Supervised learning technique for the automated identification of white matter hyperintensities in traumatic brain injury

Machine learning algorithms for predicting outcomes of traumatic brain injury: A systematic review and meta-analysis

BACKGROUND

Traumatic brain injury (TBI) is a leading cause of death and disability worldwide. The use of machine learning (ML) has emerged as a key advancement in TBI management. This study aimed to identify ML models with demonstrated effectiveness in predicting TBI outcomes.

METHODS

We conducted a systematic review in accordance with the Preferred Reporting Items for Systematic Review and Meta-Analysis statement. In total, 15 articles were identified using the search strategy. Patient demographics, clinical status, ML outcome variables, and predictive characteristics were extracted. A small meta-analysis of mortality prediction was performed, and a meta-analysis of diagnostic accuracy was conducted for ML algorithms used across multiple studies.

RESULTS

ML algorithms including support vector machine (SVM), artificial neural networks (ANN), random forest, and Naïve Bayes were compared to logistic regression (LR). Thirteen studies found significant improvement in prognostic capability using ML versus LR. The accuracy of the above algorithms was consistently over 80% when predicting mortality and unfavorable outcome measured by Glasgow Outcome Scale. Receiver operating characteristic curves analyzing the sensitivity of ANN, SVM, decision tree, and LR demonstrated consistent findings across studies. Lower admission Glasgow Coma Scale (GCS), older age, elevated serum acid, and abnormal glucose were associated with increased adverse outcomes and had the most significant impact on ML algorithms.

CONCLUSION

ML algorithms were stronger than traditional regression models in predicting adverse outcomes. Admission GCS, age, and serum metabolites all have strong predictive power when used with ML and should be considered important components of TBI risk stratification.

Prediction of shunt failure facilitated by rapid and accurate volumetric analysis: a single institution's preliminary experience

BACKGROUND

Shunt malfunction is a common complication and often presents with hydrocephalus. While the diagnosis is often supported by radiographic studies, subtle changes in CSF volume may not be detectable on routine evaluation. The purpose of this study was to develop a novel automated volumetric software for evaluation of shunt failure in pediatric patients, especially in patients who may not manifest a significant change in their ventricular size.

METHODS

A single-institution retrospective review of shunted patients was conducted. Ventricular volume measurements were performed using manual and automated methods by three independent analysts. Manual measurements were produced using OsiriX software, whereas automated measurements were produced using the proprietary software. A p value < 0.05 was considered statistically significant.

RESULTS

Twenty-two patients met the inclusion criteria (13 males, 9 females). Mean age of the cohort was 4.9 years (range 0.1-18 years). Average measured CSF volume was similar between the manual and automated methods (169.8 mL vs 172.5 mL, p = 0.56). However, the average time to generate results was significantly shorter with the automated algorithm compared to the manual method (2244 s vs 38.3 s, p < 0.01). In 3/5 symptomatic patients whose neuroimaging was interpreted as stable, the novel algorithm detected the otherwise radiographically undetectable CSF volume changes.

CONCLUSION

The automated software accurately measures the ventricular volumes in pediatric patients with hydrocephalus. The application of this technology is valuable in patients who present clinically without obvious radiographic changes. Future studies with larger cohorts are needed to validate our preliminary findings and further assess the utility of this technology.

Pediatric severe traumatic brain injury mortality prediction determined with machine learning-based modeling

INTRODUCTION

Severe traumatic brain injury (sTBI) is a leading cause of mortality in children. As clinical prognostication is important in guiding optimal care and decision making, our goal was to create a highly discriminative sTBI outcome prediction model for mortality.

METHODS

Machine learning and advanced analytics were applied to the patient admission variables obtained from a comprehensive pediatric sTBI database. Demographic and clinical data, head CT imaging abnormalities and blood biochemical data from 196 children and adolescents admitted to a tertiary pediatric intensive care unit (PICU) with sTBI were integrated using feature ranking by way of a forest of randomized decision trees, and a model was generated from a reduced number of admission variables with maximal ability to discriminate outcome.

RESULTS

In total, 36 admission variables were analyzed using feature ranking with variable weighting to determine their predictive importance for mortality following sTBI. Reduction analysis utilizing Borata feature selection resulted in a parsimonious six-variable model with a mortality classification accuracy of 82%. The final admission variables that predicted mortality were: partial thromboplastin time (22%); motor Glasgow Coma Scale (21%); serum glucose (16%); fixed pupil(s) (16%); platelet count (13%) and creatinine (12%). Using only these six admission variables, a t-distributed stochastic nearest neighbor embedding algorithm plot demonstrated visual separation of sTBI patients that lived or died, with high mortality predictive ability of this model on the validation dataset (AUC = 0.90) which was confirmed with a conventional area-under-the-curve statistical approach on the total dataset (AUC = 0.91; P < 0.001).

