3D Deep Neural Network Segmentation of Intracerebral Hemorrhage: Development and Validation for Clinical Trials

ICH-PRNet: a cross-modal intracerebral haemorrhage prognostic prediction method using joint-attention interaction mechanism

Accurately predicting intracerebral hemorrhage (ICH) prognosis is a critical and indispensable step in the clinical management of patients post-ICH. Recently, integrating artificial intelligence, particularly deep learning, has significantly enhanced prediction accuracy and alleviated neurosurgeons from the burden of manual prognosis assessment. However, uni-modal methods have shown suboptimal performance due to the intricate pathophysiology of the ICH. On the other hand, existing cross-modal approaches that incorporate tabular data have often failed to effectively extract complementary information and cross-modal features between modalities, thereby limiting their prognostic capabilities. This study introduces a novel cross-modal network, ICH-PRNet, designed to predict ICH prognosis outcomes. Specifically, we propose a joint-attention interaction encoder that effectively integrates computed tomography images and clinical texts within a unified representational space. Additionally, we define a multi-loss function comprising three components to comprehensively optimize cross-modal fusion capabilities. To balance the training process, we employ a self-adaptive dynamic prioritization algorithm that adjusts the weights of each component, accordingly. Our model, through these innovative designs, establishes robust semantic connections between modalities and uncovers rich, complementary cross-modal information, thereby achieving superior prediction results. Extensive experimental results and comparisons with state-of-the-art methods on both in-house and publicly available datasets unequivocally demonstrate the superiority and efficacy of the proposed method. Our code is at https://github.com/YU-deep/ICH-PRNet.git.

A Hybrid Transformer-Convolutional Neural Network for Segmentation of Intracerebral Hemorrhage and Perihematomal Edema on Non-Contrast Head Computed Tomography (CT) with Uncertainty Quantification to Improve Confidence

Intracerebral hemorrhage (ICH) and perihematomal edema (PHE) are key imaging markers of primary and secondary brain injury in hemorrhagic stroke. Accurate segmentation and quantification of ICH and PHE can help with prognostication and guide treatment planning. In this study, we combined Swin-Unet Transformers with nnU-NETv2 convolutional network for segmentation of ICH and PHE on non-contrast head CTs. We also applied test-time data augmentations to assess individual-level prediction uncertainty, ensuring high confidence in prediction. The model was trained on 1782 CT scans from a multicentric trial and tested in two independent datasets from Yale (n = 396) and University of Berlin Charité Hospital and University Medical Center Hamburg-Eppendorf (n = 943). Model performance was evaluated with the Dice coefficient and Volume Similarity (VS). Our dual Swin-nnUNET model achieved a median (95% confidence interval) Dice = 0.93 (0.90-0.95) and VS = 0.97 (0.95-0.98) for ICH, and Dice = 0.70 (0.64-0.75) and VS = 0.87 (0.80-0.93) for PHE segmentation in the Yale cohort. Dice = 0.86 (0.80-0.90) and VS = 0.91 (0.85-0.95) for ICH and Dice = 0.65 (0.56-0.70) and VS = 0.86 (0.77-0.93) for PHE segmentation in the Berlin/Hamburg-Eppendorf cohort. Prediction uncertainty was associated with lower segmentation accuracy, smaller ICH/PHE volumes, and infratentorial location. Our results highlight the benefits of a dual transformer-convolutional neural network architecture for ICH/PHE segmentation and test-time augmentation for uncertainty quantification.

Automated Hematoma Detection and Outcome Prediction in Patients With Traumatic Brain Injury

PURPOSE

To develop a tool for automated subtype classification and segmentation of intracranial hemorrhages (ICH) on CT scans of patients with traumatic brain injury (TBI). Furthermore, outcome prediction for patients can effectively facilitate patient management.

METHODS

This study presents a cascade framework for two-stage segmentation and multi-label classification. The hematoma region of interest (ROI) is localized, and then the ROI is cropped and resized to the original pixel size before being input into the model again to obtain the segmentation results. In multilabel classification, the mask obtained from automatic segmentation is superimposed onto the corresponding ROI and CT slices, respectively, to constitute the input image. Subsequently, the ROI image is employed as the local network input to obtain local features. Third, the CT image is utilized to construct a feature extraction network to obtain global features. Ultimately, the local and global features are fused dimensions in the pooling layer, and calculated to generate the final retrieval results. For the prediction of 14-day in-hospital mortality, automatically extracted hematoma subtype and volume features were integrated to enhance the widely used CRASH model.

RESULTS

The proposed segmentation method achieves the best estimates on the Dice similarity coefficient and Jaccard Similarity Index. The proposed multilabel classification method achieved an average accuracy of 95.91%. For mortality prediction, the best model achieved an average area under the receiver operating characteristic curve (AUC) of 0.91 by 5-fold cross-validation.

CONCLUSIONS

The proposed method enhances the precision of hematoma segmentation and subtype classification. In clinical settings, the method can streamline the evaluation of ICH for radiologists, and the automatically extracted features are anticipated to facilitate prognosis assessment.

