scholarly journals Preventing corneal blindness caused by keratitis using artificial intelligence

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Zhongwen Li ◽  
Jiewei Jiang ◽  
Kuan Chen ◽  
Qianqian Chen ◽  
Qinxiang Zheng ◽  
...  
Keyword(s):  
Early Diagnosis ◽  
Vision Loss ◽  
Learning System ◽  
Automated Classification ◽  
Slit Lamp ◽  
Resource Limited ◽  
The World ◽  
Different Types ◽  
Corneal Blindness

AbstractKeratitis is the main cause of corneal blindness worldwide. Most vision loss caused by keratitis can be avoidable via early detection and treatment. The diagnosis of keratitis often requires skilled ophthalmologists. However, the world is short of ophthalmologists, especially in resource-limited settings, making the early diagnosis of keratitis challenging. Here, we develop a deep learning system for the automated classification of keratitis, other cornea abnormalities, and normal cornea based on 6,567 slit-lamp images. Our system exhibits remarkable performance in cornea images captured by the different types of digital slit lamp cameras and a smartphone with the super macro mode (all AUCs>0.96). The comparable sensitivity and specificity in keratitis detection are observed between the system and experienced cornea specialists. Our system has the potential to be applied to both digital slit lamp cameras and smartphones to promote the early diagnosis and treatment of keratitis, preventing the corneal blindness caused by keratitis.

scholarly journals A Multitask Deep-Learning System to Classify Diabetic Macular Edema for Different Optical Coherence Tomography Devices: A Multicenter Analysis

2021 ◽  
Author(s):  
Fangyao Tang ◽  
Xi Wang ◽  
An-ran Ran ◽  
Carmen KM Chan ◽  
Mary Ho ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Deep Learning ◽  
Macular Edema ◽  
Diabetic Macular Edema ◽  
Vision Loss ◽  
Three Dimensional ◽  
Learning System ◽  
Optical Coherence ◽  
Automated Classification

<a><b>Objective:</b></a> Diabetic macular edema (DME) is the primary cause of vision loss among individuals with diabetes mellitus (DM). We developed, validated, and tested a deep-learning (DL) system for classifying DME using images from three common commercially available optical coherence tomography (OCT) devices. <p><b>Research Design and Methods:</b> We trained and validated two versions of a multi-task convolution neural network (CNN) to classify DME (center-involved DME [CI-DME], non-CI-DME, or absence of DME) using three-dimensional (3D) volume-scans and two-dimensional (2D) B-scans respectively. For both 3D and 2D CNNs, we employed the residual network (ResNet) as the backbone. For the 3D CNN, we used a 3D version of ResNet-34 with the last fully connected layer removed as the feature extraction module. A total of 73,746 OCT images were used for training and primary validation. External testing was performed using 26,981 images across seven independent datasets from Singapore, Hong Kong, the US, China, and Australia. </p> <p><b>Results:</b> In classifying the presence or absence of DME, the DL system achieved area under the receiver operating characteristic curves (AUROCs) of 0.937 (95% CI 0.920–0.954), 0.958 (0.930–0.977), and 0.965 (0.948–0.977) for primary dataset obtained from Cirrus, Spectralis, and Triton OCTs respectively, in addition to AUROCs greater than 0.906 for the external datasets. For the further classification of the CI-DME and non-CI-DME subgroups, the AUROCs were 0.968 (0.940–0.995), 0.951 (0.898–0.982), and 0.975 (0.947–0.991) for the primary dataset and greater than 0.894 for the external datasets. </p> <p><b>Conclusion:</b> We demonstrated excellent performance with a DL system for the automated classification of DME, highlighting its potential as a promising second-line screening tool for patients with DM, which may potentially create a more effective triaging mechanism to eye clinics. </p>

scholarly journals A Multitask Deep-Learning System to Classify Diabetic Macular Edema for Different Optical Coherence Tomography Devices: A Multicenter Analysis

2021 ◽  
Author(s):  
Fangyao Tang ◽  
Xi Wang ◽  
An-ran Ran ◽  
Carmen KM Chan ◽  
Mary Ho ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Deep Learning ◽  
Macular Edema ◽  
Diabetic Macular Edema ◽  
Vision Loss ◽  
Three Dimensional ◽  
Learning System ◽  
Optical Coherence ◽  
Automated Classification

