Computed tomographic pulmonary angiography (CTPA) is the gold standard for pulmonary embolism (PE) diagnosis. However, this diagnosis is susceptible to misdiagnosis. In this study, we aimed to ...perform a systematic review of current literature applying deep learning for the diagnosis of PE on CTPA. MEDLINE/PUBMED were searched for studies that reported on the accuracy of deep learning algorithms for PE on CTPA. The risk of bias was evaluated using the QUADAS-2 tool. Pooled sensitivity and specificity were calculated. Summary receiver operating characteristic curves were plotted. Seven studies met our inclusion criteria. A total of 36,847 CTPA studies were analyzed. All studies were retrospective. Five studies provided enough data to calculate summary estimates. The pooled sensitivity and specificity for PE detection were 0.88 (95% CI 0.803-0.927) and 0.86 (95% CI 0.756-0.924), respectively. Most studies had a high risk of bias. Our study suggests that deep learning models can detect PE on CTPA with satisfactory sensitivity and an acceptable number of false positive cases. Yet, these are only preliminary retrospective works, indicating the need for future research to determine the clinical impact of automated PE detection on patient care. Deep learning models are gradually being implemented in hospital systems, and it is important to understand the strengths and limitations of these algorithms.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
In this work we present a novel system for generation of virtual PET images using CT scans. We combine a fully convolutional network (FCN) with a conditional generative adversarial network (GAN) to ...generate simulated PET data from given input CT data. The synthesized PET can be used for false-positive reduction in lesion detection solutions. Clinically, such solutions may enable lesion detection and drug treatment evaluation in a CT-only environment, thus reducing the need for the more expensive and radioactive PET/CT scan. Our dataset includes 60 PET/CT scans from Sheba Medical center. We used 23 scans for training and 37 for testing. Different schemes to achieve the synthesized output were qualitatively compared. Quantitative evaluation was conducted using an existing lesion detection software, combining the synthesized PET as a false positive reduction layer for the detection of malignant lesions in the liver. Current results look promising showing a 28% reduction in the average false positive per case from 2.9 to 2.1. The suggested solution is comprehensive and can be expanded to additional body organs, and different modalities.
•An automated method to synthesize PET images from CT images is proposed.•A combination of cGAN and FCN is shown to achieve the best performance.•Custom loss function is shown to improve performance in clinically important regions.•Results are provided showing improvement in existing lesion detection frameworks when using the virtual-PET images .
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Abstract Objectives This study sought to examine whether imaging of the atrioventricular (AV) membranous septum (MS) by computed tomography (CT) can be used to identify patient-specific anatomic risk ...of high-degree AV block and permanent pacemaker (PPM) implantation before transcatheter aortic valve implantation (TAVI) with self-expandable valves. Background MS length represents an anatomic surrogate of the distance between the aortic annulus and the bundle of His and may therefore be inversely related to the risk of conduction system abnormalities after TAVI. Methods Seventy-three consecutive patients with severe aortic stenosis underwent contrast-enhanced CT before TAVI. The aortic annulus, aortic valve, and AV junction were assessed, and MS length was measured in the coronal view. Results In 13 patients (18%), high-degree AV block developed, and 21 patients (29%) received a PPM. Multivariable logistic regression analysis revealed MS length as the most powerful pre -procedural independent predictor of high-degree AV block (odds ratio OR: 1.35, 95% confidence interval CI: 1.1 to 1.7, p = 0.01) and PPM implantation (OR: 1.43, 95% CI: 1.1 to 1.8, p = 0.002). When taking into account pre- and post -procedural parameters, the difference between MS length and implantation depth emerged as the most powerful independent predictor of high-degree AV block (OR: 1.4, 95% CI: 1.2 to 1.7, p < 0.001), whereas the difference between MS length and implantation depth and calcification in the basal septum were the most powerful independent predictors of PPM implantation (OR: 1.39, 95% CI: 1.2 to 1.7, p < 0.001 and OR: 4.9, 95% CI: 1.2 to 20.5, p = 0.03; respectively). Conclusions Short MS, insufficient difference between MS length and implantation depth, and the presence of calcification in the basal septum, factors that may all facilitate mechanical compression of the conduction tissue by the implanted valve, predict conduction abnormalities after TAVI with self-expandable valves. CT assessment of membranous septal anatomy provides unique pre-procedural information about the patient-specific propensity for the risk of AV block.