Detection Of Intracranial Hemorrhage Research Articles

Decreasing false-positive detection of intracranial hemorrhage (ICH) using RAPID ICH 3

IntroductionThe prompt detection of intracranial hemorrhage (ICH) on a non-contrast head CT (NCCT) is critical for the appropriate triage of patients, particularly in high volume/high acuity settings. Several automated ICH detection tools have been introduced; however, at present, most suffer from suboptimal specificity leading to false-positive notifications. MethodsNCCT scans from 4 large databases were evaluated for the presence of an ICH (IPH, IVH, SAH or SDH) of >0.4 ml using fully-automated RAPID ICH 3.0 as compared to consensus detection from at least two neuroradiology experts. Scans were excluded for (1) severe CT artifacts, (2) prior neurosurgical procedures, or (3) recent intravenous contrast. ICH detection accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and positive and negative likelihood ratios by were determined. ResultsA total of 881 studies were included. The automated software correctly identified 453/463 ICH-positive cases and 416/418 ICH-negative cases, resulting in a sensitivity of 97.84% and specificity 99.52%, positive predictive value 99.56%, and negative predictive value 97.65% for ICH detection. The positive and negative likelihood ratios for ICH detection were similarly favorable at 204.49 and 0.02 respectively. Mean processing time was <40 seconds. ConclusionsIn this large data set of nearly 900 patients, the automated software demonstrated high sensitivity and specificity for ICH detection, with rare false-positives.

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

ObjectiveTo 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). MethodsWe 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. ResultsOut 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. ConclusionHemorrhage 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.

Automated intracranial hemorrhage detection in traumatic brain injury using 3D CNN.

Intracranial hemorrhage (ICH) is a prevalent and potentially fatal consequence of traumatic brain injury (TBI). Timely identification of ICH is crucial to ensure timely intervention and to optimize better patient outcomes. However, the current methods for diagnosing ICH from head computed tomography (CT) scans require skilled personnel (Radiologists and/or Neurosurgeons) who may be unavailable in all centers, especially in rural areas. The aim of this study is to develop a neurotrauma screening tool for identifying ICH from head CT scans of TBI patients. We prospectively collected head CT scans from the Department of Neurosurgery, All India Institute of Medical Sciences, New Delhi. Approximately 738 consecutive head CT scans from patients enrolled in the department were collected for this study spanning a duration of 9 months, that is, January 2020 to September 2020. The metadata collected along with the head CT scans consisted of demographic and clinical details and the radiologist's report which was used as the gold standard. A deep learning-based 3D convolutional neural network (CNN) model was trained on the dataset. The pre-processing, hyperparameters, and augmentation were common for training the 3D CNN model whereas the training modules were set differently. The model was trained along with the save best model option and was monitored by validation metrics. The Institute Ethics Committee permission was taken before starting the study. We developed a 3D CNN model for automatically detecting the ICH from head CT scans. The screening tool was tested in 20 cases and trained on 200 head CT scans, with 99 normal head CT and 101 CT scans with some type of ICH. The final model performed with 90% sensitivity, 70% specificity, and 80% accuracy. Our study reveals that the automated screening tool exhibits a commendable level of accuracy and sensitivity in detecting ICH from the head CT scans. The results indicate that the 3D CNN approach has a potential for further exploring the TBI-related pathologies.

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.

Fully automated sinogram-based deep learning model for detection and classification of intracranial hemorrhage.

