scholarly journals OP0327 EVALUATION OF THE ARTIFICIAL INTELLIGENCE SYSTEM ACCURACY IN DETERMINING THE RADIOGRAPHIC STAGE OF KNEE OSTEOARTHRITIS

2020 ◽  
Vol 79 (Suppl 1) ◽  
pp. 201.2-201
Author(s):  
O. Georginova ◽  
M. Kobzar
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Rapid Development ◽  
Control Sample ◽  
Magnetic Resonance Images ◽  
Knee Joints ◽  
X Rays ◽  
Intelligence System ◽  
Consumer Healthcare ◽  
Machine Reading

Background:Within the last decade, rapid development of artificial neural networks and machine reading programs and their introduction into medical practice is reported [1,2,3]. Recently, an innovative program, based on the artificial intelligence (AI) technologies (a neural network and machine reading) that analyses knee X-ray images for determining the radiographic stage of OA was created. It was launched on the Osteoscan.ru website and is available for use by patients and doctors.Objectives:to validate the system ability to accurately stage OA through machine interpretation of standard knee radiographs.Methods:Initially, 1300 x-rays of both knee joints where used to teach the neural network. Of these, 350 were presented in the form of film scans, 950 in the DICOM format.The accuracy of the system in recognition of OA stage by knee radiographs was evaluated on a quality control sample of 130 cases (of all 1300). Independently, the radiographs were assessed by certified radiologists (considered the “gold standard”) and the System.Results:In 124 out of 130 cases the conclusion of a specialist and the System was the same, which represents 95.4% predictive power. Coincidence or discrepancy is a qualitative attribute, so, the accuracy of the estimation was calculated. Assuming a discrepancy of 0, and coincidence - of 1, µ = 0,954, the standard error sp= 1.8%. It can be concluded that in 95% of cases the accuracy of the system assessment will be in the range from 91.8% to 99%.Conclusion:Osteosan is a program developed on the base of AI technologies, analyzes radiographic images of the knee joints for determining OA stage. It provides high accuracy in OA stage determining by assessing knee radiographs, in 95% of cases, the accuracy of the system varies from 91.8% to 99%.References:[1]Fischl B, Salat DH, van der Kouwe AJ, Makris N, Ségonne F, Quinn BT, Dale AM. Sequence-independent segmentation of magnetic resonance images. Neuroimage. 2004;23 Suppl 1:S69-84[2]Faust O, Acharya U R, Ng EY, Ng KH, Suri JS. Algorithms for the automated detection of diabetic retinopathy using digital fundus images: a review. J Med Syst. 2012; 36(1): 145-57.[3]Balyen L, Peto T. Promising Artificial Intelligence-Machine Learning-Deep Learning Algorithms in Ophthalmology. Asia Pac J Ophthalmol (Phila). 2019; 8(3): 264-272.Disclosure of Interests:Olga Georginova Speakers bureau: GlaxoSmithKline Consumer Healthcare, Margarita Kobzar Employee of: GSK Consumer Healthcare

scholarly journals Clinical deployment and validation of a radiology artificial intelligence system for COVID-19

2020 ◽  
Author(s):  
Behrooz Hashemian ◽  
Aman Manchanda ◽  
Matthew D. Li ◽  
Parisa Farzam ◽  
Suma D. Dash ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Medical Imaging ◽  
Real Time ◽  
Learning Algorithm ◽  
Care Delivery ◽  
Rapid Development ◽  
Severe Disease ◽  
Healthcare Providers ◽  
Clinical Workflow ◽  
Intelligence System

Abstract The global COVID-19 pandemic has disrupted patient care delivery in healthcare systems world-wide. For healthcare providers to better allocate their resources and improve the care for patients with severe disease, it is valuable to be able to identify those patients with COVID-19 who are at higher risk for clinical complications. This may help to optimize clinical workflow and more efficiently allocate scarce medical resources. To this end, medical imaging shows great potential and artificial intelligence (AI) algorithms have been developed to assist in diagnosing and risk stratifying COVID-19 patients. However, despite the rapid development of numerous AI models, these models cannot be clinically useful unless they can be deployed in real-world environments in real-time on clinical data. Here, we propose an end-to-end AI hospital-deployment architecture for COVID-19 medical imaging algorithms in hospitals. We have successfully implemented this system at our institution and it has been used in prospective clinical validation of a deep learning algorithm potentially useful for triaging of patients with COVID-19. We demonstrate that many orchestration processes are required before AI inference can be performed on a radiology studies in real-time with the AI model being just one of the components that make up the AI deployment system. We also highlight that failure of any one of these processes can adversely affect the model's performance.

