Review of deep learning algorithms for the automatic detection of intracranial hemorrhages on computed tomography head imaging

Automated neuroradiological support systems for multiple cerebrovascular disease markers - A systematic review and meta-analysis

Cerebrovascular diseases (CVD) can lead to stroke and dementia. Stroke is the second leading cause of death world wide and dementia incidence is increasing by the year. There are several markers of CVD that are visible on brain imaging, including: white matter hyperintensities (WMH), acute and chronic ischaemic stroke lesions (ISL), lacunes, enlarged perivascular spaces (PVS), acute and chronic haemorrhagic lesions, and cerebral microbleeds (CMB). Brain atrophy also occurs in CVD. These markers are important for patient management and intervention, since they indicate elevated risk of future stroke and dementia. We systematically reviewed automated systems designed to support radiologists reporting on these CVD imaging findings. We considered commercially available software and research publications which identify at least two CVD markers. In total, we included 29 commercial products and 13 research publications. Two distinct types of commercial support system were available: those which identify acute stroke lesions (haemorrhagic and ischaemic) from computed tomography (CT) scans, mainly for the purpose of patient triage; and those which measure WMH and atrophy regionally and longitudinally. In research, WMH and ISL were the markers most frequently analysed together, from magnetic resonance imaging (MRI) scans; lacunes and PVS were each targeted only twice and CMB only once. For stroke, commercially available systems largely support the emergency setting, whilst research systems consider also follow-up and routine scans. The systems to quantify WMH and atrophy are focused on neurodegenerative disease support, where these CVD markers are also of significance. There are currently no openly validated systems, commercially, or in research, performing a comprehensive joint analysis of all CVD markers (WMH, ISL, lacunes, PVS, haemorrhagic lesions, CMB, and atrophy).

Voxel-Wise Map of Intracerebral Hemorrhage Locations Associated With Worse Outcomes

BACKGROUND

Prior studies on the clinical impact of intracerebral hemorrhage (ICH) location have used visual localization of hematomas to neuroanatomical structures. However, hematomas often cross neuroanatomical structure boundaries with inter-reviewer variability in visual localization. To address these limitations, we applied voxel-wise analysis to identify brain regions where ICH presence is independently predictive of worse outcomes.

METHODS

We included consecutive patients with acute spontaneous ICH from a comprehensive stroke center in a derivation cohort and validated the results in patients from the control arm of a multicenter clinical trial. Using general linear models, we created and publicly shared a voxel-wise map of brain regions where ICH presence was associated with higher 3-month modified Rankin Scale scores, independent of hematoma volume and clinical risk factors. We also determined the optimal overlap threshold between baseline hematoma and voxel-wise map to categorize ICH location into high versus low risk.

RESULTS

Excluding those with missing variables, head computed tomography processing pipeline failure and poor scan quality, 559 of 780 patients were included in derivation (mean age, 69.3±14.5 years; 311 [55.6%] males) and 345 of 500 (mean age, 62.5±12.9 years; 206 [59.7%] males) in validation cohorts. In a voxel-wise analysis, ICH presence in deep white matter, thalami, caudate, midbrain, and pons was associated with worse outcomes. At the patient level, >22% overlap of baseline hematoma with voxel-wise map optimally binarized ICH location to high- versus low-risk categories. In both the derivation and validation cohorts, a high-risk ICH location was independently associated with worse outcomes (higher 3-month modified Rankin Scale score), after adjusting for patients' age, symptom severity at admission, baseline hematoma volume, and the presence of intraventricular hemorrhage, with adjusted odds ratios of 2 ([95% CI, 1.3-3.0] P=0.001) and 1.7 ([95% CI, 1.1-2.9] P=0.027), respectively.

CONCLUSIONS

We created and publicly shared a voxel-wise map of brain regions where hematoma presence predicts worse outcomes, independent of volume and clinical risk factors.

Applying Conformal Prediction to a Deep Learning Model for Intracranial Hemorrhage Detection to Improve Trustworthiness

Purpose To apply conformal prediction to a deep learning (DL) model for intracranial hemorrhage (ICH) detection and evaluate model performance in detection as well as model accuracy in identifying challenging cases. Materials and Methods This was a retrospective (November-December 2017) study of 491 noncontrast head CT volumes from the CQ500 dataset, in which three senior radiologists annotated sections containing ICH. The dataset was split into definite and challenging (uncertain) subsets, in which challenging images were defined as those in which there was disagreement among readers. A DL model was trained on patients from the definite data (training dataset) to perform ICH localization and classification into five classes. To develop an uncertainty-aware DL model, 1546 sections of the definite data (calibration dataset) were used for Mondrian conformal prediction (MCP). The uncertainty-aware DL model was tested on 8401 definite and challenging sections to assess its ability to identify challenging sections. The difference in predictive performance (P value) and ability to identify challenging sections (accuracy) were reported. Results The study included 146 patients (mean age, 45.7 years ± 9.9 [SD]; 76 [52.1%] men, 70 [47.9%] women). After the MCP procedure, the model achieved an F1 score of 0.919 for localization and classification. Additionally, it correctly identified patients with challenging cases with 95.3% (143 of 150) accuracy. It did not incorrectly label any definite sections as challenging. Conclusion The uncertainty-aware MCP-augmented DL model achieved high performance in ICH detection and high accuracy in identifying challenging sections, suggesting its usefulness in automated ICH detection and potential to increase trustworthiness of DL models in radiology. Keywords: CT, Head and Neck, Brain, Brain Stem, Hemorrhage, Feature Detection, Diagnosis, Supervised Learning Supplemental material is available for this article. © RSNA, 2025 See also commentary by Ngum and Filippi in this issue.

