet in ICH detection remains promising prediction was improved via training in an Architecture Learning Network (ALN).

Systematic Review of Artificial Intelligence for Abnormality Detection in High-volume Neuroimaging and Subgroup Meta-analysis for Intracranial Hemorrhage Detection

PURPOSE

Most studies evaluating artificial intelligence (AI) models that detect abnormalities in neuroimaging are either tested on unrepresentative patient cohorts or are insufficiently well-validated, leading to poor generalisability to real-world tasks. The aim was to determine the diagnostic test accuracy and summarise the evidence supporting the use of AI models performing first-line, high-volume neuroimaging tasks.

METHODS

Medline, Embase, Cochrane library and Web of Science were searched until September 2021 for studies that temporally or externally validated AI capable of detecting abnormalities in first-line computed tomography (CT) or magnetic resonance (MR) neuroimaging. A bivariate random effects model was used for meta-analysis where appropriate. This study was registered on PROSPERO as CRD42021269563.

RESULTS

Out of 42,870 records screened, and 5734 potentially eligible full texts, only 16 studies were eligible for inclusion. Included studies were not compromised by unrepresentative datasets or inadequate validation methodology. Direct comparison with radiologists was available in 4/16 studies and 15/16 had a high risk of bias. Meta-analysis was only suitable for intracranial hemorrhage detection in CT imaging (10/16 studies), where AI systems had a pooled sensitivity and specificity 0.90 (95% confidence interval [CI] 0.85-0.94) and 0.90 (95% CI 0.83-0.95), respectively. Other AI studies using CT and MRI detected target conditions other than hemorrhage (2/16), or multiple target conditions (4/16). Only 3/16 studies implemented AI in clinical pathways, either for pre-read triage or as post-read discrepancy identifiers.

CONCLUSION

The paucity of eligible studies reflects that most abnormality detection AI studies were not adequately validated in representative clinical cohorts. The few studies describing how abnormality detection AI could impact patients and clinicians did not explore the full ramifications of clinical implementation.

Hemorrhage Evaluation and Detector System for Underserved Populations: HEADS-UP

Objective

To create a rapid, cloud-based, and deployable machine learning (ML) method named hemorrhage evaluation and detector system for underserved populations, potentially across the Mayo Clinic enterprise, then expand to involve underserved areas and detect the 5 subtypes of intracranial hemorrhage (IH).

Methods

We used Radiological Society of North America dataset for IH detection. We made 4 total iterations using Google Cloud Vertex AutoML. We trained an AutoML model with 2000 images, followed by 6000 images from both IH positive and negative classes. Pixel values were measured by the Hounsfield units, presenting a width of 80 Hounsfield and a level of 40 Hounsfield as the bone window. This was followed by a more detailed image preprocessing approach by combining the pixel values from each of the brain, subdural, and soft tissue window-based gray-scale images into R(red)-channel, G(green)-channel, and B(blue)-channel images to boost the binary IH classification performance. Four experiments with AutoML were applied to study the effects of training sample size and image preprocessing on model performance.

Results

Out of the 4 AutoML experiments, the best-performing model was the fourth experiment, where 95.80% average precision, 91.40% precision, and 91.40% recall were achieved. On the basis of this analysis, our binary IH classifier hemorrhage evaluation and detector system for underserved populations appeared both accurate and performed well.

Conclusion

Hemorrhage evaluation and detector system for underserved populations is a rapid, cloud-based, deployable ML method to detect IH. This tool can help expedite the care of patients with IH in resource-limited hospitals.

Self-supervised pre-training with contrastive and masked autoencoder methods for dealing with small datasets in deep learning for medical imaging

Deep learning in medical imaging has the potential to minimize the risk of diagnostic errors, reduce radiologist workload, and accelerate diagnosis. Training such deep learning models requires large and accurate datasets, with annotations for all training samples. However, in the medical imaging domain, annotated datasets for specific tasks are often small due to the high complexity of annotations, limited access, or the rarity of diseases. To address this challenge, deep learning models can be pre-trained on large image datasets without annotations using methods from the field of self-supervised learning. After pre-training, small annotated datasets are sufficient to fine-tune the models for a specific task. The most popular self-supervised pre-training approaches in medical imaging are based on contrastive learning. However, recent studies in natural image processing indicate a strong potential for masked autoencoder approaches. Our work compares state-of-the-art contrastive learning methods with the recently introduced masked autoencoder approach "SparK" for convolutional neural networks (CNNs) on medical images. Therefore, we pre-train on a large unannotated CT image dataset and fine-tune on several CT classification tasks. Due to the challenge of obtaining sufficient annotated training data in medical imaging, it is of particular interest to evaluate how the self-supervised pre-training methods perform when fine-tuning on small datasets. By experimenting with gradually reducing the training dataset size for fine-tuning, we find that the reduction has different effects depending on the type of pre-training chosen. The SparK pre-training method is more robust to the training dataset size than the contrastive methods. Based on our results, we propose the SparK pre-training for medical imaging tasks with only small annotated datasets.

