Multiclass semantic segmentation and quantification of traumatic brain injury lesions on head CT using deep learning: an algorithm development and multicentre validation study

Hyperparameter selection for dataset-constrained semantic segmentation: Practical machine learning optimization

PURPOSE/AIM

This paper provides a pedagogical example for systematic machine learning optimization in small dataset image segmentation, emphasizing hyperparameter selections. A simple process is presented for medical physicists to examine hyperparameter optimization. This is also applied to a case-study, demonstrating the benefit of the method.

MATERIALS AND METHODS

An unrestricted public Computed Tomography (CT) dataset, with binary organ segmentation, was used to develop a multiclass segmentation model. To start the optimization process, a preliminary manual search of hyperparameters was conducted and from there a grid search identified the most influential result metrics. A total of 658 different models were trained in 2100 h, using 13 160 effective patients. The quantity of results was analyzed using random forest regression, identifying relative hyperparameter impact.

RESULTS

Metric implied segmentation quality (accuracy 96.8%, precision 95.1%) and visual inspection were found to be mismatched. In this work batch normalization was most important, but performance varied with hyperparameters and metrics selected. Targeted grid-search optimization and random forest analysis of relative hyperparameter importance, was an easily implementable sensitivity analysis approach.

CONCLUSION

The proposed optimization method gives a systematic and quantitative approach to something intuitively understood, that hyperparameters change model performance. Even just grid search optimization with random forest analysis presented here can be informative within hardware and data quality/availability limitations, adding confidence to model validity and minimize decision-making risks. By providing a guided methodology, this work helps medical physicists to improve their model optimization, irrespective of specific challenges posed by datasets and model design.

Combining Clinical-Radiomics Features With Machine Learning Methods for Building Models to Predict Postoperative Recurrence in Patients With Chronic Subdural Hematoma: Retrospective Cohort Study

BACKGROUND

Chronic subdural hematoma (CSDH) represents a prevalent medical condition, posing substantial challenges in postoperative management due to risks of recurrence. Such recurrences not only cause physical suffering to the patient but also add to the financial burden on the family and the health care system. Currently, prognosis determination largely depends on clinician expertise, revealing a dearth of precise prediction models in clinical settings.

OBJECTIVE

This study aims to use machine learning (ML) techniques for the construction of predictive models to assess the likelihood of CSDH recurrence after surgery, which leads to greater benefits for patients and the health care system.

METHODS

Data from 133 patients were amassed and partitioned into a training set (n=93) and a test set (n=40). Radiomics features were extracted from preoperative cranial computed tomography scans using 3D Slicer software. These features, in conjunction with clinical data and composite clinical-radiomics features, served as input variables for model development. Four distinct ML algorithms were used to build predictive models, and their performance was rigorously evaluated via accuracy, area under the curve (AUC), and recall metrics. The optimal model was identified, followed by recursive feature elimination for feature selection, leading to enhanced predictive efficacy. External validation was conducted using data sets from additional health care facilities.

RESULTS

Following rigorous experimental analysis, the support vector machine model, predicated on clinical-radiomics features, emerged as the most efficacious for predicting postoperative recurrence in patients with CSDH. Subsequent to feature selection, key variables exerting significant impact on the model were incorporated as the input set, thereby augmenting its predictive accuracy. The model demonstrated robust performance, with metrics including accuracy of 92.72%, AUC of 91.34%, and recall of 93.16%. External validation further substantiated its effectiveness, yielding an accuracy of 90.32%, AUC of 91.32%, and recall of 88.37%, affirming its clinical applicability.

CONCLUSIONS

This study substantiates the feasibility and clinical relevance of an ML-based predictive model, using clinical-radiomics features, for relatively accurate prognostication of postoperative recurrence in patients with CSDH. If the model is integrated into clinical practice, it will be of great significance in enhancing the quality and efficiency of clinical decision-making processes, which can improve the accuracy of diagnosis and treatment, reduce unnecessary tests and surgeries, and reduce the waste of medical resources.

Automated Measurement of Cerebral Hemorrhagic Contusions and Outcomes After Traumatic Brain Injury in the TRACK-TBI Study

Importance

Because withdrawal of life-sustaining therapy based on perceived poor prognosis is the most common cause of death after moderate or severe traumatic brain injury (TBI), the accuracy of clinical prognoses is directly associated with mortality. Although the location of brain injury is known to be important for determining recovery potential after TBI, the best available prognostic models, such as the International Mission for Prognosis and Analysis of Clinical Trials in TBI (IMPACT) score, do not currently incorporate brain injury location.

Objective

To test whether automated measurement of cerebral hemorrhagic contusion size and location is associated with improved prognostic performance of the IMPACT score.

Design, Setting, and Participants

This prognostic cohort study was performed in 18 US level 1 trauma centers between February 26, 2014, and August 8, 2018. Adult participants aged 17 years or older from the US-based Transforming Research and Clinical Knowledge in TBI (TRACK-TBI) study with moderate or severe TBI (Glasgow Coma Scale score 3-12) and contusions detected on brain computed tomography (CT) scans were included. The data analysis was performed between January 2023 and February 2024.

Exposures

Labeled contusions detected on CT scans using Brain Lesion Analysis and Segmentation Tool for Computed Tomography (BLAST-CT), a validated artificial intelligence algorithm.

Main Outcome and Measure

The primary outcome was a Glasgow Outcome Scale-Extended (GOSE) score of 4 or less at 6 months after injury. Whether frontal or temporal lobe contusion volumes improved the performance of the IMPACT score was tested using logistic regression and area under the receiver operating characteristic curve comparisons. Sparse canonical correlation analysis was used to generate a disability heat map to visualize the strongest brainwide associations with outcomes.

Results

The cohort included 291 patients with moderate or severe TBI and contusions (mean [SD] age, 42 [18] years; 221 [76%] male; median [IQR] emergency department arrival Glasgow Coma Scale score, 5 [3-10]). Only temporal contusion volumes improved the discrimination of the IMPACT score (area under the receiver operating characteristic curve, 0.86 vs 0.84; P = .03). The data-derived disability heat map of contusion locations showed that the strongest association with unfavorable outcomes was within the bilateral temporal and medial frontal lobes.

Conclusions and Relevance

These findings suggest that CT-based automated contusion measurement may be an immediately translatable strategy for improving TBI prognostic models.

Radiomics and Deep Features: Robust Classification of Brain Hemorrhages and Reproducibility Analysis Using a 3D Autoencoder Neural Network

This study evaluates the reproducibility of machine learning models that integrate radiomics and deep features (features extracted from a 3D autoencoder neural network) to classify various brain hemorrhages effectively. Using a dataset of 720 patients, we extracted 215 radiomics features (RFs) and 15,680 deep features (DFs) from CT brain images. With rigorous screening based on Intraclass Correlation Coefficient thresholds (>0.75), we identified 135 RFs and 1054 DFs for analysis. Feature selection techniques such as Boruta, Recursive Feature Elimination (RFE), XGBoost, and ExtraTreesClassifier were utilized alongside 11 classifiers, including AdaBoost, CatBoost, Decision Trees, LightGBM, Logistic Regression, Naive Bayes, Neural Networks, Random Forest, Support Vector Machines (SVM), and k-Nearest Neighbors (k-NN). Evaluation metrics included Area Under the Curve (AUC), Accuracy (ACC), Sensitivity (SEN), and F1-score. The model evaluation involved hyperparameter optimization, a 70:30 train-test split, and bootstrapping, further validated with the Wilcoxon signed-rank test and q-values. Notably, DFs showed higher accuracy. In the case of RFs, the Boruta + SVM combination emerged as the optimal model for AUC, ACC, and SEN, while XGBoost + Random Forest excelled in F1-score. Specifically, RFs achieved AUC, ACC, SEN, and F1-scores of 0.89, 0.85, 0.82, and 0.80, respectively. Among DFs, the ExtraTreesClassifier + Naive Bayes combination demonstrated remarkable performance, attaining an AUC of 0.96, ACC of 0.93, SEN of 0.92, and an F1-score of 0.92. Distinguished models in the RF category included SVM with Boruta, Logistic Regression with XGBoost, SVM with ExtraTreesClassifier, CatBoost with XGBoost, and Random Forest with XGBoost, each yielding significant q-values of 42. In the DFs realm, ExtraTreesClassifier + Naive Bayes, ExtraTreesClassifier + Random Forest, and Boruta + k-NN exhibited robustness, with 43, 43, and 41 significant q-values, respectively. This investigation underscores the potential of synergizing DFs with machine learning models to serve as valuable screening tools, thereby enhancing the interpretation of head CT scans for patients with brain hemorrhages.

Unsupervised model for structure segmentation applied to brain computed tomography

This article presents an unsupervised method for segmenting brain computed tomography scans. The proposed methodology involves image feature extraction and application of similarity and continuity constraints to generate segmentation maps of the anatomical head structures. Specifically designed for real-world datasets, this approach applies a spatial continuity scoring function tailored to the desired number of structures. The primary objective is to assist medical experts in diagnosis by identifying regions with specific abnormalities. Results indicate a simplified and accessible solution, reducing computational effort, training time, and financial costs. Moreover, the method presents potential for expediting the interpretation of abnormal scans, thereby impacting clinical practice. This proposed approach might serve as a practical tool for segmenting brain computed tomography scans, and make a significant contribution to the analysis of medical images in both research and clinical settings.