Need for Transparency and Clinical Interpretability in Hemorrhagic Stroke Artificial Intelligence Research: Promoting Effective Clinical Application

PURPOSE

This study aimed to evaluate the quality of artificial intelligence (AI)/machine learning (ML) studies on hemorrhagic stroke using the Minimum Information for Medical AI Reporting (MINIMAR) and Minimum Information About Clinical Artificial Intelligence Modeling (MI-CLAIM) frameworks to promote clinical application.

MATERIALS AND METHODS

PubMed, MEDLINE, and Embase were searched for AI/ML studies on hemorrhagic stroke. Out of the 531 articles found, 29 relevant original research articles were included. MINIMAR and MI-CLAIM scores were assigned by two experienced radiologists to assess the quality of the studies.

RESULTS

We analyzed 29 investigations that utilized AI/ML in the field of hemorrhagic stroke, involving a median of 224.5 patients. The majority of studies focused on diagnostic outcomes using computed tomography scans (89.7%) and were published in computer science journals (48.3%). The overall adherence rates to reporting guidelines, as assessed through the MINIMAR and MI-CLAIM frameworks, were 47.6% and 46.0%, respectively. In MINIMAR, none of the studies reported the socioeconomic status of the patients or how missing values had been addressed. In MI-CLAIM, only two studies applied model-examination techniques to improve model interpretability. Transparency and reproducibility were limited, as only 10.3% of the studies had publicly shared their code. Cohen's kappa between the two radiologists was 0.811 and 0.779 for MINIMAR and MI-CLAIM, respectively.

CONCLUSION

The overall reporting quality of published AI/ML studies on hemorrhagic stroke is suboptimal. It is necessary to incorporate model examination techniques for interpretability and promote code openness to enhance transparency and increase the clinical applicability of AI/ML studies.

Application of deep learning and radiomics in the prediction of hematoma expansion in intracerebral hemorrhage: a fully automated hybrid approach

PURPOSE

Spontaneous intracerebral hemorrhage (ICH) is the most severe form of stroke. The timely assessment of early hematoma enlargement and its proper treatment are of great significance in curbing the deterioration and improving the prognosis of patients with ICH. This study aimed to develop an automated hybrid approach to predict hematoma expansion in ICH.

METHODS

The transfer learning method was applied to build a hybrid model based on a convolutional neural network (CNN) to predict the expansion of hematoma. The model integrated (1) a CNN for automated hematoma segmentation and (2) a CNN-based classifier for hematoma expansion prediction that incorporated both 2-dimensional images and the radiomics features of the 3-dimensional hematoma shape.

RESULTS

The radiomics feature module had the highest area under the receiver operating characteristic curve (AUC) of 0.58, a precision of 0, a recall of 0, and an average precision (AP) of 0.26. The ResNet50 and Inception_v3 modules had AUCs of 0.79 and 0.93, a precision of 0.56 and 0.86, a recall of 0.42 and 0.75, and an AP of 0.51 and 0.85, respectively. Radiomic with Inception_v3 and Radiomic with ResNet50 had AUCs of 0.95 and 0.81, a precision of 0.90 and 0.57, a recall of 0.79 and 0.17, and an AP of 0.87 and 0.69, respectively.

CONCLUSION

A model using deep learning and radiomics was successfully developed. This model can reliably predict the hematoma expansion of ICH with a fully automated process based on non-contrast computed tomography imaging. Furthermore, the radiomics fusion with the Inception_v3 model had the highest accuracy.

Deep learning for prediction of post-thrombectomy outcomes based on admission CT angiography in large vessel occlusion stroke

Purpose

Computed Tomography Angiography (CTA) is the first line of imaging in the diagnosis of Large Vessel Occlusion (LVO) strokes. We trained and independently validated end-to-end automated deep learning pipelines to predict 3-month outcomes after anterior circulation LVO thrombectomy based on admission CTAs.

Methods

We split a dataset of 591 patients into training/cross-validation (n = 496) and independent test set (n = 95). We trained separate models for outcome prediction based on admission "CTA" images alone, "CTA + Treatment" (including time to thrombectomy and reperfusion success information), and "CTA + Treatment  + Clinical" (including admission age, sex, and NIH stroke scale). A binary (favorable) outcome was defined based on a 3-month modified Rankin Scale ≤ 2. The model was trained on our dataset based on the pre-trained ResNet-50 3D Convolutional Neural Network ("MedicalNet") and included CTA preprocessing steps.

Results

We generated an ensemble model from the 5-fold cross-validation, and tested it in the independent test cohort, with receiver operating characteristic area under the curve (AUC, 95% confidence interval) of 70 (0.59-0.81) for "CTA," 0.79 (0.70-0.89) for "CTA + Treatment," and 0.86 (0.79-0.94) for "CTA + Treatment + Clinical" input models. A "Treatment + Clinical" logistic regression model achieved an AUC of 0.86 (0.79-0.93).

Conclusion

Our results show the feasibility of an end-to-end automated model to predict outcomes from admission and post-thrombectomy reperfusion success. Such a model can facilitate prognostication in telehealth transfer and when a thorough neurological exam is not feasible due to language barrier or pre-existing morbidities.

