scholarly journals Computer-aided molecular product-process design under property uncertainties – A Monte Carlo based optimization strategy

2019 ◽  
Vol 122 ◽  
pp. 247-257 ◽  
Author(s):  
Jérôme Frutiger ◽  
Stefano Cignitti ◽  
Jens Abildskov ◽  
John M. Woodley ◽  
Gürkan Sin
Keyword(s):  
Monte Carlo ◽  
Process Design ◽  
Optimization Strategy ◽  
Molecular Product ◽  
Computer Aided

scholarly journals Towards computer-aided severity assessment via deep neural networks for geographic and opacity extent scoring of SARS-CoV-2 chest X-rays

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
A. Wong ◽  
Z. Q. Lin ◽  
L. Wang ◽  
A. G. Chung ◽  
B. Shen ◽  
...  
Keyword(s):  
Neural Networks ◽  
Monte Carlo ◽  
Lung Disease ◽  
Disease Severity ◽  
Deep Neural Networks ◽  
Cross Validation ◽  
X Rays ◽  
Computer Aided ◽  
Monte Carlo Cross Validation ◽  
Validation Experiments

AbstractA critical step in effective care and treatment planning for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the cause for the coronavirus disease 2019 (COVID-19) pandemic, is the assessment of the severity of disease progression. Chest x-rays (CXRs) are often used to assess SARS-CoV-2 severity, with two important assessment metrics being extent of lung involvement and degree of opacity. In this proof-of-concept study, we assess the feasibility of computer-aided scoring of CXRs of SARS-CoV-2 lung disease severity using a deep learning system. Data consisted of 396 CXRs from SARS-CoV-2 positive patient cases. Geographic extent and opacity extent were scored by two board-certified expert chest radiologists (with 20+ years of experience) and a 2nd-year radiology resident. The deep neural networks used in this study, which we name COVID-Net S, are based on a COVID-Net network architecture. 100 versions of the network were independently learned (50 to perform geographic extent scoring and 50 to perform opacity extent scoring) using random subsets of CXRs from the study, and we evaluated the networks using stratified Monte Carlo cross-validation experiments. The COVID-Net S deep neural networks yielded R$$^2$$ 2 of $$0.664 \pm 0.032$$ 0.664 ± 0.032 and $$0.635 \pm 0.044$$ 0.635 ± 0.044 between predicted scores and radiologist scores for geographic extent and opacity extent, respectively, in stratified Monte Carlo cross-validation experiments. The best performing COVID-Net S networks achieved R$$^2$$ 2 of 0.739 and 0.741 between predicted scores and radiologist scores for geographic extent and opacity extent, respectively. The results are promising and suggest that the use of deep neural networks on CXRs could be an effective tool for computer-aided assessment of SARS-CoV-2 lung disease severity, although additional studies are needed before adoption for routine clinical use.

scholarly journals Quantifying the uncertainty of deep learning-based computer-aided diagnosis for patient safety

2019 ◽  
Vol 5 (1) ◽  
pp. 223-226
Author(s):  
Max-Heinrich Laves ◽  
Sontje Ihler ◽  
Tobias Ortmaier ◽  
Lüder A. Kahrs
Keyword(s):  
Monte Carlo ◽  
Patient Safety ◽  
Deep Learning ◽  
Epistemic Uncertainty ◽  
Computer Aided Diagnosis ◽  
Uncertainty Estimation ◽  
Test Time ◽  
Prediction Uncertainty ◽  
Computer Aided ◽  
Aided Diagnosis

AbstractIn this work, we discuss epistemic uncertainty estimation obtained by Bayesian inference in diagnostic classifiers and show that the prediction uncertainty highly correlates with goodness of prediction. We train the ResNet-18 image classifier on a dataset of 84,484 optical coherence tomography scans showing four different retinal conditions. Dropout is added before every building block of ResNet, creating an approximation to a Bayesian classifier. Monte Carlo sampling is applied with dropout at test time for uncertainty estimation. In Monte Carlo experiments, multiple forward passes are performed to get a distribution of the class labels. The variance and the entropy of the distribution is used as metrics for uncertainty. Our results show strong correlation with ρ = 0.99 between prediction uncertainty and prediction error. Mean uncertainty of incorrectly diagnosed cases was significantly higher than mean uncertainty of correctly diagnosed cases. Modeling of the prediction uncertainty in computer-aided diagnosis with deep learning yields more reliable results and is therefore expected to increase patient safety. This will help to transfer such systems into clinical routine and to increase the acceptance of machine learning in diagnosis from the standpoint of physicians and patients.

View-independent Modeling of Lighting Systems by Local Estimations of the Monte Carlo Method

Vestnik MEI ◽  
2021 ◽  
Vol 1 (1) ◽  
pp. 70-75
Author(s):  
Vladimir P. Budak ◽  
◽  
Viktor S. Zheltov ◽  
Tatyana V. Meshkova ◽  
Viktor D. Chembaev ◽  
...  
Keyword(s):  
Monte Carlo ◽  
Angular Distribution ◽  
Monte Carlo Method ◽  
Light Source ◽  
Global Illumination ◽  
The Monte Carlo Method ◽  
Computer Aided ◽  
Radiosity Equation ◽  
Lighting Systems ◽  
Independent Calculation

Computer-aided designing of lighting systems has been remaining of relevance for more than ten years. The most popular CAD packages for calculating lighting systems, such as DIAlux and Relux, are based on solving the radiosity equation. By using this equation, the illuminance distributions can be modeled, based on which the standardized quantitative lighting characteristics can be calculated. However, the human eye perceives brightness, not illuminance. The qualitative parameters of lighting are closely linked with the spatial-angular distribution of brightness, for calculation of which it is necessary to solve the global illumination equation. An analysis of the engineering matters concerned with designing of lighting systems points to the obvious need for a so-called view-independent calculation of lighting scenes, which means the possibility to visually represent a scene from different positions of sighting (a camera). The approach based on local estimations of the Monte Carlo method as one of efficient techniques for solving the global illumination equation is considered, and an algorithm for view-independent modeling based on the local estimations method is presented. Various algorithms for solving the problem of searching the intersection for the casted beams from a light source with the studied illumination scene are investigated.

Sign in / Sign up

Export Citation Format

Share Document