The new era of artificial intelligence in neuroradiology: current research and promising tools

Radiology has a number of characteristics that make it an especially suitable medical discipline for early artificial intelligence (AI) adoption. These include having a well-established digital workflow, standardized protocols for image storage, and numerous well-defined interpretive activities. The more than 200 commercial radiologic AI-based products recently approved by the Food and Drug Administration (FDA) to assist radiologists in a number of narrow image-analysis tasks such as image enhancement, workflow triage, and quantification, corroborate this observation. However, in order to leverage AI to boost efficacy and efficiency, and to overcome substantial obstacles to widespread successful clinical use of these products, radiologists should become familiarized with the emerging applications in their particular areas of expertise. In light of this, in this article we survey the existing literature on the application of AI-based techniques in neuroradiology, focusing on conditions such as vascular diseases, epilepsy, and demyelinating and neurodegenerative conditions. We also introduce some of the algorithms behind the applications, briefly discuss a few of the challenges of generalization in the use of AI models in neuroradiology, and skate over the most relevant commercially available solutions adopted in clinical practice. If well designed, AI algorithms have the potential to radically improve radiology, strengthening image analysis, enhancing the value of quantitative imaging techniques, and mitigating diagnostic errors.

Deep Learning for Automated Detection and Localization of Traumatic Abdominal Solid Organ Injuries on CT Scans

Computed tomography (CT) is the most commonly used diagnostic modality for blunt abdominal trauma (BAT), significantly influencing management approaches. Deep learning models (DLMs) have shown great promise in enhancing various aspects of clinical practice. There is limited literature available on the use of DLMs specifically for trauma image evaluation. In this study, we developed a DLM aimed at detecting solid organ injuries to assist medical professionals in rapidly identifying life-threatening injuries. The study enrolled patients from a single trauma center who received abdominal CT scans between 2008 and 2017. Patients with spleen, liver, or kidney injury were categorized as the solid organ injury group, while others were considered negative cases. Only images acquired from the trauma center were enrolled. A subset of images acquired in the last year was designated as the test set, and the remaining images were utilized to train and validate the detection models. The performance of each model was assessed using metrics such as the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value, and negative predictive value based on the best Youden index operating point. The study developed the models using 1302 (87%) scans for training and tested them on 194 (13%) scans. The spleen injury model demonstrated an accuracy of 0.938 and a specificity of 0.952. The accuracy and specificity of the liver injury model were reported as 0.820 and 0.847, respectively. The kidney injury model showed an accuracy of 0.959 and a specificity of 0.989. We developed a DLM that can automate the detection of solid organ injuries by abdominal CT scans with acceptable diagnostic accuracy. It cannot replace the role of clinicians, but we can expect it to be a potential tool to accelerate the process of therapeutic decisions for trauma care.

Imaging Findings in Acute Traumatic Brain Injury: a National Institute of Neurological Disorders and Stroke Common Data Element-Based Pictorial Review and Analysis of Over 4000 Admission Brain Computed Tomography Scans from the Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) Study

In 2010, the National Institute of Neurological Disorders and Stroke (NINDS) created a set of common data elements (CDEs) to help standardize the assessment and reporting of imaging findings in traumatic brain injury (TBI). However, as opposed to other standardized radiology reporting systems, a visual overview and data to support the proposed standardized lexicon are lacking. We used over 4000 admission computed tomography (CT) scans of patients with TBI from the Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) study to develop an extensive pictorial overview of the NINDS TBI CDEs, with visual examples and background information on individual pathoanatomical lesion types, up to the level of supplemental and emerging information (e.g., location and estimated volumes). We documented the frequency of lesion occurrence, aiming to quantify the relative importance of different CDEs for characterizing TBI, and performed a critical appraisal of our experience with the intent to inform updating of the CDEs. In addition, we investigated the co-occurrence and clustering of lesion types and the distribution of six CT classification systems. The median age of the 4087 patients in our dataset was 50 years (interquartile range, 29-66; range, 0-96), including 238 patients under 18 years old (5.8%). Traumatic subarachnoid hemorrhage (45.3%), skull fractures (37.4%), contusions (31.3%), and acute subdural hematoma (28.9%) were the most frequently occurring CT findings in acute TBI. The ranking of these lesions was the same in patients with mild TBI (baseline Glasgow Coma Scale [GCS] score 13-15) compared with those with moderate-severe TBI (baseline GCS score 3-12), but the frequency of occurrence was up to three times higher in moderate-severe TBI. In most TBI patients with CT abnormalities, there was co-occurrence and clustering of different lesion types, with significant differences between mild and moderate-severe TBI patients. More specifically, lesion patterns were more complex in moderate-severe TBI patients, with more co-existing lesions and more frequent signs of mass effect. These patients also had higher and more heterogeneous CT score distributions, associated with worse predicted outcomes. The critical appraisal of the NINDS CDEs was highly positive, but revealed that full assessment can be time consuming, that some CDEs had very low frequencies, and identified a few redundancies and ambiguity in some definitions. Whilst primarily developed for research, implementation of CDE templates for use in clinical practice is advocated, but this will require development of an abbreviated version. In conclusion, with this study, we provide an educational resource for clinicians and researchers to help assess, characterize, and report the vast and complex spectrum of imaging findings in patients with TBI. Our data provides a comprehensive overview of the contemporary landscape of TBI imaging pathology in Europe, and the findings can serve as empirical evidence for updating the current NINDS radiologic CDEs to version 3.0.

The Australian Traumatic Brain Injury Initiative: Single Data Dictionary to Predict Outcome for People With Moderate-Severe Traumatic Brain Injury

In this series of eight articles, the Australian Traumatic Brain Injury Initiative (AUS-TBI) consortium describes the Australian approach used to select the common data elements collected acutely that have been shown to predict outcome following moderate-severe traumatic brain injury (TBI) across the lifespan. This article presents the unified single data dictionary, together with additional measures chosen to facilitate comparative effectiveness research and data linkage. Consultations with the AUS-TBI Lived Experience Expert Group provided insights on the merits and considerations regarding data elements for some of the study areas, as well as more general principles to guide the collection of data and the selection of meaningful measures. These are presented as a series of guiding principles and themes. The AUS-TBI Aboriginal and Torres Strait Islander Advisory Group identified a number of key points and considerations for the project approach specific to Aboriginal and Torres Strait Islander peoples, including key issues of data sovereignty and community involvement. These are outlined in the form of principles to guide selection of appropriate methodologies, data management, and governance. Implementation of the AUS-TBI approach aims to maximize ongoing data collection and linkage, to facilitate personalization of care and improved outcomes for people who experience moderate-severe TBI.

Predicting hematoma expansion in acute spontaneous intracerebral hemorrhage: integrating clinical factors with a multitask deep learning model for non-contrast head CT

PURPOSE

To predict hematoma growth in intracerebral hemorrhage patients by combining clinical findings with non-contrast CT imaging features analyzed through deep learning.

METHODS

Three models were developed to predict hematoma expansion (HE) in 572 patients. We utilized multi-task learning for both hematoma segmentation and prediction of expansion: the Image-to-HE model processed hematoma slices, extracting features and computing a normalized DL score for HE prediction. The Clinical-to-HE model utilized multivariate logistic regression on clinical variables. The Integrated-to-HE model combined image-derived and clinical data. Significant clinical variables were selected using forward selection in logistic regression. The two models incorporating clinical variables were statistically validated.

RESULTS

For hematoma detection, the diagnostic performance of the developed multi-task model was excellent (AUC, 0.99). For expansion prediction, three models were evaluated for predicting HE. The Image-to-HE model achieved an accuracy of 67.3%, sensitivity of 81.0%, specificity of 64.0%, and an AUC of 0.76. The Clinical-to-HE model registered an accuracy of 74.8%, sensitivity of 81.0%, specificity of 73.3%, and an AUC of 0.81. The Integrated-to-HE model, merging both image and clinical data, excelled with an accuracy of 81.3%, sensitivity of 76.2%, specificity of 82.6%, and an AUC of 0.83. The Integrated-to-HE model, aligning closest to the diagonal line and indicating the highest level of calibration, showcases superior performance in predicting HE outcomes among the three models.

CONCLUSION

The integration of clinical findings with non-contrast CT imaging features analyzed through deep learning showed the potential for improving the prediction of HE in acute spontaneous intracerebral hemorrhage patients.

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.

Automated volumetric evaluation of intracranial compartments and cerebrospinal fluid distribution on emergency trauma head CT scans to quantify mass effect

Background

Intracranial space is divided into three compartments by the falx cerebri and tentorium cerebelli. We assessed whether cerebrospinal fluid (CSF) distribution evaluated by a specifically developed deep-learning neural network (DLNN) could assist in quantifying mass effect.

Methods

Head trauma CT scans from a high-volume emergency department between 2018 and 2020 were retrospectively analyzed. Manual segmentations of intracranial compartments and CSF served as the ground truth to develop a DLNN model to automate the segmentation process. Dice Similarity Coefficient (DSC) was used to evaluate the segmentation performance. Supratentorial CSF Ratio was calculated by dividing the volume of CSF on the side with reduced CSF reserve by the volume of CSF on the opposite side.