Brain tumor segmentation and detection in MRI using convolutional neural networks and VGG16

BackgroundIn this research, we explore the application of Convolutional Neural Networks (CNNs) for the development of an automated cancer detection system, particularly for MRI images. By leveraging deep learning and image processing techniques, we aim to build a system that can accurately detect and classify tumors in medical images. The system's performance depends on several stages, including image enhancement, segmentation, data augmentation, feature extraction, and classification. Through these stages, CNNs can be effectively trained to detect tumors in MRI images with high accuracy. This automated cancer detection system can assist healthcare professionals in diagnosing cancer more quickly and accurately, improving patient outcomes. The integration of deep learning and image processing in medical diagnostics has the potential to revolutionize healthcare, making it more efficient and accessible.MethodsIn this paper, we examine the failure of semantic segmentation by predicting the mean intersection over union (mIoU), which is a standard evaluation metric for segmentation tasks. mIoU calculates the overlap between the predicted segmentation map and the ground truth segmentation map, offering a way to evaluate the model's performance. A low mIoU indicates poor segmentation, suggesting that the model has failed to accurately classify parts of the image. To further improve the robustness of the system, we introduce a deep neural network capable of predicting the mIoU of a segmentation map. The key innovation here is the ability to predict the mIoU without needing access to ground truth data during testing. This allows the system to estimate how well the model is performing on a given image and detect potential failure cases early in the process. The proposed method not only predicts the mIoU but also uses the expected mIoU value to detect failure events. For instance, if the predicted mIoU falls below a certain threshold, the system can flag this as a potential failure, prompting further investigation or triggering a safety mechanism in the autonomous vehicle. This mechanism can prevent the vehicle from making decisions based on faulty segmentation, improving safety and performance. Furthermore, the system is designed to handle imbalanced data, which is a common challenge in training deep learning models. In autonomous driving, certain objects, such as pedestrians or cyclists, might appear much less frequently than other objects like vehicles or roads. The imbalance can cause the model to be biased toward the more frequent objects. By leveraging the expected mIoU, the method can effectively balance the influence of different object classes, ensuring that the model does not overlook critical elements in the scene. This approach offers a novel way of not only training the model to be more accurate but also incorporating failure prediction as an additional layer of safety. It is a significant step forward in ensuring that autonomous systems, especially self-driving cars, operate in a safe and reliable manner, minimizing the risk of accidents caused by misinterpretations of visual data. In summary, this research introduces a deep learning model that predicts segmentation performance and detects failure events by using the mIoU metric. By improving both the accuracy of semantic segmentation and the detection of failures, we contribute to the development of more reliable autonomous driving systems. Moreover, the technique can be extended to other domains where segmentation plays a critical role, such as medical imaging or robotics, enhancing their ability to function safely and effectively in complex environments.Results and DiscussionBrain tumor detection from MRI images is a critical task in medical image analysis that can significantly impact patient outcomes. By leveraging a hybrid approach that combines traditional image processing techniques with modern deep learning methods, this research aims to create an automated system that can segment and identify brain tumors with high accuracy and efficiency. Deep learning techniques, particularly CNNs, have proven to be highly effective in medical image analysis due to their ability to learn complex features from raw image data. The use of deep learning for automated brain tumor segmentation provides several benefits, including faster processing times, higher accuracy, and more consistent results compared to traditional manual methods. As a result, this research not only contributes to the development of advanced methods for brain tumor detection but also demonstrates the potential of deep learning in revolutionizing medical image analysis and assisting healthcare professionals in diagnosing and treating brain tumors more effectively.ConclusionIn conclusion, this research demonstrates the potential of deep learning techniques, particularly CNNs, in automating the process of brain tumor detection from MRI images. By combining traditional image processing methods with deep learning, we have developed an automated system that can quickly and accurately segment tumors from MRI scans. This system has the potential to assist healthcare professionals in diagnosing and treating brain tumors more efficiently, ultimately improving patient outcomes. As deep learning continues to evolve, we expect these systems to become even more accurate, robust, and widely applicable in clinical settings. The use of deep learning for brain tumor detection represents a significant step forward in medical image analysis, and its integration into clinical workflows could greatly enhance the speed and accuracy of diagnosis, ultimately saving lives. The suggested plan also includes a convolutional neural network-based classification technique to improve accuracy and save computation time. Additionally, the categorization findings manifest as images depicting either a healthy brain or one that is cancerous. CNN, a form of deep learning, employs a number of feed-forward layers. Additionally, it functions using Python. The Image Net database groups the images. The database has already undergone training and preparation. Therefore, we have completed the final training layer. Along with depth, width, and height feature information, CNN also extracts raw pixel values.We then use the Gradient decent-based loss function to achieve a high degree of precision. We can determine the training accuracy, validation accuracy, and validation loss separately. 98.5% of the training is accurate. Similarly, both validation accuracy and validation loss are high.

Machine learning-based pipeline for automated intracerebral hemorrhage and drain detection, quantification, and classification in non-enhanced CT images (NeuroDrAIn)

BACKGROUND AND PURPOSE

External drainage represents a well-established treatment option for acute intracerebral hemorrhage. The current standard of practice includes post-operative computer tomography imaging, which is subjectively evaluated. The implementation of an objective, automated evaluation of postoperative studies may enhance diagnostic accuracy and facilitate the scaling of research projects. The objective is to develop and validate a fully automated pipeline for intracerebral hemorrhage and drain detection, quantification of intracerebral hemorrhage coverage, and detection of malpositioned drains.