Automated screening of computed tomography using weakly supervised anomaly detection

BACKGROUND

Current artificial intelligence studies for supporting CT screening tasks depend on either supervised learning or detecting anomalies. However, the former involves a heavy annotation workload owing to requiring many slice-wise annotations (ground truth labels); the latter is promising, but while it reduces the annotation workload, it often suffers from lower performance. This study presents a novel weakly supervised anomaly detection (WSAD) algorithm trained based on scan-wise normal and anomalous annotations to provide better performance than conventional methods while reducing annotation workload.

METHODS

Based on surveillance video anomaly detection methodology, feature vectors representing each CT slice were trained on an AR-Net-based convolutional network using a dynamic multiple-instance learning loss and a center loss function. The following two publicly available CT datasets were retrospectively analyzed: the RSNA brain hemorrhage dataset (normal scans: 12,862; scans with intracranial hematoma: 8882) and COVID-CT set (normal scans: 282; scans with COVID-19: 95).

RESULTS

Anomaly scores of each slice were successfully predicted despite inaccessibility to any slice-wise annotations. Slice-level area under the curve (AUC), sensitivity, specificity, and accuracy from the brain CT dataset were 0.89, 0.85, 0.78, and 0.79, respectively. The proposed method reduced the number of annotations in the brain dataset by 97.1% compared to an ordinary slice-level supervised learning method.

CONCLUSION

This study demonstrated a significant annotation reduction in identifying anomalous CT slices compared to a supervised learning approach. The effectiveness of the proposed WSAD algorithm was verified through higher AUC than existing anomaly detection techniques.

Application of deep learning models for detection of subdural hematoma: a systematic review and meta-analysis

BACKGROUND

This study aimed to investigate the application of deep learning (DL) models for the detection of subdural hematoma (SDH).

METHODS

We conducted a comprehensive search using relevant keywords. Articles extracted were original studies in which sensitivity and/or specificity were reported. Two different approaches of frequentist and Bayesian inference were applied. For quality and risk of bias assessment we used Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2).

RESULTS

We analyzed 22 articles that included 1,997,749 patients. In the first step, the frequentist method showed a pooled sensitivity of 88.8% (95% confidence interval (CI): 83.9% to 92.4%) and a specificity of 97.2% (95% CI 94.6% to 98.6%). In the second step, using Bayesian methods including 11 studies that reported sensitivity and specificity, a sensitivity rate of 86.8% (95% CI: 77.6% to 92.9%) at a specificity level of 86.9% (95% CI: 60.9% to 97.2%) was achieved. The risk of bias assessment was not remarkable using QUADAS-2.

CONCLUSION

DL models might be an appropriate tool for detecting SDHs with a reasonably high sensitivity and specificity.

A systematic review on intracranial aneurysm and hemorrhage detection using machine learning and deep learning techniques

The risk of discovering an intracranial aneurysm during the initial screening and follow-up screening are reported as around 11%, and 7% respectively (Zuurbie et al., 2023) to these mass effects, unruptured aneurysms frequently generate symptoms, however, the real hazard occurs when an aneurysm ruptures and results in a cerebral hemorrhage known as a subarachnoid hemorrhage. The objective is to study the multiple kinds of hemorrhage and aneurysm detection problems and develop machine and deep learning models to recognise them. Due to its early stage, subarachnoid hemorrhage, the most typical symptom after aneurysm rupture, is an important medical condition. It frequently results in severe neurological emergencies or even death. Although most aneurysms are asymptomatic and won't burst, because of their unpredictable growth, even small aneurysms are susceptible. A timely diagnosis is essential to prevent early mortality because a large percentage of hemorrhage cases present can be fatal. Physiological/imaging markers and the degree of the subarachnoid hemorrhage can be used as indicators for potential early treatments in hemorrhage. The hemodynamic pathomechanisms and microcellular environment should remain a priority for academics and medical professionals. There is still disagreement about how and when to care for aneurysms that have not ruptured despite studies reporting on the risk of rupture and outcomes. We are optimistic that with the progress in our understanding of the pathophysiology of hemorrhages and aneurysms and the advancement of artificial intelligence has made it feasible to conduct analyses with a high degree of precision, effectiveness and reliability.