Results

Two hundred and seventy-four patients (mean age, 61 years ± 18.6) after traumatic brain injury (TBI) who had an emergency head CT scan were included. The average DSC for training and validation datasets were respectively: 0.782 and 0.765. Lower DSC were observed in the segmentation of CSF, respectively 0.589, 0.615, and 0.572 for the right supratentorial, left supratentorial, and infratentorial CSF regions in the training dataset, and slightly lower values in the validation dataset, respectively 0.567, 0.574, and 0.556. Twenty-two patients (8%) had midline shift exceeding 5 mm, and 24 (8.8%) presented with high/mixed density lesion exceeding >25 ml. Fifty-five patients (20.1%) exhibited mass effect requiring neurosurgical treatment. They had lower supratentorial CSF volume and lower Supratentorial CSF Ratio (both p < 0.001). A Supratentorial CSF Ratio below 60% had a sensitivity of 74.5% and specificity of 87.7% (AUC 0.88, 95%CI 0.82-0.94) in identifying patients that require neurosurgical treatment for mass effect. On the other hand, patients with CSF constituting 10-20% of the intracranial space, with 80-90% of CSF specifically in the supratentorial compartment, and whose Supratentorial CSF Ratio exceeded 80% had minimal risk.

Conclusion

CSF distribution may be presented as quantifiable ratios that help to predict surgery in patients after TBI. Automated segmentation of intracranial compartments using the DLNN model demonstrates a potential of artificial intelligence in quantifying mass effect. Further validation of the described method is necessary to confirm its efficacy in triaging patients and identifying those who require neurosurgical treatment.

Prediction of therapeutic intensity level from automatic multiclass segmentation of traumatic brain injury lesions on CT-scans

The prediction of the therapeutic intensity level (TIL) for severe traumatic brain injury (TBI) patients at the early phase of intensive care unit (ICU) remains challenging. Computed tomography images are still manually quantified and then underexploited. In this study, we develop an artificial intelligence-based tool to segment brain lesions on admission CT-scan and predict TIL within the first week in the ICU. A cohort of 29 head injured patients (87 CT-scans; Dataset1) was used to localize (using a structural atlas), segment (manually or automatically with or without transfer learning) 4 or 7 types of lesions and use these metrics to train classifiers, evaluated with AUC on a nested cross-validation, to predict requirements for TIL sum of 11 points or more during the 8 first days in ICU. The validation of the performances of both segmentation and classification tasks was done with Dice and accuracy scores on a sub-dataset of Dataset1 (internal validation) and an external dataset of 12 TBI patients (12 CT-scans; Dataset2). Automatic 4-class segmentation (without transfer learning) was not able to correctly predict the apparition of a day of extreme TIL (AUC = 60 ± 23%). In contrast, manual quantification of volumes of 7 lesions and their spatial location provided a significantly better prediction power (AUC = 89 ± 17%). Transfer learning significantly improved the automatic 4-class segmentation (DICE scores 0.63 vs 0.34) and trained more efficiently a 7-class convolutional neural network (DICE = 0.64). Both validations showed that segmentations based on transfer learning were able to predict extreme TIL with better or equivalent accuracy (83%) as those made with manual segmentations. Our automatic characterization (volume, type and spatial location) of initial brain lesions observed on CT-scan, publicly available on a dedicated computing platform, could predict requirements for high TIL during the first 8 days after severe TBI. Transfer learning strategies may improve the accuracy of CNN-based segmentation models.Trial registrations Radiomic-TBI cohort; NCT04058379, first posted: 15 august 2019; Radioxy-TC cohort; Health Data Hub index F20220207212747, first posted: 7 February 2022.

Validation of a deep learning model for traumatic brain injury detection and NIRIS grading on non-contrast CT: a multi-reader study with promising results and opportunities for improvement

PURPOSE

This study aimed to assess and externally validate the performance of a deep learning (DL) model for the interpretation of non-contrast computed tomography (NCCT) scans of patients with suspicion of traumatic brain injury (TBI).

METHODS

This retrospective and multi-reader study included patients with TBI suspicion who were transported to the emergency department and underwent NCCT scans. Eight reviewers, with varying levels of training and experience (two neuroradiology attendings, two neuroradiology fellows, two neuroradiology residents, one neurosurgery attending, and one neurosurgery resident), independently evaluated NCCT head scans. The same scans were evaluated using the version 5.0 of the DL model icobrain tbi. The establishment of the ground truth involved a thorough assessment of all accessible clinical and laboratory data, as well as follow-up imaging studies, including NCCT and magnetic resonance imaging, as a consensus amongst the study reviewers. The outcomes of interest included neuroimaging radiological interpretation system (NIRIS) scores, the presence of midline shift, mass effect, hemorrhagic lesions, hydrocephalus, and severe hydrocephalus, as well as measurements of midline shift and volumes of hemorrhagic lesions. Comparisons using weighted Cohen's kappa coefficient were made. The McNemar test was used to compare the diagnostic performance. Bland-Altman plots were used to compare measurements.

RESULTS

One hundred patients were included, with the DL model successfully categorizing 77 scans. The median age for the total group was 48, with the omitted group having a median age of 44.5 and the included group having a median age of 48. The DL model demonstrated moderate agreement with the ground truth, trainees, and attendings. With the DL model's assistance, trainees' agreement with the ground truth improved. The DL model showed high specificity (0.88) and positive predictive value (0.96) in classifying NIRIS scores as 0-2 or 3-4. Trainees and attendings had the highest accuracy (0.95). The DL model's performance in classifying various TBI CT imaging common data elements was comparable to that of trainees and attendings. The average difference for the DL model in quantifying the volume of hemorrhagic lesions was 6.0 mL with a wide 95% confidence interval (CI) of - 68.32 to 80.22, and for midline shift, the average difference was 1.4 mm with a 95% CI of - 3.4 to 6.2.

CONCLUSION

While the DL model outperformed trainees in some aspects, attendings' assessments remained superior in most instances. Using the DL model as an assistive tool benefited trainees, improving their NIRIS score agreement with the ground truth. Although the DL model showed high potential in classifying some TBI CT imaging common data elements, further refinement and optimization are necessary to enhance its clinical utility.

Comparative analysis between different volumetric methods on measuring intracranial hemorrhage incorporating roundness index

Intracranial hematoma (ICH) volume is considered a predictor of clinical outcome and mortality rate in ICH patients with traumatic brain injury (TBI). The ABC/2 method for ICH volume is the standard method used to date, however, its level of accuracy has been questioned in some studies. This study compared the performance of the ABC/2 method with planimetry and truncated pyramidal methods to highlight the potential of the planimetry method applied with automatic segmentation for evaluation of epidural hematoma (EDH) and intraparenchymal hematoma (IPH) volume. Six different phantoms were designed to evaluate the accuracy of volume estimation methods. 221 hematoma regions extracted from CT scans of 125 patients with head injury were also used to analyze the efficiency. The roundness index was utilized for the quantification of the ellipsoid-like shape. Regions of EDH and IPH on the CT scans were annotated by radiologists. The estimation errors for each method were statistically analyzed and compared. In addition, the relationship between the errors and roundness index was examined. The planimetry method showed the lowest relative error on phantom data. In the case of the CT scan data, the truncated pyramidal method resulted in the underestimation of the volumes of EDH and IPH. Meanwhile, the ABC/2, through principal component analysis (PCA) in the two-dimensional and PCA in the three-dimensional methods, resulted in a significant overestimation. In addition, both these approaches produced relative errors that showed a correlation with the roundness indexes for IPH. In comparison to other methods, the planimetry method had the lowest level of error with regards to calculation of the volume and it was also independent of the hematoma shape. The planimetry method, therefore, has the potential to serve as a useful tool for the assessment of ICH volume in TBI patients by using a deep learning system.

The Application of Design Thinking in Developing a Deep Learning Algorithm for Hip Fracture Detection

(1) Background: Design thinking is a problem-solving approach that has been applied in various sectors, including healthcare and medical education. While deep learning (DL) algorithms can assist in clinical practice, integrating them into clinical scenarios can be challenging. This study aimed to use design thinking steps to develop a DL algorithm that accelerates deployment in clinical practice and improves its performance to meet clinical requirements. (2) Methods: We applied the design thinking process to interview clinical doctors and gain insights to develop and modify the DL algorithm to meet clinical scenarios. We also compared the DL performance of the algorithm before and after the integration of design thinking. (3) Results: After empathizing with clinical doctors and defining their needs, we identified the unmet need of five trauma surgeons as "how to reduce the misdiagnosis of femoral fracture by pelvic plain film (PXR) at initial emergency visiting". We collected 4235 PXRs from our hospital, of which 2146 had a hip fracture (51%) from 2008 to 2016. We developed hip fracture DL detection models based on the Xception convolutional neural network by using these images. By incorporating design thinking, we improved the diagnostic accuracy from 0.91 (0.84-0.96) to 0.95 (0.93-0.97), the sensitivity from 0.97 (0.89-1.00) to 0.97 (0.94-0.99), and the specificity from 0.84 (0.71-0.93) to 0.93(0.990-0.97). (4) Conclusions: In summary, this study demonstrates that design thinking can ensure that DL solutions developed for trauma care are user-centered and meet the needs of patients and healthcare providers.

Automatic localisation and per-region quantification of traumatic brain injury on head CT using atlas mapping

Rationale and objectives

To develop a method for automatic localisation of brain lesions on head CT, suitable for both population-level analysis and lesion management in a clinical setting.