scholarly journals Toward Understanding COVID-19 Pneumonia: A Deep-learning-based Approach for Severity Analysis and Monitoring the Disease

2020 ◽  
Author(s):  
Mohammadreza Zandehshahvar ◽  
Marly van Assen ◽  
Hossein Maleki ◽  
Yashar Kiarashi ◽  
Carlo N. De Cecco ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Area Under Curve ◽  
Valuable Insight ◽  
X Rays ◽  
Course Of Disease ◽  
New Approach ◽  
Clinical Model ◽  
Average Area ◽  
Learning Technique

ABSTRACTWe report a new approach using artificial intelligence to study and classify the severity of COVID-19 using 1208 chest X-rays (CXRs) of 396 COVID-19 patients obtained through the course of disease at Emory Healthcare affiliated hospitals (Atlanta, GA, USA). Using a two-stage transfer learning technique to train a convolutional neural network (CNN), we show that the algorithm is able to classify four classes of disease severity (normal, mild, moderate, and severe) with average area under curve (AUC) of 0.93. In addition, we show that the outputs of different layers of the CNN under dominant filters provide valuable insight about the subtle patterns in the CXRs, which can improve the accuracy in the reading of CXRs by a radiologist. Finally, we show that our approach can be used for studying the disease progression in single patients and its influencing factors. The results suggest that our technique can form the foundation of a more concrete clinical model to predict the evolution of COVID-19 severity and the efficacy of different treatments for each patient through using CXRs and clinical data in early stages. This will be essential in dealing with the upcoming waves of COVID-19 and optimizing resource allocation and treatment.

scholarly journals Feasibility of an AI-Based Measure of the Hand Motions of Expert and Novice Surgeons

2018 ◽  
Vol 2018 ◽  
pp. 1-6 ◽  
Author(s):  
Munenori Uemura ◽  
Morimasa Tomikawa ◽  
Tiejun Miao ◽  
Ryota Souzaki ◽  
Satoshi Ieiri ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Training Dataset ◽  
Artificial Intelligence System ◽  
Correct Judgment ◽  
Skill Levels ◽  
Intelligence System ◽  
The Neural Network ◽  
Expert And Novice ◽  
Novice Surgeons

This study investigated whether parameters derived from hand motions of expert and novice surgeons accurately and objectively reflect laparoscopic surgical skill levels using an artificial intelligence system consisting of a three-layer chaos neural network. Sixty-seven surgeons (23 experts and 44 novices) performed a laparoscopic skill assessment task while their hand motions were recorded using a magnetic tracking sensor. Eight parameters evaluated as measures of skill in a previous study were used as inputs to the neural network. Optimization of the neural network was achieved after seven trials with a training dataset of 38 surgeons, with a correct judgment ratio of 0.99. The neural network that prospectively worked with the remaining 29 surgeons had a correct judgment rate of 79% for distinguishing between expert and novice surgeons. In conclusion, our artificial intelligence system distinguished between expert and novice surgeons among surgeons with unknown skill levels.

scholarly journals Features of Signature Verification By a Person as a Primary Criteria for Developing an Artificial Intelligence System

2020 ◽  
Vol 17 (4) ◽  
pp. 514-522
Author(s):  
D. V. Bakhteev
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Artificial Neural Network ◽  
Artificial Intelligence System ◽  
Experimental Conditions ◽  
Intelligence System ◽  
Initial Stage ◽  
Correct Determination ◽  
Artificial Neural ◽  
Applied Artificial Intelligence