Radiological features of brain hemorrhage through automated segmentation from computed tomography in stroke and traumatic brain injury

Introduction

Radiological assessment is necessary to diagnose spontaneous intracerebral hemorrhage (ICH) and traumatic brain injury intracranial hemorrhage (TBI-bleed). Artificial intelligence (AI) deep learning tools provide a means for decision support. This study evaluates the hemorrhage segmentations produced from three-dimensional deep learning AI model that was developed using non-contrast computed tomography (CT) imaging data external to the current study.

Methods

Non-contrast CT imaging data from 1263 patients were accessed across seven data sources (referred to as sites) in Norway and Sweden. Patients were included based on ICH, TBI-bleed, or mild TBI diagnosis. Initial non-contrast CT images were available for all participants. Hemorrhage location frequency maps were generated. The number of estimated haematoma clusters was correlated with the total haematoma volume. Ground truth expert annotations were available for one ICH site; hence, a comparison was made with the estimated haematoma volumes. Segmentation volume estimates were used in a receiver operator characteristics (ROC) analysis for all samples (i.e., bleed detected) and then specifically for one site with few TBI-bleed cases.

Results

The hemorrhage frequency maps showed spatial patterns of estimated lesions consistent with ICH or TBI-bleed presentations. There was a positive correlation between the estimated number of clusters and total haematoma volume for each site (correlation range: 0.45-0.74; each p-value < 0.01) and evidence of ICH between-site differences. Relative to hand-drawn annotations for one ICH site, the VIOLA-AI segmentation mask achieved a median Dice Similarity Coefficient of 0.82 (interquartile range: 0.78 and 0.83), resulting in a small overestimate in the haematoma volume by a median of 0.47 mL (interquartile range: 0.04 and 1.75 mL). The bleed detection ROC analysis for the whole sample gave a high area-under-the-curve (AUC) of 0.92 (with sensitivity and specificity of 83.28% and 95.41%); however, when considering only the mild head injury site, the TBI-bleed detection gave an AUC of 0.70.

Discussion

An open-source segmentation tool was used to visualize hemorrhage locations across multiple data sources and revealed quantitative hemorrhage site differences. The automated total hemorrhage volume estimate correlated with a per-participant hemorrhage cluster count. ROC results were moderate-to-high. The VIOLA-AI tool had promising results and might be useful for various types of intracranial hemorrhage.

Automated Computer-Aided Detection and Classification of Intracranial Hemorrhage Using Ensemble Deep Learning Techniques

Diagnosing Intracranial Hemorrhage (ICH) at an early stage is difficult since it affects the blood vessels in the brain, often resulting in death. We propose an ensemble of Convolutional Neural Networks (CNNs) combining Squeeze and Excitation-based Residual Networks with the next dimension (SE-ResNeXT) and Long Short-Term Memory (LSTM) Networks in order to address this issue. This research work primarily used data from the Radiological Society of North America (RSNA) brain CT hemorrhage challenge dataset and the CQ500 dataset. Preprocessing and data augmentation are performed using the windowing technique in the proposed work. The ICH is then classified using ensembled CNN techniques after being preprocessed, followed by feature extraction in an automatic manner. ICH is classified into the following five types: epidural, intraventricular, subarachnoid, intra-parenchymal, and subdural. A gradient-weighted Class Activation Mapping method (Grad-CAM) is used for identifying the region of interest in an ICH image. A number of performance measures are used to compare the experimental results with various state-of-the-art algorithms. By achieving 99.79% accuracy with an F-score of 0.97, the proposed model proved its efficacy in detecting ICH compared to other deep learning models. The proposed ensembled model can classify epidural, intraventricular, subarachnoid, intra-parenchymal, and subdural hemorrhages with an accuracy of 99.89%, 99.65%, 98%, 99.75%, and 99.88%. Simulation results indicate that the suggested approach can categorize a variety of intracranial bleeding types. By implementing the ensemble deep learning technique using the SE-ResNeXT and LSTM models, we achieved significant classification accuracy and AUC scores.