Materials and methods

Lesions were located by mapping a bespoke CT brain atlas to the patient's head CT in which lesions had been previously segmented. The atlas mapping was achieved through robust intensity-based registration enabling the calculation of per-region lesion volumes. Quality control (QC) metrics were derived for automatic detection of failure cases. The CT brain template was built using 182 non-lesioned CT scans and an iterative template construction strategy. Individual brain regions in the CT template were defined via non-linear registration of an existing MRI-based brain atlas.Evaluation was performed on a multi-centre traumatic brain injury dataset (TBI) (n = 839 scans), including visual inspection by a trained expert. Two population-level analyses are presented as proof-of-concept: a spatial assessment of lesion prevalence, and an exploration of the distribution of lesion volume per brain region, stratified by clinical outcome.

Results

95.7% of the lesion localisation results were rated by a trained expert as suitable for approximate anatomical correspondence between lesions and brain regions, and 72.5% for more quantitatively accurate estimates of regional lesion load. The classification performance of the automatic QC showed an AUC of 0.84 when compared to binarised visual inspection scores. The localisation method has been integrated into the publicly available Brain Lesion Analysis and Segmentation Tool for CT (BLAST-CT).

Conclusion

Automatic lesion localisation with reliable QC metrics is feasible and can be used for patient-level quantitative analysis of TBI, as well as for large-scale population analysis due to its computational efficiency (<2 min/scan on GPU).

Investigating the characteristics and correlates of systemic inflammation after traumatic brain injury: the TBI-BraINFLAMM study

INTRODUCTION

A significant environmental risk factor for neurodegenerative disease is traumatic brain injury (TBI). However, it is not clear how TBI results in ongoing chronic neurodegeneration. Animal studies show that systemic inflammation is signalled to the brain. This can result in sustained and aggressive microglial activation, which in turn is associated with widespread neurodegeneration. We aim to evaluate systemic inflammation as a mediator of ongoing neurodegeneration after TBI.

METHODS AND ANALYSIS

TBI-braINFLAMM will combine data already collected from two large prospective TBI studies. The CREACTIVE study, a broad consortium which enrolled >8000 patients with TBI to have CT scans and blood samples in the hyperacute period, has data available from 854 patients. The BIO-AX-TBI study recruited 311 patients to have acute CT scans, longitudinal blood samples and longitudinal MRI brain scans. The BIO-AX-TBI study also has data from 102 healthy and 24 non-TBI trauma controls, comprising blood samples (both control groups) and MRI scans (healthy controls only). All blood samples from BIO-AX-TBI and CREACTIVE have already been tested for neuronal injury markers (GFAP, tau and NfL), and CREACTIVE blood samples have been tested for inflammatory cytokines. We will additionally test inflammatory cytokine levels from the already collected longitudinal blood samples in the BIO-AX-TBI study, as well as matched microdialysate and blood samples taken during the acute period from a subgroup of patients with TBI (n=18).We will use this unique dataset to characterise post-TBI systemic inflammation, and its relationships with injury severity and ongoing neurodegeneration.

ETHICS AND DISSEMINATION

Ethical approval for this study has been granted by the London-Camberwell St Giles Research Ethics Committee (17/LO/2066). Results will be submitted for publication in peer-review journals, presented at conferences and inform the design of larger observational and experimental medicine studies assessing the role and management of post-TBI systemic inflammation.

AI-Based Decision Support System for Traumatic Brain Injury: A Survey

Traumatic brain injury (TBI) is one of the major causes of disability and mortality worldwide. Rapid and precise clinical assessment and decision-making are essential to improve the outcome and the resulting complications. Due to the size and complexity of the data analyzed in TBI cases, computer-aided data processing, analysis, and decision support systems could play an important role. However, developing such systems is challenging due to the heterogeneity of symptoms, varying data quality caused by different spatio-temporal resolutions, and the inherent noise associated with image and signal acquisition. The purpose of this article is to review current advances in developing artificial intelligence-based decision support systems for the diagnosis, severity assessment, and long-term prognosis of TBI complications.

Manual lesion segmentations for traumatic brain injury characterization

Traumatic brain injury (TBI) often results in heterogenous lesions that can be visualized through various neuroimaging techniques, such as magnetic resonance imaging (MRI). However, injury burden varies greatly between patients and structural deformations often impact usability of available analytic algorithms. Therefore, it is difficult to segment lesions automatically and accurately in TBI cohorts. Mislabeled lesions will ultimately lead to inaccurate findings regarding imaging biomarkers. Therefore, manual segmentation is currently considered the gold standard as this produces more accurate masks than existing automated algorithms. These masks can provide important lesion phenotype data including location, volume, and intensity, among others. There has been a recent push to investigate the correlation between these characteristics and the onset of post traumatic epilepsy (PTE), a disabling consequence of TBI. One motivation of the Epilepsy Bioinformatics Study for Antiepileptogenic Therapy (EpiBioS4Rx) is to identify reliable imaging biomarkers of PTE. Here, we report the protocol and importance of our manual segmentation process in patients with moderate-severe TBI enrolled in EpiBioS4Rx. Through these methods, we have generated a dataset of 127 validated lesion segmentation masks for TBI patients. These ground-truths can be used for robust PTE biomarker analyses, including optimization of multimodal MRI analysis via inclusion of lesioned tissue labels. Moreover, our protocol allows for analysis of the refinement process. Though tedious, the methods reported in this work are necessary to create reliable data for effective training of future machine-learning based lesion segmentation methods in TBI patients and subsequent PTE analyses.

Fully Automated MRI Segmentation and Volumetric Measurement of Intracranial Meningioma Using Deep Learning

BACKGROUND

Accurate and rapid measurement of the MRI volume of meningiomas is essential in clinical practice to determine the growth rate of the tumor. Imperfect automation and disappointing performance for small meningiomas of previous automated volumetric tools limit their use in routine clinical practice.

PURPOSE

To develop and validate a computational model for fully automated meningioma segmentation and volume measurement on contrast-enhanced MRI scans using deep learning.

STUDY TYPE

Retrospective.

POPULATION

A total of 659 intracranial meningioma patients (median age, 59.0 years; interquartile range: 53.0-66.0 years) including 554 women and 105 men.

FIELD STRENGTH/SEQUENCE

The 1.0 T, 1.5 T, and 3.0 T; three-dimensional, T₁ -weighted gradient-echo imaging with contrast enhancement.

ASSESSMENT

The tumors were manually segmented by two neurosurgeons, H.K. and C.-K.P., with 10 and 26 years of clinical experience, respectively, for use as the ground truth. Deep learning models based on U-Net and nnU-Net were trained using 459 subjects and tested for 100 patients from a single institution (internal validation set [IVS]) and 100 patients from other 24 institutions (external validation set [EVS]), respectively. The performance of each model was evaluated with the Sørensen-Dice similarity coefficient (DSC) compared with the ground truth.

STATISTICAL TESTS

According to the normality of the data distribution verified by the Shapiro-Wilk test, variables with three or more categories were compared by the Kruskal-Wallis test with Dunn's post hoc analysis.

RESULTS

A two-dimensional (2D) nnU-Net showed the highest median DSCs of 0.922 and 0.893 for the IVS and EVS, respectively. The nnU-Nets achieved superior performance in meningioma segmentation than the U-Nets. The DSCs of the 2D nnU-Net for small meningiomas less than 1 cm³ were 0.769 and 0.780 with the IVS and EVS, respectively.

DATA CONCLUSION

A fully automated and accurate volumetric measurement tool for meningioma with clinically applicable performance for small meningioma using nnU-Net was developed.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 2.

An end-end deep learning framework for lesion segmentation on multi-contrast MR images-an exploratory study in a rat model of traumatic brain injury

Traumatic brain injury (TBI) engenders traumatic necrosis and penumbra-areas of secondary neural injury which are crucial targets for therapeutic interventions. Segmenting manually areas of ongoing changes like necrosis, edema, hematoma, and inflammation is tedious, error-prone, and biased. Using the multi-parametric MR data from a rodent model study, we demonstrate the effectiveness of an end-end deep learning global-attention-based UNet (GA-UNet) framework for automatic segmentation and quantification of TBI lesions. Longitudinal MR scans (2 h, 1, 3, 7, 14, 30, and 60 days) were performed on eight Sprague-Dawley rats after controlled cortical injury was performed. TBI lesion and sub-regions segmentation was performed using 3D-UNet and GA-UNet. Dice statistics (DSI) and Hausdorff distance were calculated to assess the performance. MR scan variations-based (bias, noise, blur, ghosting) data augmentation was performed to develop a robust model.Training/validation median DSI for U-Net was 0.9368 with T2w and MPRAGE inputs, whereas GA-UNet had 0.9537 for the same. Testing accuracies were higher for GA-UNet than U-Net with a DSI of 0.8232 for the T2w-MPRAGE inputs.Longitudinally, necrosis remained constant while oligemia and penumbra decreased, and edema appearing around day 3 which increased with time. GA-UNet shows promise for multi-contrast MR image-based segmentation/quantification of TBI in large cohort studies.