<a><b>Objective:</b></a> Diabetic macular edema (DME) is the primary cause of vision loss among individuals with diabetes mellitus (DM). We developed, validated, and tested a deep-learning (DL) system for classifying DME using images from three common commercially available optical coherence tomography (OCT) devices. <p><b>Research Design and Methods:</b> We trained and validated two versions of a multi-task convolution neural network (CNN) to classify DME (center-involved DME [CI-DME], non-CI-DME, or absence of DME) using three-dimensional (3D) volume-scans and two-dimensional (2D) B-scans respectively. For both 3D and 2D CNNs, we employed the residual network (ResNet) as the backbone. For the 3D CNN, we used a 3D version of ResNet-34 with the last fully connected layer removed as the feature extraction module. A total of 73,746 OCT images were used for training and primary validation. External testing was performed using 26,981 images across seven independent datasets from Singapore, Hong Kong, the US, China, and Australia. </p> <p><b>Results:</b> In classifying the presence or absence of DME, the DL system achieved area under the receiver operating characteristic curves (AUROCs) of 0.937 (95% CI 0.920–0.954), 0.958 (0.930–0.977), and 0.965 (0.948–0.977) for primary dataset obtained from Cirrus, Spectralis, and Triton OCTs respectively, in addition to AUROCs greater than 0.906 for the external datasets. For the further classification of the CI-DME and non-CI-DME subgroups, the AUROCs were 0.968 (0.940–0.995), 0.951 (0.898–0.982), and 0.975 (0.947–0.991) for the primary dataset and greater than 0.894 for the external datasets. </p> <p><b>Conclusion:</b> We demonstrated excellent performance with a DL system for the automated classification of DME, highlighting its potential as a promising second-line screening tool for patients with DM, which may potentially create a more effective triaging mechanism to eye clinics. </p>

scholarly journals A Review on Epilepsy and its Management

2020 ◽  
Vol 10 (3) ◽  
pp. 273-279
Author(s):  
V.V. Potnis ◽  
Ketan G. Albhar ◽  
Pritamsinh Arjun Nanaware ◽  
Vishal S. Pote
Keyword(s):  
Developing Countries ◽  
Neurological Disorders ◽  
Genetic Factors ◽  
Future Trends ◽  
Brain Infection ◽  
The World ◽  
Different Types ◽  
Patients With Epilepsy ◽  
The Brain

Today, people face various types of stress in everyday fast life and most people in the world suffer from various neurological disorder. Epilepsy is one of the most common neurological disorders of the brain, affecting about 50 million people around the world, and 90% of them are coming from developing countries. Genetic factors and brain infection, stroke, tumors and epilepsy cause high fever. It imposes a great economic burden on the health systems of countries associated with stigma and discrimination against the patient and also his family in the community, in the workplace, school and home. Many patients with epilepsy suffer from severe emotional stress, behavioral disorders and extreme social isolation. There are many different types of seizure and mechanisms by which the brain generates seizures. The two features of generating seizures are hyperexcitability of neurons and a hyper synchronousneural circuits. A variety of mechanisms alters the balance between excitation and inhibition in predisposing brain local or generalized hyperexcitability region and a hypersynchronia. Purpose of the review is to discuss the history, epidemiology, etiology, pathophysiology, classification of epilepsy, symtomps, diagnosis, management of epilepsy and future trends. Keywords: Anti-epileptic drugs, pathophysiology, seizures, epidemiology, hypersynchrony

scholarly journals Evaluation Methods for the Impacts of Shared Mobility: Classification and Critical Review

2020 ◽  
Vol 12 (24) ◽  
pp. 10504
Author(s):  
Anastasia Roukouni ◽  
Gonçalo Homem de Almeida Correia
Keyword(s):  
State Of The Art ◽  
The State ◽  
Added Value ◽  
Research And Practice ◽  
Shared Mobility ◽  
The World ◽  
Different Types ◽  
Pros And Cons

In recent years, shared mobility services have had a growing presence in cities all over the world. Developing methodologies to measure and evaluate the impacts of shared mobility has therefore become of critical importance for city authorities. This paper conducts a thorough review of the different types of methods that can be used for this evaluation and suggests a classification of them. The pros and cons of each method are also discussed. The added value of the paper is twofold; first, we provide a systematic recording of the state of the art and the state of the practice regarding the evaluation of the impacts of shared mobility, from the perspective of city authorities, reflecting on their role, needs, and expectations. Second, by identifying the existing gaps in the literature, we highlight the specific needs for research and practice in this field that can help society figure out the role of urban shared mobility.