Role of artificial intelligence and machine learning in the diagnosis of cerebrovascular disease

Introduction

Cerebrovascular diseases are known to cause significant morbidity and mortality to the general population. In patients with cerebrovascular disease, prompt clinical evaluation and radiographic interpretation are both essential in optimizing clinical management and in triaging patients for critical and potentially life-saving neurosurgical interventions. With recent advancements in the domains of artificial intelligence (AI) and machine learning (ML), many AI and ML algorithms have been developed to further optimize the diagnosis and subsequent management of cerebrovascular disease. Despite such advances, further studies are needed to substantively evaluate both the diagnostic accuracy and feasibility of these techniques for their application in clinical practice. This review aims to analyze the current use of AI and MI algorithms in the diagnosis of, and clinical decision making for cerebrovascular disease, and to discuss both the feasibility and future applications of utilizing such algorithms.

Methods

We review the use of AI and ML algorithms to assist clinicians in the diagnosis and management of ischemic stroke, hemorrhagic stroke, intracranial aneurysms, and arteriovenous malformations (AVMs). After identifying the most widely used algorithms, we provide a detailed analysis of the accuracy and effectiveness of these algorithms in practice.

Results

The incorporation of AI and ML algorithms for cerebrovascular patients has demonstrated improvements in time to detection of intracranial pathologies such as intracerebral hemorrhage (ICH) and infarcts. For ischemic and hemorrhagic strokes, commercial AI software platforms such as RapidAI and Viz.AI have bene implemented into routine clinical practice at many stroke centers to expedite the detection of infarcts and ICH, respectively. Such algorithms and neural networks have also been analyzed for use in prognostication for such cerebrovascular pathologies. These include predicting outcomes for ischemic stroke patients, hematoma expansion, risk of aneurysm rupture, bleeding of AVMs, and in predicting outcomes following interventions such as risk of occlusion for various endovascular devices. Preliminary analyses have yielded promising sensitivities when AI and ML are used in concert with imaging modalities and a multidisciplinary team of health care providers.

Conclusion

The implementation of AI and ML algorithms to supplement clinical practice has conferred a high degree of accuracy, efficiency, and expedited detection in the clinical and radiographic evaluation and management of ischemic and hemorrhagic strokes, AVMs, and aneurysms. Such algorithms have been explored for further purposes of prognostication for these conditions, with promising preliminary results. Further studies should evaluate the longitudinal implementation of such techniques into hospital networks and residency programs to supplement clinical practice, and the extent to which these techniques improve patient care and clinical outcomes in the long-term.

Artificial Intelligence in Neuroradiology: A Review of Current Topics and Competition Challenges

There is an expanding body of literature that describes the application of deep learning and other machine learning and artificial intelligence methods with potential relevance to neuroradiology practice. In this article, we performed a literature review to identify recent developments on the topics of artificial intelligence in neuroradiology, with particular emphasis on large datasets and large-scale algorithm assessments, such as those used in imaging AI competition challenges. Numerous applications relevant to ischemic stroke, intracranial hemorrhage, brain tumors, demyelinating disease, and neurodegenerative/neurocognitive disorders were discussed. The potential applications of these methods to spinal fractures, scoliosis grading, head and neck oncology, and vascular imaging were also reviewed. The AI applications examined perform a variety of tasks, including localization, segmentation, longitudinal monitoring, diagnostic classification, and prognostication. While research on this topic is ongoing, several applications have been cleared for clinical use and have the potential to augment the accuracy or efficiency of neuroradiologists.

Real world validation of an AI-based CT hemorrhage detection tool

Introduction

Intracranial hemorrhage (ICH) is a potentially life-threatening medical event that requires expedited diagnosis with computed tomography (CT). Automated medical imaging triaging tools can rapidly bring scans containing critical abnormalities, such as ICH, to the attention of radiologists and clinicians. Here, we retrospectively investigated the real-world performance of VeriScout™, an artificial intelligence-based CT hemorrhage detection and triage tool.

Methods

Ground truth for the presence or absence of ICH was iteratively determined by expert consensus in an unselected dataset of 527 consecutively acquired non-contrast head CT scans, which were sub-grouped according to the presence of artefact, post-operative features and referral source. The performance of VeriScout™ was compared with the ground truths for all groups.