Proceedings of the First Pediatric Coma and Disorders of Consciousness Symposium by the Curing Coma Campaign, Pediatric Neurocritical Care Research Group, and NINDS: Gearing for Success in Coma Advancements for Children and Neonates

This proceedings article presents the scope of pediatric coma and disorders of consciousness based on presentations and discussions at the First Pediatric Disorders of Consciousness Care and Research symposium held on September 14th, 2021. Herein we review the current state of pediatric coma care and research opportunities as well as shared experiences from seasoned researchers and clinicians. Salient current challenges and opportunities in pediatric and neonatal coma care and research were identified through the contributions of the presenters, who were Jose I. Suarez, MD, Nina F. Schor, MD, PhD, Beth S. Slomine, PhD Erika Molteni, PhD, and Jan-Marino Ramirez, PhD, and moderated by Varina L. Boerwinkle, MD, with overview by Mark Wainwright, MD, and subsequent audience discussion. The program, executively planned by Varina L. Boerwinkle, MD, Mark Wainwright, MD, and Michelle Elena Schober, MD, drove the identification and development of priorities for the pediatric neurocritical care community.

Statistical and machine learning approaches to predict the necessity for computed tomography in children with mild traumatic brain injury

BACKGROUND

Minor head trauma in children is a common reason for emergency department visits, but the risk of traumatic brain injury (TBI) in those children is very low. Therefore, physicians should consider the indication for computed tomography (CT) to avoid unnecessary radiation exposure to children. The purpose of this study was to statistically assess the differences between control and mild TBI (mTBI). In addition, we also investigate the feasibility of machine learning (ML) to predict the necessity of CT scans in children with mTBI.

METHODS AND FINDINGS

The study enrolled 1100 children under the age of 2 years to assess pre-verbal children. Other inclusion and exclusion criteria were per the PECARN study. Data such as demographics, injury details, medical history, and neurological assessment were used for statistical evaluation and creation of the ML algorithm. The number of children with clinically important TBI (ciTBI), mTBI on CT, and controls was 28, 30, and 1042, respectively. Statistical significance between the control group and clinically significant TBI requiring hospitalization (csTBI: ciTBI+mTBI on CT) was demonstrated for all nonparametric predictors except severity of the injury mechanism. The comparison between the three groups also showed significance for all predictors (p<0.05). This study showed that supervised ML for predicting the need for CT scan can be generated with 95% accuracy. It also revealed the significance of each predictor in the decision tree, especially the "days of life."

CONCLUSIONS

These results confirm the role and importance of each of the predictors mentioned in the PECARN study and show that ML could discriminate between children with csTBI and the control group.

Artificial intelligence in critical illness and its impact on patient care: a comprehensive review

Artificial intelligence (AI) has great potential to improve the field of critical care and enhance patient outcomes. This paper provides an overview of current and future applications of AI in critical illness and its impact on patient care, including its use in perceiving disease, predicting changes in pathological processes, and assisting in clinical decision-making. To achieve this, it is important to ensure that the reasoning behind AI-generated recommendations is comprehensible and transparent and that AI systems are designed to be reliable and robust in the care of critically ill patients. These challenges must be addressed through research and the development of quality control measures to ensure that AI is used in a safe and effective manner. In conclusion, this paper highlights the numerous opportunities and potential applications of AI in critical care and provides guidance for future research and development in this field. By enabling the perception of disease, predicting changes in pathological processes, and assisting in the resolution of clinical decisions, AI has the potential to revolutionize patient care for critically ill patients and improve the efficiency of health systems.

A Machine Learning-Based Approach to Predict Prognosis and Length of Hospital Stay in Adults and Children With Traumatic Brain Injury: Retrospective Cohort Study

BACKGROUND

The treatment and care of adults and children with traumatic brain injury (TBI) constitute an intractable global health problem. Predicting the prognosis and length of hospital stay of patients with TBI may improve therapeutic effects and significantly reduce societal health care burden. Applying novel machine learning methods to the field of TBI may be valuable for determining the prognosis and cost-effectiveness of clinical treatment.

OBJECTIVE

We aimed to combine multiple machine learning approaches to build hybrid models for predicting the prognosis and length of hospital stay for adults and children with TBI.

METHODS

We collected relevant clinical information from patients treated at the Neurosurgery Center of the Second Affiliated Hospital of Anhui Medical University between May 2017 and May 2022, of which 80% was used for training the model and 20% for testing via screening and data splitting. We trained and tested the machine learning models using 5 cross-validations to avoid overfitting. In the machine learning models, 11 types of independent variables were used as input variables and Glasgow Outcome Scale score, used to evaluate patients' prognosis, and patient length of stay were used as output variables. Once the models were trained, we obtained and compared the errors of each machine learning model from 5 rounds of cross-validation to select the best predictive model. The model was then externally tested using clinical data of patients treated at the First Affiliated Hospital of Anhui Medical University from June 2021 to February 2022.

RESULTS

The final convolutional neural network-support vector machine (CNN-SVM) model predicted Glasgow Outcome Scale score with an accuracy of 93% and 93.69% in the test and external validation sets, respectively, and an area under the curve of 94.68% and 94.32% in the test and external validation sets, respectively. The mean absolute percentage error of the final built convolutional neural network-support vector regression (CNN-SVR) model predicting inpatient time in the test set and external validation set was 10.72% and 10.44%, respectively. The coefficient of determination (R²) was 0.93 and 0.92 in the test set and external validation set, respectively. Compared with back-propagation neural network, CNN, and SVM models built separately, our hybrid model was identified to be optimal and had high confidence.

CONCLUSIONS

This study demonstrates the clinical utility of 2 hybrid models built by combining multiple machine learning approaches to accurately predict the prognosis and length of stay in hospital for adults and children with TBI. Application of these models may reduce the burden on physicians when assessing TBI and assist clinicians in the medical decision-making process.

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

BACKGROUND

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

METHODS

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

RESULTS

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

CONCLUSION

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

Fully Convolutional Network for the Semantic Segmentation of Medical Images: A Survey

There have been major developments in deep learning in computer vision since the 2010s. Deep learning has contributed to a wealth of data in medical image processing, and semantic segmentation is a salient technique in this field. This study retrospectively reviews recent studies on the application of deep learning for segmentation tasks in medical imaging and proposes potential directions for future development, including model development, data augmentation processing, and dataset creation. The strengths and deficiencies of studies on models and data augmentation, as well as their application to medical image segmentation, were analyzed. Fully convolutional network developments have led to the creation of the U-Net and its derivatives. Another noteworthy image segmentation model is DeepLab. Regarding data augmentation, due to the low data volume of medical images, most studies focus on means to increase the wealth of medical image data. Generative adversarial networks (GAN) increase data volume via deep learning. Despite the increasing types of medical image datasets, there is still a deficiency of datasets on specific problems, which should be improved moving forward. Considering the wealth of ongoing research on the application of deep learning processing to medical image segmentation, the data volume and practical clinical application problems must be addressed to ensure that the results are properly applied.

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.

Traumatic brain injury: progress and challenges in prevention, clinical care, and research

Traumatic brain injury (TBI) has the highest incidence of all common neurological disorders, and poses a substantial public health burden. TBI is increasingly documented not only as an acute condition but also as a chronic disease with long-term consequences, including an increased risk of late-onset neurodegeneration. The first Lancet Neurology Commission on TBI, published in 2017, called for a concerted effort to tackle the global health problem posed by TBI. Since then, funding agencies have supported research both in high-income countries (HICs) and in low-income and middle-income countries (LMICs). In November 2020, the World Health Assembly, the decision-making body of WHO, passed resolution WHA73.10 for global actions on epilepsy and other neurological disorders, and WHO launched the Decade for Action on Road Safety plan in 2021. New knowledge has been generated by large observational studies, including those conducted under the umbrella of the International Traumatic Brain Injury Research (InTBIR) initiative, established as a collaboration of funding agencies in 2011. InTBIR has also provided a huge stimulus to collaborative research in TBI and has facilitated participation of global partners. The return on investment has been high, but many needs of patients with TBI remain unaddressed. This update to the 2017 Commission presents advances and discusses persisting and new challenges in prevention, clinical care, and research.

In LMICs, the occurrence of TBI is driven by road traffic incidents, often involving vulnerable road users such as motorcyclists and pedestrians. In HICs, most TBI is caused by falls, particularly in older people (aged ≥65 years), who often have comorbidities. Risk factors such as frailty and alcohol misuse provide opportunities for targeted prevention actions. Little evidence exists to inform treatment of older patients, who have been commonly excluded from past clinical trials—consequently, appropriate evidence is urgently required. Although increasing age is associated with worse outcomes from TBI, age should not dictate limitations in therapy. However, patients injured by low-energy falls (who are mostly older people) are about 50% less likely to receive critical care or emergency interventions, compared with those injured by high-energy mechanisms, such as road traffic incidents.

Mild TBI, defined as a Glasgow Coma sum score of 13–15, comprises most of the TBI cases (over 90%) presenting to hospital. Around 50% of adult patients with mild TBI presenting to hospital do not recover to pre-TBI levels of health by 6 months after their injury. Fewer than 10% of patients discharged after presenting to an emergency department for TBI in Europe currently receive follow-up. Structured follow-up after mild TBI should be considered good practice, and urgent research is needed to identify which patients with mild TBI are at risk for incomplete recovery.

The selection of patients for CT is an important triage decision in mild TBI since it allows early identification of lesions that can trigger hospital admission or life-saving surgery. Current decision making for deciding on CT is inefficient, with 90–95% of scanned patients showing no intracranial injury but being subjected to radiation risks. InTBIR studies have shown that measurement of blood-based biomarkers adds value to previously proposed clinical decision rules, holding the potential to improve efficiency while reducing radiation exposure. Increased concentrations of biomarkers in the blood of patients with a normal presentation CT scan suggest structural brain damage, which is seen on MR scanning in up to 30% of patients with mild TBI. Advanced MRI, including diffusion tensor imaging and volumetric analyses, can identify additional injuries not detectable by visual inspection of standard clinical MR images. Thus, the absence of CT abnormalities does not exclude structural damage—an observation relevant to litigation procedures, to management of mild TBI, and when CT scans are insufficient to explain the severity of the clinical condition.