Deep learning survival model predicts outcome after intracerebral hemorrhage from initial CT scan

BACKGROUND

Predicting functional impairment after intracerebral hemorrhage (ICH) provides valuable information for planning of patient care and rehabilitation strategies. Current prognostic tools are limited in making long term predictions and require multiple expert-defined inputs and interpretation that make their clinical implementation challenging. This study aimed to predict long term functional impairment of ICH patients from admission non-contrast CT scans, leveraging deep learning models in a survival analysis framework.

METHODS

We used the admission non-contrast CT scans from 882 patients from the Massachusetts General Hospital ICH Study for training, hyperparameter optimization, and model selection, and 146 patients from the Yale New Haven ICH Study for external validation of a deep learning model predicting functional outcome. Disability (modified Rankin scale [mRS] > 2), severe disability (mRS > 4), and dependent living status were assessed via telephone interviews after 6, 12, and 24 months. The prediction methods were evaluated by the c-index and compared with ICH score and FUNC score.

RESULTS

Using non-contrast CT, our deep learning model achieved higher prediction accuracy of post-ICH dependent living, disability, and severe disability by 6, 12, and 24 months (c-index 0.742 [95% CI -0.700 to 0.778], 0.712 [95% CI -0.674 to 0.752], 0.779 [95% CI -0.733 to 0.832] respectively) compared with the ICH score (c-index 0.673 [95% CI -0.662 to 0.688], 0.647 [95% CI -0.637 to 0.661] and 0.697 [95% CI -0.675 to 0.717]) and FUNC score (c-index 0.701 [95% CI- 0.698 to 0.723], 0.668 [95% CI -0.657 to 0.680] and 0.727 [95% CI -0.708 to 0.753]). In the external independent Yale-ICH cohort, similar performance metrics were obtained for disability and severe disability (c-index 0.725 [95% CI -0.673 to 0.781] and 0.747 [95% CI -0.676 to 0.807], respectively). Similar AUC of predicting each outcome at 6 months, 1 and 2 years after ICH was achieved compared with ICH score and FUNC score.

CONCLUSION

We developed a generalizable deep learning model to predict onset of dependent living and disability after ICH, which could help to guide treatment decisions, advise relatives in the acute setting, optimize rehabilitation strategies, and anticipate long-term care needs.

Artificial Intelligence and Machine Learning Applications in Critically Ill Brain Injured Patients

The utilization of Artificial Intelligence (AI) and Machine Learning (ML) is paving the way for significant strides in patient diagnosis, treatment, and prognostication in neurocritical care. These technologies offer the potential to unravel complex patterns within vast datasets ranging from vast clinical data and EEG (electroencephalogram) readings to advanced cerebral imaging facilitating a more nuanced understanding of patient conditions. Despite their promise, the implementation of AI and ML faces substantial hurdles. Historical biases within training data, the challenge of interpreting multifaceted data streams, and the "black box" nature of ML algorithms present barriers to widespread clinical adoption. Moreover, ethical considerations around data privacy and the need for transparent, explainable models remain paramount to ensure trust and efficacy in clinical decision-making.This article reflects on the emergence of AI and ML as integral tools in neurocritical care, discussing their roles from the perspective of both their scientific promise and the associated challenges. We underscore the importance of extensive validation in diverse clinical settings to ensure the generalizability of ML models, particularly considering their potential to inform critical medical decisions such as withdrawal of life-sustaining therapies. Advancement in computational capabilities is essential for implementing ML in clinical settings, allowing for real-time analysis and decision support at the point of care. As AI and ML are poised to become commonplace in clinical practice, it is incumbent upon health care professionals to understand and oversee these technologies, ensuring they adhere to the highest safety standards and contribute to the realization of personalized medicine. This engagement will be pivotal in integrating AI and ML into patient care, optimizing outcomes in neurocritical care through informed and data-driven decision-making.

Applications of deep learning in trauma radiology: A narrative review

Diagnostic imaging is essential in modern trauma care for initial evaluation and identifying injuries requiring intervention. Deep learning (DL) has become mainstream in medical image analysis and has shown promising efficacy for classification, segmentation, and lesion detection. This narrative review provides the fundamental concepts for developing DL algorithms in trauma imaging and presents an overview of current progress in each modality. DL has been applied to detect free fluid on Focused Assessment with Sonography for Trauma (FAST), traumatic findings on chest and pelvic X-rays, and computed tomography (CT) scans, identify intracranial hemorrhage on head CT, detect vertebral fractures, and identify injuries to organs like the spleen, liver, and lungs on abdominal and chest CT. Future directions involve expanding dataset size and diversity through federated learning, enhancing model explainability and transparency to build clinician trust, and integrating multimodal data to provide more meaningful insights into traumatic injuries. Though some commercial artificial intelligence products are Food and Drug Administration-approved for clinical use in the trauma field, adoption remains limited, highlighting the need for multi-disciplinary teams to engineer practical, real-world solutions. Overall, DL shows immense potential to improve the efficiency and accuracy of trauma imaging, but thoughtful development and validation are critical to ensure these technologies positively impact patient care.