MATERIALS AND METHODS

In this retrospective study, we selected patients (n = 68) suffering from supratentorial intracerebral hemorrhage treated by minimally invasive surgery, from years 2010-2018. These were divided into training (n = 21), validation (n = 3) and testing (n = 44) datasets. Mean age (SD) was 70 (±13.56) years, 32 female. Intracerebral hemorrhage and drains were automatically segmented using a previously published artificial intelligence-based approach. From this, we calculated coverage profiles of the correctly detected drains to quantify the drains' coverage by the intracerebral hemorrhage and classify malpositioning. We used accuracy measures to assess detection and classification results and intraclass correlation coefficient to assess the quantification of the drain coverage by the intracerebral hemorrhage.

RESULTS

In the test dataset, the pipeline showed a drain detection accuracy of 0.97 (95% CI: 0.92 to 0.99), an agreement between predicted and ground truth coverage profiles of 0.86 (95% CI: 0.85 to 0.87) and a drain position classification accuracy of 0.88 (95% CI: 0.77 to 0.95) resulting in area under the receiver operating characteristic curve of 0.92 (95% CI: 0.85 to 0.99).

CONCLUSION

We developed and statistically validated an automated pipeline for evaluating computed tomography scans after minimally invasive surgery for intracerebral hemorrhage. The algorithm reliably detects drains, quantifies drain coverage by the hemorrhage, and uses machine learning to detect malpositioned drains. This pipeline has the potential to impact the daily clinical workload, as well as to facilitate the scaling of data collection for future research into intracerebral hemorrhage and other diseases.

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.

Prospective Evaluation of Artificial Intelligence Triage of Intracranial Hemorrhage on Noncontrast Head CT Examinations

BACKGROUND. Retrospective studies evaluating artificial intelligence (AI) algorithms for intracranial hemorrhage (ICH) detection on noncontrast CT (NCCT) have shown promising results but lack prospective validation. OBJECTIVE. The purpose of this article was to evaluate the impact on radiologists' real-world aggregate performance for ICH detection and report turnaround times for ICH-positive examinations of a radiology department's implementation of an AI triage and notification system for ICH detection on head NCCT examinations. METHODS. This prospective single-center study included adult patients who underwent head NCCT examinations from May 12, 2021, to June 30, 2021 (phase 1), or from September 30, 2021, to December 4, 2021 (phase 2). Before phase 1, the radiology department implemented a commercial AI triage system for ICH detection that processed head NCCT examinations and notified radiologists of positive results through a widget with a floating pop-up display. Examinations were interpreted by neuroradiologists or emergency radiologists, who evaluated examinations without and with AI assistance in phases 1 and 2, respectively. A panel of radiologists conducted a review process for all examinations with discordance between the radiology report and AI and a subset of remaining examinations to establish the reference standard. Diagnostic performance and report turnaround times were compared using the Pearson chi-square test and Wilcoxon rank sum test, respectively. Bonferroni correction was used to account for five diagnostic performance metrics (adjusted significance threshold, .01 [α = .05/5]). RESULTS. A total of 9954 examinations from 7371 patients (mean age, 54.8 ± 19.8 [SD] years; 3773 women, 3598 men) were included. In phases 1 and 2, 19.8% (735/3716) and 21.9% (1368/6238) of examinations, respectively, were positive for ICH (p = .01). Radiologists without versus with AI showed no significant difference in accuracy (99.5% vs 99.2%), sensitivity (98.6% vs 98.9%), PPV (99.0% vs 97.5%), or NPV (99.7% vs 99.7%) (all p > .01); specificity was higher for radiologists without than with AI (99.8% vs 99.3%, respectively, p = .004). Mean report turnaround time for ICH-positive examinations was 147.1 minutes without AI versus 149.9 minutes with AI (p = .11). CONCLUSION. An AI triage system for ICH detection did not improve radiologists' diagnostic performance or report turnaround times. CLINICAL IMPACT. This large prospective real-world study does not support use of AI assistance for ICH detection.

Impact of a deep learning-based brain CT interpretation algorithm on clinical decision-making for intracranial hemorrhage in the emergency department

Intracranial hemorrhage is a critical emergency that requires prompt and accurate diagnosis in the emergency department (ED). Deep learning technology can assist in interpreting non-enhanced brain CT scans, but its real-world impact on clinical decision-making is uncertain. This study assessed a deep learning-based intracranial hemorrhage detection algorithm (DLHD) in a simulated clinical environment with ten emergency medical professionals from a tertiary hospital's ED. The participants reviewed CT scans with clinical information in two steps: without and with DLHD. Diagnostic performance was measured, including sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve. Consistency in clinical decision-making was evaluated using the kappa statistic. The results demonstrated that DLHD minimally affected experienced participants' diagnostic performance and decision-making. In contrast, inexperienced participants exhibited significantly increased sensitivity (59.33-72.67%, p < 0.001) and decreased specificity (65.49-53.73%, p < 0.001) with the algorithm. Clinical decision-making consistency was moderate among inexperienced professionals (k = 0.425) and higher among experienced ones (k = 0.738). Inexperienced participants changed their decisions more frequently, mainly due to the algorithm's false positives. The study highlights the need for thorough evaluation and careful integration of deep learning tools into clinical workflows, especially for less experienced professionals.