Although blood-based protein biomarkers have been shown to have important roles in the evaluation of TBI, most available assays are for research use only. To date, there is only one vendor of such assays with regulatory clearance in Europe and the USA with an indication to rule out the need for CT imaging for patients with suspected TBI. Regulatory clearance is provided for a combination of biomarkers, although evidence is accumulating that a single biomarker can perform as well as a combination. Additional biomarkers and more clinical-use platforms are on the horizon, but cross-platform harmonisation of results is needed. Health-care efficiency would benefit from diversity in providers.

In the intensive care setting, automated analysis of blood pressure and intracranial pressure with calculation of derived parameters can help individualise management of TBI. Interest in the identification of subgroups of patients who might benefit more from some specific therapeutic approaches than others represents a welcome shift towards precision medicine. Comparative-effectiveness research to identify best practice has delivered on expectations for providing evidence in support of best practices, both in adult and paediatric patients with TBI.

Progress has also been made in improving outcome assessment after TBI. Key instruments have been translated into up to 20 languages and linguistically validated, and are now internationally available for clinical and research use. TBI affects multiple domains of functioning, and outcomes are affected by personal characteristics and life-course events, consistent with a multifactorial bio-psycho-socio-ecological model of TBI, as presented in the US National Academies of Sciences, Engineering, and Medicine (NASEM) 2022 report. Multidimensional assessment is desirable and might be best based on measurement of global functional impairment. More work is required to develop and implement recommendations for multidimensional assessment. Prediction of outcome is relevant to patients and their families, and can facilitate the benchmarking of quality of care. InTBIR studies have identified new building blocks (eg, blood biomarkers and quantitative CT analysis) to refine existing prognostic models. Further improvement in prognostication could come from MRI, genetics, and the integration of dynamic changes in patient status after presentation.

Neurotrauma researchers traditionally seek translation of their research findings through publications, clinical guidelines, and industry collaborations. However, to effectively impact clinical care and outcome, interactions are also needed with research funders, regulators, and policy makers, and partnership with patient organisations. Such interactions are increasingly taking place, with exemplars including interactions with the All Party Parliamentary Group on Acquired Brain Injury in the UK, the production of the NASEM report in the USA, and interactions with the US Food and Drug Administration. More interactions should be encouraged, and future discussions with regulators should include debates around consent from patients with acute mental incapacity and data sharing. Data sharing is strongly advocated by funding agencies. From January 2023, the US National Institutes of Health will require upload of research data into public repositories, but the EU requires data controllers to safeguard data security and privacy regulation. The tension between open data-sharing and adherence to privacy regulation could be resolved by cross-dataset analyses on federated platforms, with the data remaining at their original safe location. Tools already exist for conventional statistical analyses on federated platforms, however federated machine learning requires further development. Support for further development of federated platforms, and neuroinformatics more generally, should be a priority.

This update to the 2017 Commission presents new insights and challenges across a range of topics around TBI: epidemiology and prevention (section 1 ); system of care (section 2 ); clinical management (section 3 ); characterisation of TBI (section 4 ); outcome assessment (section 5 ); prognosis (Section 6 ); and new directions for acquiring and implementing evidence (section 7 ). Table 1 summarises key messages from this Commission and proposes recommendations for the way forward to advance research and clinical management of TBI.

Segmentation for Multi-Rock Types on Digital Outcrop Photographs Using Deep Learning Techniques

The basic identification and classification of sedimentary rocks into sandstone and mudstone are important in the study of sedimentology and they are executed by a sedimentologist. However, such manual activity involves countless hours of observation and data collection prior to any interpretation. When such activity is conducted in the field as part of an outcrop study, the sedimentologist is likely to be exposed to challenging conditions such as the weather and their accessibility to the outcrops. This study uses high-resolution photographs which are acquired from a sedimentological study to test an alternative basic multi-rock identification through machine learning. While existing studies have effectively applied deep learning techniques to classify the rock types in field rock images, their approaches only handle a single rock-type classification per image. One study applied deep learning techniques to classify multi-rock types in each image; however, the test was performed on artificially overlaid images of different rock types in a test sample and not of naturally occurring rock surfaces of multiple rock types. To the best of our knowledge, no study has applied semantic segmentation to solve the multi-rock classification problem using digital photographs of multiple rock types. This paper presents the application of two state-of-the-art segmentation models, namely U-Net and LinkNet, to identify multiple rock types in digital photographs by segmenting the sandstone, mudstone, and background classes in a self-collected dataset of 102 images from a field in Brunei Darussalam. Four pre-trained networks, including Resnet34, Inceptionv3, VGG16, and Efficientnetb7 were used as a backbone for both models, and the performances of the individual models and their ensembles were compared. We also investigated the impact of image enhancement and different color representations on the performances of these segmentation models. The experiment results of this study show that among the individual models, LinkNet with Efficientnetb7 as a backbone had the best performance with a mean over intersection (MIoU) value of 0.8135 for all of the classes. While the ensemble of U-Net models (with all four backbones) performed slightly better than the LinkNet with Efficientnetb7 did with an MIoU of 0.8201. When different color representations and image enhancements were explored, the best performance (MIoU = 0.8178) was noticed for the L*a*b* color representation with Efficientnetb7 using U-Net segmentation. For the individual classes of interest (sandstone and mudstone), U-Net with Efficientnetb7 was found to be the best model for the segmentation. Thus, this study presents the potential of semantic segmentation in automating the reservoir characterization process whereby we can extract the patches of interest from the rocks for much deeper study and modeling to be conducted.

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.

Deep learning with weak annotation from diagnosis reports for detection of multiple head disorders: a prospective, multicentre study

BACKGROUND

A large training dataset with high-quality annotations is necessary for building an accurate and generalisable deep learning system, which can be difficult and expensive to prepare in medical applications. We present a novel deep-learning-based system, requiring no annotator but weak annotation from a diagnosis report, for accurate and generalisable performance in detecting multiple head disorders from CT scans, including ischaemia, haemorrhage, tumours, and skull fractures.

METHODS

Our system was developed on 104 597 head CT scans from the Chinese PLA General Hospital, with associated textual diagnosis reports. Without expert annotation, we used keyword matching on the reports to automatically generate disorder labels for each scan. The labels were inaccurate because of the unreliable annotator-free strategy and inexact because of scan-level annotation. We proposed RoLo, a novel weakly supervised learning algorithm, with a noise-tolerant mechanism and a multi-instance learning strategy to address these issues. RoLo was tested on retrospective (2357 scans from the Chinese PLA General Hospital), prospective (650 scans from the Chinese PLA General Hospital), cross-centre (1525 scans from the Brain Hospital of Hunan Province), cross-equipment (1484 scans from the Chinese PLA General Hospital), and cross-nation (CQ500 public dataset from India) test datasets. Four radiologists were tested on the prospective test dataset before and after viewing system recommendations to assess whether the system could improve diagnostic performance.

FINDINGS

The area under the receiver operating characteristic curve for detecting the four disorder types was 0·976 (95% CI 0·976-0·976) for retrospective, 0·975 (0·974-0·976) for prospective, 0·965 (0·964-0·966) for cross-centre, and 0·971 (0·971-0·972) for cross-equipment test datasets, and 0·964 (0·964-0·966) for CQ500 (with only haemorrhage and fracture). The system achieved similar performance to four radiologists and helped to improve sensitivity and specificity by 0·109 (95% CI 0·086-0·131) and 0·022 (0·017-0·026), respectively.

INTERPRETATION

Without expert annotated data, our system achieved accurate and generalisable performance for head disorder detection. The system improved the diagnostic performance of radiologists. Because of its accuracy and generalisability, our computer-aided diganostic system could be used in clinical practice to improve the accuracy and efficiency of radiologists in different hospitals.

FUNDING

National Key R&D Program of China, National Natural Science Foundation of China, and Beijing Natural Science Foundation.

Prediction of Intraparenchymal Hemorrhage Progression and Neurologic Outcome in Traumatic Brain Injury Patients Using Radiomics Score and Clinical Parameters

(1) Background: Radiomics analysis of spontaneous intracerebral hemorrhages on computed tomography (CT) images has been proven effective in predicting hematoma expansion and poor neurologic outcome. In contrast, there is limited evidence on its predictive abilities for traumatic intraparenchymal hemorrhage (IPH). (2) Methods: A retrospective analysis of 107 traumatic IPH patients was conducted. Among them, 45 patients (42.1%) showed hemorrhagic progression of contusion (HPC) and 51 patients (47.7%) had poor neurological outcome. The IPH on the initial CT was manually segmented for radiomics analysis. After feature extraction, selection and repeatability evaluation, several machine learning algorithms were used to derive radiomics scores (R-scores) for the prediction of HPC and poor neurologic outcome. (3) Results: The AUCs for R-scores alone to predict HPC and poor neurologic outcome were 0.76 and 0.81, respectively. Clinical parameters were used to build comparison models. For HPC prediction, variables including age, multiple IPH, subdural hemorrhage, Injury Severity Score (ISS), international normalized ratio (INR) and IPH volume taken together yielded an AUC of 0.74, which was significantly (p = 0.022) increased to 0.83 after incorporation of the R-score in a combined model. For poor neurologic outcome prediction, clinical variables of age, Glasgow Coma Scale, ISS, INR and IPH volume showed high predictability with an AUC of 0.92, and further incorporation of the R-score did not improve the AUC. (4) Conclusion: The results suggest that radiomics analysis of IPH lesions on initial CT images has the potential to predict HPC and poor neurologic outcome in traumatic IPH patients. The clinical and R-score combined model further improves the performance of HPC prediction.