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Objectives The purpose of this study was to assess deformation dynamics and in vivo mechanical properties of the aortic annulus throughout the cardiac cycle. Background Understanding dynamic aspects ...of functional aortic valve anatomy is important for beating-heart transcatheter aortic valve implantation. Methods Thirty-five patients with aortic stenosis and 11 normal subjects underwent 256-slice computed tomography. The aortic annulus plane was reconstructed in 10% increments over the cardiac cycle. For each phase, minimum diameter, ellipticity index, cross-sectional area (CSA), and perimeter (Perim) were measured. In a subset of 10 patients, Young's elastic module was calculated from the stress-strain relationship of the annulus. Results In both subjects with normal and with calcified aortic valves, minimum diameter increased in systole (12.3 ± 7.3% and 9.8 ± 3.4%, respectively; p < 0.001), and ellipticity index decreased (12.7 ± 8.8% and 10.3 ± 2.7%, respectively; p < 0.001). The CSA increased by 11.2 ± 5.4% and 6.2 ± 4.8%, respectively (p < 0.001). Perim increase was negligible in patients with calcified valves (0.56 ± 0.85%; p < 0.001) and small even in normal subjects (2.2 ± 2.2%; p = 0.01). Accordingly, relative percentage differences between maximum and minimum values were significantly smallest for Perim compared with all other parameters. Young's modulus was calculated as 22.6 ± 9.2 MPa in patients and 13.8 ± 6.4 MPa in normal subjects. Conclusions The aortic annulus, generally elliptic, assumes a more round shape in systole, thus increasing CSA without substantial change in perimeter. Perimeter changes are negligible in patients with calcified valves, because tissue properties allow very little expansion. Aortic annulus perimeter appears therefore ideally suited for accurate sizing in transcatheter aortic valve implantation.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Objectives This study sought to determine whether alginate biomaterial can be delivered effectively into the infarcted myocardium by intracoronary injection to prevent left ventricular (LV) ...remodeling early after myocardial infarction (MI). Background Although injectable biomaterials can improve infarct healing and repair, the feasibility and effectiveness of intracoronary injection have not been studied. Methods We prepared a calcium cross-linked alginate solution that undergoes liquid to gel phase transition after deposition in infarcted myocardium. Anterior MI was induced in swine by transient balloon occlusion of left anterior descending coronary artery. At 4 days after MI, either alginate solution (2 or 4 ml) or saline was injected selectively into the infarct-related coronary artery. An additional group (n = 19) was treated with incremental volumes of biomaterial (1, 2, and 4 ml) or 2 ml saline and underwent serial echocardiography studies. Results Examination of hearts harvested after injection showed that the alginate crossed the infarcted leaky vessels and was deposited as hydrogel in the infarcted tissue. At 60 days, control swine experienced an increase in left ventricular (LV) diastolic area by 44%, LV systolic area by 45%, and LV mass by 35%. In contrast, intracoronary injection of alginate (2 and 4 ml) prevented and even reversed LV enlargement (p < 0.01). Post-mortem analysis showed that the biomaterial (2 ml) increased scar thickness by 53% compared with control (2.9 ± 0.1 mm vs. 1.9 ± 0.3 mm; p < 0.01) and was replaced by myofibroblasts and collagen. Conclusions Intracoronary injection of alginate biomaterial is feasible, safe, and effective. Our findings suggest a new percutaneous intervention to improve infarct repair and prevent adverse remodeling after reperfused MI.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Purpose
While MRI is the modality of choice for the assessment of patients with brain tumors, differentiation between various tumors based on their imaging characteristics might be challenging due to ...overlapping imaging features. The purpose of this study was to apply a machine learning scheme using basic and advanced MR sequences for distinguishing different types of brain tumors.
Methods
The study cohort included 141 patients (41 glioblastoma, 38 metastasis, 50 meningioma, and 12 primary central nervous system lymphoma). A computer-assisted classification scheme, combining morphologic MRI, perfusion MRI, and DTI metrics, was developed and used for tumor classification. The proposed multistep scheme consists of pre-processing, ROI definition, features extraction, feature selection, and classification. Feature subset selection was performed using support vector machines (SVMs). Classification performance was assessed by leave-one-out cross-validation. Given an ROI, the entire classification process was done automatically via computer and without any human intervention.
Results
A binary hierarchical classification tree was chosen. In the first step, selected features were chosen for distinguishing glioblastoma from the remaining three classes, followed by separation of meningioma from metastasis and PCNSL, and then to discriminate PCNSL from metastasis. The binary SVM classification accuracy, sensitivity and specificity for glioblastoma, metastasis, meningiomas, and primary central nervous system lymphoma were 95.7, 81.6, and 91.2%; 92.7, 95.1, and 93.6%; 97, 90.8, and 58.3%; and 91.5, 90, and 96.9%, respectively.
Conclusion
A machine learning scheme using data from anatomical and advanced MRI sequences resulted in high-performance automatic tumor classification algorithm. Such a scheme can be integrated into clinical decision support systems to optimize tumor classification.