To propose an automated approach for detecting and classifying Intracranial Hemorrhages (ICH) directly from sinograms using a deep learning framework. This method is proposed to overcome the limitations of the conventional diagnosis by eliminating the time-consuming reconstruction step and minimizing the potential noise and artifacts that can occur during the Computed Tomography (CT) reconstructionprocess. This study proposes a two-stage automated approach for detecting and classifying ICH from sinograms using a deep learning framework. The first stage of the framework is Intensity Transformed Sinogram Sythesizer, which synthesizes sinograms that are equivalent to the intensity-transformed CT images. The second stage comprises of a cascaded Convolutional Neural Network-Recurrent Neural Network (CNN-RNN) model that detects and classifies hemorrhages from the synthesized sinograms. The CNN module extracts high-level features from each input sinogram, while the RNN module provides spatial correlation of the neighborhood regions in the sinograms. The proposed method was evaluated on a publicly available RSNA dataset consisting of a large sample size of 8652patients. The results showed that the proposed method had a notable improvement as high as 27% in patient-wise accuracies when compared to state-of-the-art methods like ResNext-101, Inception-v3 and Vision Transformer. Furthermore, the sinogram-based approach was found to be more robust to noise and offset errors in comparison to CT image-based approaches. The proposed model was also subjected to a multi-label classification analysis to determine the hemorrhage type from a given sinogram. The learning patterns of the proposed model were also examined for explainability using the activationmaps. The proposed sinogram-based approach can provide an accurate and efficient diagnosis of ICH without the need for the time-consuming reconstruction step and can potentially overcome the limitations of CT image-based approaches. The results show promising outcomes for the use of sinogram-based approaches in detecting hemorrhages, and further research can explore the potential of this approach in clinicalsettings.

An efficient stacked bidirectionalGRU‐LSTMnetwork for intracranial hemorrhage detection

AbstractIntracranial hemorrhage (ICH) is a dangerous condition that needs prompt diagnosis and treatment. Computed tomography (CT) images are employed in examination of individuals with ICH, which produces better results and cost‐effective than MRI. The existing convolutional neural network (CNN) models are unable to consider inter‐pixel dependency, which leads to false predictions while considering the input CT Images. In this study, we implemented an efficient model of a stack of bidirectional gated recurrent unit (Bi‐GRU) with a bidirectional long short‐term memory (Bi‐LSTM) based CNN to improve detection accuracy in the case of 2D slices. The proposed model holds slice‐wise information by accessing the properties of both Bi‐LSTM and Bi‐GRU modules in a single unit. As a result, the model attained a testing and training accuracy of 96.2% and 93.4%, respectively, with a test loss score of 0.126. In addition, the proposed model could outperform the state‐of‐the‐art CNN in identifying brain hemorrhages.

Advancing edema detection: Harnessing the power of machine learning and near infrared spectroscopy for cerebral and cerebellar edema assessment

Edema, characterized by brain swelling, is a common response observed in various brain injuries. Timely detection of edema is crucial to mitigate the associated risks and improve patient care. This study evaluates the efficacy of CEREBO®, a non-invasive machine learning-powered near-infrared spectroscopy (mNIRS) based device, in detecting edema. The study was conducted on 234 participants with suspected head injuries who underwent simultaneous CEREBO® scans and CT head scans. The results of the study showed that CEREBO® effectively identified edematous lobes, achieving a sensitivity of 95.7%, specificity of 97%, and accuracy of 96.9% for cases with intracranial hemorrhage (ICH). Additionally, for cases without ICH, the device exhibited a sensitivity of 100%, specificity of 97.2%, and accuracy of 97.2%. Two cases were reported where CEREBO® failed to detect edematous ICH. The study highlights the potential of CEREBO® as a valuable tool for early detection of pre-symptomatic edema and ICH, enabling timely interventions and improved patient care. The findings support the reliability of near-infrared spectroscopy as a diagnostic modality for edema.

