The prognostic value of visual and automatic coronary calcium -scoring from low dose CT-[15O]-water PET.

PURPOSE: Firstly, to validate automatically and visually scored coronary artery calcium (CAC) on low dose CT (LDCT) scans with a dedicated calcium scoring CT (CSCT) scan. Secondly, to assess the added value of CAC scored from LDCT scans acquired during [15O]-water-PET myocardial perfusion imaging (MPI) on prediction of major adverse cardiac events (MACE). METHODS: 572 consecutive patients with suspected coronary artery disease, who underwent [15O]-water-PET MPI with LDCT and a dedicated CSCT scan were included. In the reference CSCT scans, manual CAC scoring was performed, while LDCT scans were scored visually and automatically using deep learning approach. Subsequently, based on CAC score results from CSCT and LDCT scans, each patient's scan was assigned to one out of five cardiovascular risk groups (0; 1-100; 101-400; 401-1000; >1000) and the agreement in risk group classification between CSCT and LDCT scans was investigated. MACE was defined as a composite of all-cause death, nonfatal myocardial infarction, coronary revascularization, and unstable angina. RESULTS: The agreement in risk group classification between reference CSCT manual scoring and visual/automatic LDCT scoring from LDCT was 0.66 (95% CI: 0.62-0.70) and 0.58 (95% CI: 0.53-0.62), respectively. Based on visual and automatic CAC scoring from LDCT scans, patients with CAC>100 and CAC>400, respectively, were at increased risk of MACE, independently of ischemic information from the [15O]-water-PET scan. CONCLUSIONS: There is a moderate agreement in risk classification between visual and automatic CAC scoring from LDCT and reference CSCT scans. Visual and automatic CAC scoring from LDCT scans improve identification of patients at higher risk of MACE.

Automated cardiovascular risk categorization through AI-driven coronary calcium quantification in cardiac PET acquired attenuation correction CT.

BACKGROUND: We present an automatic method for coronary artery calcium (CAC) quantification and cardiovascular risk categorization in CT attenuation correction (CTAC) scans acquired at rest and stress during cardiac PET/CT. The method segments CAC according to visual assessment rather than the commonly used CT-number threshold. METHODS: The method decomposes an image containing CAC into a synthetic image without CAC and an image showing only CAC. Extensive evaluation was performed in a set of 98 patients, each having rest and stress CTAC scans and a dedicated calcium scoring CT (CSCT). Standard manual calcium scoring in CSCT provided the reference standard. RESULTS: The interscan reproducibility of CAC quantification computed as average absolute relative differences between CTAC and CSCT scan pairs was 75% and 85% at rest and stress using the automatic method compared to 121% and 114% using clinical calcium scoring. Agreement between automatic risk assessment in CTAC and clinical risk categorization in CSCT resulted in linearly weighted kappa of 0.65 compared to 0.40 between CTAC and CSCT using clinically used calcium scoring. CONCLUSION: The increased interscan reproducibility achieved by our method may allow routine cardiovascular risk assessment in CTAC, potentially relieving the need for dedicated CSCT.

Current state of artificial intelligence-based algorithms for hospital admission prediction in patients with heart failure: a scoping review.

Aims: Patients with congestive heart failure (HF) are prone to clinical deterioration leading to hospital admissions, burdening both patients and the healthcare system. Predicting hospital admission in this patient group could enable timely intervention, with subsequent reduction of these admissions. To date, hospital admission prediction remains challenging. Increasing amounts of acquired data and development of artificial intelligence (AI) technology allow for the creation of reliable hospital prediction algorithms for HF patients. This scoping review describes the current literature on strategies and performance of AI-based algorithms for prediction of hospital admission in patients with HF. Methods and results: PubMed, EMBASE, and the Web of Science were used to search for articles using machine learning (ML) and deep learning methods to predict hospitalization in patients with HF. After eligibility screening, 23 articles were included. Sixteen articles predicted 30-day hospital (re-)admission resulting in an area under the curve (AUC) ranging from 0.61 to 0.79. Six studies predicted hospital admission over longer time periods ranging from 6 months to 3 years, with AUC's ranging from 0.65 to 0.78. One study prospectively evaluated performance of a disposable sensory patch at home after hospitalization which resulted in an AUC of 0.89 for unplanned hospital admission prediction. Conclusion: AI has the potential to enable prediction of hospital admission in HF patients. Improvement of data management, adding new data sources such as telemonitoring data and ML models and prospective and external validation of current models must be performed before clinical applicability is possible.