CONCLUSIONS

Machine learning-based modeling identified the most clinically important prognostic factors resulting in a pragmatic, high performing prognostic tool for pediatric sTBI with excellent discriminative ability to predict mortality risk with 82% classification accuracy (AUC = 0.90). After external multicenter validation, our prognostic model might help to guide treatment decisions, aggressiveness of therapy and prepare family members and caregivers for timely end-of-life discussions and decision making.

LEVEL OF EVIDENCE

III; Prognostic.

Applications of artificial intelligence in nuclear medicine image generation

Recently, the application of artificial intelligence (AI) in medical imaging (including nuclear medicine imaging) has rapidly developed. Most AI applications in nuclear medicine imaging have focused on the diagnosis, treatment monitoring, and correlation analyses with pathology or specific gene mutation. It can also be used for image generation to shorten the time of image acquisition, reduce the dose of injected tracer, and enhance image quality. This work provides an overview of the application of AI in image generation for single-photon emission computed tomography (SPECT) and positron emission tomography (PET) either without or with anatomical information [CT or magnetic resonance imaging (MRI)]. This review focused on four aspects, including imaging physics, image reconstruction, image postprocessing, and internal dosimetry. AI application in generating attenuation map, estimating scatter events, boosting image quality, and predicting internal dose map is summarized and discussed.

Automatic brain lesion segmentation on standard magnetic resonance images: a scoping review

OBJECTIVES

Medical image analysis practices face challenges that can potentially be addressed with algorithm-based segmentation tools. In this study, we map the field of automatic MR brain lesion segmentation to understand the clinical applicability of prevalent methods and study designs, as well as challenges and limitations in the field.

DESIGN

Scoping review.

SETTING

Three databases (PubMed, IEEE Xplore and Scopus) were searched with tailored queries. Studies were included based on predefined criteria. Emerging themes during consecutive title, abstract, methods and whole-text screening were identified. The full-text analysis focused on materials, preprocessing, performance evaluation and comparison.

RESULTS

Out of 2990 unique articles identified through the search, 441 articles met the eligibility criteria, with an estimated growth rate of 10% per year. We present a general overview and trends in the field with regard to publication sources, segmentation principles used and types of lesions. Algorithms are predominantly evaluated by measuring the agreement of segmentation results with a trusted reference. Few articles describe measures of clinical validity.

CONCLUSIONS

The observed reporting practices leave room for improvement with a view to studying replication, method comparison and clinical applicability. To promote this improvement, we propose a list of recommendations for future studies in the field.

Automatic segmentation of white matter hyperintensities from brain magnetic resonance images in the era of deep learning and big data - A systematic review

BACKGROUND

White matter hyperintensities (WMH), of presumed vascular origin, are visible and quantifiable neuroradiological markers of brain parenchymal change. These changes may range from damage secondary to inflammation and other neurological conditions, through to healthy ageing. Fully automatic WMH quantification methods are promising, but still, traditional semi-automatic methods seem to be preferred in clinical research. We systematically reviewed the literature for fully automatic methods developed in the last five years, to assess what are considered state-of-the-art techniques, as well as trends in the analysis of WMH of presumed vascular origin.

METHOD

We registered the systematic review protocol with the International Prospective Register of Systematic Reviews (PROSPERO), registration number - CRD42019132200. We conducted the search for fully automatic methods developed from 2015 to July 2020 on Medline, Science direct, IEE Explore, and Web of Science. We assessed risk of bias and applicability of the studies using QUADAS 2.

RESULTS

The search yielded 2327 papers after removing 104 duplicates. After screening titles, abstracts and full text, 37 were selected for detailed analysis. Of these, 16 proposed a supervised segmentation method, 10 proposed an unsupervised segmentation method, and 11 proposed a deep learning segmentation method. Average DSC values ranged from 0.538 to 0.91, being the highest value obtained from an unsupervised segmentation method. Only four studies validated their method in longitudinal samples, and eight performed an additional validation using clinical parameters. Only 8/37 studies made available their methods in public repositories.