Toward automatic reformation at the orbitomeatal line in head computed tomography using object detection algorithm

Consistent cross-sectional imaging is desirable to accurately detect lesions and facilitate follow-up in head computed tomography (CT). However, manual reformation causes image variations among technologists and requires additional time. We therefore developed a system that reformats head CT images at the orbitomeatal (OM) line and evaluated the system performance using real-world clinical data. Retrospective data were obtained for 681 consecutive patients who underwent non-contrast head CT. The datasets were randomly divided into one of three sets for training, validation, or testing. Four landmarks (bilateral eyes and external auditory canal) were detected with the trained You Look Only Once (YOLO)v5 model, and the head CT images were reformatted at the OM line. The precision, recall, and mean average precision at the intersection over union threshold of 0.5 were computed in the validation sets. The reformation quality in testing sets was evaluated by three radiological technologists on a qualitative 4-point scale. The precision, recall, and mean average precision of the trained YOLOv5 model for all categories were 0.688, 0.949, and 0.827, respectively. In our environment, the mean implementation time was 23.5 ± 2.4 s for each case. The qualitative evaluation in the testing sets showed that post-processed images of automatic reformation had clinically useful quality with scores 3 and 4 in 86.8%, 91.2%, and 94.1% for observers 1, 2, and 3, respectively. Our system demonstrated acceptable quality in reformatting the head CT images at the OM line using an object detection algorithm and was highly time efficient.

Al-Khateeb Z, Michael-Titus AT, Tremoleda JL, Hao Y. Deep learning for behaviour classification in a preclinical brain injury model

The early detection of traumatic brain injuries can directly impact the prognosis and survival of patients. Preceding attempts to automate the detection and the assessment of the severity of traumatic brain injury continue to be based on clinical diagnostic methods, with limited tools for disease outcomes in large populations. Despite advances in machine and deep learning tools, current approaches still use simple trends of statistical analysis which lack generality. The effectiveness of deep learning to extract information from large subsets of data can be further emphasised through the use of more elaborate architectures. We therefore explore the use of a multiple input, convolutional neural network and long short-term memory (LSTM) integrated architecture in the context of traumatic injury detection through predicting the presence of brain injury in a murine preclinical model dataset. We investigated the effectiveness and validity of traumatic brain injury detection in the proposed model against various other machine learning algorithms such as the support vector machine, the random forest classifier and the feedforward neural network. Our dataset was acquired using a home cage automated (HCA) system to assess the individual behaviour of mice with traumatic brain injury or non-central nervous system (non-CNS) injured controls, whilst housed in their cages. Their distance travelled, body temperature, separation from other mice and movement were recorded every 15 minutes, for 72 hours weekly, for 5 weeks following intervention. The HCA behavioural data was used to train a deep learning model, which then predicts if the animals were subjected to a brain injury or just a sham intervention without brain damage. We also explored and evaluated different ways to handle the class imbalance present in the uninjured class of our training data. We then evaluated our models with leave-one-out cross validation. Our proposed deep learning model achieved the best performance and showed promise in its capability to detect the presence of brain trauma in mice.

Deep Gaussian processes for multiple instance learning: Application to CT intracranial hemorrhage detection

BACKGROUND AND OBJECTIVE

Intracranial hemorrhage (ICH) is a life-threatening emergency that can lead to brain damage or death, with high rates of mortality and morbidity. The fast and accurate detection of ICH is important for the patient to get an early and efficient treatment. To improve this diagnostic process, the application of Deep Learning (DL) models on head CT scans is an active area of research. Although promising results have been obtained, many of the proposed models require slice-level annotations by radiologists, which are costly and time-consuming.

METHODS

We formulate the ICH detection as a problem of Multiple Instance Learning (MIL) that allows training with only scan-level annotations. We develop a new probabilistic method based on Deep Gaussian Processes (DGP) that is able to train with this MIL setting and accurately predict ICH at both slice- and scan-level. The proposed DGPMIL model is able to capture complex feature relations by using multiple Gaussian Process (GP) layers, as we show experimentally.

RESULTS

To highlight the advantages of DGPMIL in a general MIL setting, we first conduct several controlled experiments on the MNIST dataset. We show that multiple GP layers outperform one-layer GP models, especially for complex feature distributions. For ICH detection experiments, we use two public brain CT datasets (RSNA and CQ500). We first train a Convolutional Neural Network (CNN) with an attention mechanism to extract the image features, which are fed into our DGPMIL model to perform the final predictions. The results show that DGPMIL model outperforms VGPMIL as well as the attention-based CNN for MIL and other state-of-the-art methods for this problem. The best performing DGPMIL model reaches an AUC-ROC of 0.957 (resp. 0.909) and an AUC-PR of 0.961 (resp. 0.889) on the RSNA (resp. CQ500) dataset.

CONCLUSION

The competitive performance at slice- and scan-level shows that DGPMIL model provides an accurate diagnosis on slices without the need for slice-level annotations by radiologists during training. As MIL is a common problem setting, our model can be applied to a broader range of other tasks, especially in medical image classification, where it can help the diagnostic process.

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.

Development and Validation of an Automatic System for Intracerebral Hemorrhage Medical Text Recognition and Treatment Plan Output

The main purpose of the study was to explore a reliable way to automatically handle emergency cases, such as intracerebral hemorrhage (ICH). Therefore, an artificial intelligence (AI) system, named, H-system, was designed to automatically recognize medical text data of ICH patients and output the treatment plan. Furthermore, the efficiency and reliability of the H-system were tested and analyzed. The H-system, which is mainly based on a pretrained language model Bidirectional Encoder Representations from Transformers (BERT) and an expert module for logical judgment of extracted entities, was designed and founded by the neurosurgeon and AI experts together. All emergency medical text data were from the neurosurgery emergency electronic medical record database (N-eEMRD) of the First Affiliated Hospital of Chongqing Medical University, Chongqing Emergency Medical Center, and Chongqing First People’s Hospital, and the treatment plans of these ICH cases were divided into two types. A total of 1,000 simulated ICH cases were randomly selected as training and validation sets. After training and validating on simulated cases, real cases from three medical centers were provided to test the efficiency of the H-system. Doctors with 1 and 5 years of working experience in neurosurgery (Doctor-1Y and Doctor-5Y) were included to compare with H-system. Furthermore, the data of the H-system, for instance, sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), and the area under the receiver operating characteristics curve (AUC), were calculated and compared with Doctor-1Y and Doctor-5Y. In the testing set, the time H-system spent on ICH cases was significantly shorter than that of doctors with Doctor-1Y and Doctor-5Y. In the testing set, the accuracy of the H-system’s treatment plan was 88.55 (88.16–88.94)%, the specificity was 85.71 (84.99–86.43)%, and the sensitivity was 91.83 (91.01–92.65)%. The AUC value of the H-system in the testing set was 0.887 (0.884–0.891). Furthermore, the time H-system spent on ICH cases was significantly shorter than that of doctors with Doctor-1Y and Doctor-5Y. The accuracy and AUC of the H-system were significantly higher than that of Doctor-1Y. In addition, the accuracy of the H-system was more closed to that of Doctor-5Y. The H-system designed in the study can automatically recognize and analyze medical text data of patients with ICH and rapidly output accurate treatment plans with high efficiency. It may provide a reliable and novel way to automatically and rapidly handle emergency cases, such as ICH.

Artificial Intelligence in Critical Care Medicine

This article is one of ten reviews selected from the Annual Update in Intensive Care and Emergency Medicine 2022. Other selected articles can be found online at https://www.biomedcentral.com/collections/annualupdate2022 . Further information about the Annual Update in Intensive Care and Emergency Medicine is available from https://link.springer.com/bookseries/8901 .

Computational Approaches for Acute Traumatic Brain Injury Image Recognition

In recent years, there have been major advances in deep learning algorithms for image recognition in traumatic brain injury (TBI). Interest in this area has increased due to the potential for greater objectivity, reduced interpretation times and, ultimately, higher accuracy. Triage algorithms that can re-order radiological reading queues have been developed, using classification to prioritize exams with suspected critical findings. Localization models move a step further to capture more granular information such as the location and, in some cases, size and subtype, of intracranial hematomas that could aid in neurosurgical management decisions. In addition to the potential to improve the clinical management of TBI patients, the use of algorithms for the interpretation of medical images may play a transformative role in enabling the integration of medical images into precision medicine. Acute TBI is one practical example that can illustrate the application of deep learning to medical imaging. This review provides an overview of computational approaches that have been proposed for the detection and characterization of acute TBI imaging abnormalities, including intracranial hemorrhage, skull fractures, intracranial mass effect, and stroke.

