RESUMO
BACKGROUND: Machine learning (ML) models have been proposed to predict risk related to transvenous lead extraction (TLE). OBJECTIVE: The purpose of this study was to test whether integrating imaging data into an existing ML model increases its ability to predict major adverse events (MAEs; procedure-related major complications and procedure-related deaths) and lengthy procedures (≥100 minutes). METHODS: We hypothesized certain features-(1) lead angulation, (2) coil percentage inside the superior vena cava (SVC), and (3) number of overlapping leads in the SVC-detected from a pre-TLE plain anteroposterior chest radiograph (CXR) would improve prediction of MAE and long procedural times. A deep-learning convolutional neural network was developed to automatically detect these CXR features. RESULTS: A total of 1050 cases were included, with 24 MAEs (2.3%) . The neural network was able to detect (1) heart border with 100% accuracy; (2) coils with 98% accuracy; and (3) acute angle in the right ventricle and SVC with 91% and 70% accuracy, respectively. The following features significantly improved MAE prediction: (1) ≥50% coil within the SVC; (2) ≥2 overlapping leads in the SVC; and (3) acute lead angulation. Balanced accuracy (0.74-0.87), sensitivity (68%-83%), specificity (72%-91%), and area under the curve (AUC) (0.767-0.962) all improved with imaging biomarkers. Prediction of lengthy procedures also improved: balanced accuracy (0.76-0.86), sensitivity (75%-85%), specificity (63%-87%), and AUC (0.684-0.913). CONCLUSION: Risk prediction tools integrating imaging biomarkers significantly increases the ability of ML models to predict risk of MAE and long procedural time related to TLE.
Assuntos
Remoção de Dispositivo , Aprendizado de Máquina , Humanos , Masculino , Feminino , Remoção de Dispositivo/métodos , Medição de Risco/métodos , Idoso , Desfibriladores Implantáveis/efeitos adversos , Estudos Retrospectivos , Veia Cava Superior/diagnóstico por imagem , Pessoa de Meia-Idade , Redes Neurais de Computação , BiomarcadoresRESUMO
Background: Delayed enhancement CT (CT-DE) has been evaluated as a tool for the detection of myocardial scar and compares well to the gold standard of MRI with late gadolinium enhancement (MRI-LGE). Prior work has established that high performance can be achieved with manual reading; however, few studies have looked at quantitative measures to differentiate scar and healthy myocardium on CT-DE or automated analysis. Methods: Eighteen patients with clinically indicated MRI-LGE were recruited for CT-DE at multiple 80 and 100 kV post contrast imaging. Left ventricle segmentation was performed on both imaging modalities, along with scar segmentation on MRI-LGE. Segmentations were registered together and scar regions were estimated on CT-DE. 93 radiomic features were calculated and analysed for their ability to differentiate between scarred and non-scarred myocardium regions. Machine learning (ML) classifiers were trained using the strongest set of radiomic features to classify segments containing scar on CT-DE. Features and classifiers were compared across both tube voltages and combined-energy images. Results: There were 59 and 51 statistically significant features in the 80 and 100 kV images respectively. Combined-energy imaging increased this to 63 with more features having area under the curve (AUC) above 0.9. The 10 highest AUC features for each image were used in the ML classifiers. The 100 kV images produced the best ML classifier, a support vector machine with an AUC of 0.88 (95% CI 0.87-0.90). Comparable performance was achieved with both the 80 kV and combined-energy images. Conclusions: CT-DE can be quantitatively analyzed using radiomic feature calculations. These features may be suitable for ML classification techniques to prospectively identify AHA segments with performance comparable to previously reported manual reading. Future work on larger CT-DE datasets is warranted to establish optimum imaging parameters and features.
RESUMO
OBJECTIVES: The aim of this study is to develop an automated method of regional scar detection on clinically standard computed tomography angiography (CTA) using encoder-decoder networks with latent space classification. BACKGROUND: Localising scar in cardiac patients can assist in diagnosis and guide interventions. Magnetic resonance imaging (MRI) with late gadolinium enhancement (LGE) is the clinical gold standard for scar imaging; however, it is commonly contraindicated. CTA is an alternative imaging modality that has fewer contraindications and is widely used as a first-line imaging modality of cardiac applications. METHODS: A dataset of 79 patients with both clinically indicated MRI LGE and subsequent CTA scans was used to train and validate networks to classify septal and lateral scar presence within short axis left ventricle slices. Two designs of encoder-decoder networks were compared, with one encoding anatomical shape in the latent space. Ground truth was established by segmenting scar in MRI LGE and registering this to the CTA images. Short axis slices were taken from the CTA, which served as the input to the networks. An independent external set of 22 cases (27% the size of the cross-validation set) was used to test the best network. RESULTS: A network classifying lateral scar only achieved an area under ROC curve of 0.75, with a sensitivity of 0.79 and specificity of 0.62 on the independent test set. The results of septal scar classification were poor (AUC < 0.6) for all networks. This was likely due to a high class imbalance. The highest AUC network encoded anatomical shape information in the network latent space, indicating it was important for the successful classification of lateral scar. CONCLUSIONS: Automatic lateral wall scar detection can be performed from a routine cardiac CTA with reasonable accuracy, without any scar specific imaging. This requires only a single acquisition in the cardiac cycle. In a clinical setting, this could be useful for pre-procedure planning, especially where MRI is contraindicated. Further work with more septal scar present is warranted to improve the usefulness of this approach.