scholarly journals DENOTATIVE-NOMINATIVE TYPOLOGY OF ENGLISH IDEONYMS

2018 ◽  
pp. 3-8
Author(s):  
Olga Vasilyeva
Keyword(s):  
Proper Names ◽  
Electronic Media ◽  
Computer Art ◽  
Television Programs ◽  
Frequency Of Use ◽  
The World ◽  
Named Objects ◽  
Different Types ◽  
The Media

The article considers denotative nominative classification of English ideonyms. One thousand English ideonyms selected according to the frequency of use in print and electronic media have provided the material for this research. The topical problems of ideonymics incude establishment of denotative nominative systematization of the relevant proprietary units, which involves their grouping according to the type of the named objects. The denotative nominative classification of ideonyms embraces four divisions: artionyms, i.e. proper names of works of art, which are further divided into imagionyms, sсeneonyms, musiconyms and filmonyms; biblionyms that cover proper names of all written and verbal texts as well as their series and collections; gemeronyms, i.e. proper names of the media, which are divided into pressonyms and electronyms according to the method of transmitting the information and include both radio and television programs of exclusively informational nature rather than those of entertaining or educational character; computeronyms, which absorb all proper names designed to designate different types of computer programs. The poetonymic sphere is understood as a collection of onyms in artistic texts creating a complex and harmonious system existing in any artistic work as a result of their interrelations. This concerns not only literary works but also those in cinematography, computer art, etc., since proper names act in each of them as components of the virtual picture of the world, thus enabling to refer to the existence of not only the poetonymic sphere, but also the virtualonymosphere. Therefore, it can be concluded that ideonyms can be divided into four classes by their correlation with denotate, namely artionyms, biblionyms, gemeronyms and computeronyms, subject to further specification. Separate terms have been created for ideonyms of the first and second specification levels whereas descriptive terminology is applied for further subdivisions. Each of the analyzed divisions has its own specific functioning, both structural and semantic, which makes further intvestigation in this direction relevant.

Cordon approach to rivers

2020 ◽  
pp. 198-241
Author(s):  
S. Nazrul Islam
Keyword(s):  
United States ◽  
Case Studies ◽  
The United States ◽  
River Channels ◽  
The World ◽  
Different Types ◽  
Levee System ◽  
The Relationship ◽  
Different Parts

Chapter 9 presents the Cordon approach, describing its methods, reviewing its spread across the world, and analyzing its consequences. It discusses the general relationship between river channels and their floodplains and explains the nurturing functions that regular river inundations perform. The chapter then outlines the instruments of the Cordon approach, such as embankments, floodwalls, channelization, and canalization. It goes on to explain the relationship between the Cordon and the Polder approaches and offers a classification of cordons into different types. The chapter reviews the consequences of the Cordon approach, distinguishing between those for river channels and for floodplains. It provides an overview of the experience of the Cordon approach in different parts of the world, focusing on the United States, Europe, and India. It also presents two case studies of the Cordon approach: the Mississippi levee system in the United States and the Huang He River embankments in China.

scholarly journals FUNGAL KERATITIS WITH CORNEAL ULCER IN FARMER

2020 ◽  
Vol 3 (1) ◽  
pp. 58
Author(s):  
Nugraha Wahyu Cahyana
Keyword(s):  
Visual Acuity ◽  
Corneal Ulcer ◽  
Fungal Keratitis ◽  
Eye Drops ◽  
Slit Lamp ◽  
Good Clinical Response ◽  
Specific Diagnosis ◽  
The World ◽  
Corneal Blindness ◽  
Test Result

Fungal keratitis is an important cause of corneal blindness all over the world, especially in developing countries. Fungal Keratitis can diagnosis by slit-lamp biomicroscopic examination and culture is essential for early specific diagnosis and must be taken into consideration to establish the most effective treatment and avoid severe complications. The study was present a case of Fungal Keratitis in Farmer with a corneal ulcer caused by rice seeds corneal corpus allienum. A corneal ulcer is a complication was caused by ineffective therapy especially Steroid topical that should be avoided. The culture test result was C. Albicans and was treated with natamycin 5% Eye drops. Finally, patients have a good clinical response, however with the sequel of decreased visual acuity.  