Usage of image registration and three-dimensional visualization tools on serial computed tomography for the analysis of patients with traumatic intraparenchymal hemorrhages

The aim of this study was to apply registration and three-dimensional (3D) display tools to assess the evolution of intraparenchymal hemorrhage (IPH) in patients with traumatic brain injury (TBI). We identified 109 TBI patients who had two computed tomography (CT) scans within 4 days retrospectively. The IPH was manually outlined. The registration was performed in 39 lesions from 29 patients with lesion volume < 1.5 cm on both baseline and follow-up CT. The center of mass (COM) of each lesion was calculated, and the distance between baseline and follow-up CT was used to evaluate the registration effect. The mean distances of COM before registration in the XYZ, XY, and YZ coordinates were 20.5 ± 10.2 mm, 17.8 ± 9.4 mm, and 15.9 ± 9.4 mm, respectively, which decreased significantly (p < 0.001) to 7.9 ± 4.9, 7.8 ± 5.0, and 6.1 ± 4.1 mm after registration. A 3D short video displaying the rendering view of all lesions in 34 randomly selected patients from baseline and follow-up scans were presented side-by-side for comparison. The detection rate of new IPH lesions increased in 3D videos (100%) as compared with axial CT slices (78.6-92.9%). A very high interrater agreement (k = 0.856) on perceiving IPH lesion progression upon viewing 3D video was noted, and the absolute volume increase was significantly higher (p < 0.001) for progressive lesions (median 7.36 cc) over non-progressive lesions (median 0.01 cc). Compared to patients with spontaneous hemorrhagic stroke, evaluation of multiple small traumatic hemorrhages in TBI is more challenging. The applied image analysis and visualization methods may provide helpful tools for comparing changes between serial CT scans.

Prediction and Risk Assessment Models for Subarachnoid Hemorrhage: A Systematic Review on Case Studies

Subarachnoid hemorrhage (SAH) is one of the major health issues known to society and has a higher mortality rate. The clinical factors with computed tomography (CT), magnetic resonance image (MRI), and electroencephalography (EEG) data were used to evaluate the performance of the developed method. In this paper, various methods such as statistical analysis, logistic regression, machine learning, and deep learning methods were used in the prediction and detection of SAH which are reviewed. The advantages and limitations of SAH prediction and risk assessment methods are also being reviewed. Most of the existing methods were evaluated on the collected dataset for the SAH prediction. In some researches, deep learning methods were applied, which resulted in higher performance in the prediction process. EEG data were applied in the existing methods for the prediction process, and these methods demonstrated higher performance. However, the existing methods have the limitations of overfitting problems, imbalance data problems, and lower efficiency in feature analysis. The artificial neural network (ANN) and support vector machine (SVM) methods have been applied for the prediction process, and considerably higher performance is achieved by using this method.

Relationship of admission blood proteomic biomarkers levels to lesion type and lesion burden in traumatic brain injury: A CENTER-TBI study

BACKGROUND

We aimed to understand the relationship between serum biomarker concentration and lesion type and volume found on computed tomography (CT) following all severities of TBI.

METHODS

Concentrations of six serum biomarkers (GFAP, NFL, NSE, S100B, t-tau and UCH-L1) were measured in samples obtained <24 hours post-injury from 2869 patients with all severities of TBI, enrolled in the CENTER-TBI prospective cohort study (NCT02210221). Imaging phenotypes were defined as intraparenchymal haemorrhage (IPH), oedema, subdural haematoma (SDH), extradural haematoma (EDH), traumatic subarachnoid haemorrhage (tSAH), diffuse axonal injury (DAI), and intraventricular haemorrhage (IVH). Multivariable polynomial regression was performed to examine the association between biomarker levels and both distinct lesion types and lesion volumes. Hierarchical clustering was used to explore imaging phenotypes; and principal component analysis and k-means clustering of acute biomarker concentrations to explore patterns of biomarker clustering.

FINDINGS

2869 patient were included, 68% (n=1946) male with a median age of 49 years (range 2-96). All severities of TBI (mild, moderate and severe) were included for analysis with majority (n=1946, 68%) having a mild injury (GCS 13-15). Patients with severe diffuse injury (Marshall III/IV) showed significantly higher levels of all measured biomarkers, with the exception of NFL, than patients with focal mass lesions (Marshall grades V/VI). Patients with either DAI+IVH or SDH+IPH+tSAH, had significantly higher biomarker concentrations than patients with EDH. Higher biomarker concentrations were associated with greater volume of IPH (GFAP, S100B, t-tau;adj r2 range:0·48-0·49; p<0·05), oedema (GFAP, NFL, NSE, t-tau, UCH-L1;adj r2 range:0·44-0·44; p<0·01), IVH (S100B;adj r2 range:0.48-0.49; p<0.05), Unsupervised k-means biomarker clustering revealed two clusters explaining 83·9% of variance, with phenotyping characteristics related to clinical injury severity.

INTERPRETATION

Interpretation: Biomarker concentration within 24 hours of TBI is primarily related to severity of injury and intracranial disease burden, rather than pathoanatomical type of injury.

FUNDING

CENTER-TBI is funded by the European Union 7th Framework programme (EC grant 602150).

Semantic Segmentation of Urinary Bladder Cancer Masses from CT Images: A Transfer Learning Approach

Simple Summary

Bladder cancer is a common cancer of the urinary tract, characterized by high metastatic potential and recurrence. The research applies a transfer learning approach on CT images (frontal, axial, and saggital axes) for the purpose of semantic segmentation of areas affected by bladder cancer. A system consisting of AlexNet network for plane recognition, using transfer learning-based U-net networks for the segmentation task. Achieved results show that the proposed system has a high performance, suggesting possible use in clinical practice.

Abstract

Urinary bladder cancer is one of the most common cancers of the urinary tract. This cancer is characterized by its high metastatic potential and recurrence rate. Due to the high metastatic potential and recurrence rate, correct and timely diagnosis is crucial for successful treatment and care. With the aim of increasing diagnosis accuracy, artificial intelligence algorithms are introduced to clinical decision making and diagnostics. One of the standard procedures for bladder cancer diagnosis is computer tomography (CT) scanning. In this research, a transfer learning approach to the semantic segmentation of urinary bladder cancer masses from CT images is presented. The initial data set is divided into three sub-sets according to image planes: frontal (4413 images), axial (4993 images), and sagittal (996 images). First, AlexNet is utilized for the design of a plane recognition system, and it achieved high classification and generalization performances with an AUCmicro¯ of 0.9999 and σ(AUCmicro) of 0.0006. Furthermore, by applying the transfer learning approach, significant improvements in both semantic segmentation and generalization performances were achieved. For the case of the frontal plane, the highest performances were achieved if pre-trained ResNet101 architecture was used as a backbone for U-net with DSC¯ up to 0.9587 and σ(DSC) of 0.0059. When U-net was used for the semantic segmentation of urinary bladder cancer masses from images in the axial plane, the best results were achieved if pre-trained ResNet50 was used as a backbone, with a DSC¯ up to 0.9372 and σ(DSC) of 0.0147. Finally, in the case of images in the sagittal plane, the highest results were achieved with VGG-16 as a backbone. In this case, DSC¯ values up to 0.9660 with a σ(DSC) of 0.0486 were achieved. From the listed results, the proposed semantic segmentation system worked with high performance both from the semantic segmentation and generalization standpoints. The presented results indicate that there is the possibility for the utilization of the semantic segmentation system in clinical practice.

Development and Evaluation of a Deep Learning Algorithm for Rib Segmentation and Fracture Detection from Multicenter Chest CT Images

Purpose

To evaluate the performance of a deep learning-based algorithm for automatic detection and labeling of rib fractures from multicenter chest CT images.

Materials and Methods

This retrospective study included 10 943 patients (mean age, 55 years; 6418 men) from six hospitals (January 1, 2017 to December 30, 2019), which consisted of patients with and without rib fractures who underwent CT. The patients were separated into one training set (n = 2425), two lesion-level test sets (n = 362 and 105), and one examination-level test set (n = 8051). Free-response receiver operating characteristic (FROC) score (mean sensitivity of seven different false-positive rates), precision, sensitivity, and F1 score were used as metrics to assess rib fracture detection performance. Area under the receiver operating characteristic curve (AUC), sensitivity, and specificity were employed to evaluate the classification accuracy. The mean Dice coefficient and accuracy were used to assess the performance of rib labeling.

Results

In the detection of rib fractures, the model showed an FROC score of 84.3% on test set 1. For test set 2, the algorithm achieved a detection performance (precision, 82.2%; sensitivity, 84.9%; F1 score, 83.3%) comparable to three radiologists (precision, 81.7%, 98.0%, 92.0%; sensitivity, 91.2%, 78.6%, 69.2%; F1 score, 86.1%, 87.2%, 78.9%). When the radiologists used the algorithm, the mean sensitivity of the three radiologists showed an improvement (from 79.7% to 89.2%), with precision achieving similar performance (from 90.6% to 88.4%). Furthermore, the model achieved an AUC of 0.93 (95% CI: 0.91, 0.94), sensitivity of 87.9% (95% CI: 83.7%, 91.4%), and specificity of 85.3% (95% CI: 74.6%, 89.8%) on test set 3. On a subset of test set 1, the model achieved a Dice score of 0.827 with an accuracy of 96.0% for rib segmentation.

Conclusion

The developed deep learning algorithm was capable of detecting rib fractures, as well as corresponding anatomic locations on CT images.Keywords CT, Ribs© RSNA, 2021.

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.