Assuntos
Meios de Contraste , Ventrículos do Coração , Humanos , Ventrículos do Coração/diagnóstico por imagem , Cicatriz/diagnóstico por imagem , Gadolínio , Imageamento por Ressonância Magnética/métodos , AngiografiaRESUMO
BACKGROUND: Transvenous lead extraction (TLE) remains a high-risk procedure. OBJECTIVE: The purpose of this study was to develop a machine learning (ML)-based risk stratification system to predict the risk of major adverse events (MAEs) after TLE. A MAE was defined as procedure-related major complication and procedure-related death. METHODS: We designed and evaluated an ML-based risk stratification system trained using the European Lead Extraction ConTRolled (ELECTRa) registry to predict the risk of MAEs in 3555 patients undergoing TLE and tested this on an independent registry of 1171 patients. ML models were developed, including a self-normalizing neural network (SNN), stepwise logistic regression model ("stepwise model"), support vector machines, and random forest model. These were compared with the ELECTRa Registry Outcome Score (EROS) for MAEs. RESULTS: There were 53 MAEs (1.7%) in the training cohort and 24 (2.4%) in the test cohort. Thirty-two clinically important features were used to train the models. ML techniques were similar to EROS by balanced accuracy (stepwise model: 0.74 vs EROS: 0.70) and superior by area under the curve (support vector machines: 0.764 vs EROS: 0.677). The SNN provided a finite risk for MAE and accurately identified MAE in 14 of 169 "high (>80%) risk" patients (8.3%) and no MAEs in all 198 "low (<20%) risk" patients (100%). CONCLUSION: ML models incrementally improved risk prediction for identifying those at risk of MAEs. The SNN has the additional advantage of providing a personalized finite risk assessment for patients. This may aid patient decision making and allow better preoperative risk assessment and resource allocation.
Assuntos
Desfibriladores Implantáveis , Marca-Passo Artificial , Desfibriladores Implantáveis/efeitos adversos , Remoção de Dispositivo/efeitos adversos , Remoção de Dispositivo/métodos , Humanos , Aprendizado de Máquina , Marca-Passo Artificial/efeitos adversos , Sistema de RegistrosRESUMO
PURPOSE: Reducing X-ray dose increases safety in cardiac electrophysiology procedures but also increases image noise and artifacts which may affect the discernibility of devices and anatomical cues. Previous denoising methods based on convolutional neural networks (CNNs) have shown improvements in the quality of low-dose X-ray fluoroscopy images but may compromise clinically important details required by cardiologists. METHODS: In order to obtain denoised X-ray fluoroscopy images whilst preserving details, we propose a novel deep-learning-based denoising framework, namely edge-enhancement densenet (EEDN), in which an attention-awareness edge-enhancement module is designed to increase edge sharpness. In this framework, a CNN-based denoiser is first used to generate an initial denoising result. Contours representing edge information are then extracted using an attention block and a group of interacted ultra-dense blocks for edge feature representation. Finally, the initial denoising result and enhanced edges are combined to generate the final X-ray image. The proposed denoising framework was tested on a total of 3262 clinical images taken from 100 low-dose X-ray sequences acquired from 20 patients. The performance was assessed by pairwise voting from five cardiologists as well as quantitative indicators. Furthermore, we evaluated our technique's effect on catheter detection using 416 images containing coronary sinus catheters in order to examine its influence as a pre-processing tool. RESULTS: The average signal-to-noise ratio of X-ray images denoised with EEDN was 24.5, which was 2.2 times higher than that of the original images. The accuracy of catheter detection from EEDN denoised sequences showed no significant difference compared with their original counterparts. Moreover, EEDN received the highest average votes in our clinician assessment when compared to our existing technique and the original images. CONCLUSION: The proposed deep learning-based framework shows promising capability for denoising interventional X-ray fluoroscopy images. The results from the catheter detection show that the network does not affect the results of such an algorithm when used as a pre-processing step. The extensive qualitative and quantitative evaluations suggest that the network may be of benefit to reduce radiation dose when applied in real time in the catheter laboratory.