Classification of Types of Interreligious Dialogue

Communicology ◽  
2020 ◽  
Vol 8 (2) ◽  
pp. 25-51
Author(s):  
S.V. Melnik
Keyword(s):  
Interreligious Dialogue ◽  
Comparative Theology ◽  
Theology Of Religions ◽  
The World ◽  
Different Types ◽  
To Come ◽  
First Time ◽  
Original Classification

The existing classifications of types of interreligious dialogue have significant limitations and shortcomings and do not allow us to describe this extremely complex, multi- faceted phenomenon in a systematic and complete way. This paper represents original classification of interreligious dialogue, which overcomes the disadvantages of current research approaches in this area. On the basis of the «intention» criterion, i.e. the motivation that encourages followers of different religions to come into contact with each other, four types of interreligious dialogue are distinguished: polemical, cognitive, peacemaking and partnership. These types of dialogue are lined up respectively around the following questions: Who is right?, Who are you?, How can we live together peacefully? and What can we do to improve the world?. In each of the four types of interreligious dialogue using the criteria goal (i.e. tasks headed towards by the participants in the dialogue); principles i.e. the starting points, which determine the interaction), and form (i.e. participants in the dialogue) various sorts of them are identified and described. For example, the following sorts of cognitive dialogue are considered: theological, spiritual, human (Buberian), truth-seeking dialogue, theology of religions, theology of interreligious dialogue, comparative theology. According to the author, the presented classification allows for the first time to describe different types of interreligious dialogue in a complex, systematic and interrelated way.

scholarly journals The CURRENT TRENDS AND TREATMENTS IN DIABETIC RETINOPATHY

2019 ◽  
pp. 27-33
Author(s):  
FIROZ MV ◽  
VISHAL GUPTA N ◽  
SANDEEP KANNA
Keyword(s):  
Diabetic Retinopathy ◽  
Laser Photocoagulation ◽  
Vision Loss ◽  
Renin Angiotensin System ◽  
Chemical Degradation ◽  
Common Causes ◽  
The World ◽  
Different Types ◽  
New Treatment ◽  
Endothelial Growth Factor

The drastically increasing issues of the disease scenario currently are with different types of diabetes all over the world. It has been reported, approximately 592 million are suffering from the disease throughout the world. It affects differently in different patients with the disease. There have been reports that it is affected differently and also has different side effects. It is also been reported that diabetes mellitus leads to the cause of diabetic retinopathy (DR) and also diabetic macular edema. It is considered as one of the most common causes which is linked to DR. DR has been considered as one of the most important causes for the loss of vision or impaired vision. The drugs show different types of incompatibility such as toxicity, solubility issues, aggregation, and chemical degradation these can be improved by applying several methods. DR is classified according to “Airlie House” into different categories and based on different strategies and consideration. It was found that DR is the main cause for vision loss and also there no much strategies for development of new treatment. The treatment involved is laser photocoagulation and vitrectomy, among these the effective treatment, was found to be laser photocoagulation. This is mainly characterized as proliferative and non-proliferative DR. Different therapeutic agents have been taken for the study these includes vascular endothelial growth factor, renin-angiotensin system inhibitors and nonsteroidal anti-inflammatory drugs, they are certainly different interventions for the treatment, they are nanotechnology and liposome. Nanotechnology applied is the most effective and also acceptable way of treatment.

scholarly journals Early diagnosis and Prediction of Breast Cancer

2020 ◽  
Vol 9 (6) ◽  
pp. 148-151
Keyword(s):  
Breast Cancer ◽  
Early Diagnosis ◽  
New Techniques ◽  
Healthy Life ◽  
Time Prediction ◽  
Medical Sector ◽  
The World ◽  
Prevention Of Cancer ◽  
Early Detection And Prevention

Nowadays Cancer is one of the frequent diseases for all the humans in the world. Particularly, in women’s Breast Cancer is one of the most frequent diseases. Therefore, early detection and prevention of cancer is very important to get healthy life so we need to develop new techniques for diagnosis and prediction of cancer. Many ML techniques are used for early diagnosis and prediction of cancer. In this paper, we are proposing new techniques for the classification of Breast cancer and the time prediction when that breast cancer has occurred using some ML techniques and our proposed work is medical sector application. We compared our proposed methodology result with each other techniques to get the highest accurate value.

Sign in / Sign up

Export Citation Format

Share Document