The impact on clinical outcomes after 1 year of implementation of an artificial intelligence solution for the detection of intracranial hemorrhage

BackgroundTo assess the effect of a commercial artificial intelligence (AI) solution implementation in the emergency department on clinical outcomes in a single level 1 trauma center.MethodsA retrospective cohort study for two time periods—pre-AI (1.1.2017–1.1.2018) and post-AI (1.1.2019–1.1.2020)—in a level 1 trauma center was performed. The ICH algorithm was applied to 587 consecutive patients with a confirmed diagnosis of ICH on head CT upon admission to the emergency department.Study variables included demographics, patient outcomes, and imaging data. Participants admitted to the emergency department during the same time periods for other acute diagnoses (ischemic stroke (IS) and myocardial infarction (MI)) served as control groups. Primary outcomes were 30- and 120-day all-cause mortality. The secondary outcome was morbidity based on Modified Rankin Scale for Neurologic Disability (mRS) at discharge.ResultsFive hundred eighty-seven participants (289 pre-AI—age 71 ± 1, 169 men; 298 post-AI—age 69 ± 1, 187 men) with ICH were eligible for the analyzed period. Demographics, comorbidities, Emergency Severity Score, type of ICH, and length of stay were not significantly different between the two time periods. The 30- and 120-day all-cause mortality were significantly reduced in the post-AI group when compared to the pre-AI group (27.7% vs 17.5%; p = 0.004 and 31.8% vs 21.7%; p = 0.017, respectively). Modified Rankin Scale (mRS) at discharge was significantly reduced post-AI implementation (3.2 vs 2.8; p = 0.044).ConclusionThe added value of this study emphasizes the introduction of artificial intelligence (AI) computer-aided triage and prioritization software in an emergent care setting that demonstrated a significant reduction in a 30- and 120-day all-cause mortality and morbidity for patients diagnosed with intracranial hemorrhage (ICH). Along with mortality rates, the AI software was associated with a significant reduction in the Modified Ranking Scale (mRs).

Optimizing Patient-Centered Stroke Care and Research in the Prehospital Setting.

Over the past decades, continuous technological advances and the availability of novel therapies have enabled treatment of more acute medical conditions than ever before. Many of these treatments, such as intravenous thrombolysis and mechanical thrombectomy for acute ischemic stroke, are highly time sensitive. This has raised interest in shifting advanced acute care from hospitals to the prehospital setting. Key objectives of advanced prehospital stroke care may include (1) early targeted treatments in the prehospital setting, for example, intravenous thrombolysis for acute stroke, and (2) advanced prehospital diagnostics such as prehospital large vessel occlusion and intracranial hemorrhage detection, to help inform patient triage and potentially reduce subsequent workload in emergency departments. Major challenges that may hamper a swift transition to more advanced prehospital care are related to conducting clinical trials in the prehospital setting to provide sufficient evidence for emergency interventions, as well as ambulance design, infrastructure, emergency medical service personnel training and workload, and cost barriers. Utilizing new technologies such as telemedicine, mobile stroke units and portable diagnostic devices, customized software applications, and smart storage space management may help surmount these challenges and establish efficient, targeted care strategies that are achievable in the prehospital setting. In this article, we delineate the paradigm of shifting advanced stroke care to the prehospital setting and outline future directions in providing evidence-based, patient-centered prehospital care. While we use acute stroke as an illustrative example, these principles are not limited to stroke patients and can be applied to prehospital triage for any time-critical disease.

A Deep Learning-Based Automatic Segmentation and 3D Visualization Technique for Intracranial Hemorrhage Detection Using Computed Tomography Images.

Intracranial hemorrhage (ICH) occurs when blood leaks inside the skull as a result of trauma to the skull or due to medical conditions. ICH usually requires immediate medical and surgical attention because the disease has a high mortality rate, long-term disability potential, and other potentially life-threatening complications. There are a wide range of severity levels, sizes, and morphologies of ICHs, making accurate identification challenging. Hemorrhages that are small are more likely to be missed, particularly in healthcare systems that experience high turnover when it comes to computed tomography (CT) investigations. Although many neuroimaging modalities have been developed, CT remains the standard for diagnosing trauma and hemorrhage (including non-traumatic ones). A CT scan-based diagnosis can provide time-critical, urgent ICH surgery that could save lives because CT scan-based diagnoses can be obtained rapidly. The purpose of this study is to develop a machine-learning algorithm that can detect intracranial hemorrhage based on plain CT images taken from 75 patients. CT images were preprocessed using brain windowing, skull-stripping, and image inversion techniques. Hemorrhage segmentation was performed using multiple pre-trained models on preprocessed CT images. A U-Net model with DenseNet201 pre-trained encoder outperformed other U-Net, U-Net++, and FPN (Feature Pyramid Network) models with the highest Dice similarity coefficient (DSC) and intersection over union (IoU) scores, which were previously used in many other medical applications. We presented a three-dimensional brain model highlighting hemorrhages from ground truth and predicted masks. The volume of hemorrhage was measured volumetrically to determine the size of the hematoma. This study is essential in examining ICH for diagnostic purposes in clinical practice by comparing the predicted 3D model with the ground truth.

Development and characterization of transfontanelle photoacoustic imaging system for detection of intracranial hemorrhages and measurement of brain oxygenation: Ex-vivo

We have developed and optimized an imaging system to study and improve the detection of brain hemorrhage and to quantify oxygenation. Since this system is intended to be used for brain imaging in neonates through the skull opening, i.e., fontanelle, we called it, Transfontanelle Photoacoustic Imaging (TFPAI) system. The system is optimized in terms of optical and acoustic designs, thermal safety, and mechanical stability. The lower limit of quantification of TFPAI to detect the location of hemorrhage and its size is evaluated using in-vitro and ex-vivo experiments. The capability of TFPAI in measuring the tissue oxygenation and detection of vasogenic edema due to brain blood barrier disruption are demonstrated. The results obtained from our experimental evaluations strongly suggest the potential utility of TFPAI, as a portable imaging modality in the neonatal intensive care unit. Confirmation of these findings in-vivo could facilitate the translation of this promising technology to the clinic.

Label-efficient deep semantic segmentation of intracranial hemorrhages in CT-scans.

Intracranial hemorrhage (ICH) is a common finding in traumatic brain injury (TBI) and computed tomography (CT) is considered the gold standard for diagnosis. Automated detection of ICH provides clinical value in diagnostics and in the ability to feed robust quantification measures into future prediction models. Several studies have explored ICH detection and segmentation but the research process is somewhat hindered due to a lack of open large and labeled datasets, making validation and comparison almost impossible. The complexity of the task is further challenged by the heterogeneity of ICH patterns, requiring a large number of labeled data to train robust and reliable models. Consequently, due to the labeling cost, there is a need for label-efficient algorithms that can exploit easily available unlabeled or weakly-labeled data. Our aims for this study were to evaluate whether transfer learning can improve ICH segmentation performance and to compare a variety of transfer learning approaches that harness unlabeled and weakly-labeled data. Three self-supervised and three weakly-supervised transfer learning approaches were explored. To be used in our comparisons, we also manually labeled a dataset of 51 CT scans. We demonstrate that transfer learning improves ICH segmentation performance on both datasets. Unlike most studies on ICH segmentation our work relies exclusively on publicly available datasets, allowing for easy comparison of performances in future studies. To further promote comparison between studies, we also present a new public dataset of ICH-labeled CT scans, Seq-CQ500.

Automated Detection of Intracranial Hemorrhage from Head CT Scans Applying Deep Learning Techniques in Traumatic Brain Injuries: A Comparative Review