Assuntos
Técnicas Eletrofisiológicas Cardíacas , Redes Neurais de Computação , Fluoroscopia , Humanos , Razão Sinal-Ruído , Raios XRESUMO
BACKGROUND: Longer-term outcomes of patients post transvenous lead extraction (TLE) are poorly understood in patients with cardiac resynchronization therapy (CRT) devices. OBJECTIVES: A propensity score (PS)-matched analysis evaluating outcomes post TLE in CRT and non-CRT populations was performed. METHODS: Data from consecutive patients undergoing TLE between 2000 and 2019 were prospectively collected. Patients surviving to discharge and reimplanted with the same device were included. The cohort was split depending on presence of CRT device. Associations with all-cause mortality and hospitalization were assessed by Kaplan-Meier estimates. An exploratory endpoint was evaluated whether early (<7 days) or late (>7 days) reimplantation was associated with poorer outcomes. RESULTS: Of 1005 patients included, 285 (25%) had a CRT device. Median follow-up was 57.00 [27.00-93.00] months, age at explant was 67.7 ± 12.1 years, 83.3% were male, and 54.4% had an infective indication for TLE. PS was calculated using 43 baseline characteristics. After matching, 192 CRT patients were compared with 192 non-CRT patients. In the matched cohort, no significant difference with respect to mortality (hazard ratio [HR] = 1.01, 95% confidence interval [CI] [0.74-1.39], P = .093) or hospitalization risk (HR = 1.2, 95% CI [0.87-1.66], P = .265) was observed. In the matched CRT group, late reimplantation was associated with increased mortality (HR = 1.64, [1.04-2.57], P = .032) and hospitalization risk (HR = 1.57, 95% CI [1.00-2.46], P = .049]. CONCLUSION: Outcomes of CRT patients post TLE are similarly as poor as those of non-CRT patients in matched populations. Reimplantation within 7 days was associated with better outcomes in a CRT population but was not observed in a non-CRT population, suggesting prolonged periods without biventricular pacing should be avoided.
RESUMO
Objectives: The aim of this study is to develop a scar detection method for routine computed tomography angiography (CTA) imaging using deep convolutional neural networks (CNN), which relies solely on anatomical information as input and is compatible with existing clinical workflows. Background: Identifying cardiac patients with scar tissue is important for assisting diagnosis and guiding interventions. Late gadolinium enhancement (LGE) magnetic resonance imaging (MRI) is the gold standard for scar imaging; however, there are common instances where it is contraindicated. CTA is an alternative imaging modality that has fewer contraindications and is faster than Cardiovascular magnetic resonance imaging but is unable to reliably image scar. Methods: A dataset of LGE MRI (200 patients, 83 with scar) was used to train and validate a CNN to detect ischemic scar slices using segmentation masks as input to the network. MRIs were segmented to produce 3D left ventricle meshes, which were sampled at points along the short axis to extract anatomical masks, with scar labels from LGE as ground truth. The trained CNN was tested with an independent CTA dataset (25 patients, with ground truth established with paired LGE MRI). Automated segmentation was performed to provide the same input format of anatomical masks for the network. The CNN was compared against manual reading of the CTA dataset by 3 experts. Results: Note that 84.7% cross-validated accuracy (AUC: 0.896) for detecting scar slices in the left ventricle on the MRI data was achieved. The trained network was tested against the CTA-derived data, with no further training, where it achieved an 88.3% accuracy (AUC: 0.901). The automated pipeline outperformed the manual reading by clinicians. Conclusion: Automatic ischemic scar detection can be performed from a routine cardiac CTA, without any scar-specific imaging or contrast agents. This requires only a single acquisition in the cardiac cycle. In a clinical setting, with near zero additional cost, scar presence could be detected to triage images, reduce reading times, and guide clinical decision-making.
RESUMO
Retrospective gated cardiac computed tomography (CCT) images can provide high contrast and resolution images of the heart throughout the cardiac cycle. Feature tracking in retrospective CCT images using the temporal sparse free-form deformations (TSFFDs) registration method has previously been optimised for the left ventricle (LV). However, there is limited work on optimising nonrigid registration methods for feature tracking in the left atria (LA). This paper systematically optimises the sparsity weight (SW) and bending energy (BE) as two hyperparameters of the TSFFD method to track the LA endocardium from end-diastole (ED) to end-systole (ES) using 10-frame retrospective gated CCT images. The effect of two different control point (CP) grid resolutions was also investigated. TSFFD optimisation was achieved using the average surface distance (ASD), directed Hausdorff distance (DHD) and Dice score between the registered and ground truth surface meshes and segmentations at ES. For baseline comparison, the configuration optimised for LV feature tracking gave errors across the cohort of 0.826 ± 0.172mm ASD, 5.882 ± 1.524mm DHD, and 0.912 ± 0.033 Dice score. Optimising the SW and BE hyperparameters improved the TSFFD performance in tracking LA features, with case specific optimisations giving errors across the cohort of 0.750 ± 0.144mm ASD, 5.096 ± 1.246mm DHD, and 0.919 ± 0.029 Dice score. Increasing the CP resolution and optimising the SW and BE further improved tracking performance, with case specific optimisation errors of 0.372 ± 0.051mm ASD, 2.739 ± 0.843mm DHD and 0.949 ± 0.018 Dice score across the cohort. We therefore show LA feature tracking using TSFFDs is improved through a chamber-specific optimised configuration.