Accuracy of automated segmentation and volumetry of acute intracerebral hemorrhage following minimally invasive surgery using a patch-based convolutional neural network in a small dataset

PURPOSE

In cases of acute intracerebral hemorrhage (ICH) volume estimation is of prognostic and therapeutic value following minimally invasive surgery (MIS). The ABC/2 method is widely used, but suffers from inaccuracies and is time consuming. Supervised machine learning using convolutional neural networks (CNN), trained on large datasets, is suitable for segmentation tasks in medical imaging. Our objective was to develop a CNN based machine learning model for the segmentation of ICH and of the drain and volumetry of ICH following MIS of acute supratentorial ICH on a relatively small dataset.

METHODS

Ninety two scans were assigned to training (n = 29 scans), validation (n = 4 scans) and testing (n = 59 scans) datasets. The mean age (SD) was 70 (± 13.56) years. Male patients were 36. A hierarchical, patch-based CNN for segmentation of ICH and drain was trained. Volume of ICH was calculated from the segmentation mask.

RESULTS

The best performing model achieved a Dice similarity coefficient of 0.86 and 0.91 for the ICH and drain respectively. Automated ICH volumetry yielded high agreement with ground truth (Intraclass correlation coefficient = 0.94 [95% CI: 0.91, 0.97]). Average difference in the ICH volume was 1.33 mL.

CONCLUSION

Using a relatively small dataset, originating from different CT-scanners and with heterogeneous voxel dimensions, we applied a patch-based CNN framework and successfully developed a machine learning model, which accurately segments the intracerebral hemorrhage (ICH) and the drains. This provides automated and accurate volumetry of the bleeding in acute ICH treated with minimally invasive surgery.

The Artificial Intelligence Revolution in Stroke Care: A Decade of Scientific Evidence in Review

BACKGROUND

The emergence of artificial intelligence (AI) has significantly influenced the diagnostic evaluation of stroke and has revolutionized acute stroke care delivery. The scientific evidence evaluating the role of AI, especially in areas of stroke treatment and rehabilitation is limited but continues to accumulate. We performed a systemic review of current scientific evidence evaluating the use of AI in stroke evaluation and care and examined the publication trends during the past decade.

METHODS

A systematic search of electronic databases was conducted to identify all studies published from 2012 to 2022 that incorporated AI in any aspect of stroke care. Studies not directly relevant to stroke care in the context of AI and duplicate studies were excluded. The level of evidence and publication trends were examined.

RESULTS

A total of 623 studies were examined, including 101 reviews (16.2%), 9 meta-analyses (1.4%), 140 original articles on AI methodology (22.5%), 2 case reports (0.3%), 2 case series (0.3%), 31 case-control studies (5%), 277 cohort studies (44.5%), 16 cross-sectional studies (2.6%), and 45 experimental studies (7.2%). The highest published area of AI in stroke was diagnosis (44.1%) and the lowest was rehabilitation (12%). A 10-year trend analysis revealed a significant increase in AI literature in stroke care.

CONCLUSIONS

Most research on AI is in the diagnostic area of stroke care, with a recent noteworthy trend of increased research focus on stroke treatment and rehabilitation.

Systematic reviews of machine learning in healthcare: a literature review

INTRODUCTION

The increasing availability of data and computing power has made machine learning (ML) a viable approach to faster, more efficient healthcare delivery.

METHODS

A systematic literature review (SLR) of published SLRs evaluating ML applications in healthcare settings published between1 January 2010 and 27 March 2023 was conducted.

RESULTS

In total 220 SLRs covering 10,462 ML algorithms were reviewed. The main application of AI in medicine related to the clinical prediction and disease prognosis in oncology and neurology with the use of imaging data. Accuracy, specificity, and sensitivity were provided in 56%, 28%, and 25% SLRs respectively. Internal and external validation was reported in 53% and less than 1% of the cases respectively. The most common modeling approach was neural networks (2,454 ML algorithms), followed by support vector machine and random forest/decision trees (1,578 and 1,522 ML algorithms, respectively).

EXPERT OPINION

The review indicated considerable reporting gaps in terms of the ML's performance, both internal and external validation. Greater accessibility to healthcare data for developers can ensure the faster adoption of ML algorithms into clinical practice.

Examination-Level Supervision for Deep Learning-based Intracranial Hemorrhage Detection on Head CT Scans

Purpose To compare the effectiveness of weak supervision (ie, with examination-level labels only) and strong supervision (ie, with image-level labels) in training deep learning models for detection of intracranial hemorrhage (ICH) on head CT scans. Materials and Methods In this retrospective study, an attention-based convolutional neural network was trained with either local (ie, image level) or global (ie, examination level) binary labels on the Radiological Society of North America (RSNA) 2019 Brain CT Hemorrhage Challenge dataset of 21 736 examinations (8876 [40.8%] ICH) and 752 422 images (107 784 [14.3%] ICH). The CQ500 (436 examinations; 212 [48.6%] ICH) and CT-ICH (75 examinations; 36 [48.0%] ICH) datasets were employed for external testing. Performance in detecting ICH was compared between weak (examination-level labels) and strong (image-level labels) learners as a function of the number of labels available during training. Results On examination-level binary classification, strong and weak learners did not have different area under the receiver operating characteristic curve values on the internal validation split (0.96 vs 0.96; P = .64) and the CQ500 dataset (0.90 vs 0.92; P = .15). Weak learners outperformed strong ones on the CT-ICH dataset (0.95 vs 0.92; P = .03). Weak learners had better section-level ICH detection performance when more than 10 000 labels were available for training (average f1 = 0.73 vs 0.65; P < .001). Weakly supervised models trained on the entire RSNA dataset required 35 times fewer labels than equivalent strong learners. Conclusion Strongly supervised models did not achieve better performance than weakly supervised ones, which could reduce radiologist labor requirements for prospective dataset curation. Keywords: CT, Head/Neck, Brain/Brain Stem, Hemorrhage Supplemental material is available for this article. © RSNA, 2023 See also commentary by Wahid and Fuentes in this issue.

