Ground-glass nodule classification with multiple 2.5-dimensional deep convolutional neural networks in chest CT images

2019 ◽  
Author(s):  
So Hyun Byun ◽  
Julip Jung ◽  
Helen Hong ◽  
Yong Sub Song ◽  
Hyungjin Kim ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Ct Images ◽  
Chest Ct ◽  
Ground Glass ◽  
Deep Convolutional Neural Networks ◽  
Ground Glass Nodule ◽  
Nodule Classification

COVID-19 image transmission using convolutional neural networks based algorithms for medical applications

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Gangadhar Ch ◽  
Nama Ajay Nagendra ◽  
Syed Mutahar Aaqib ◽  
C.M. Sulaikha ◽  
Shaheena Kv ◽  
...  
Keyword(s):  
Neural Networks ◽  
Information Systems ◽  
Ct Scan ◽  
Health Information ◽  
Convolutional Neural Networks ◽  
Health Information Systems ◽  
Ct Images ◽  
Chest Ct ◽  
Content Type ◽  
Chest Ct Scan

Purpose COVID-19 would have a far-reaching impact on the international health-care industry and the patients. For COVID-19, there is a need for unique screening tests to reliably and rapidly determine who is infected. Medical COVID images protection is critical when data pertaining to computer images are being transmitted through public networks in health information systems. Design/methodology/approach Medical images such as computed tomography (CT) play key role in the diagnosis of COVID-19 patients. Neural networks-based methods are designed to detect COVID patients using chest CT scan images. And CT images are transmitted securely in health information systems. Findings The authors hereby examine neural networks-based COVID diagnosis methods using chest CT scan images and secure transmission of CT images for health information systems. For screening patients infected with COVID-19, a new approach using convolutional neural networks is proposed, and its output is simulated. Originality/value The required patient’s chest CT scan images have been taken from online databases such as GitHub. The experiments show that neural networks-based methods are effective in the diagnosis of COVID-19 patients using chest CT scan images.

scholarly journals Urinary Stone Detection on CT Images Using Deep Convolutional Neural Networks: Evaluation of Model Performance and Generalization

2019 ◽  
Vol 1 (4) ◽  
pp. e180066 ◽  
Author(s):  
Anushri Parakh ◽  
Hyunkwang Lee ◽  
Jeong Hyun Lee ◽  
Brian H. Eisner ◽  
Dushyant V. Sahani ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Model Performance ◽  
Urinary Stone ◽  
Ct Images ◽  
Deep Convolutional Neural Networks ◽  
Stone Detection

scholarly journals Pulmonary Nodule Classification with Deep Convolutional Neural Networks on Computed Tomography Images

2016 ◽  
Vol 2016 ◽  
pp. 1-7 ◽  
Author(s):  
Wei Li ◽  
Peng Cao ◽  
Dazhe Zhao ◽  
Junbo Wang
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Lung Nodule ◽  
Ground Glass Opacity ◽  
Feature Representation ◽  
Deep Convolutional Neural Networks ◽  
Computed Tomography Images ◽  
False Positive Reduction ◽  
Diagnosis Of Lung Cancer ◽  
Nodule Classification

Computer aided detection (CAD) systems can assist radiologists by offering a second opinion on early diagnosis of lung cancer. Classification and feature representation play critical roles in false-positive reduction (FPR) in lung nodule CAD. We design a deep convolutional neural networks method for nodule classification, which has an advantage of autolearning representation and strong generalization ability. A specified network structure for nodule images is proposed to solve the recognition of three types of nodules, that is, solid, semisolid, and ground glass opacity (GGO). Deep convolutional neural networks are trained by 62,492 regions-of-interest (ROIs) samples including 40,772 nodules and 21,720 nonnodules from the Lung Image Database Consortium (LIDC) database. Experimental results demonstrate the effectiveness of the proposed method in terms of sensitivity and overall accuracy and that it consistently outperforms the competing methods.

Sign in / Sign up

Export Citation Format

Share Document