Deep-Learning-Based Feature Encoding of Clinical Parameters for Patient Specific CTA Dose Optimization

2021 ◽  
pp. 315-322
Author(s):  
Marja Fleitmann ◽  
Hristina Uzunova ◽  
Andreas Martin Stroth ◽  
Jan Gerlach ◽  
Alexander Fürschke ◽  
...  
Keyword(s):  
Deep Learning ◽  
Patient Specific ◽  
Dose Optimization ◽  
Clinical Parameters ◽  
Feature Encoding

scholarly journals Assessment of patient specific information in the wild on fundus photography and optical coherence tomography

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Marion R. Munk ◽  
Thomas Kurmann ◽  
Pablo Márquez-Neila ◽  
Martin S. Zinkernagel ◽  
Sebastian Wolf ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cross Sections ◽  
Underlying Disease ◽  
Geographic Atrophy ◽  
Clinical Population ◽  
Fundus Photography ◽  
Peak Performance ◽  
Patient Specific ◽  
Specific Information ◽  
Fundus Images

AbstractIn this paper we analyse the performance of machine learning methods in predicting patient information such as age or sex solely from retinal imaging modalities in a heterogeneous clinical population. Our dataset consists of N = 135,667 fundus images and N = 85,536 volumetric OCT scans. Deep learning models were trained to predict the patient’s age and sex from fundus images, OCT cross sections and OCT volumes. For sex prediction, a ROC AUC of 0.80 was achieved for fundus images, 0.84 for OCT cross sections and 0.90 for OCT volumes. Age prediction mean absolute errors of 6.328 years for fundus, 5.625 years for OCT cross sections and 4.541 for OCT volumes were observed. We assess the performance of OCT scans containing different biomarkers and note a peak performance of AUC = 0.88 for OCT cross sections and 0.95 for volumes when there is no pathology on scans. Performance drops in case of drusen, fibrovascular pigment epitheliuum detachment and geographic atrophy present. We conclude that deep learning based methods are capable of classifying the patient’s sex and age from color fundus photography and OCT for a broad spectrum of patients irrespective of underlying disease or image quality. Non-random sex prediction using fundus images seems only possible if the eye fovea and optic disc are visible.

scholarly journals Prediction of 3D Cardiovascular hemodynamics before and after coronary artery bypass surgery via deep learning

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Gaoyang Li ◽  
Haoran Wang ◽  
Mingzi Zhang ◽  
Simon Tupin ◽  
Aike Qiao ◽  
...  
Keyword(s):  
Deep Learning ◽  
Artery Bypass ◽  
Computational Cost ◽  
Specific Model ◽  
Arterial System ◽  
Patient Specific ◽  
Cardiovascular Hemodynamics ◽  
Before And After ◽  
Deep Learning Network ◽  
Cfd Method

AbstractThe clinical treatment planning of coronary heart disease requires hemodynamic parameters to provide proper guidance. Computational fluid dynamics (CFD) is gradually used in the simulation of cardiovascular hemodynamics. However, for the patient-specific model, the complex operation and high computational cost of CFD hinder its clinical application. To deal with these problems, we develop cardiovascular hemodynamic point datasets and a dual sampling channel deep learning network, which can analyze and reproduce the relationship between the cardiovascular geometry and internal hemodynamics. The statistical analysis shows that the hemodynamic prediction results of deep learning are in agreement with the conventional CFD method, but the calculation time is reduced 600-fold. In terms of over 2 million nodes, prediction accuracy of around 90%, computational efficiency to predict cardiovascular hemodynamics within 1 second, and universality for evaluating complex arterial system, our deep learning method can meet the needs of most situations.

scholarly journals Deep learning for automatic quantification of lung abnormalities in COVID-19 patients: First experience and correlation with clinical parameters

2020 ◽  
Vol 7 ◽  
pp. 100272
Author(s):  
Victor Mergen ◽  
Adrian Kobe ◽  
Christian Blüthgen ◽  
André Euler ◽  
Thomas Flohr ◽  
...  
Keyword(s):  
Deep Learning ◽  
Clinical Parameters ◽  
Automatic Quantification ◽  
Lung Abnormalities

scholarly journals Detecting Cardiomyopathies in Pregnancy and the Postpartum Period with an Electrocardiogram-Based Deep Learning Model

2021 ◽  
Author(s):  
Demilade A Adedinsewo ◽  
Patrick W Johnson ◽  
Erika J Douglass ◽  
Itzhak Zachi Attia ◽  
Sabrina D Phillips ◽  
...  
Keyword(s):  
Deep Learning ◽  
Natriuretic Peptides ◽  
Postpartum Period ◽  
Learning Model ◽  
Left Ventricular ◽  
Left Ventricular Ejection ◽  
Clinical Parameters ◽  
Multivariable Model ◽  
Ventricular Ejection Fraction ◽  
Deep Learning Model