Clinical Trial Protocol for BEACH: A Phase 2a Study of MW189 in Patients with Acute Nontraumatic Intracerebral Hemorrhage

Patients with acute spontaneous intracerebral hemorrhage (ICH) develop secondary neuroinflammation and cerebral edema that can further damage the brain and lead to increased risk of neurologic complications. Preclinical studies in animal models of acute brain injury have shown that a novel small-molecule drug candidate, MW01-6-189WH (MW189), decreases neuroinflammation and cerebral edema and improves functional outcomes. MW189 was also safe and well tolerated in phase 1 studies in healthy adults. The proof-of-concept phase 2a Biomarker and Edema Attenuation in IntraCerebral Hemorrhage (BEACH) clinical trial is a first-in-patient, multicenter, randomized, double-blind, placebo-controlled trial. It is designed to determine the safety and tolerability of MW189 in patients with acute ICH, identify trends in potential mitigation of neuroinflammation and cerebral edema, and assess effects on functional outcomes. A total of 120 participants with nontraumatic ICH will be randomly assigned 1:1 to receive intravenous MW189 (0.25 mg/kg) or placebo (saline) within 24 h of symptom onset and every 12 h for up to 5 days or until hospital discharge. The 120-participant sample size (60 per group) will allow testing of the null hypothesis of noninferiority with a tolerance limit of 12% and assuming a "worst-case" safety assumption of 10% rate of death in each arm with 10% significance and 80% power. The primary outcome is all-cause mortality at 7 days post randomization between treatment arms. Secondary end points include all-cause mortality at 30 days, perihematomal edema volume after symptom onset, adverse events, vital signs, pharmacokinetics of MW189, and inflammatory cytokine concentrations in plasma (and cerebrospinal fluid if available). Other exploratory end points are functional outcomes collected on days 30, 90, and 180. BEACH will provide important information about the utility of targeting neuroinflammation in ICH and will inform the design of future larger trials of acute central nervous system injury.

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.

Vision Transformer-based Decision Support for Neurosurgical Intervention in Acute Traumatic Brain Injury: Automated Surgical Intervention Support Tool

Purpose To develop an automated triage tool to predict neurosurgical intervention for patients with traumatic brain injury (TBI). Materials and Methods A provincial trauma registry was reviewed to retrospectively identify patients with TBI from 2005 to 2022 treated at a specialized Canadian trauma center. Model training, validation, and testing were performed using head CT scans with binary reference standard patient-level labels corresponding to whether the patient received neurosurgical intervention. Performance and accuracy of the model, the Automated Surgical Intervention Support Tool for TBI (ASIST-TBI), were also assessed using a held-out consecutive test set of all patients with TBI presenting to the center between March 2021 and September 2022. Results Head CT scans from 2806 patients with TBI (mean age, 57 years ± 22 [SD]; 1955 [70%] men) were acquired between 2005 and 2021 and used for training, validation, and testing. Consecutive scans from an additional 612 patients (mean age, 61 years ± 22; 443 [72%] men) were used to assess the performance of ASIST-TBI. There was accurate prediction of neurosurgical intervention with an area under the receiver operating characteristic curve (AUC) of 0.92 (95% CI: 0.88, 0.94), accuracy of 87% (491 of 562), sensitivity of 87% (196 of 225), and specificity of 88% (295 of 337) on the test dataset. Performance on the held-out test dataset remained robust with an AUC of 0.89 (95% CI: 0.85, 0.91), accuracy of 84% (517 of 612), sensitivity of 85% (199 of 235), and specificity of 84% (318 of 377). Conclusion A novel deep learning model was developed that could accurately predict the requirement for neurosurgical intervention using acute TBI CT scans. Keywords: CT, Brain/Brain Stem, Surgery, Trauma, Prognosis, Classification, Application Domain, Traumatic Brain Injury, Triage, Machine Learning, Decision Support Supplemental material is available for this article. © RSNA, 2024 See also commentary by Haller in this issue.

An overview of clinical machine learning applications in neurology

Machine learning techniques for clinical applications are evolving, and the potential impact this will have on clinical neurology is important to recognize. By providing a broad overview on this growing paradigm of clinical tools, this article aims to help healthcare professionals in neurology prepare to navigate both the opportunities and challenges brought on through continued advancements in machine learning. This narrative review first elaborates on how machine learning models are organized and implemented. Machine learning tools are then classified by clinical application, with examples of uses within neurology described in more detail. Finally, this article addresses limitations and considerations regarding clinical machine learning applications in neurology.

Prognostic Neuroimaging Biomarkers in Acute Vascular Brain Injury and Traumatic Brain Injury

Prognostic imaging biomarkers after acute brain injury inform treatment decisions, track the progression of intracranial injury, and can be used in shared decision-making processes with families. Herein, key established biomarkers and prognostic scoring systems are surveyed in the literature, and their applications in clinical practice and clinical trials are discussed. Biomarkers in acute ischemic stroke include computed tomography (CT) hypodensity scoring, diffusion-weighted lesion volume, and core infarct size on perfusion imaging. Intracerebral hemorrhage biomarkers include hemorrhage volume, expansion, and location. Aneurysmal subarachnoid biomarkers include hemorrhage grading, presence of diffusion-restricting lesions, and acute hydrocephalus. Traumatic brain injury CT scoring systems, contusion expansion, and diffuse axonal injury grading are reviewed. Emerging biomarkers including white matter disease scoring, diffusion tensor imaging, and the automated calculation of scoring systems and volumetrics are discussed.