Deep Learning-Based Data-Point Precise R-Peak Detection in Single-Lead Electrocardiograms.

Low-cost wearables with capability to record electrocardiograms (ECG) are becoming increasingly available. These wearables typically acquire single-lead ECGs that are mainly used for screening of cardiac arrhythmias such as atrial fibrillation. Most arrhythmias are characteruzed by changes in the RR-interval, hence automatic methods to diagnose arrythmia may utilize R-peak detection. Existing R-peak detection methods are fairly accurate but have limited precision. To enable data-point precise detection of R-peaks, we propose a method that uses a fully convolutional dilated neural network. The network is trained and evaluated with manually annotated R-peaks in a heterogeneous set of ECGs that contain a wide range of cardiac rhythms and acquisition noise. 700 randomly chosen ECGs from the PhysioNet/CinC challenge 2017 were used for training (n=500), validation (n=100) and testing (n=100). The network achieves a precision of 0.910, recall of 0.926, and an F1-score of 0.918 on the test set. Our data-point precise R-peak detector may be important step towards fully automatic cardiac arrhythmia detection.Clinical relevance- This method enables data-point precise detection of R-peaks that provides a basis for detection and characterization of arrhythmias.

Automatic extraction of the intracranial volume in fetal and neonatal MR scans using convolutional neural networks.

MR images of infants and fetuses allow non-invasive analysis of the brain. Quantitative analysis of brain development requires automatic brain tissue segmentation that is typically preceded by segmentation of the intracranial volume (ICV). Fast changes in the size and morphology of the developing brain, motion artifacts, and large variation in the field of view make ICV segmentation a challenging task. We propose an automatic method for segmentation of the ICV in fetal and neonatal MRI scans. The method was developed and tested with a diverse set of scans regarding image acquisition parameters (i.e. field strength, image acquisition plane, image resolution), infant age (23-45 weeks post menstrual age), and pathology (posthaemorrhagic ventricular dilatation, stroke, asphyxia, and Down syndrome). The results demonstrate that the method achieves accurate segmentation with a Dice coefficient (DC) ranging from 0.98 to 0.99 in neonatal and fetal scans regardless of image acquisition parameters or patient characteristics. Hence, the algorithm provides a generic tool for segmentation of the ICV that may be used as a preprocessing step for brain tissue segmentation in fetal and neonatal brain MR scans.

Automatic brain tissue segmentation in fetal MRI using convolutional neural networks.

MR images of fetuses allow clinicians to detect brain abnormalities in an early stage of development. The cornerstone of volumetric and morphologic analysis in fetal MRI is segmentation of the fetal brain into different tissue classes. Manual segmentation is cumbersome and time consuming, hence automatic segmentation could substantially simplify the procedure. However, automatic brain tissue segmentation in these scans is challenging owing to artifacts including intensity inhomogeneity, caused in particular by spontaneous fetal movements during the scan. Unlike methods that estimate the bias field to remove intensity inhomogeneity as a preprocessing step to segmentation, we propose to perform segmentation using a convolutional neural network that exploits images with synthetically introduced intensity inhomogeneity as data augmentation. The method first uses a CNN to extract the intracranial volume. Thereafter, another CNN with the same architecture is employed to segment the extracted volume into seven brain tissue classes: cerebellum, basal ganglia and thalami, ventricular cerebrospinal fluid, white matter, brain stem, cortical gray matter and extracerebral cerebrospinal fluid. To make the method applicable to slices showing intensity inhomogeneity artifacts, the training data was augmented by applying a combination of linear gradients with random offsets and orientations to image slices without artifacts. To evaluate the performance of the method, Dice coefficient (DC) and Mean surface distance (MSD) per tissue class were computed between automatic and manual expert annotations. When the training data was enriched by simulated intensity inhomogeneity artifacts, the average achieved DC over all tissue classes and images increased from 0.77 to 0.88, and MSD decreased from 0.78 mm to 0.37 mm. These results demonstrate that the proposed approach can potentially replace or complement preprocessing steps, such as bias field corrections, and thereby improve the segmentation performance.

Enhancing cardiovascular artificial intelligence (AI) research in the Netherlands: CVON-AI consortium.

