scholarly journals The Application of Deep Learning for the Classification of Internal Human Cardiac Anatomy

2018 ◽  
Author(s):  
Erik Gaasedelen ◽  
Alex Deakyne ◽  
Paul Iaizzo
Keyword(s):  
Deep Learning ◽  
Surgical Procedures ◽  
Electrical Conduction ◽  
Human Heart ◽  
Cardiac Anatomy ◽  
Non Invasive ◽  
Spatial Environment ◽  
The Creation

The applications of sensing and localization are becoming more sophisticated in many invasive and non-invasive surgical procedures and there is great interest to apply them to the human heart. Ideally, such tools could be indispensable for allowing physicians to spatially understand relative tissue morphologies and their associated electrical conduction. Yet today there remains a steep divide between the creation of spatial environment models and the contextual understandings of adjacent features. To begin to address this, we explore the problem of anatomical perception by applying deep learning to the identification of internal cardiac anatomy images.

Portal hypertension and its management in children

2017 ◽  
Vol 103 (2) ◽  
pp. 186-191 ◽  
Author(s):  
Tassos Grammatikopoulos ◽  
Patrick James McKiernan ◽  
Anil Dhawan
Keyword(s):  
Portal Hypertension ◽  
Liver Disease ◽  
Gastrointestinal Bleeding ◽  
Surgical Procedures ◽  
Vascular Occlusion ◽  
Portal System ◽  
Mortality And Morbidity ◽  
Non Invasive ◽  
Intravascular Pressure

Portal hypertension (PHT), defined as raised intravascular pressure in the portal system, is a complication of chronic liver disease or liver vascular occlusion. Advances in our ability to diagnose and monitor the condition but also predict the risk of gastrointestinal bleeding have enabled us to optimise the management of children with PHT either at a surveillance or at a postbleeding stage. A consensus among paediatric centres in the classification of varices can be beneficial in streamlining future paediatric studies. New invasive (endoscopic and surgical procedures) and non-invasive (pharmacotherapy) techniques are currently used enabling clinicians to reduce mortality and morbidity in children with PHT.

scholarly journals Comparison of Object Detection Approaches Applied to Field Images of Papanicolaou Stained Cytology Slides

2021 ◽  
Author(s):  
André Victória Matias ◽  
Allan Cerentini ◽  
Luiz Antonio Buschetto Macarini ◽  
João Gustavo Atkinson Amorim ◽  
Felipe Perozzo Daltoé ◽  
...  
Keyword(s):  
Cervical Cancer ◽  
Deep Learning ◽  
Oral Cancer ◽  
Global Health ◽  
Object Detection ◽  
Learning Approach ◽  
Non Invasive ◽  
Global Health Issue ◽  
Invasive Method

Papanicolaou is an inexpensive and non-invasive method, generally applied to detect cervical cancer, that can also be useful to detect cancer on oral cavities. Although oral cancer is considered a global health issue with 350.000 people diagnosed over a year it can successfully be treated if diagnosed at early stages. The manual process of analyzing cells to detect abnormalities is time-consuming and subject to variations in perceptions from different professionals. To evaluate a possible solution to the automation of this process, in this paper we employ the object detection deep learning approach in the analysis of this type of image using 3 models: RetinaNet, Faster R-CNN, and Mask R-CNN. We trained and tested the models using images from 6 cytology slides (4 cancer cases and 2 healthy samples) and our results show that Mask R-CNN was the best model for localization and classification of nuclei with an IoU of 0.51 and recall of abnormal nuclei of 0.67.

scholarly journals Robust deep learning classification of adamantinomatous craniopharyngioma from limited preoperative radiographic images

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Eric W. Prince ◽  
Ros Whelan ◽  
David M. Mirsky ◽  
Nicholas Stence ◽  
Susan Staulcup ◽  
...  
Keyword(s):  
Deep Learning ◽  
Model Performance ◽  
Pediatric Brain Tumor ◽  
Training Data ◽  
Small Scale ◽  
Radiographic Images ◽  
Non Invasive ◽  
Magnetic Resonance Imaging Mri ◽  
Adamantinomatous Craniopharyngioma

Abstract Deep learning (DL) is a widely applied mathematical modeling technique. Classically, DL models utilize large volumes of training data, which are not available in many healthcare contexts. For patients with brain tumors, non-invasive diagnosis would represent a substantial clinical advance, potentially sparing patients from the risks associated with surgical intervention on the brain. Such an approach will depend upon highly accurate models built using the limited datasets that are available. Herein, we present a novel genetic algorithm (GA) that identifies optimal architecture parameters using feature embeddings from state-of-the-art image classification networks to identify the pediatric brain tumor, adamantinomatous craniopharyngioma (ACP). We optimized classification models for preoperative Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and combined CT and MRI datasets with demonstrated test accuracies of 85.3%, 83.3%, and 87.8%, respectively. Notably, our GA improved baseline model performance by up to 38%. This work advances DL and its applications within healthcare by identifying optimized networks in small-scale data contexts. The proposed system is easily implementable and scalable for non-invasive computer-aided diagnosis, even for uncommon diseases.

MEDIATEXT IS A TOOL THAT DETERMINES THE QUALITY OF INFORMATION

2020 ◽  
Vol 6 (3) ◽  
pp. 158-164
Author(s):  
Navruza Yakhyayeva ◽  
Keyword(s):  
Functional Properties ◽  
Linguistic Features ◽  
Text Linguistics ◽  
Quality Of Information ◽  
The Creation ◽  
Linguistic Units ◽  
Scientific Classification

The quality and content of information in the article media text is based on scientific classification of linguistic features. The study of functional styles of speech, the identification of their linguistic signs, the discovery of the functional properties of linguistic units and their separation on the basis of linguistic facts is one of thetasks that modern linguistics is waiting for a solution. Text Linguistics, which deals with the creation, modeling of its structure and the study of the process of such activity, is of interest to journalists today as a science.

Sign in / Sign up

Export Citation Format

Share Document