AbstractTraumatic brain injury (TBI) is not only an acute condition but also a chronic disease with long-term consequences. Intracranial hematomas are considered the primary consequences that occur in TBI and may have devastating effects that may lead to mass effect on the brain and eventually cause secondary brain injury. Emergent detection of hematoma in computed tomography (CT) scans and assessment of three major determinants, namely, location, volume, and size, is crucial for prognosis and decision-making, and artificial intelligence (AI) using deep learning techniques, such as convolutional neural networks (CNN) has received extended attention after demonstrations that it could perform at least as well as humans in imaging classification tasks. This article conducts a comparative review of medical and technological literature to update and establish evidence as to how technology can be utilized rightly for increasing the efficiency of the clinical workflow in emergency cases. A systematic and comprehensive literature search was conducted in the electronic database of PubMed and Google Scholar from 2013 to 2023 to identify studies related to the automated detection of intracranial hemorrhage (ICH). Inclusion and exclusion criteria were set to filter out the most relevant articles. We identified 15 studies on the development and validation of computer-assisted screening and analysis algorithms that used head CT scans. Our review shows that AI algorithms can prioritize radiology worklists to reduce time to screen for ICH in the head scans sufficiently and may also identify subtle ICH overlooked by radiologists, and that automated ICH detection tool holds promise for introduction into routine clinical practice.

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

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. 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. 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.

Electromagnetic induction detection techniques for craniocerebral injury: A review

Assessing the severity and prognosis of patients with craniocerebral damage is a major research area in medicine since it is a prevalent clinical disease. Acute craniocerebral injury, a common traumatic condition, is often caused by traffic accidents, collisions, and falls in daily life. Secondary craniocerebral injury refers to symptoms such as brain edema and intracranial hemorrhage after acute craniocerebral injury, which will aggravate the injury. Secondary craniocerebral injury can be avoided by effective and timely treatment, and real-time detection of brain edema and intracranial hemorrhage by non-invasive medical imaging is a solution. Therefore, non-invasive medical imaging technology has recently emerged as a new area of study. A new imaging technology, namely the brain injury detection technology based on electromagnetic induction, has been discovered after years of research on non-invasive detection of brain injury. Initially, electromagnetic induction technology was widely used in metal nondestructive testing. The human body, as a conductor, also has electromagnetic induction, allowing this technology to be used on the human body. This study reviews the technologies for detecting electromagnetic induction in cases of craniocerebral damage, including induced current electrical impedance tomography, magneto-acoustic tomography, and eddy current damping sensors for detection and imaging.

Comparison of diffusion weighted imaging b0 with T2*-weighted gradient echo or susceptibility weighted imaging for intracranial hemorrhage detection after reperfusion therapy for ischemic stroke

PurposeDiffusion-weighted imaging (DWI) b0 may be able to substitute T2*-weighted gradient echo (GRE) or susceptibility-weighted imaging (SWI) in case of comparable detection of intracranial hemorrhage (ICH), thereby reducing MRI examination time. We evaluated the diagnostic accuracy of DWI b0 compared to T2*GRE or SWI for detection of ICH after reperfusion therapy for ischemic stroke.MethodsWe pooled 300 follow-up MRI scans acquired within 1 week after reperfusion therapy. Six neuroradiologists each rated DWI images (b0 and b1000; b0 as index test) of 100 patients and, after a minimum of 4 weeks, T2*GRE or SWI images (reference standard) paired with DWI images of the same patients. Readers assessed the presence of ICH (yes/no) and type of ICH according to the Heidelberg Bleeding Classification. We determined the sensitivity and specificity of DWI b0 for detection of any ICH, and the sensitivity for detection of hemorrhagic infarction (HI1 & HI2) and parenchymal hematoma (PH1 & PH2).ResultsWe analyzed 277 scans of ischemic stroke patients with complete image series and sufficient image quality (median age 65 years [interquartile range, 54–75], 158 [57%] men). For detection of any ICH on DWI b0, the sensitivity was 62% (95% CI: 50–76) and specificity 96% (95% CI: 93–99). The sensitivity of DWI b0 was 52% (95% CI: 28–68) for detection of hemorrhagic infarction and 84% (95% CI: 70–92) for parenchymal hematoma.ConclusionDWI b0 is inferior for detection of ICH compared to T2*GRE/SWI, especially for smaller and more subtle hemorrhages. Follow-up MRI protocols should include T2*GRE/SWI for detection of ICH after reperfusion therapy.