Results

VeriScout™ detected hemorrhage with a sensitivity of 0.92 (CI 0.84-0.96) and a specificity of 0.96 (CI 0.94-0.98) in the global dataset, exceeding the sensitivity of general radiologists (0.88) with only a minor relative decrement in specificity (0.98). Crucially, the AI tool detected 13/14 cases of subarachnoid hemorrhage, a potentially fatal condition that is often missed in emergency department settings. There was no decrement in the performance of VeriScout™ in scans containing artefact or postoperative change. Using an integrated informatics platform, VeriScout™ was deployed into the existing radiology workflow. Detected hemorrhage cases were flagged in the hospital radiology information system (RIS) and relevant, annotated, preview images made available in the picture archiving and communications system (PACS) within 10 min.

Conclusion

AI-based radiology worklist prioritization for critical abnormalities, such as ICH, may enhance patient care without adding to radiologist or clinician burden.

Intracranial hemorrhage detection in 3D computed tomography images using a bi-directional long short-term memory network-based modified genetic algorithm

Introduction

Intracranial hemorrhage detection in 3D Computed Tomography (CT) brain images has gained more attention in the research community. The major issue to deal with the 3D CT brain images is scarce and hard to obtain the labelled data with better recognition results.

Methods

To overcome the aforementioned problem, a new model has been implemented in this research manuscript. After acquiring the images from the Radiological Society of North America (RSNA) 2019 database, the region of interest (RoI) was segmented by employing Otsu's thresholding method. Then, feature extraction was performed utilizing Tamura features: directionality, contrast, coarseness, and Gradient Local Ternary Pattern (GLTP) descriptors to extract vectors from the segmented RoI regions. The extracted vectors were dimensionally reduced by proposing a modified genetic algorithm, where the infinite feature selection technique was incorporated with the conventional genetic algorithm to further reduce the redundancy within the regularized vectors. The selected optimal vectors were finally fed to the Bi-directional Long Short Term Memory (Bi-LSTM) network to classify intracranial hemorrhage sub-types, such as subdural, intraparenchymal, subarachnoid, epidural, and intraventricular.

Results

The experimental investigation demonstrated that the Bi-LSTM based modified genetic algorithm obtained 99.40% sensitivity, 99.80% accuracy, and 99.48% specificity, which are higher compared to the existing machine learning models: Naïve Bayes, Random Forest, Support Vector Machine (SVM), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) network.

Predicting vasospasm risk using first presentation aneurysmal subarachnoid hemorrhage volume: A semi-automated CT image segmentation analysis using ITK-SNAP

PURPOSE

Cerebral vasospasm following aneurysmal subarachnoid hemorrhage (aSAH) is a significant complication associated with poor neurological outcomes. We present a novel, semi-automated pipeline, implemented in the open-source medical imaging analysis software ITK-SNAP, to segment subarachnoid blood volume from initial CT head (CTH) scans and use this to predict future radiological vasospasm.

METHODS

42 patients were admitted between February 2020 and December 2021 to our tertiary neurosciences center, and whose initial referral CTH scan was used for this retrospective cohort study. Blood load was segmented using a semi-automated random forest classifier and active contour evolution implemented in ITK-SNAP. Clinical data were extracted from electronic healthcare records in order to fit models aimed at predicting radiological vasospasm risk.

RESULTS

Semi-automated segmentations demonstrated excellent agreement with manual, expert-derived volumes (mean Dice coefficient = 0.92). Total normalized blood volume, extracted from CTH images at first presentation, was significantly associated with greater odds of later radiological vasospasm, increasing by approximately 7% for each additional cm3 of blood (OR = 1.069, 95% CI: 1.021-1.120; p < .005). Greater blood volume was also significantly associated with vasospasm of a higher Lindegaard ratio, of longer duration, and a greater number of discrete episodes. Total blood volume predicted radiological vasospasm with a greater accuracy as compared to the modified Fisher scale (AUC = 0.86 vs 0.70), and was of independent predictive value.

CONCLUSION

Semi-automated methods provide a plausible pipeline for the segmentation of blood from CT head images in aSAH, and total blood volume is a robust, extendable predictor of radiological vasospasm, outperforming the modified Fisher scale. Greater subarachnoid blood volume significantly increases the odds of subsequent vasospasm, its time course and its severity.

External Validation of an Artificial Intelligence Device for Intracranial Hemorrhage Detection

BACKGROUND

Artificial intelligence applications have gained traction in the field of cerebrovascular disease by assisting in the triage, classification, and prognostication of both ischemic and hemorrhagic stroke. The Caire ICH system aims to be the first device to move into the realm of assisted diagnosis for intracranial hemorrhage (ICH) and its subtypes.