BACKGROUND: Machine learning (ML) allows the exploration and progressive improvement of very complex high-dimensional data patterns that can be utilised to optimise specific classification and prediction tasks, outperforming traditional statistical approaches. An enormous acceleration of ready-to-use tools and artificial intelligence (AI) applications, shaped by the emergence, refinement, and application of powerful ML algorithms in several areas of knowledge, is ongoing. Although such progress has begun to permeate the medical sciences and clinical medicine, implementation in cardiovascular medicine and research is still in its infancy. OBJECTIVES: To lay out the theoretical framework, purpose, and structure of a novel AI consortium. METHODS: We have established a new Dutch research consortium, the CVON-AI, supported by the Netherlands Heart Foundation, to catalyse and facilitate the development and utilisation of AI solutions for existing and emerging cardiovascular research initiatives and to raise AI awareness in the cardiovascular research community. CVON-AI will connect to previously established CVON consortia and apply a cloud-based AI platform to supplement their planned traditional data-analysis approach. RESULTS: A pilot experiment on the CVON-AI cloud was conducted using cardiac magnetic resonance data. It demonstrated the feasibility of the platform and documented excellent correlation between AI-generated ventricular function estimates as compared to expert manual annotations. The resulting AI solution was then integrated in a web application. CONCLUSION: CVON-AI is a new consortium meant to facilitate the implementation and raise awareness of AI in cardiovascular research in the Netherlands. CVON-AI will create an accessible cloud-based platform for cardiovascular researchers, demonstrate the clinical applicability of AI, optimise the analytical methodology of other ongoing CVON consortia, and promote AI awareness through education and training.

Brain and CSF Volumes in Fetuses and Neonates with Antenatal Diagnosis of Critical Congenital Heart Disease: A Longitudinal MRI Study.

BACKGROUND AND PURPOSE: Fetuses and neonates with critical congenital heart disease are at risk of delayed brain development and neurodevelopmental impairments. Our aim was to investigate the association between fetal and neonatal brain volumes and neonatal brain injury in a longitudinally scanned cohort with an antenatal diagnosis of critical congenital heart disease and to relate fetal and neonatal brain volumes to postmenstrual age and type of congenital heart disease. MATERIALS AND METHODS: This was a prospective, longitudinal study including 61 neonates with critical congenital heart disease undergoing surgery with cardiopulmonary bypass <30 days after birth and MR imaging of the brain; antenatally (33 weeks postmenstrual age), neonatal preoperatively (first week), and postoperatively (7 days postoperatively). Twenty-six had 3 MR imaging scans; 61 had at least 1 fetal and/or neonatal MR imaging scan. Volumes (cubic centimeters) were calculated for total brain volume, unmyelinated white matter, cortical gray matter, cerebellum, extracerebral CSF, and ventricular CSF. MR images were reviewed for ischemic brain injury. RESULTS: Total fetal brain volume, cortical gray matter, and unmyelinated white matter positively correlated with preoperative neonatal total brain volume, cortical gray matter, and unmyelinated white matter (r = 0.5-0.58); fetal ventricular CSF and extracerebral CSF correlated with neonatal ventricular CSF and extracerebral CSF (r = 0.64 and 0.82). Fetal cortical gray matter, unmyelinated white matter, and the cerebellum were negatively correlated with neonatal ischemic injury (r = -0.46 to -0.41); fetal extracerebral CSF and ventricular CSF were positively correlated with neonatal ischemic injury (r = 0.40 and 0.23). Unmyelinated white matter:total brain volume ratio decreased with increasing postmenstrual age, with a parallel increase of cortical gray matter:total brain volume and cerebellum:total brain volume. Fetal ventricular CSF:intracranial volume and extracerebral CSF:intracranial volume ratios decreased with increasing postmenstrual age; however, neonatal ventricular CSF:intracranial volume and extracerebral CSF:intracranial volume ratios increased with postmenstrual age. CONCLUSIONS: This study reveals that fetal brain volumes relate to neonatal brain volumes in critical congenital heart disease, with a negative correlation between fetal brain volumes and neonatal ischemic injury. Fetal brain imaging has the potential to provide early neurologic biomarkers.

Osteoporosis markers on low-dose lung cancer screening chest computed tomography scans predict all-cause mortality.