CONCLUSIONS

We found no evidence that favours deep learning methods over the more established k-NN, linear regression and unsupervised methods in this task. Data and code availability, bias in study design and ground truth generation influence the wider validation and applicability of these methods in clinical research.

Artificial intelligence-based education assists medical students' interpretation of hip fracture

Background

With recent transformations in medical education, the integration of technology to improve medical students’ abilities has become feasible. Artificial intelligence (AI) has impacted several aspects of healthcare. However, few studies have focused on medical education. We performed an AI-assisted education study and confirmed that AI can accelerate trainees’ medical image learning.

Materials

We developed an AI-based medical image learning system to highlight hip fracture on a plain pelvic film. Thirty medical students were divided into a conventional (CL) group and an AI-assisted learning (AIL) group. In the CL group, the participants received a prelearning test and a postlearning test. In the AIL group, the participants received another test with AI-assisted education before the postlearning test. Then, we analyzed changes in diagnostic accuracy.

Results

The prelearning performance was comparable in both groups. In the CL group, postlearning accuracy (78.66 ± 14.53) was higher than prelearning accuracy (75.86 ± 11.36) with no significant difference (p = .264). The AIL group showed remarkable improvement. The WithAI score (88.87 ± 5.51) was significantly higher than the prelearning score (75.73 ± 10.58, p < 0.01). Moreover, the postlearning score (84.93 ± 14.53) was better than the prelearning score (p < 0.01). The increase in accuracy was significantly higher in the AIL group than in the CL group.

Conclusion

The study demonstrated the viability of AI for augmenting medical education. Integrating AI into medical education requires dynamic collaboration from research, clinical, and educational perspectives.

Diverse Applications of Artificial Intelligence in Neuroradiology

Recent advances in artificial intelligence (AI) and deep learning (DL) hold promise to augment neuroimaging diagnosis for patients with brain tumors and stroke. Here, the authors review the diverse landscape of emerging neuroimaging applications of AI, including workflow optimization, lesion segmentation, and precision education. Given the many modalities used in diagnosing neurologic diseases, AI may be deployed to integrate across modalities (MR imaging, computed tomography, PET, electroencephalography, clinical and laboratory findings), facilitate crosstalk among specialists, and potentially improve diagnosis in patients with trauma, multiple sclerosis, epilepsy, and neurodegeneration. Together, there are myriad applications of AI for neuroradiology."

MR Image-Based Attenuation Correction of Brain PET Imaging: Review of Literature on Machine Learning Approaches for Segmentation

Recent emerging hybrid technology of positron emission tomography/magnetic resonance (PET/MR) imaging has generated a great need for an accurate MR image-based PET attenuation correction. MR image segmentation, as a robust and simple method for PET attenuation correction, has been clinically adopted in commercial PET/MR scanners. The general approach in this method is to segment the MR image into different tissue types, each assigned an attenuation constant as in an X-ray CT image. Machine learning techniques such as clustering, classification and deep networks are extensively used for brain MR image segmentation. However, only limited work has been reported on using deep learning in brain PET attenuation correction. In addition, there is a lack of clinical evaluation of machine learning methods in this application. The aim of this review is to study the use of machine learning methods for MR image segmentation and its application in attenuation correction for PET brain imaging. Furthermore, challenges and future opportunities in MR image-based PET attenuation correction are discussed.

Artificial Intelligence in Neuroradiology: Current Status and Future Directions

Fueled by new techniques, computational tools, and broader availability of imaging data, artificial intelligence has the potential to transform the practice of neuroradiology. The recent exponential increase in publications related to artificial intelligence and the central focus on artificial intelligence at recent professional and scientific radiology meetings underscores the importance. There is growing momentum behind leveraging artificial intelligence techniques to improve workflow and diagnosis and treatment and to enhance the value of quantitative imaging techniques. This article explores the reasons why neuroradiologists should care about the investments in new artificial intelligence applications, highlights current activities and the roles neuroradiologists are playing, and renders a few predictions regarding the near future of artificial intelligence in neuroradiology.

Convolutional Neural Network for Automated FLAIR Lesion Segmentation on Clinical Brain MR Imaging

BACKGROUND AND PURPOSE

Most brain lesions are characterized by hyperintense signal on FLAIR. We sought to develop an automated deep learning-based method for segmentation of abnormalities on FLAIR and volumetric quantification on clinical brain MRIs across many pathologic entities and scanning parameters. We evaluated the performance of the algorithm compared with manual segmentation and existing automated methods.