What Is Machine Learning, Artificial Neural Networks and Deep Learning?-Examples of Practical Applications in Medicine

Machine learning (ML), artificial neural networks (ANNs), and deep learning (DL) are all topics that fall under the heading of artificial intelligence (AI) and have gained popularity in recent years. ML involves the application of algorithms to automate decision-making processes using models that have not been manually programmed but have been trained on data. ANNs that are a part of ML aim to simulate the structure and function of the human brain. DL, on the other hand, uses multiple layers of interconnected neurons. This enables the processing and analysis of large and complex databases. In medicine, these techniques are being introduced to improve the speed and efficiency of disease diagnosis and treatment. Each of the AI techniques presented in the paper is supported with an example of a possible medical application. Given the rapid development of technology, the use of AI in medicine shows promising results in the context of patient care. It is particularly important to keep a close eye on this issue and conduct further research in order to fully explore the potential of ML, ANNs, and DL, and bring further applications into clinical use in the future.

A revolutionary acute subdural hematoma detection based on two-tiered artificial intelligence model

BACKGROUND

The article was planned to make the first evaluation in terms of acute subdural hemorrhages, thinking that it can help in appropriate pathologies by tomography interpretation with the artificial intelligence (AI) method, at least in a way to quickly warn the responsible doctor.

METHODS

A two-level AI-based hybrid method was developed. The proposed model uses the mask-region convolutional neural network (Mask R-CNN) technique, which is a deep learning model, in the hemorrhagic region's mask generation stage, and a problem-specific, optimized support vector machines (SVM) technique which is a machine learning model in the binary classification stage. Furthermore, the bee colony algorithm was used for the optimization of SVM algorithms' parameters.

RESULTS

In the first stage, the mean average precision (mAP) value was obtained as 0.754 when the intercept over union (IOU) value was taken as 0.5 with the Mask R-CNN architecture used. At the same time, when a 5-fold cross-validation was applied, the mAP value was obtained 0.736. With the hyperparameter optimization for both Mask R-CNN and the SVM algorithm, the accuracy of the two-level classification process was obtained as 96.36%. Furthermore, final false-negative rate and false-positive rate values were obtained as 6.20%, and 2.57%, respectively.

CONCLUSION

With the proposed model, both the detection of hemorrhage and the presentation of the suspicious area to the physician were performed more successfully on two dimensional (2D) images with low cost and high accuracy compared to similar studies and today's interpretations with telemedicine techniques.

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

BACKGROUND AND PURPOSE

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.

MATERIALS AND METHODS

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.

RESULTS

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).

CONCLUSIONS

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.

External Validation and Retraining of DeepBleed: The First Open-Source 3D Deep Learning Network for the Segmentation of Spontaneous Intracerebral and Intraventricular Hemorrhage

BACKGROUND

The objective of this study was to assess the performance of the first publicly available automated 3D segmentation for spontaneous intracerebral hemorrhage (ICH) based on a 3D neural network before and after retraining.

METHODS

We performed an independent validation of this model using a multicenter retrospective cohort. Performance metrics were evaluated using the dice score (DSC), sensitivity, and positive predictive values (PPV). We retrained the original model (OM) and assessed the performance via an external validation design. A multivariate linear regression model was used to identify independent variables associated with the model's performance. Agreements in volumetric measurements and segmentation were evaluated using Pearson's correlation coefficients (r) and intraclass correlation coefficients (ICC), respectively. With 1040 patients, the OM had a median DSC, sensitivity, and PPV of 0.84, 0.79, and 0.93, compared to thoseo f 0.83, 0.80, and 0.91 in the retrained model (RM). However, the median DSC for infratentorial ICH was relatively low and improved significantly after retraining, at p < 0.001. ICH volume and location were significantly associated with the DSC, at p < 0.05. The agreement between volumetric measurements (r > 0.90, p > 0.05) and segmentations (ICC ≥ 0.9, p < 0.001) was excellent.

CONCLUSION

The model demonstrated good generalization in an external validation cohort. Location-specific variances improved significantly after retraining. External validation and retraining are important steps to consider before applying deep learning models in new clinical settings.

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

PURPOSE

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

METHODS

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

RESULTS

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

CONCLUSION

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

Deep-learning measurement of intracerebral haemorrhage with mixed precision training: a coarse-to-fine study

AIM

To develop a unified deep-learning-based method for automated intracerebral haemorrhage (ICH) segmentation on computed tomography (CT) images with different layer thickness parameters.

MATERIALS AND METHODS

A total of 134 patients from an internal database (67 patients) and an external database (called CQ500, 67 patients) were employed. The CT examinations included multiple layer thicknesses such as 0.625, 1.25 and 5 mm. ICH segmentation was performed by a coarse-to-fine strategy, including three stages of three-dimensional (3D) skull-stripping segmentation, 3D ICH localisation segmentation, and two-dimensional (2D) ICH fine segmentation. The three stages shared the same sICHNet for segmentation and employed mixed precision training to speed up the training process. In addition, the 3D contextual information from CT was maintained by formatting the consecutive slices into a three-channel image in the 2D ICH fine segmentation.