Deep learning-based segmentation of brain parenchyma and ventricular system in CT scans in the presence of anomalies

INTRODUCTION

The automatic segmentation of brain parenchyma and cerebrospinal fluid-filled spaces such as the ventricular system is the first step for quantitative and qualitative analysis of brain CT data. For clinical practice and especially for diagnostics, it is crucial that such a method is robust to anatomical variability and pathological changes such as (hemorrhagic or neoplastic) lesions and chronic defects. This study investigates the increase in overall robustness of a deep learning algorithm that is gained by adding hemorrhage training data to an otherwise normal training cohort.

METHODS

A 2D U-Net is trained on subjects with normal appearing brain anatomy. In a second experiment the training data includes additional subjects with brain hemorrhage on image data of the RSNA Brain CT Hemorrhage Challenge with custom reference segmentations. The resulting networks are evaluated on normal and hemorrhage test casesseparately, and on an independent test set of patients with brain tumors of the publicly available GLIS-RT dataset.

RESULTS

Adding data with hemorrhage to the training set significantly improves the segmentation performance over an algorithm trained exclusively on normally appearing data, not only in the hemorrhage test set but also in the tumor test set. The performance on normally appearing data is stable. Overall, the improved algorithm achieves median Dice scores of 0.98 (parenchyma), 0.91 (left ventricle), 0.90 (right ventricle), 0.81 (third ventricle), and 0.80 (fourth ventricle) on the hemorrhage test set. On the tumor test set, the median Dice scores are 0.96 (parenchyma), 0.90 (left ventricle), 0.90 (right ventricle), 0.75 (third ventricle), and 0.73 (fourth ventricle).

CONCLUSION

Training on an extended data set that includes pathologies is crucial and significantly increases the overall robustness of a segmentation algorithm for brain parenchyma and ventricular system in CT data, also for anomalies completely unseen during training. Extension of the training set to include other diseases may further improve the generalizability of the algorithm.

Challenges of implementing computer-aided diagnostic models for neuroimages in a clinical setting

Advances in artificial intelligence have cultivated a strong interest in developing and validating the clinical utilities of computer-aided diagnostic models. Machine learning for diagnostic neuroimaging has often been applied to detect psychological and neurological disorders, typically on small-scale datasets or data collected in a research setting. With the collection and collation of an ever-growing number of public datasets that researchers can freely access, much work has been done in adapting machine learning models to classify these neuroimages by diseases such as Alzheimer's, ADHD, autism, bipolar disorder, and so on. These studies often come with the promise of being implemented clinically, but despite intense interest in this topic in the laboratory, limited progress has been made in clinical implementation. In this review, we analyze challenges specific to the clinical implementation of diagnostic AI models for neuroimaging data, looking at the differences between laboratory and clinical settings, the inherent limitations of diagnostic AI, and the different incentives and skill sets between research institutions, technology companies, and hospitals. These complexities need to be recognized in the translation of diagnostic AI for neuroimaging from the laboratory to the clinic.

Development and External Validation of a Deep Learning Algorithm to Identify and Localize Subarachnoid Hemorrhage on CT Scans

BACKGROUND AND OBJECTIVES

In medical imaging, a limited number of trained deep learning algorithms have been externally validated and released publicly. We hypothesized that a deep learning algorithm can be trained to identify and localize subarachnoid hemorrhage (SAH) on head computed tomography (CT) scans and that the trained model performs satisfactorily when tested using external and real-world data.

METHODS

We used noncontrast head CT images of patients admitted to Helsinki University Hospital between 2012 and 2017. We manually segmented (i.e., delineated) SAH on 90 head CT scans and used the segmented CT scans together with 22 negative (no SAH) control CT scans in training an open-source convolutional neural network (U-Net) to identify and localize SAH. We then tested the performance of the trained algorithm by using external data sets (137 SAH and 1,242 control cases) collected in 2 foreign countries and also by creating a data set of consecutive emergency head CT scans (8 SAH and 511 control cases) performed during on-call hours in 5 different domestic hospitals in September 2021. We assessed the algorithm's capability to identify SAH by calculating patient- and slice-level performance metrics, such as sensitivity and specificity.

RESULTS

In the external validation set of 1,379 cases, the algorithm identified 136 of 137 SAH cases correctly (sensitivity 99.3% and specificity 63.2%). Of the 49,064 axial head CT slices, the algorithm identified and localized SAH in 1845 of 2,110 slices with SAH (sensitivity 87.4% and specificity 95.3%). Of 519 consecutive emergency head CT scans imaged in September 2021, the algorithm identified all 8 SAH cases correctly (sensitivity 100.0% and specificity 75.3%). The slice-level (27,167 axial slices in total) sensitivity and specificity were 87.3% and 98.8%, respectively, as the algorithm identified and localized SAH in 58 of 77 slices with SAH. The performance of the algorithm can be tested on through a web service.