High-resolution computed tomography (HRCT) is paramount in the assessment of interstitial lung disease (ILD). Yet, HRCT interpretation of ILDs may be hampered by inter- and intra-observer ...variability. Recently, artificial intelligence (AI) has revolutionized medical image analysis. This technology has the potential to advance patient care in ILD. We aimed to systematically evaluate the application of AI for the analysis of ILD in HRCT.
We searched MEDLINE/PubMed databases for original publications of deep learning for ILD analysis on chest CT. The search included studies published up to March 1, 2021. The risk of bias evaluation included tailored Quality Assessment of Diagnostic Accuracy Studies and the modified Joanna Briggs Institute Critical Appraisal checklist.
Data was extracted from 19 retrospective studies. Deep learning techniques included detection, segmentation, and classification of ILD on HRCT. Most studies focused on the classification of ILD into different morphological patterns. Accuracies of 78%-91% were achieved. Two studies demonstrated near-expert performance for the diagnosis of idiopathic pulmonary fibrosis (IPF). The Quality Assessment of Diagnostic Accuracy Studies tool identified a high risk of bias in 15/19 (78.9%) of the studies.
AI has the potential to contribute to the radiologic diagnosis and classification of ILD. However, the accuracy performance is still not satisfactory, and research is limited by a small number of retrospective studies. Hence, the existing published data may not be sufficiently reliable. Only well-designed prospective controlled studies can accurately assess the value of existing AI tools for ILD evaluation.
Rapid and sensitive screening tools for SARS-CoV-2 infection are essential to limit the spread of COVID-19 and to properly allocate national resources. Here, we developed a new point-of-care, ...non-contact thermal imaging tool to detect COVID-19, based on advanced image processing algorithms. We captured thermal images of the backs of individuals with and without COVID-19 using a portable thermal camera that connects directly to smartphones. Our novel image processing algorithms automatically extracted multiple texture and shape features of the thermal images and achieved an area under the curve (AUC) of 0.85 in COVID-19 detection with up to 92% sensitivity. Thermal imaging scores were inversely correlated with clinical variables associated with COVID-19 disease progression. In summary, we show, for the first time, that a hand-held thermal imaging device can be used to detect COVID-19. Non-invasive thermal imaging could be used to screen for COVID-19 in out-of-hospital settings, especially in low-income regions with limited imaging resources.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
Objective: We present a novel variant of the bag-of-visual-words (BoVW) method for automated medical image classification. Methods: Our approach improves the BoVW model by learning a task-driven ...dictionary of the most relevant visual words per task using a mutual information-based criterion. Additionally, we generate relevance maps to visualize and localize the decision of the automatic classification algorithm. These maps demonstrate how the algorithm works and show the spatial layout of the most relevant words. Results: We applied our algorithm to three different tasks: chest x-ray pathology identification (of four pathologies: cardiomegaly, enlarged mediastinum, right consolidation, and left consolidation), liver lesion classification into four categories in computed tomography (CT) images and benign/malignant clusters of microcalcifications (MCs) classification in breast mammograms. Validation was conducted on three datasets: 443 chest x-rays, 118 portal phase CT images of liver lesions, and 260 mammography MCs. The proposed method improves the classical BoVW method for all tested applications. For chest x-ray, area under curve of 0.876 was obtained for enlarged mediastinum identification compared to 0.855 using classical BoVW (with p-value <; 0.01). For MC classification, a significant improvement of 4% was achieved using our new approach (with p-value = 0.03). For liver lesion classification, an improvement of 6% in sensitivity and 2% in specificity were obtained (with p-value <; 0.001). Conclusion: We demonstrated that classification based on informative selected set of words results in significant improvement. Significance: Our new BoVW approach shows promising results in clinically important domains. Additionally, it can discover relevant parts of images for the task at hand without explicit annotations for training data. This can provide computer-aided support for medical experts in challenging image analysis tasks.
Pulmonary embolism (PE) is a common, life threatening cardiovascular emergency. Risk stratification is one of the core principles of acute PE management and determines the choice of diagnostic and ...therapeutic strategies. In routine clinical practice, clinicians rely on the patient's electronic health record (EHR) to provide a context for their medical imaging interpretation. Most deep learning models for radiology applications only consider pixel-value information without the clinical context. Only a few integrate both clinical and imaging data. In this work, we develop and compare multimodal fusion models that can utilize multimodal data by combining both volumetric pixel data and clinical patient data for automatic risk stratification of PE. Our best performing model is an intermediate fusion model that incorporates both bilinear attention and TabNet, and can be trained in an end-to-end manner. The results show that multimodality boosts performance by up to 14% with an area under the curve (AUC) of 0.96 for assessing PE severity, with a sensitivity of 90% and specificity of 94%, thus pointing to the value of using multimodal data to automatically assess PE severity.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK