Publications by authors named "Thomas Decourselle"
A thoracic aortic aneurysm is an abnormal dilatation of the aorta that can progress and lead to rupture. The decision to conduct surgery is made by considering the maximum diameter, but it is now well known that this metric alone is not completely reliable. The advent of 4D flow magnetic resonance imaging has allowed for the calculation of new biomarkers for the study of aortic diseases, such as wall shear stress.
View Article and Find Full Text PDFBackground: In acute cardiovascular disease management, the delay between the admission in a hospital emergency department and the assessment of the disease from a Delayed Enhancement cardiac MRI (DE-MRI) scan is one of the barriers for an immediate management of patients with suspected myocardial infarction or myocarditis.
Objectives: This work targets patients who arrive at the hospital with chest pain and are suspected of having a myocardial infarction or a myocarditis. The main objective is to classify these patients based solely on clinical data in order to provide an early accurate diagnosis.
Comparison of In-Vivo and Ex-Vivo Ascending Aorta Elastic Properties through Automatic Deep Learning Segmentation of Cine-MRI and Biomechanical Testing.
J Clin Med
January 2023
Article Synopsis
- Ascending aortic aneurysms are serious conditions where the aorta dilates and stiffens, potentially leading to life-threatening complications like aortic dissection; monitoring and surgical intervention are critical.
- This study aims to evaluate the elastic properties of the ascending aorta in vivo using cine-MRI imaging from 73 patients with dilated aortas, comparing results to those obtained ex vivo.
- The research finds that using a deep learning U-Net network for automatic segmentation achieves high accuracy, revealing that the lateral and posterior quadrants of the aorta are the stiffest, while the medial and anterior quadrants are the least stiff, aligning with ex vivo findings.
Article Synopsis
- A key method for evaluating heart health after a heart attack (myocardial infarction) is using delayed enhancement MRI (DE-MRI), which identifies viable versus nonviable heart tissue effectively.
- The EMIDEC challenge aimed to assess whether deep learning techniques could differentiate between healthy and pathological heart exams, and also to automatically calculate the extent of myocardial injury using a dataset of 150 MRI cases.
- Results showed that high accuracy (up to 0.92) in classifying heart exams is achievable, but improvements are needed for accurately segmenting the affected areas due to their small size and low contrast with surrounding tissues.
This study proposes machine learning-based models to automatically evaluate the severity of myocardial infarction (MI) from physiological, clinical, and paraclinical features. Two types of machine learning models are investigated for the MI assessment: the classification models classify the presence of the infarct and the persistent microvascular obstruction (PMO), and the regression models quantify the Percentage of Infarcted Myocardium (PIM) of patients suspected of having an acute MI during their reception in the emergency department. The ground truth labels for these supervised models are derived from the corresponding Delayed Enhancement MRI (DE-MRI) exams and manual annotations of the myocardium and scar tissues.
View Article and Find Full Text PDFAutomatic deep learning-based myocardial infarction segmentation from delayed enhancement MRI.
Comput Med Imaging Graph
January 2022
Delayed Enhancement cardiac MRI (DE-MRI) has become indispensable for the diagnosis of myocardial diseases. However, to quantify the disease severity, doctors need time to manually annotate the scar and myocardium. To address this issue, in this paper we propose an automatic myocardial infarction segmentation approach on the left ventricle from short-axis DE-MRI based on Convolutional Neural Networks (CNN).
View Article and Find Full Text PDF