Abstract Aims Cardiovascular disease is a major threat to maternal health, with cardiomyopathy being among the most common acquired cardiovascular diseases during pregnancy and the postpartum period. The aim of our study was to evaluate the effectiveness of an electrocardiogram (ECG)-based deep learning model in identifying cardiomyopathy during pregnancy and the postpartum period. Methods and Results We used an ECG-based deep learning model to detect cardiomyopathy in a cohort of women who were pregnant or in the postpartum period seen at Mayo Clinic. Model performance was evaluated using area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. We compared the diagnostic probabilities of the deep learning model with natriuretic peptides and a multivariable model consisting of demographic and clinical parameters. The study cohort included 1,807 women; 7%, 10%, and 13% had left ventricular ejection fraction (LVEF) of 35% or less, less than 45%, and less than 50%, respectively. The ECG-based deep learning model identified cardiomyopathy with AUCs of 0.92 (LVEF ≤35%), 0.89 (LVEF <45%), and 0.87 (LVEF <50%). For LVEF of 35% or less, AUC was higher in Black (0.95) and Hispanic (0.98) women compared to White (0.91). Natriuretic peptides and the multivariable model had AUCs of 0.85 to 0.86 and 0.72, respectively. Conclusions An ECG-based deep learning model effectively identifies cardiomyopathy during pregnancy and the postpartum period and outperforms natriuretic peptides and traditional clinical parameters with the potential to become a powerful initial screening tool for cardiomyopathy in the obstetric care setting.

scholarly journals Deep Learning Based Proarrhythmia Analysis Using Field Potentials Recorded from Human Pluripotent Stem Cells Derived Cardiomyocytes

2018 ◽  
Author(s):  
Zeinab Golgooni ◽  
Sara Mirsadeghi ◽  
Mahdieh Soleymani Baghshah ◽  
Pedram Ataee ◽  
Hossein Baharvand ◽  
...  
Keyword(s):  
Neural Network ◽  
Stem Cells ◽  
Deep Learning ◽  
Pluripotent Stem Cells ◽  
Field Potential ◽  
Input Sequence ◽  
Patient Specific ◽  
Field Potentials ◽  
Drug Induced

AbstractAimAn early characterization of drug-induced cardiotoxicity may be possible by combining comprehensive in vitro pro-arrhythmia assay and deep learning techniques. The goal of this study was to develop a deep learning method to automatically detect irregular beating rhythm as well as abnormal waveforms of field potentials in an in vitro cardiotoxicity assay using human pluripotent stem cell (hPSC) derived cardiomyocytes and multi-electrode array (MEA) system.Methods and ResultsWe included field potential waveforms from 380 experiments which obtained by application of some cardioactive drugs on healthy and/or patient-specific induced pluripotent stem cells derived cardiomyocytes (iPSC-CM). We employed convolutional and recurrent neural networks, in order to develop a new method for automatic classification of field potential recordings without using any hand-engineered features. In the proposed method, a preparation phase was initially applied to split 60-second long recordings into a series of 5-second long windows. Thereafter, the classification phase comprising of two main steps was designed. In the first step, 5-second long windows were classified using a designated convolutional neural network (CNN). In the second step, the results of 5-second long window assessments were used as the input sequence to a recurrent neural network (RNN). The output was then compared to electrophysiologist-level arrhythmia (irregularity or abnormal waveforms) detection, resulting in 0.84 accuracy, 0.84 sensitivity, 0.85 specificity, and 0.88 precision.ConclusionA novel deep learning approach based on a two-step CNN-RNN method can be used for automated analysis of “irregularity or abnormal waveforms” in an in vitro model of cardiotoxicity experiments.

A deep learning-based prediction model for gamma evaluation in patient-specific quality assurance

2018 ◽  
Vol 45 (9) ◽  
pp. 4055-4065 ◽  
Author(s):  
Seiji Tomori ◽  
Noriyuki Kadoya ◽  
Yoshiki Takayama ◽  
Tomohiro Kajikawa ◽  
Katsumi Shima ◽  
...  
Keyword(s):  
Quality Assurance ◽  
Deep Learning ◽  
Prediction Model ◽  
Patient Specific ◽  
Gamma Evaluation

scholarly journals Diagnostic Performance of Deep LearnIng AlgoriThm for Analysis of Computed Tomography Myocardial PerfusION