METHODS

A single-center retrospective dataset of 402 head noncontrast CT scans (NCCT) with an intracranial hemorrhage were retrospectively collected from January 2012 to July 2020; an additional 108 NCCT scans with no intracranial hemorrhage findings were also included. The presence of an ICH and its subtype were determined from the International Classification of Diseases-10 code associated with the scan and validated by an expert panel. We used the Caire ICH vR1 to analyze these scans, and we evaluated its performance in terms of accuracy, sensitivity, and specificity.

RESULTS

We found the Caire ICH system to have an accuracy of 98.05% (95% confidence interval [CI]: 96.44%-99.06%), a sensitivity of 97.52% (95% CI: 95.50%-98.81%), and a specificity of 100% (95% CI: 96.67%-100.00%) in the detection of ICH. Experts reviewed the 10 incorrectly classified scans.

CONCLUSIONS

The Caire ICH vR1 algorithm was highly accurate, sensitive, and specific in detecting the presence or absence of an ICH and its subtypes in NCCTs. This work suggests that the Caire ICH device has potential to minimize clinical errors in ICH diagnosis that could improve patient outcomes and current workflows as both a point-of-care tool for diagnostics and as a safety net for radiologists.

Research advances in imaging markers for predicting hematoma expansion in intracerebral hemorrhage: a narrative review

Introduction

Stroke is a major global health concern and is ranked as the second leading cause of death worldwide, with the third highest incidence of disability. Intracerebral hemorrhage (ICH) is a devastating form of stroke that is responsible for a significant proportion of stroke-related morbidity and mortality worldwide. Hematoma expansion (HE), which occurs in up to one-third of ICH patients, is a strong predictor of poor prognosis and can be potentially preventable if high-risk patients are identified early. In this review, we provide a comprehensive summary of previous research in this area and highlight the potential use of imaging markers for future research studies.

Recent advances

Imaging markers have been developed in recent years to aid in the early detection of HE and guide clinical decision-making. These markers have been found to be effective in predicting HE in ICH patients and include specific manifestations on Computed Tomography (CT) and CT Angiography (CTA), such as the spot sign, leakage sign, spot-tail sign, island sign, satellite sign, iodine sign, blend sign, swirl sign, black hole sign, and hypodensities. The use of imaging markers holds great promise for improving the management and outcomes of ICH patients.

Conclusion

The management of ICH presents a significant challenge, and identifying high-risk patients for HE is crucial to improving outcomes. The use of imaging markers for HE prediction can aid in the rapid identification of such patients and may serve as potential targets for anti-HE therapies in the acute phase of ICH. Therefore, further research is needed to establish the reliability and validity of these markers in identifying high-risk patients and guiding appropriate treatment decisions.

Intracranial Hemorrhage Detection Using Parallel Deep Convolutional Models and Boosting Mechanism

Intracranial hemorrhage (ICH) can lead to death or disability, which requires immediate action from radiologists. Due to the heavy workload, less experienced staff, and the complexity of subtle hemorrhages, a more intelligent and automated system is necessary to detect ICH. In literature, many artificial-intelligence-based methods are proposed. However, they are less accurate for ICH detection and subtype classification. Therefore, in this paper, we present a new methodology to improve the detection and subtype classification of ICH based on two parallel paths and a boosting technique. The first path employs the architecture of ResNet101-V2 to extract potential features from windowed slices, whereas Inception-V4 captures significant spatial information in the second path. Afterwards, the detection and subtype classification of ICH is performed by the light gradient boosting machine (LGBM) using the outputs of ResNet101-V2 and Inception-V4. Thus, the combined solution, known as ResNet101-V2, Inception-V4, and LGBM (Res-Inc-LGBM), is trained and tested over the brain computed tomography (CT) scans of CQ500 and Radiological Society of North America (RSNA) datasets. The experimental results state that the proposed solution efficiently obtains 97.7% accuracy, 96.5% sensitivity, and 97.4% F1 score using the RSNA dataset. Moreover, the proposed Res-Inc-LGBM outperforms the standard benchmarks for the detection and subtype classification of ICH regarding the accuracy, sensitivity, and F1 score. The results prove the significance of the proposed solution for its real-time application.

Deep Learning Applied to Intracranial Hemorrhage Detection

Intracranial hemorrhage is a serious medical problem that requires rapid and often intensive medical care. Identifying the location and type of any hemorrhage present is a critical step in the treatment of the patient. Detection of, and diagnosis of, a hemorrhage that requires an urgent procedure is a difficult and time-consuming process for human experts. In this paper, we propose methods based on EfficientDet's deep-learning technology that can be applied to the diagnosis of hemorrhages at a patient level and which could, thus, become a decision-support system. Our proposal is two-fold. On the one hand, the proposed technique classifies slices of computed tomography scans for the presence of hemorrhage or its lack of, and evaluates whether the patient is positive in terms of hemorrhage, and achieving, in this regard, 92.7% accuracy and 0.978 ROC AUC. On the other hand, our methodology provides visual explanations of the chosen classification using the Grad-CAM methodology.

[Machine learning technologies in CT-based diagnostics and classification of intracranial hemorrhages]

This review discusses pooled experience of creation, implementation and effectiveness of machine learning technologies in CT-based diagnosis of intracranial hemorrhages. The authors analyzed 21 original articles between 2015 and 2022 using the following keywords: «intracranial hemorrhage», «machine learning», «deep learning», «artificial intelligence». The review contains general data on basic concepts of machine learning and also considers in more detail such aspects as technical characteristics of data sets used for creation of AI algorithms for certain type of clinical task, their possible impact on effectiveness and clinical experience.

Automated identification and quantification of traumatic brain injury from CT scans: Are we there yet?

BACKGROUND

The purpose of this study was to conduct a systematic review for understanding the availability and limitations of artificial intelligence (AI) approaches that could automatically identify and quantify computed tomography (CT) findings in traumatic brain injury (TBI).

METHODS

Systematic review, in accordance with PRISMA 2020 and SPIRIT-AI extension guidelines, with a search of 4 databases (Medline, Embase, IEEE Xplore, and Web of Science) was performed to find AI studies that automated the clinical tasks for identifying and quantifying CT findings of TBI-related abnormalities.

RESULTS

A total of 531 unique publications were reviewed, which resulted in 66 articles that met our inclusion criteria. The following components for identification and quantification regarding TBI were covered and automated by existing AI studies: identification of TBI-related abnormalities; classification of intracranial hemorrhage types; slice-, pixel-, and voxel-level localization of hemorrhage; measurement of midline shift; and measurement of hematoma volume. Automated identification of obliterated basal cisterns was not investigated in the existing AI studies. Most of the AI algorithms were based on deep neural networks that were trained on 2- or 3-dimensional CT imaging datasets.

CONCLUSION

We identified several important TBI-related CT findings that can be automatically identified and quantified with AI. A combination of these techniques may provide useful tools to enhance reproducibility of TBI identification and quantification by supporting radiologists and clinicians in their TBI assessments and reducing subjective human factors.

Multi-Layer ResNet-DenseNet architecture in consort with the XgBoost classifier for intracranial hemorrhage (ICH) subtype detection and classification

Intracerebral haemorrhage (ICH) is defined as bleeding occurs in the brain and causes vascular abnormality, tumor, venous Infarction, therapeutic anticoagulation, trauma property, and cerebral aneurysm. It is a dangerous disease and increases high mortality rate within the age of 15 to 24. It may be cured by finding what type of ICH is affected in the brain within short period with more accuracy. The previous method did not provide adequate accuracy and increase the computational time. Therefore, in this manuscript Detection and Categorization of Acute Intracranial Hemorrhage (ICH) subtypes using a Multi-Layer DenseNet-ResNet Architecture with Improved Random Forest Classifier (IRF) is proposed to detect the subtypes of ICH with high accuracy, less computational time with maximal speed. Here, the brain CT images are collected from Physionet repository publicly dataset. Then the images are pre-processed to eliminate the noises. After that, the image features are extracted by using multi layer Densely Connected Convolutional Network (DenseNet) combined with Residual Network (ResNet) architecture with multiple Convolutional layers. The sub types of ICH (Epidural Hemorrhage (EDH), Subarachnoid Hemorrhage (SAH), Intracerebral Hemorrhage (ICH), Subdural Hemorrhage (SDH), Intraventricular Hemorrhage (IVH), normal is classified by using Improved Random Forest (IRF) Classifier with high accuracy. The simulation is activated in MATLAB platform. The proposed Multilayer-DenseNet-ResNet-IRF approach attains higher accuracy 23.44%, 31.93%, 42.83%, 41.9% compared with existing approaches, like Detection with classification of intracranial haemorrhage on CT images utilizing new deep-learning algorithm (ICH-DC-CNN), Detection with classification of intracranial haemorrhage on CT images utilizing new deep-learning algorithm (ICH-DC-CNN-ResNet-50), Shallow 3D CNN for detecting acute brain hemorrhage from medical imaging sensors (ICH-DC-S-3D-CNN), Convolutional neural network: a review of models, methods and applications to object detection (ICH-DC-CNN-AlexNet) respectively.