DISCUSSION

We show that the shared algorithm identifies SAH cases with a high sensitivity and that the slice-level specificity is high. In addition to openly sharing a high-performing deep learning algorithm, our work presents infrequently used approaches in designing, training, testing, and reporting deep learning algorithms developed for medical imaging diagnostics.

CLASSIFICATION OF EVIDENCE

This study provides Class III evidence that a deep learning algorithm correctly identifies the presence of subarachnoid hemorrhage on CT scan.

Grade Classification of Tumors from Brain Magnetic Resonance Images Using a Deep Learning Technique

To improve the accuracy of tumor identification, it is necessary to develop a reliable automated diagnostic method. In order to precisely categorize brain tumors, researchers developed a variety of segmentation algorithms. Segmentation of brain images is generally recognized as one of the most challenging tasks in medical image processing. In this article, a novel automated detection and classification method was proposed. The proposed approach consisted of many phases, including pre-processing MRI images, segmenting images, extracting features, and classifying images. During the pre-processing portion of an MRI scan, an adaptive filter was utilized to eliminate background noise. For feature extraction, the local-binary grey level co-occurrence matrix (LBGLCM) was used, and for image segmentation, enhanced fuzzy c-means clustering (EFCMC) was used. After extracting the scan features, we used a deep learning model to classify MRI images into two groups: glioma and normal. The classifications were created using a convolutional recurrent neural network (CRNN). The proposed technique improved brain image classification from a defined input dataset. MRI scans from the REMBRANDT dataset, which consisted of 620 testing and 2480 training sets, were used for the research. The data demonstrate that the newly proposed method outperformed its predecessors. The proposed CRNN strategy was compared against BP, U-Net, and ResNet, which are three of the most prevalent classification approaches currently being used. For brain tumor classification, the proposed system outcomes were 98.17% accuracy, 91.34% specificity, and 98.79% sensitivity.

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.

Retrospective analysis and prospective validation of an AI-based software for intracranial haemorrhage detection at a high-volume trauma centre

Rapid detection of intracranial haemorrhage (ICH) is crucial for assessing patients with neurological symptoms. Prioritising these urgent scans for reporting presents a challenge for radiologists. Artificial intelligence (AI) offers a solution to enable radiologists to triage urgent scans and reduce reporting errors. This study aims to evaluate the accuracy of an ICH-detection AI software and whether it benefits a high-volume trauma centre in terms of triage and reducing diagnostic errors. A peer review of head CT scans performed prior to the implementation of the AI was conducted to identify the department's current miss-rate. Once implemented, the AI software was validated using CT scans performed over one month, and was reviewed by a neuroradiologist. The turn-around-time was calculated as the time taken from scan completion to report finalisation. 2916 head CT scans and reports were reviewed as part of the audit. The AI software flagged 20 cases that were negative-by-report. Two of these were true-misses that had no follow-up imaging. Both patients were followed up and exhibited no long-term neurological sequelae. For ICH-positive scans, there was an increase in TAT in the total sample (35.6%), and a statistically insignificant decrease in TAT in the emergency (- 5.1%) and outpatient (- 14.2%) cohorts. The AI software was tested on a sample of real-world data from a high-volume Australian centre. The diagnostic accuracy was comparable to that reported in literature. The study demonstrated the institution's low miss-rate and short reporting time, therefore any improvements from the use of AI would be marginal and challenging to measure.

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.

Randomized Controlled Trials of Artificial Intelligence in Clinical Practice: Systematic Review

BACKGROUND

The number of artificial intelligence (AI) studies in medicine has exponentially increased recently. However, there is no clear quantification of the clinical benefits of implementing AI-assisted tools in patient care.

OBJECTIVE

This study aims to systematically review all published randomized controlled trials (RCTs) of AI-assisted tools to characterize their performance in clinical practice.

METHODS

CINAHL, Cochrane Central, Embase, MEDLINE, and PubMed were searched to identify relevant RCTs published up to July 2021 and comparing the performance of AI-assisted tools with conventional clinical management without AI assistance. We evaluated the primary end points of each study to determine their clinical relevance. This systematic review was conducted following the updated PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 guidelines.

RESULTS

Among the 11,839 articles retrieved, only 39 (0.33%) RCTs were included. These RCTs were conducted in an approximately equal distribution from North America, Europe, and Asia. AI-assisted tools were implemented in 13 different clinical specialties. Most RCTs were published in the field of gastroenterology, with 15 studies on AI-assisted endoscopy. Most RCTs studied biosignal-based AI-assisted tools, and a minority of RCTs studied AI-assisted tools drawn from clinical data. In 77% (30/39) of the RCTs, AI-assisted interventions outperformed usual clinical care, and clinically relevant outcomes improved with AI-assisted intervention in 70% (21/30) of the studies. Small sample size and single-center design limited the generalizability of these studies.

CONCLUSIONS

There is growing evidence supporting the implementation of AI-assisted tools in daily clinical practice; however, the number of available RCTs is limited and heterogeneous. More RCTs of AI-assisted tools integrated into clinical practice are needed to advance the role of AI in medicine.

TRIAL REGISTRATION

PROSPERO CRD42021286539; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=286539.