A comparison of performance between a deep learning model with residents for localization and classification of intracranial hemorrhage

Intracranial hemorrhage (ICH) from traumatic brain injury (TBI) requires prompt radiological investigation and recognition by physicians. Computed tomography (CT) scanning is the investigation of choice for TBI and has become increasingly utilized under the shortage of trained radiology personnel. It is anticipated that deep learning models will be a promising solution for the generation of timely and accurate radiology reports. Our study examines the diagnostic performance of a deep learning model and compares the performance of that with detection, localization and classification of traumatic ICHs involving radiology, emergency medicine, and neurosurgery residents. Our results demonstrate that the high level of accuracy achieved by the deep learning model, (0.89), outperforms the residents with regard to sensitivity (0.82) but still lacks behind in specificity (0.90). Overall, our study suggests that the deep learning model may serve as a potential screening tool aiding the interpretation of head CT scans among traumatic brain injury patients.

Crowd-Sourced Deep Learning for Intracranial Hemorrhage Identification: Wisdom of Crowds or Laissez-Faire.

Researchers and clinical radiology practices are increasingly faced with the task of selecting the most accurate artificial intelligence tools from an ever-expanding range. In this study, we sought to test the utility of ensemble learning for determining the best combination from 70 models trained to identify intracranial hemorrhage. Furthermore, we investigated whether ensemble deployment is preferred to use of the single best model. It was hypothesized that any individual model in the ensemble would be outperformed by the ensemble. In this retrospective study, de-identified clinical head CT scans from 134 patients were included. Every section was annotated with "no-intracranial hemorrhage" or "intracranial hemorrhage," and 70 convolutional neural networks were used for their identification. Four ensemble learning methods were researched, and their accuracies as well as receiver operating characteristic curves and the corresponding areas under the curve were compared with those of individual convolutional neural networks. The areas under the curve were compared for a statistical difference using a generalized U-statistic. The individual convolutional neural networks had an average test accuracy of 67.8% (range, 59.4%-76.0%). Three ensemble learning methods outperformed this average test accuracy, but only one achieved an accuracy above the 95th percentile of the individual convolutional neural network accuracy distribution. Only 1 ensemble learning method achieved a similar area under the curve as the single best convolutional neural network (Δarea under the curve = 0.03; 95% CI, -0.01-0.06; P = .17). None of the ensemble learning methods outperformed the accuracy of the single best convolutional neural network, at least in the context of intracranial hemorrhage detection.

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

PurposeMost 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.MethodsMedline, 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.ResultsOut 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.ConclusionThe 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.

Artificial intelligence for detection of intracranial haemorrhage on head computed tomography scans: diagnostic accuracy in Hong Kong.

The use of artificial intelligence (AI) to identify acute intracranial haemorrhage (ICH) on computed tomography (CT) scans may facilitate initial imaging interpretation in the accident and emergency department. However, AI model construction requires a large amount of annotated data for training, and validation with real-world data has been limited. We developed an algorithm using an open-access dataset of CT slices, then assessed its utility in clinical practice by validating its performance on CT scans from our institution. Using a publicly available international dataset of >750 000 expert-labelled CT slices, we developed an AI model which determines ICH probability for each CT scan and nominates five potential ICH-positive CT slices for review. We validated the model using retrospective data from 1372 non-contrast head CT scans (84 [6.1%] with ICH) collected at our institution. The model achieved an area under the curve of 0.842 (95% confidence interval=0.791-0.894; P<0.001) for scan-based detection of ICH. A pre-specified probability threshold of ≥50% for the presence of ICH yielded 78.6% accuracy, 73% sensitivity, 79% specificity, 18.6% positive predictive value, and 97.8% negative predictive value. There were 62 true-positive scans and 22 false-negative scans, which could be reduced to six false-negative scans by manual review of model-nominated CT slices. Our model exhibited good accuracy in the CT scan-based detection of ICH, considering the low prevalence of ICH in Hong Kong. Model refinement to allow direct localisation of ICH will facilitate the use of AI solutions in clinical practice.