RESULTS

Experimental results demonstrated that the coarse-to-fine segmentation strategy achieved the best performance with a mean Dice coefficient of 0.887. ICH volume consistency was observed (p<0.05) between manual and automatic segmentations, and between segmentations of same individual but with different layer thicknesses in internal dataset and external database. Automated segmentation achieved a relatively consistent segmentation time of 20.01 ± 2.03 seconds no matter the layer thickness of the CT images and the extent of ICH. Longitudinal studies with conservative management and surgical treatment were also visualised.

CONCLUSIONS

The coarse-to-fine deep learning strategy achieved the best ICH segmentation performance on CT images. The automated segmentation was 5-42 times faster than manual segmentation given ICH of different extents and using different layer thickness parameters.

Unified ICH quantification and prognosis prediction in NCCT images using a multi-task interpretable network

With the recent development of deep learning, the regression, classification, and segmentation tasks of Computer-Aided Diagnosis (CAD) using Non-Contrast head Computed Tomography (NCCT) for spontaneous IntraCerebral Hematoma (ICH) have become popular in the field of emergency medicine. However, a few challenges such as time-consuming of ICH volume manual evaluation, excessive cost demanding patient-level predictions, and the requirement for high performance in both accuracy and interpretability remain. This paper proposes a multi-task framework consisting of upstream and downstream components to overcome these challenges. In the upstream, a weight-shared module is trained as a robust feature extractor that captures global features by performing multi-tasks (regression and classification). In the downstream, two heads are used for two different tasks (regression and classification). The final experimental results show that the multi-task framework has better performance than single-task framework. And it also reflects its good interpretability in the heatmap generated by Gradient-weighted Class Activation Mapping (Grad-CAM), which is a widely used model interpretation method, and will be presented in subsequent sections.

Semantic Segmentation of Spontaneous Intracerebral Hemorrhage, Intraventricular Hemorrhage, and Associated Edema on CT Images Using Deep Learning

This study evaluated deep learning algorithms for semantic segmentation and quantification of intracerebral hemorrhage (ICH), perihematomal edema (PHE), and intraventricular hemorrhage (IVH) on noncontrast CT scans of patients with spontaneous ICH. Models were assessed on 1732 annotated baseline noncontrast CT scans obtained from the Tranexamic Acid for Hyperacute Primary Intracerebral Haemorrhage (ie, TICH-2) international multicenter trial (ISRCTN93732214), and different loss functions using a three-dimensional no-new-U-Net (nnU-Net) were examined to address class imbalance (30% of participants with IVH in dataset). On the test cohort (n = 174, 10% of dataset), the top-performing models achieved median Dice similarity coefficients of 0.92 (IQR, 0.89-0.94), 0.66 (0.58-0.71), and 1.00 (0.87-1.00), respectively, for ICH, PHE, and IVH segmentation. U-Net-based networks showed comparable, satisfactory performances on ICH and PHE segmentations (P > .05), but all nnU-Net variants achieved higher accuracy than the Brain Lesion Analysis and Segmentation Tool for CT (BLAST-CT) and DeepLabv3+ for all labels (P < .05). The Focal model showed improved performance in IVH segmentation compared with the Tversky, two-dimensional nnU-Net, U-Net, BLAST-CT, and DeepLabv3+ models (P < .05). Focal achieved concordance values of 0.98, 0.88, and 0.99 for ICH, PHE, and ICH volumes, respectively. The mean volumetric differences between the ground truth and prediction were 0.32 mL (95% CI: -8.35, 9.00), 1.14 mL (-9.53, 11.8), and 0.06 mL (-1.71, 1.84), respectively. In conclusion, U-Net-based networks provide accurate segmentation on CT images of spontaneous ICH, and Focal loss can address class imbalance. International Clinical Trials Registry Platform (ICTRP) no. ISRCTN93732214 Supplemental material is available for this article. © RSNA, 2022 Keywords: Head/Neck, Brain/Brain Stem, Hemorrhage, Segmentation, Quantification, Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms.

Bayesian deep learning outperforms clinical trial estimators of intracerebral and intraventricular hemorrhage volume

BACKGROUND AND PURPOSE

Intracerebral hemorrhage (ICH) and intraventricular hemorrhage (IVH) clinical trials rely on manual linear and semi-quantitative (LSQ) estimators like the ABC/2, modified Graeb and IVH scores for timely volumetric estimation from CT. Deep learning (DL) volumetrics of ICH have recently approached the accuracy of gold-standard planimetry. However, DL and LSQ strategies have been limited by unquantified uncertainty, in particular when ICH and IVH estimates intersect. Bayesian deep learning methods can be used to approximate uncertainty, presenting an opportunity to improve quality assurance in clinical trials.

METHODS

A DL model was trained to simultaneously segment ICH and IVH using diagnostic CT data from the Minimally Invasive Surgery Plus Alteplase for ICH Evacuation (MISTIE) III and Clot Lysis: Evaluating Accelerated Resolution of IVH (CLEAR) III clinical trials. Bayesian uncertainty approximation was performed using Monte-Carlo dropout. We compared the performance of our model with estimators used in the CLEAR IVH and MISTIE II trials. The reliability of planimetry, DL, and LSQ volumetrics in the setting of high ICH and IVH intersection is quantified using consensus estimates.

RESULTS

Our DL model produced volume correlations and median Dice scores of .994 and .946 for ICH in MISTIE II, and .980 and .863 for IVH in CLEAR IVH, respectively, outperforming LSQ estimates from the clinical trials. We found significant linear relationships between ICH uncertainty, Dice scores (r = -.849), and relative volume difference (r = .735).

CONCLUSION

In our validation clinical trial dataset, DL models with Bayesian uncertainty approximation provided superior volumetric estimates to LSQ methods with real-time estimates of model uncertainty.

Automatic hemorrhage segmentation on head CT scan for traumatic brain injury using 3D deep learning model

The most common cause of long-term disability and death in young adults is a traumatic brain injury. The decision for surgical intervention for craniotomy is dependent on the injury type and the patient's neurologic exam. The potential subtypes of intracranial hemorrhage that may necessitate surgical intervention include subdural hemorrhage, epidural hemorrhage, and intraparenchymal hemorrhage. We proposed a novel automatic method for segmenting the hemorrhage subtypes on a CT scan by integrated CT scan with bone window as input of a deep learning model. Brain CT scans were collected from adult patients and annotated regions of subdural hemorrhage, epidural hemorrhage, and intraparenchymal hemorrhage by neuroradiologists. Their raw DICOM images were preprocessed by two different window settings i.e., subdural and bone windows. The collected CT scans were divided into two datasets namely training and test datasets. A deep-learning model was modified to segment regions of each hemorrhage subtype. The model is a three-dimensional convolutional neural network including four parallel pathways that process the input at different resolutions. It was trained by a training dataset. After the segmentation result was produced by the deep-learning model, it was then improved in the post-processing step. The size of the segmented lesion was considered, and a region-growing algorithm was applied. We evaluated the performance of the proposed method on the test dataset. The method reached the median Dice similarity coefficients higher than 0.37 for each hemorrhage subtype. The proposed method demonstrates higher Dice similarity coefficients and improved segmentation performance compared to previously published literature.

Can Artificial Intelligence Be Applied to Diagnose Intracerebral Hemorrhage under the Background of the Fourth Industrial Revolution? A Novel Systemic Review and Meta-Analysis

Aim

We intended to provide the clinical evidence that artificial intelligence (AI) could be used to assist doctors in the diagnosis of intracerebral hemorrhage (ICH).

Methods

Studies published in 2021 were identified after the literature search of PubMed, Embase, and Cochrane. Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) was used to perform the quality assessment of studies. Data extraction of diagnosis effect included accuracy (ACC), sensitivity (SEN), specificity (SPE), positive predictive value (PPV), negative predictive value (NPV), area under curve (AUC), and Dice scores (Dices). The pooled effect with its 95% confidence interval (95%CI) was calculated by the random effects model. I-Square (I 2) was used to test heterogeneity. To check the stability of the overall results, sensitivity analysis was conducted by recalculating the pooled effect of the remaining studies after omitting the study with the highest quality or the random effects model was switched to the fixed effects model. Funnel plot was used to evaluate publication bias. To reduce heterogeneity, recalculating the pooled effect of the remaining studies after omitting the study with the lowest quality or perform subgroup analysis.

Results

Twenty-five diagnostic tests of ICH via AI and doctors with overall high quality were included. Pooled ACC, SEN, SPE, PPV, NPV, AUC, and Dices were 0.88 (0.83∼0.93), 0.85 (0.81∼0.89), 0.90 (0.88∼0.92), 0.80 (0.75∼0.85), 0.93 (0.91∼0.95), 0.84 (0.80∼0.89), and 0.90 (0.85∼0.95), respectively. There was no publication bias. All of results were stable as revealed by sensitivity analysis and were accordant as outcomes via subgroups analysis.

Conclusion

Under the background of the fourth industrial revolution, AI might be an effective and efficient tool to assist doctors in the clinical diagnosis of ICH.

Potential role of artificial intelligence in craniofacial surgery

The field of artificial intelligence (AI) is rapidly advancing, and AI models are increasingly applied in the medical field, especially in medical imaging, pathology, natural language processing, and biosignal analysis. On the basis of these advances, telemedicine, which allows people to receive medical services outside of hospitals or clinics, is also developing in many countries. The mechanisms of deep learning used in medical AI include convolutional neural networks, residual neural networks, and generative adversarial networks. Herein, we investigate the possibility of using these AI methods in the field of craniofacial surgery, with potential applications including craniofacial trauma, congenital anomalies, and cosmetic surgery.

An optimal deep learning framework for multi-type hemorrhagic lesions detection and quantification in head CT images for traumatic brain injury

Traumatic Brain Injury (TBI) could lead to intracranial hemorrhage (ICH), which has now been identified as a major cause of death after trauma if it is not adequately diagnosed and properly treated within the first 24 hours. CT examination is widely preferred for urgent ICH diagnosis, which enables the fast identification and detection of ICH regions. However, the use of it requires the clinical interpretation by experts to identify the subtypes of ICH. Besides, it is unable to provide the details needed to conduct quantitative assessment, such as the volume and thickness of hemorrhagic lesions, which may have prognostic importance to the decision-making on emergency treatment. In this paper, an optimal deep learning framework is proposed to assist the quantitative assessment for ICH diagnosis and the accurate detection of different subtypes of ICH through head CT scan. Firstly, the format of raw input data is converted from 3D DICOM to NIfTI. Secondly, a pre-trained multi-class semantic segmentation model is applied to each slice of CT images, so as to obtain a precise 3D mask of the whole ICH region. Thirdly, a fine-tuned classification neural network is employed to extract the key features from the raw input data and identify the subtypes of ICH. Finally, a quantitative assessment algorithm is adopted to automatically measure both thickness and volume via the 3D shape mask combined with the output probabilities of the classification network. The results of our extensive experiments demonstrate the effectiveness of the proposed framework where the average accuracy of 96.21 percent is achieved for three types of hemorrhage. The capability of our optimal classification model to distinguish between different types of lesion plays a significant role in reducing the false-positive rate in the existing work. Furthermore, the results suggest that our automatic quantitative assessment algorithm is effective in providing clinically relevant quantification in terms of volume and thickness. It is more important than the qualitative assessment conducted through visual inspection to the decision-making on emergency surgical treatment.

Post-Trial Enhanced Deployment and Technical Performance with the MISTIE Procedure per Lessons Learned

OBJECTIVE

We hypothesize that procedure deployment rates and technical performance with minimally invasive surgery and thrombolysis for intracerebral hemorrhage (ICH) evacuation (MISTIE) can be enhanced in post-trial clinical practice, per Phase III trial results and lessons learned.

MATERIALS AND METHODS

We identified ICH patients and those who underwent MISTIE procedure between 2017-2021 at a single site, after completed enrollments in the Phase III trial. Deployment rates, complications and technical outcomes were compared to those observed in the trial. Initial and final hematoma volume were compared between site measurements using ABC/2, MISTIE trial reading center utilizing manual segmentation, and a novel Artificial Intelligence (AI) based volume assessment.

RESULTS

Nineteen of 286 patients were eligible for MISTIE. All 19 received the procedure (6.6% enrollment to screening rate 6.6% compared to 1.6% at our center in the trial; p=0.0018). Sixteen patients (84%) achieved evaculation target < 15 mL residual ICH or > 70% removal, compared to 59.7% in the trial surgical cohort (p=0.034). No poor catheter placement occurred and no surgical protocol deviations. Limitations of ICH volume assessments using the ABC/2 method were shown, while AI based methodology of ICH volume assessments had excellent correlation with manual segmentation by experienced reading centers.

CONCLUSIONS

Greater procedure deployment and higher technical success rates can be achieved in post-trial clinical practice than in the MISTIE III trial. AI based measurements can be deployed to enhance clinician estimated ICH volume. Clinical outcome implications of this enhanced technical performance cannot be surmised, and will need assessment in future trials.

Automated Detection and Screening of Traumatic Brain Injury (TBI) Using Computed Tomography Images: A Comprehensive Review and Future Perspectives

Traumatic brain injury (TBI) occurs due to the disruption in the normal functioning of the brain by sudden external forces. The primary and secondary injuries due to TBI include intracranial hematoma (ICH), raised intracranial pressure (ICP), and midline shift (MLS), which can result in significant lifetime disabilities and death. Hence, early diagnosis of TBI is crucial to improve patient outcome. Computed tomography (CT) is the preferred modality of choice to assess the severity of TBI. However, manual visualization and inspection of hematoma and its complications from CT scans is a highly operator-dependent and time-consuming task, which can lead to an inappropriate or delayed prognosis. The development of computer aided diagnosis (CAD) systems could be helpful for accurate, early management of TBI. In this paper, a systematic review of prevailing CAD systems for the detection of hematoma, raised ICP, and MLS in non-contrast axial CT brain images is presented. We also suggest future research to enhance the performance of CAD for early and accurate TBI diagnosis.

Hemorrhagic stroke lesion segmentation using a 3D U-Net with squeeze-and-excitation blocks

Hemorrhagic stroke is the condition involving the rupture of a vessel inside the brain and is characterized by high mortality rates. Even if the patient survives, stroke can cause temporary or permanent disability depending on how long blood flow has been interrupted. Therefore, it is crucial to act fast to prevent irreversible damage. In this work, a deep learning-based approach to automatically segment hemorrhagic stroke lesions in CT scans is proposed. Our approach is based on a 3D U-Net architecture which incorporates the recently proposed squeeze-and-excitation blocks. Moreover, a restrictive patch sampling is proposed to alleviate the class imbalance problem and also to deal with the issue of intra-ventricular hemorrhage, which has not been considered as a stroke lesion in our study. Moreover, we also analyzed the effect of patch size, the use of different modalities, data augmentation and the incorporation of different loss functions on the segmentation results. All analyses have been performed using a five fold cross-validation strategy on a clinical dataset composed of 76 cases. Obtained results demonstrate that the introduction of squeeze-and-excitation blocks, together with the restrictive patch sampling and symmetric modality augmentation, significantly improved the obtained results, achieving a mean DSC of 0.86±0.074, showing promising automated segmentation results.