RESUMO
BACKGROUND: Multi-tracer PET/SPECT imaging enables different modality tracers to be present simultaneously, allowing multiple physiological processes to be imaged in the same subject, within a short time-frame. Fluorine-18 and technetium-99m, two commonly used PET and SPECT radionuclides, respectively, possess different emission profiles, offering the potential for imaging one in the presence of the other. However, the impact of the presence of each radionuclide on scanning the other could be significant and lead to confounding results. Here we use combinations of 18F and 99mTc to explore the challenges posed by dual tracer PET/SPECT imaging, and investigate potential practical ways to overcome them. METHODS: Mixed-radionuclide 18F/99mTc phantom PET and SPECT imaging experiments were carried out to determine the crossover effects of each radionuclide on the scans using Mediso nanoScan PET/CT and SPECT/CT small animal scanners. RESULTS: PET scan image quality and quantification were adversely affected by 99mTc activities higher than 100 MBq due to a high singles rate increasing dead-time of the detectors. Below 100 MBq 99mTc, PET scanner quantification accuracy was preserved. SPECT scan image quality and quantification were adversely affected by the presence of 18F due to Compton scattering of 511 keV photons leading to over-estimation of 99mTc activity and increased noise. However, 99mTc:18F activity ratios of > 70:1 were found to mitigate this effect completely on the SPECT. A method for correcting for Compton scatter was also explored. CONCLUSION: Suitable combinations of injection sequence and imaging sequence can be devised to meet specific experimental multi-tracer imaging needs, with only minor or insignificant effects of each radionuclide on the scan of the other.
RESUMO
The Mawat ophiolite, NE Iraq, is one of the Neo-Tethyan ophiolites within the Iraqi Zagros orogen. It consists of many metre-to kilometre-sized tectonic slices of serpentinized dunite, peridotite, gabbro, basaltic rocks and associated oceanic metasediments. Felsic intrusions crosscut the ophiolite. We present U-Pb zircon and monazite ages and Hf zircon isotopes from two crosscutting felsic dykes and a gabbro from the mantle section of the ophiolite. Zircons from the felsic dykes contain spongy domains and xenotime and monazite inclusions. They give ages from 222 to 46 Ma. The age range is interpreted to be caused by secondary processes such as radiogenic Pb mobility and Pb loss. The monazite age of 94.6 ± 1.2 Ma is considered to give a crystallisation age of the felsic dykes. The gabbro zircons give ages between 81 to 38 Ma of which the two oldest grains give the weighted average age of 81.2 ± 2.5 Ma which we interpret to be the crystallisation age of the gabbro. The zircon initial εHf values in the felsic dykes are negative (averages -2.7 and -3.1) while they in the gabbro are positive (average + 3.5), indicating that the felsic magma comes from an older source while the mafic magma comes from a juvenile one. Two mafic units of different ages were identified: the older unit is cut by the 95 Ma felsic dykes and the younger one is represented by the 81 Ma gabbro located within a thrust zone. The youngest ages of 40 Ma are considered to be related to crustal extension.
RESUMO
In this paper we introduce a new Android library, called ULTEMAT, for the delivery of ecological momentary assessments (EMAs) on mobile devices and we present its use in the MoodBuster app developed in the H2020 E-COMPARED project. We discuss context-aware, or event-based, triggers for the presentation of EMAs and discuss the potential they have to improve the effectiveness of mobile provision of mental health interventions as they allow for the delivery of assessments to the patients when and where these are most appropriate. Following this, we present the abilities of ULTEMAT to use such context-aware triggers to schedule EMAs and we discuss how a similar approach can be used for Ecological Momentary Interventions (EMIs).
RESUMO
Falls are a societal and economic problem of great concern with large parts of the population, in particular older citizens, at significant risk and the result of a fall often being grave. It has long been established that it is of importance to provide help to a faller soon after the event to prevent complications and this can be achieved with a fall monitor. Yet, the practical use of currently available fall monitoring solutions is limited due to accuracy, usability, cost, and, not in the least, the stigmatising effect of many solutions. This paper proposes a fall sensor concept that can be embedded in the user's footwear and discusses algorithms, software and hardware developed. Sensor performance is illustrated using results of a series of functional tests. These show that the developed sensor can be used for the accurate measurement of various mobility and gait parameters and that falls are detected accurately.