Accuracy of artificial intelligence for the detection of intracranial hemorrhage and chronic cerebral microbleeds: a systematic review and pooled analysis

BACKGROUND

Artificial intelligence (AI)-driven software has been developed and become commercially available within the past few years for the detection of intracranial hemorrhage (ICH) and chronic cerebral microbleeds (CMBs). However, there is currently no systematic review that summarizes all of these tools or provides pooled estimates of their performance.

METHODS

In this PROSPERO-registered, PRISMA compliant systematic review, we sought to compile and review all MEDLINE and EMBASE published studies that have developed and/or tested AI algorithms for ICH detection on non-contrast CT scans (NCCTs) or MRI scans and CMBs detection on MRI scans.

RESULTS

In total, 40 studies described AI algorithms for ICH detection in NCCTs/MRIs and 19 for CMBs detection in MRIs. The overall sensitivity, specificity, and accuracy were 92.06%, 93.54%, and 93.46%, respectively, for ICH detection and 91.6%, 93.9%, and 92.7% for CMBs detection. Some of the challenges encountered in the development of these algorithms include the laborious work of creating large, labeled and balanced datasets, the volumetric nature of the imaging examinations, the fine tuning of the algorithms, and the reduction in false positives.

CONCLUSIONS

Numerous AI-driven software tools have been developed over the last decade. On average, they are characterized by high performance and expert-level accuracy for the diagnosis of ICH and CMBs. As a result, implementing these tools in clinical practice may improve workflow and act as a failsafe for the detection of such lesions. REGISTRATION-URL: https://www.crd.york.ac.uk/prospero/ Unique Identifier: CRD42021246848.

Brain Tumor Analysis Using Deep Learning and VGG-16 Ensembling Learning Approaches

A brain tumor is a distorted tissue wherein cells replicate rapidly and indefinitely, with no control over tumor growth. Deep learning has been argued to have the potential to overcome the challenges associated with detecting and intervening in brain tumors. It is well established that the segmentation method can be used to remove abnormal tumor regions from the brain, as this is one of the advanced technological classification and detection tools. In the case of brain tumors, early disease detection can be achieved effectively using reliable advanced A.I. and Neural Network classification algorithms. This study aimed to critically analyze the proposed literature solutions, use the Visual Geometry Group (VGG 16) for discovering brain tumors, implement a convolutional neural network (CNN) model framework, and set parameters to train the model for this challenge. VGG is used as one of the highest-performing CNN models because of its simplicity. Furthermore, the study developed an effective approach to detect brain tumors using MRI to aid in making quick, efficient, and precise decisions. Faster CNN used the VGG 16 architecture as a primary network to generate convolutional feature maps, then classified these to yield tumor region suggestions. The prediction accuracy was used to assess performance. Our suggested methodology was evaluated on a dataset for brain tumor diagnosis using MR images comprising 253 MRI brain images, with 155 showing tumors. Our approach could identify brain tumors in MR images. In the testing data, the algorithm outperformed the current conventional approaches for detecting brain tumors (Precision = 96%, 98.15%, 98.41% and F1-score = 91.78%, 92.6% and 91.29% respectively) and achieved an excellent accuracy of CNN 96%, VGG 16 98.5% and Ensemble Model 98.14%. The study also presents future recommendations regarding the proposed research work.

Accuracy of Automated Computer-Aided Diagnosis for Stroke Imaging: A Critical Evaluation of Current Evidence

There is increasing interest in computer applications, using artificial intelligence methodologies, to perform health care tasks previously performed by humans, particularly in medical imaging for diagnosis. In stroke, there are now commercial artificial intelligence software for use with computed tomography or MR imaging to identify acute ischemic brain tissue pathology, arterial obstruction on computed tomography angiography or as hyperattenuated arteries on computed tomography, brain hemorrhage, or size of perfusion defects. A rapid, accurate diagnosis may aid treatment decisions for individual patients and could improve outcome if it leads to effective and safe treatment; or conversely, to disaster if a delayed or incorrect diagnosis results in inappropriate treatment. Despite this potential clinical impact, diagnostic tools including artificial intelligence methods are not subjected to the same clinical evaluation standards as are mandatory for drugs. Here, we provide an evidence-based review of the pros and cons of commercially available automated methods for medical imaging diagnosis, including those based on artificial intelligence, to diagnose acute brain pathology on computed tomography or magnetic resonance imaging in patients with stroke.

Deep Learning Paradigm for Cardiovascular Disease/Stroke Risk Stratification in Parkinson's Disease Affected by COVID-19: A Narrative Review

Background and Motivation: Parkinson's disease (PD) is one of the most serious, non-curable, and expensive to treat. Recently, machine learning (ML) has shown to be able to predict cardiovascular/stroke risk in PD patients. The presence of COVID-19 causes the ML systems to become severely non-linear and poses challenges in cardiovascular/stroke risk stratification. Further, due to comorbidity, sample size constraints, and poor scientific and clinical validation techniques, there have been no well-explained ML paradigms. Deep neural networks are powerful learning machines that generalize non-linear conditions. This study presents a novel investigation of deep learning (DL) solutions for CVD/stroke risk prediction in PD patients affected by the COVID-19 framework. Method: The PRISMA search strategy was used for the selection of 292 studies closely associated with the effect of PD on CVD risk in the COVID-19 framework. We study the hypothesis that PD in the presence of COVID-19 can cause more harm to the heart and brain than in non-COVID-19 conditions. COVID-19 lung damage severity can be used as a covariate during DL training model designs. We, therefore, propose a DL model for the estimation of, (i) COVID-19 lesions in computed tomography (CT) scans and (ii) combining the covariates of PD, COVID-19 lesions, office and laboratory arterial atherosclerotic image-based biomarkers, and medicine usage for the PD patients for the design of DL point-based models for CVD/stroke risk stratification. Results: We validated the feasibility of CVD/stroke risk stratification in PD patients in the presence of a COVID-19 environment and this was also verified. DL architectures like long short-term memory (LSTM), and recurrent neural network (RNN) were studied for CVD/stroke risk stratification showing powerful designs. Lastly, we examined the artificial intelligence bias and provided recommendations for early detection of CVD/stroke in PD patients in the presence of COVID-19. Conclusion: The DL is a very powerful tool for predicting CVD/stroke risk in PD patients affected by COVID-19.