MATERIALS AND METHODS

We adapted a U-Net convolutional neural network architecture for brain MRIs using 3D volumes. This network was retrospectively trained on 295 brain MRIs to perform automated FLAIR lesion segmentation. Performance was evaluated on 92 validation cases using Dice scores and voxelwise sensitivity and specificity, compared with radiologists' manual segmentations. The algorithm was also evaluated on measuring total lesion volume.

RESULTS

Our model demonstrated accurate FLAIR lesion segmentation performance (median Dice score, 0.79) on the validation dataset across a large range of lesion characteristics. Across 19 neurologic diseases, performance was significantly higher than existing methods (Dice, 0.56 and 0.41) and approached human performance (Dice, 0.81). There was a strong correlation between the predictions of lesion volume of the algorithm compared with true lesion volume (ρ = 0.99). Lesion segmentations were accurate across a large range of image-acquisition parameters on >30 different MR imaging scanners.

CONCLUSIONS

A 3D convolutional neural network adapted from a U-Net architecture can achieve high automated FLAIR segmentation performance on clinical brain MR imaging across a variety of underlying pathologies and image acquisition parameters. The method provides accurate volumetric lesion data that can be incorporated into assessments of disease burden or into radiologic reports.

Machine learning in mental health: a scoping review of methods and applications

BACKGROUND

This paper aims to synthesise the literature on machine learning (ML) and big data applications for mental health, highlighting current research and applications in practice.

METHODS

We employed a scoping review methodology to rapidly map the field of ML in mental health. Eight health and information technology research databases were searched for papers covering this domain. Articles were assessed by two reviewers, and data were extracted on the article's mental health application, ML technique, data type, and study results. Articles were then synthesised via narrative review.

RESULTS

Three hundred papers focusing on the application of ML to mental health were identified. Four main application domains emerged in the literature, including: (i) detection and diagnosis; (ii) prognosis, treatment and support; (iii) public health, and; (iv) research and clinical administration. The most common mental health conditions addressed included depression, schizophrenia, and Alzheimer's disease. ML techniques used included support vector machines, decision trees, neural networks, latent Dirichlet allocation, and clustering.

CONCLUSIONS

Overall, the application of ML to mental health has demonstrated a range of benefits across the areas of diagnosis, treatment and support, research, and clinical administration. With the majority of studies identified focusing on the detection and diagnosis of mental health conditions, it is evident that there is significant room for the application of ML to other areas of psychology and mental health. The challenges of using ML techniques are discussed, as well as opportunities to improve and advance the field.

Application of a deep learning algorithm for detection and visualization of hip fractures on plain pelvic radiographs

Objective

To identify the feasibility of using a deep convolutional neural network (DCNN) for the detection and localization of hip fractures on plain frontal pelvic radiographs (PXRs).

Summary of background data

Hip fracture is a leading worldwide health problem for the elderly. A missed diagnosis of hip fracture on radiography leads to a dismal prognosis. The application of a DCNN to PXRs can potentially improve the accuracy and efficiency of hip fracture diagnosis.

Methods

A DCNN was pretrained using 25,505 limb radiographs between January 2012 and December 2017. It was retrained using 3605 PXRs between August 2008 and December 2016. The accuracy, sensitivity, false-negative rate, and area under the receiver operating characteristic curve (AUC) were evaluated on 100 independent PXRs acquired during 2017. The authors also used the visualization algorithm gradient-weighted class activation mapping (Grad-CAM) to confirm the validity of the model.

Results

The algorithm achieved an accuracy of 91%, a sensitivity of 98%, a false-negative rate of 2%, and an AUC of 0.98 for identifying hip fractures. The visualization algorithm showed an accuracy of 95.9% for lesion identification.

Conclusions

A DCNN not only detected hip fractures on PXRs with a low false-negative rate but also had high accuracy for localizing fracture lesions. The DCNN might be an efficient and economical model to help clinicians make a diagnosis without interrupting the current clinical pathway.

Key Points

• Automated detection of hip fractures on frontal pelvic radiographs may facilitate emergent screening and evaluation efforts for primary physicians.

• Good visualization of the fracture site by Grad-CAM enables the rapid integration of this tool into the current medical system.

• The feasibility and efficiency of utilizing a deep neural network have been confirmed for the screening of hip fractures.