OBJECTIVES: Further survival benefits may be gained from low-dose chest computed tomography (CT) by assessing vertebral fractures and bone density. We sought to assess the association between CT-measured vertebral fractures and bone density with all-cause mortality in lung cancer screening participants. METHODS: Following a case-cohort design, lung cancer screening trial participants (N = 3,673) who died (N = 196) during a median follow-up of 6 years (inter-quartile range: 5.7-6.3) were identified and added to a random sample of N = 383 from the trial. We assessed vertebral fractures using Genant's semiquantative method on sagittal reconstructions and measured bone density (Hounsfield Units (HU)) in vertebrae. Cox proportional hazards modelling was used to determine if vertebral fractures or bone density were independently predictive of mortality. RESULTS: The prevalence of vertebral fractures was 35% (95% confidence interval 30-40%) among survivors and 51% (44-58%) amongst cases. After adjusting for age, gender, smoking status, pack years smoked, coronary and aortic calcium volume and pulmonary emphysema, the adjusted hazard ratio (HR) for vertebral fracture was 2.04 (1.43-2.92). For each 10 HU decline in trabecular bone density, the adjusted HR was 1.08 (1.02-1.15). CONCLUSIONS: Vertebral fractures and bone density are independently associated with all-cause mortality. KEY POINTS: • Lung cancer screening chest computed tomography contains additional, potentially useful information. • Vertebral fractures and bone density are independently predictive of mortality. • This finding has implications for screening and management decisions.

Brain tissue volumes in preterm infants: prematurity, perinatal risk factors and neurodevelopmental outcome: a systematic review.

OBJECTIVE: To evaluate the clinical value of neonatal brain tissue segmentation in preterm infants according to the literature. METHODS: A structured literature search was undertaken in MEDLINE/Pubmed. This included all publications on volumetric brain tissue assessment in preterm infants at term-equivalent age (TEA) compared to brain tissue volumes of term-born infants, related to perinatal risk factors or related to neurodevelopmental outcome. RESULTS: Sixteen prospective cohort studies, described in 30 articles, fulfilled the criteria. Preterm infants displayed total and regional brain tissue alterations compared to healthy, term-born controls. These alterations seemed more prominent with decreasing gestational age. White matter injury, intraventricular haemorrhage, postnatal corticosteroid therapy, intra-uterine growth retardation and chronic lung disease were frequently associated with volume changes. Associations between volume alterations at TEA and neurodevelopmental outcome in early childhood were shown in a few studies. CONCLUSIONS: Preterm birth is associated with brain tissue volume alterations that become more pronounced in the presence of perinatal risk factors and white matter injury. Moreover, associations between volumetric alterations as early as TEA and long-term neurodevelopmental impairments are scarce.

Calcium scoring with prospectively ECG-triggered CT: using overlapping datasets generated with MPR decreases inter-scan variability.

OBJECTIVE: To examine the feasibility of reducing the inter-scan variability of prospectively ECG-triggered calcium-scoring scans by using overlapping 3-mm datasets generated from multiplanar reformation (MPR) instead of non-overlapping 3-mm or 1.5-mm datasets. PATIENTS AND METHODS: Seventy-five women (59-79 years old) underwent two sequential prospectively ECG-triggered calcium-scoring scans with 16 mm×1.5mm collimation in one session. Between the two scans patients got off and on the table. We performed calcium scoring (Agatston and mass scores) on the following datasets: contiguous 3-mm sections reconstructed from the raw data (A), contiguous 3-mm sections from MPR (B), overlapping 3-mm sections from MPR (C) and contiguous 1.5-mm sections from the raw data (D). To determine the feasibility of the MPR approach, we compared MPR (B) with direct raw data reconstruction (A). Inter-scan variability was calculated for each type of dataset (A-D). RESULTS: Calcium scores ranged from 0 to 1455 (Agatston) and 0 to 279 mg (mass) for overlapping 3-mm sections (C). Calcium scores (both Agatston and mass) were nearly identical for MPR (B) and raw data approaches (A), with inter-quartile ranges of 0-1% for inter-scan variability. Median inter-scan variability with contiguous 3-mm sections (B) was 13% (Agatston) and 11% (mass). Median variability was reduced to 10% (Agatston and mass) with contiguous 1.5-mm sections (D) and to 8% (Agatston) and 7% (mass) with overlapping 3-mm MPR (A). CONCLUSION: Calcium scoring on MPR yields nearly identical results to calcium scoring on images directly reconstructed from raw data. Overlapping MPR from prospectively ECG-triggered scans improve inter-scan variability of calcium scoring without increasing patient radiation dose.