Generating pseudo‐CT scan images from MRI images using machine learning algorithms based on fuzzy theory for radiotherapy treatment planning

2021 ◽  
Author(s):  
Niloofar Yousefi Moteghaed ◽  
Ahmad Mostaar ◽  
Payam Azadeh
Keyword(s):  
Machine Learning ◽  
Ct Scan ◽  
Treatment Planning ◽  
Fuzzy Theory ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Radiotherapy Treatment Planning ◽  
Radiotherapy Treatment

scholarly journals Certain Investigations on the Application of Machine learning Algorithms and Deep Learning Architectures for Covid -19 Diagnosis

2021 ◽  
Author(s):  
Soundariya R.S. ◽  
◽  
Tharsanee R.M. ◽  
Vishnupriya B ◽  
Ashwathi R ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Mathematical Models ◽  
Ct Scan ◽  
Virus Disease ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
X Ray ◽  
Laboratory Test Results ◽  
Learning Architectures

Corona virus disease (Covid - 19) has started to promptly spread worldwide from April 2020 till date, leading to massive death and loss of lives of people across various countries. In accordance to the advices of WHO, presently the diagnosis is implemented by Reverse Transcription Polymerase Chain Reaction (RT- PCR) testing, that incurs four to eight hours’ time to process test samples and adds 48 hours to categorize whether the samples are positive or negative. It is obvious that laboratory tests are time consuming and hence a speedy and prompt diagnosis of the disease is extremely needed. This can be attained through several Artificial Intelligence methodologies for prior diagnosis and tracing of corona diagnosis. Those methodologies are summarized into three categories: (i) Predicting the pandemic spread using mathematical models (ii) Empirical analysis using machine learning models to forecast the global corona transition by considering susceptible, infected and recovered rate. (iii) Utilizing deep learning architectures for corona diagnosis using the input data in the form of X-ray images and CT scan images. When X-ray and CT scan images are taken into account, supplementary data like medical signs, patient history and laboratory test results can also be considered while training the learning model and to advance the testing efficacy. Thus the proposed investigation summaries the several mathematical models, machine learning algorithms and deep learning frameworks that can be executed on the datasets to forecast the traces of COVID-19 and detect the risk factors of coronavirus.

Abstract WMP101: Prediction of Clinical Outcome in Supratentorial Intracerebral Hemorrhage: Application of Baseline Ct Scan Radiomics Feature Extraction and Machine Learning Classifiers

Stroke ◽  
2020 ◽  
Vol 51 (Suppl_1) ◽  
Author(s):  
Seyedmehdi Payabvash ◽  
Julian Acosta ◽  
Stefan Haider ◽  
Rommell Noche ◽  
Elayna Kirsch ◽  
...  
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Intracerebral Hemorrhage ◽  
Ct Scan ◽  
Outcome Prediction ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Lasso Regression ◽  
Machine Learning Classifiers ◽  
Clinical Variables

Aim: Radiomics refers to automatic extraction of numerous quantitative features from medical images to supplement visual assessment. Machine-learning algorithms provide a suitable statistical methodology for devising predictive classifiers based on large radiomics datasets. We aimed to predict intracerebral hemorrhage (ICH) outcome by applying machine-learning classifiers to both clinical data and hematoma radiomics features. Methods: Patients enrolled in the Yale Longitudinal Study of ICH were included if they had (1) spontaneous supratentorial ICH, (2) baseline CT scan, (3) known admission Glasgow Coma Scale (GCS), and (4) 3-month modified Rankin Scale (mRS). A total of 1134 radiomics features related to the intensity, shape, texture, and waveform were extracted from manually segmented ICH lesions on baseline CT. Clinical variables were patients’ age, gender, GCS, presence of intraventricular hemorrhage, and thalamic ICH. We calculated the averaged receiver operating characteristics (ROC) area under curve (AUC) in outcome prediction among 100 repeats of 5-fold cross-validation (x500 iterations) for different combinations of feature selection and machine-learning algorithms. Results: A total of 119 ICH patients were included, of whom 60 had poor outcome (mRS ≥4). Among different combinations, lasso regression feature selection and partial least square (PLS) classification model yielded the highest accuracy in outcome prediction (Figure), with an averaged (95% confidence interval) ROC AUC of 0.86 (0.83 - 0.89) using clinical variables “only”, versus 0.92 (0.89 - 0.95) using combination of clinical variables and 54 radiomics features selected by lasso regression. Among radiomics features selected by lasso regression, ICH lesion flatness had the highest variable importance and was the only shape feature selected. Conclusion: Addition of ICH lesion radiomics to clinical variables using machine-learning models can improve outcome prediction.

scholarly journals Automatic Classification of COVID-19 using CT-Scan Images

2021 ◽  
Vol 43 ◽  
pp. e55189
Author(s):  
Hatice Catal Reis
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Ct Scan ◽  
Mean Squared Error ◽  
Close Contact ◽  
Learning Algorithms ◽  
Area Under The Curve ◽  
Point Of View ◽  
Machine Learning Algorithms ◽  
Engineering Sciences

Medicine and engineering sciences have been working in close contact for common purposes. Machine learning algorithms are used in the medical field for early diagnosis prediction. The major aim of this study is to evaluate machine learning algorithms and deep learning algorithms using computed tomography scan (CT-scan) images for automated detection of the coronavirus disease 2019 (COVID-19) patients. We obtained seven hundred and fifty-seven (757) CT-scan images from a public platform. We applied four automated traditional classification methods to predict COVID-19 using deep learning and machine learning. These algorithms are SVM, AdaBoost, NASNetMobile, and InceptionV3. Comparative analyses are presented among the four models by considering metric performance factors to find the best model. The results show that the InceptionV3 model achieves better performance in terms of accuracy, precision, recall, Cohen’s kappa, F1- score, root mean squared error (RMSE), and receiver operating characteristic- area under the curve (ROC-AUC), in comparison with the other Covid-19 classifiers. Accordingly, the InceptionV3 approach is recommended for the automatic diagnosis of Covid-19 and assessments. This research can present a second point of view to medical experts and it can save time for researchers as the performance of standard machine learning methods in detecting COVID-19 is evaluated.

scholarly journals OC-0253: Machine Learning-Based Enables Data-driven Radiotherapy Treatment Planning Decision Support

2017 ◽  
Vol 123 ◽  
pp. S127-S128 ◽  
Author(s):  
G. Valdes ◽  
L. Wojtowicz ◽  
A.J. Pattison ◽  
C. Carpenter ◽  
C. Simone ◽  
...  
Keyword(s):  
Machine Learning ◽  
Decision Support ◽  
Treatment Planning ◽  
Data Driven ◽  
Radiotherapy Treatment Planning ◽  
Planning Decision ◽  
Radiotherapy Treatment
Sign in / Sign up

Export Citation Format

Share Document