Search results for " Medical imaging"
showing 10 items of 1067 documents
Phantom development for daily checks in electron intraoperative radiotherapy with a mobile linac.
2020
Abstract Purpose IORT with mobile linear accelerators is a well-established modality where the dose rate and, therefore, the dose per pulse are very high. The constancy of the dosimetric parameters of the accelerator has to be checked daily. The aim of this work is to develop a phantom with embedded detectors to improve both accuracy and efficiency in the daily test of an IORT linac at the surgery room. Methods The developed phantom is manufactured with transparent polymethyl methacrylate (PMMA), allocating 6 parallel-plate chambers: a central one to evaluate the on-axis beam output, another on-axis one placed at a fixed depth under the previous one to evaluate the energy constancy and four…
Intravenous Contrast Agent in Abdominal CT: Is It Really Needed to Identify the Cause of Bowel Obstruction? Proof of Concept
2019
Background. To compare sensitivity of unenhanced computed tomography (CT) and contrast-enhanced CT for the identification of the etiology of bowel obstruction.Materials and Methods. We retrospectively evaluated abdominal CT scans of patients operated for bowel obstruction from March 2013 to October 2017. Two radiologists evaluated CT scans before and after contrast agent in two reading sessions. Then, we calculated sensitivity of CT in the diagnosis of bowel obstruction and determined in which cases the etiology of bowel obstruction was detected on both unenhanced and enhanced CT or on enhanced CT only. The reference standard was defined as the final diagnosis obtained after surgery.Results…
A 3D deep learning approach based on Shape Prior for automatic segmentation of myocardial diseases
2020
Accurate three-dimensional (3D) cardiac segmentation from late gadolinium enhancement (LGE)-MRI plays a critical role in designing a structure of reference for diagnosing many cardiac pathologies such as ischemia, myocarditis and myocardial infarction. This segmentation is however still a non-trivial task, due to the motion artifacts during acquisition, and heterogeneous intensity distributions. In this study, we develop a fully 3D automated model based on deep neural networks (DNN) for LGE-MRI myocardial pathologies (scar and No-reflow tissues) segmentation in a new expert annotated dataset. Considering that damaged tissue constitutes a small area of the whole LGE-MRI, we concentrated on m…
Status of HIGISOL a new version equipped with SPIG and electric field guidance
2001
A new HIGISOL chamber devoted to the study of short-lived products from heavy-ion-induced fusion-evaporation reactions is proposed. It enables, via the extraction of ions by means of a SPIG (SextuPole rf Ion Guide), to improve the mass resolving power by a factor 2.5 compared to the previous system using a skimmer-ring assembly. The gas cell was also equiped with an electric field for faster transportation of recoiling ions to the nozzle where they are ejected with the gas jet. The first results obtained both with a radioactive α-source and cyclotron beam will be reported.
The use of in vivo confocal microscopy in fungal keratitis – Progress and challenges
2022
Fungal keratitis (FK) is a serious and sight-threatening corneal infection with global reach. The need for prompt diagnosis is paramount, as a delay in initiation of treatment could lead to irreversible vision loss. Current “gold standard” diagnostic methods, namely corneal smear and culture, have limitations due to diagnostic insensitivity and their time-consuming nature. PCR is a newer, complementary method used in the diagnosis of fungal keratitis, whose results are also sample-dependent. In vivo confocal microscopy (IVCM) is a promising complementary diagnostic method of increasing importance as it allows non-invasive real-time direct visualization of potential fungal pathogens and mani…
Lung CT Image Registration through Landmark-constrained Learning with Convolutional Neural Network
2020
Accurate registration of lung computed tomography (CT) image is a significant task in thorax image analysis. Recently deep learning-based medical image registration methods develop fast and achieve promising performance on accuracy and speed. However, most of them learned the deformation field through intensity similarity but ignored the importance of aligning anatomical landmarks (e.g., the branch points of airway and vessels). Accurate alignment of anatomical landmarks is essential for obtaining anatomically correct registration. In this work, we propose landmark constrained learning with a convolutional neural network (CNN) for lung CT registration. Experimental results of 40 lung 3D CT …
Computerised tomography and magnetic resonance imaging of laryngeal squamous cell carcinoma: A practical approach
2017
Squamous cell carcinoma is the most common head and neck cancer. This review describes the state-of-the-art computerised tomography and magnetic resonance imaging protocols of the neck and the normal larynx anatomy, and provides a practical approach for the diagnosis and staging of laryngeal squamous cell carcinoma.
Algorithms as legal norms: About extending traditional legal safeguards for regulations enacted by public administrations to the algorithms used by p…
2020
En este trabajo se argumenta que los algoritmos empleados por parte de las Administraciones públicas para la adopción efectiva de decisiones han de ser considerados reglamentos por cumplir una función material estrictamente equivalente a la de las normas jurídicas, al reglar y predeterminar la actuación de los poderes públicos. Adicionalmente se estudia cómo, una vez asumida esta naturaleza jurídica reglamentaria de estas herramientas de programación, se deducen consecuencias jurídicas respecto de cómo han de realizarse los procedimientos de elaboración y aprobación de estos algoritmos, la necesidad de que los mismos estén debidamente publicados como normas jurídicas que son o la exigencia …
Review on Machine Learning Based Lesion Segmentation Methods from Brain MR Images
2016
Brain lesions are life threatening diseases. Traditional diagnosis of brain lesions is performed visually by neuro-radiologists. Nowadays, advanced technologies and the progress in magnetic resonance imaging provide computer aided diagnosis using automated methods that can detect and segment abnormal regions from different medical images. Among several techniques, machine learning based methods are flexible and efficient. Therefore, in this paper, we present a review on techniques applied for detection and segmentation of brain lesions from magnetic resonance images with supervised and unsupervised machine learning techniques.