2021 ◽  
Author(s):  
Giuseppe Muscogiuri ◽  
Mattia Chiesa ◽  
Andrea Baggiano ◽  
Pierino Spadafora ◽  
Rossella De Santis ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Diagnostic Accuracy ◽  
Learning Algorithm ◽  
Significant Coronary Artery Disease ◽  
Patient Specific ◽  
Fractional Flow ◽  
Flow Reserve ◽  
Specific Sensitivity ◽  
Sensitivity Specificity

Abstract Purpose: Artificial intelligence could play a key role in cardiac imaging analysis. To evaluate the diagnostic accuracy of a deep learning (DL) algorithm predicting hemodynamically significant coronary artery disease (CAD) by using a rest dataset of myocardial computed tomography perfusion (CTP) as compared to invasive evaluation. Methods: One hundred and twelve consecutive symptomatic patients scheduled for clinically indicated invasive coronary angiography (ICA) underwent CCTA plus static stress CTP and ICA with invasive fractional flow reserve (FFR) for stenoses ranging between 30% and 80%. Subsequently, a DL algorithm for the prediction of significant CAD by using the rest dataset (CTP-DLrest) and stress dataset (CTP-DLstress) was developed. The diagnostic accuracy for identification of significant CAD using CCTA, CCTA+CTPStress, CCTA+CTP-DLrest, and CCTA+CTP-DLstress were measured and compared. The time of analysis for CTPStress, CTP-DLrest and CTP-DLStress were recorded. Results: Patient-specific sensitivity, specificity, NPV, PPV, accuracy and area under the curve (AUC) of CCTA alone and CCTA+CTPStress were 100%, 33%, 100%, 54%, 63%, 67% and 86%, 89%, 89%, 86%, 88%, 87%, respectively. Patient-specific sensitivity, specificity, NPV, PPV, accuracy and AUC of CCTA+DLrest and CCTA+DLstress were 100%, 72%, 100%, 74%, 84%, 96% and 93%, 83%, 94%, 81%,88%,98%, respectively. All CCTA+CTPStress, CCTA+CTP-DLRest and CCTA+CTP-DLStress significantly improved detection of hemodynamically significant CAD (p<0.01).Time of CTP-DL was significantly lower as compared to human analysis (39.2±3.2 vs. 379.6±68.0 seconds, p<0.001).Conclusion: Evaluation of myocardial ischemia using a DL approach on rest CTP datasets is feasible and accurate. This approach may be a useful gatekeeper prior to CTPStress.

scholarly journals Explaining decisions of Graph Convolutional Neural Networks: patient-specific molecular subnetworks responsible for metastasis prediction in breast cancer

2020 ◽  
Author(s):  
Hryhorii Chereda ◽  
Annalen Bleckmann ◽  
Kerstin Menck ◽  
Júlia Perera-Bel ◽  
Philip Stegmaier ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Gene Expression ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Gene Expression Data ◽  
Molecular Network ◽  
Patient Specific ◽  
Expression Data ◽  
Learning Methods

AbstractMotivationContemporary deep learning approaches show cutting-edge performance in a variety of complex prediction tasks. Nonetheless, the application of deep learning in healthcare remains limited since deep learning methods are often considered as non-interpretable black-box models. Layer-wise Relevance Propagation (LRP) is a technique to explain decisions of deep learning methods. It is widely used to interpret Convolutional Neural Networks (CNNs) applied on image data. Recently, CNNs started to extend towards non-euclidean domains like graphs. Molecular networks are commonly represented as graphs detailing interactions between molecules. Gene expression data can be assigned to the vertices of these graphs. In other words, gene expression data can be structured by utilizing molecular network information as prior knowledge. Graph-CNNs can be applied to structured gene expression data, for example, to predict metastatic events in breast cancer. Therefore, there is a need for explanations showing which part of a molecular network is relevant for predicting an event, e.g. distant metastasis in cancer, for each individual patient.ResultsWe extended the procedure of LRP to make it available for Graph-CNN and tested its applicability on a large breast cancer dataset. We present Graph Layer-wise Relevance Propagation (GLRP) as a new method to explain the decisions made by Graph-CNNs. We demonstrate a sanity check of the developed GLRP on a hand-written digits dataset, and then applied the method on gene expression data. We show that GLRP provides patient-specific molecular subnetworks that largely agree with clinical knowledge and identify common as well as novel, and potentially druggable, drivers of tumor progression. As a result this method could be potentially highly useful on interpreting classification results on the individual patient level, as for example in precision medicine approaches or a molecular tumor board.Availabilityhttps://gitlab.gwdg.de/UKEBpublic/graph-lrphttps://frankkramer-lab.github.io/MetaRelSubNetVis/[email protected]

Sign in / Sign up

Export Citation Format

Share Document