Robotics and Artificial Intelligence in Endovascular Neurosurgery

The use of artificial intelligence (AI) and robotics in endovascular neurosurgery promises to transform neurovascular care. We present a review of the recently published neurosurgical literature on artificial intelligence and robotics in endovascular neurosurgery to provide insights into the current advances and applications of this technology.

The PubMed database was searched for "neurosurgery" OR "endovascular" OR "interventional" AND "robotics" OR "artificial intelligence" between January 2016 and August 2021. A total of 1296 articles were identified, and after applying the inclusion and exclusion criteria, 38 manuscripts were selected for review and analysis. These manuscripts were divided into four categories: 1) robotics and AI for the diagnosis of cerebrovascular pathology, 2) robotics and AI for the treatment of cerebrovascular pathology, 3) robotics and AI for training in neuroendovascular procedures, and 4) robotics and AI for clinical outcome optimization.

The 38 articles presented include 23 articles on AI-based diagnosis of cerebrovascular disease, 10 articles on AI-based treatment of cerebrovascular disease, two articles on AI-based training techniques for neuroendovascular procedures, and three articles reporting AI prediction models of clinical outcomes in vascular disorders of the brain. Innovation with robotics and AI focus on diagnostic efficiency, optimizing treatment and interventional procedures, improving physician procedural performance, and predicting clinical outcomes with the use of artificial intelligence and robotics. Experimental studies with robotic systems have demonstrated safety and efficacy in treating cerebrovascular disorders, and novel microcatheterization techniques may permit access to deeper brain regions. Other studies show that pre-procedural simulations increase overall physician performance. Artificial intelligence also shows superiority over existing statistical tools in predicting clinical outcomes.

The recent advances and current usage of robotics and AI in the endovascular neurosurgery field suggest that the collaboration between physicians and machines has a bright future for the improvement of patient care. The aim of this work is to equip the medical readership, in particular the neurosurgical specialty, with tools to better understand and apply findings from research on artificial intelligence and robotics in endovascular neurosurgery.

Utilization of Artificial Intelligence-based Intracranial Hemorrhage Detection on Emergent Noncontrast CT Images in Clinical Workflow

Authors implemented an artificial intelligence (AI)-based detection tool for intracranial hemorrhage (ICH) on noncontrast CT images into an emergent workflow, evaluated its diagnostic performance, and assessed clinical workflow metrics compared with pre-AI implementation. The finalized radiology report constituted the ground truth for the analysis, and CT examinations (n = 4450) before and after implementation were retrieved using various keywords for ICH. Diagnostic performance was assessed, and mean values with their respective 95% CIs were reported to compare workflow metrics (report turnaround time, communication time of a finding, consultation time of another specialty, and turnaround time in the emergency department). Although practicable diagnostic performance was observed for overall ICH detection with 93.0% diagnostic accuracy, 87.2% sensitivity, and 97.8% negative predictive value, the tool yielded lower detection rates for specific subtypes of ICH (eg, 69.2% [74 of 107] for subdural hemorrhage and 77.4% [24 of 31] for acute subarachnoid hemorrhage). Common false-positive findings included postoperative and postischemic defects (23.6%, 37 of 157), artifacts (19.7%, 31 of 157), and tumors (15.3%, 24 of 157). Although workflow metrics such as communicating a critical finding (70 minutes [95% CI: 54, 85] vs 63 minutes [95% CI: 55, 71]) were on average reduced after implementation, future efforts are necessary to streamline the workflow all along the workflow chain. It is crucial to define a clear framework and recognize limitations as AI tools are only as reliable as the environment in which they are deployed. Keywords: CT, CNS, Stroke, Diagnosis, Classification, Application Domain © RSNA, 2022.

How to Improve the Management of Acute Ischemic Stroke by Modern Technologies, Artificial Intelligence, and New Treatment Methods

Stroke remains one of the leading causes of death and disability in Europe. The European Stroke Action Plan (ESAP) defines four main targets for the years 2018 to 2030. The COVID-19 pandemic forced the use of innovative technologies and created pressure to improve internet networks. Moreover, 5G internet network will be helpful for the transfer and collecting of extremely big databases. Nowadays, the speed of internet connection is a limiting factor for robotic systems, which can be controlled and commanded potentially from various places in the world. Innovative technologies can be implemented for acute stroke patient management soon. Artificial intelligence (AI) and robotics are used increasingly often without the exception of medicine. Their implementation can be achieved in every level of stroke care. In this article, all steps of stroke health care processes are discussed in terms of how to improve them (including prehospital diagnosis, consultation, transfer of the patient, diagnosis, techniques of the treatment as well as rehabilitation and usage of AI). New ethical problems have also been discovered. Everything must be aligned to the concept of “time is brain”.