Amyloid beta-positive subjects exhibit longitudinal network-specific reductions in spontaneous brain activity

Amyloid beta (Aβ) deposition and cognitive decline are key features of Alzheimer's disease. The relationship between Aβ status and changes in neuronal function over time, however, remains unclear. We evaluated the effect of baseline Aβ status on reference region spontaneous brain activity (SBA-rr) using resting-state functional magnetic resonance imaging and fluorodeoxyglucose positron emission tomography in patients with mild cognitive impairment. Patients (N = 62, [43 Aβ-positive]) from the Alzheimer's Disease Neuroimaging Initiative were divided into Aβ-positive and Aβ-negative groups via prespecified cerebrospinal fluid Aβ42 or 18F-florbetapir positron emission tomography standardized uptake value ratio cutoffs measured at baseline. We analyzed interaction of biomarker-confirmed Aβ status with SBA-rr change over a 2-year period using mixed-effects modeling. SBA-rr differences between Aβ-positive and Aβ-negative subjects increased significantly over time within subsystems of the default and visual networks. Changes exhibit an interaction with memory performance over time but were independent of glucose metabolism. Results reinforce the value of resting-state functional magnetic resonance imaging in evaluating Alzheimer''s disease progression and suggest spontaneous neuronal activity changes are concomitant with cognitive decline.

The Dynamics of Concussion: Mapping Pathophysiology, Persistence, and Recovery With Causal-Loop Diagramming

Despite increasing public awareness and a growing body of literature on the subject of concussion, or mild traumatic brain injury, an urgent need still exists for reliable diagnostic measures, clinical care guidelines, and effective treatments for the condition. Complexity and heterogeneity complicate research efforts and indicate the need for innovative approaches to synthesize current knowledge in order to improve clinical outcomes. Methods from the interdisciplinary field of systems science, including models of complex systems, have been increasingly applied to biomedical applications and show promise for generating insight for traumatic brain injury. The current study uses causal-loop diagramming to visualize relationships between factors influencing the pathophysiology and recovery trajectories of concussive injury, including persistence of symptoms and deficits. The primary output is a series of preliminary systems maps detailing feedback loops, intrinsic dynamics, exogenous drivers, and hubs across several scales, from micro-level cellular processes to social influences. Key system features, such as the role of specific restorative feedback processes and cross-scale connections, are examined and discussed in the context of recovery trajectories. This systems approach integrates research findings across disciplines and allows components to be considered in relation to larger system influences, which enables the identification of research gaps, supports classification efforts, and provides a framework for interdisciplinary collaboration and communication-all strides that would benefit diagnosis, prognosis, and treatment in the clinic.

Different MRI-defined tuber types in tuberous sclerosis complex: Quantitative evaluation and association with disease manifestations

BACKGROUND

Tuberous sclerosis complex (TSC) is a rare genetic disorder with multisystem involvement. A magnetic-resonance (MRI) based classification of tubers into types A, B and C has been proposed. However, the relationship between different tuber types and their quantitative characteristics, also the non-neurological manifestations of TSC remains unknown.

AIMS

To quantitatively evaluate different MRI-defined tuber types and to explore their relationships with major disease manifestations in patients with tuberous sclerosis complex.

METHODS

We performed quantitative manual assessment of tubers visible on T1W, T2W/FLAIR images and DW/ADC maps of 20 patients with TSC. Tubers were classified into types A, B and C based on their signal intensity on MRI. General clinical information and quantitative tuber characteristics were evaluated. Between-group comparisons were made using the nonparametric Mann-Whitney U test with Bonferroni correction.

RESULTS

In total, 20 patients with 770 tubers were evaluated. Type A tubers were most numerous followed closely by Type B tubers, whereas Type C tubers were relatively rare. Tuber size was markedly different among the three tuber types: it increased from Type A to Type B to Type C. Infantile spasms, generalized-tonic clonic seizures, poor seizure control, cardiac rhabdomyomas, SEGA and developmental delay were not associated with quantitative tuber characteristics. Increased total Type B tuber load was associated with early onset epilepsy, while individually larger Type A and Type B tubers were associated with the presence angiomyolipoma (AML) and renal cysts.

CONCLUSIONS

MRI-defined tuber types differ significantly in their size and number. Larger total Type B tuber load and larger individual Type A and Type B tubers were found to be most associated with early seizure onset and renal angiomyolipomas, respectively. One possible explanation for the observed differences in the clinical phenotype based on MRI-defined tuber types is not the intrinsic qualitative distinctions between different tuber types, but rather their individual size and total tuber load.