CT and DSA for evaluation of spontaneous intracerebral lobar bleedings

Purpose

This study retrospectively examined the extent to which computed tomography angiography (CTA) and digital subtraction angiography (DSA) can help identify the cause of lobar intracerebral bleeding.

Materials and methods

In the period from 2002 to 2020, data from patients who were >18 years at a university and an academic teaching hospital with lobar intracerebral bleeding were evaluated retrospectively. The CTA DSA data were reviewed separately by two neuroradiologists, and differences in opinion were resolved by consensus after discussion. A positive finding was defined as an underlying vascular etiology of lobar bleeding.

Results

The data of 412 patients were retrospectively investigated. DSA detected a macrovascular cause of bleeding in 125/412 patients (33%). In total, sixty patients had AVMs (15%), 30 patients with aneurysms (7%), 12 patients with vasculitis (3%), and 23 patients with dural fistulas (6%). The sensitivity, specificity, positive and negative predictive values, and accuracy of CTA compared with DSA were 93, 97, 100, and 97%. There were false-negative CTA readings for two AVMs and one dural fistula.

Conclusion

The DSA is still the gold standard diagnostic modality for detecting macrovascular causes of ICH; however, most patients with lobar ICH can be investigated first with CTA, and the cause of bleeding can be found. Our results showed higher sensitivity and specificity than those of other CTA studies.

Artificial Intelligence in Healthcare Competition (TEKNOFEST-2021): Stroke Data Set

OBJECTIVE

The artificial intelligence competition in healthcare was organized for the first time at the annual aviation, space, and technology festival (TEKNOFEST), Istanbul/Türkiye, in September 2021. In this article, the data set preparation and competition processes were explained in detail; the anonymized and annotated data set is also provided via official website for further research.

MATERIALS AND METHODS

Data set recorded over the period covering 2019 and 2020 were centrally screened from the e-Pulse and Teleradiology System of the Republic of Türkiye, Ministry of Health using various codes and filtering criteria. The data set was anonymized. The data set was prepared, pooled, curated, and annotated by 7 radiologists. The training data set was shared with the teams via a dedicated file transfer protocol server, which could be accessed using private usernames and passwords given to the teams under a nondisclosure agreement signed by the representative of each team.

RESULTS

The competition consisted of 2 stages. In the first stage, teams were given 192 digital imaging and communications in medicine images that belong to 1 of 3 possible categories namely, hemorrhage, ischemic, or non-stroke. Teams were asked to classify each image as either stroke present or absent. In the second stage of the competition, qualifying 36 teams were given 97 digital imaging and communications in medicine images that contained hemorrhage, ischemia, or both lesions. Among the employed methods, Unet and DeepLabv3 were the most frequently observed ones.

CONCLUSION

Artificial intelligence competitions in healthcare offer good opportunities to collect data reflecting various cases and problems. Especially, annotated data set by domain experts is more valuable.

Detection of Subarachnoid Hemorrhage in Computed Tomography Using Association Rules Mining

Subarachnoid hemorrhage (SAH) is one of the serious strokes of cerebrovascular accidents. There is an approx. 15% probability of spontaneous subarachnoid hemorrhage in all acute cerebrovascular accidents (CVAs). Most spontaneous subarachnoid hemorrhages are caused by ruptures of intracranial aneurysms, accounting for about 85% of all occurrences. About 15% of acute cerebrovascular disorders are caused by spontaneous subarachnoid hemorrhage. This illness is mostly caused by brain/spinal arteriovenous malformations, extracranial aneurysms, and hypertension. Computed tomography (CT) scan is the common diagnostic modality to evaluate SAH, but it is very difficult to identify the abnormality. Thus, automatic detection of SAH is required to recognize the early signs and symptoms of SAH and to provide appropriate therapeutic intervention and treatment. In this article, the gray-level cooccurrence matrix (GLCM) is used to extract useful features from CT images. Then, the New Association Classification Frequent Pattern (NCFP-growth) algorithm is applied, which is based on association rules. Then, it is compared with FP-growth methods with association rules and FP-growth methods without association rules. The experimental results indicate that the suggested approach outperforms in terms of classification accuracy. The proposed approach equates to a 95.2% accuracy rate compared to the conventional data mining algorithm.