The modern capabilities of computers have returned interest in artificial intelligence technologies. A particular area of application of these technologies is pattern recognition, which can be applied to the traditional forensic task – identification of signs of forgery (imitation) of a signature. The results of forgery are differentiated into three types: auto-forgery, simple and skilled forgeries. Only skilled forgeries are considered in this study. The online and offline approaches to the study of signatures and other handwriting material are described. The developed artificial intelligence system based on an artificial neural network refers to the offline type of signature recognition – that is, it is focused on working exclusively with the consequences of the signature – its graphic image. The content and principles of the formation of a hypothesis for the development of an artificial intelligence system are described with a combination of humanitarian (legal) knowledge and natural-technical knowledge. At the initial stage of the study, in order to develop an experimental-applied artificial intelligence system based on an artificial neural network focused on identifying forged signatures, 127 people were questioned in order to identify a person's ability to detect fake signatures. It was found that under experimental conditions the probability of a correct determination of the originality or forgery of the presented signature for the respondent is on average 69.29 %. Accordingly, this value can be used as a threshold for determining the effectiveness of the developed artificial intelligence system. In the process of preparing the dataset (an array for training and verification of its results) of the system in terms of fraudulent signatures, some forensically significant features were revealed, associated with the psychological and anatomical features of the person performing the forgery, both known to criminalistics and new ones. It is emphasized that the joint development of artificial intelligence systems by the methods of computer science and criminalistics can generate additional results that may be useful outside the scope of the research tasks.

Role of AI for application of marketing teaching –A research perspective1

2020 ◽  
pp. 1-9
Author(s):  
Jiheng Hu ◽  
Boya Liu ◽  
Hao Peng
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Probabilistic Neural Network ◽  
Rapid Development ◽  
Development Trend ◽  
Colleges And Universities ◽  
System Reform ◽  
Good Convergence ◽  
Learning Platform ◽  
Modern Media

With the arrival of the era of artificial intelligence, based on the problems existing in the teaching process of marketing specialty, combined with the future business development trend and the core needs of enterprise operation, this paper analyzes the system reform of the practical courses of artificial intelligence and marketing specialty. With the rapid development of computer technology, intelligence has gradually become an important means to solve problems in various industries. In this paper, the modern media as a means, marketing teaching in Colleges and universities as the research background, through the establishment of the depth of marketing in Colleges and Universities Based on artificial intelligence network research learning platform, build a post-modern media communication perspective system. Based on probabilistic neural network and from the perspective of modern media marketing application system construction, the paper proves that the artificial intelligence prediction based on probabilistic neural network has good convergence, fault tolerance and data processing ability through MATLAB. Finally, this paper takes the pricing strategy in marketing as an example, and focuses on the application of artificial intelligence technology in marketing teaching from four aspects: preparation before class, implementation in class, consolidation after class and marketing teaching examination. According to the function and application of the theory of artificial intelligences in marketing teaching, we can find out that teachers must deeply understand the situation of each student’s artificial intelligences, so as to use the theory of artificial intelligences to change the traditional view of students and talents, and teach students according to their aptitude, so as to achieve better teaching effect.

scholarly journals Toward understanding COVID-19 pneumonia: a deep-learning-based approach for severity analysis and monitoring the disease

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Mohammadreza Zandehshahvar ◽  
Marly van Assen ◽  
Hossein Maleki ◽  
Yashar Kiarashi ◽  
Carlo N. De Cecco ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Area Under The Curve ◽  
Valuable Insight ◽  
X Rays ◽  
Single Patient ◽  
New Approach ◽  
Clinical Model ◽  
Average Area ◽  
Learning Technique

AbstractWe report a new approach using artificial intelligence (AI) to study and classify the severity of COVID-19 using 1208 chest X-rays (CXRs) of 396 COVID-19 patients obtained through the course of the disease at Emory Healthcare affiliated hospitals (Atlanta, GA, USA). Using a two-stage transfer learning technique to train a convolutional neural network (CNN), we show that the algorithm is able to classify four classes of disease severity (normal, mild, moderate, and severe) with the average Area Under the Curve (AUC) of 0.93. In addition, we show that the outputs of different layers of the CNN under dominant filters provide valuable insight about the subtle patterns in the CXRs, which can improve the accuracy in the reading of CXRs by a radiologist. Finally, we show that our approach can be used for studying the disease progression in a single patient and its influencing factors. The results suggest that our technique can form the foundation of a more concrete clinical model to predict the evolution of COVID-19 severity and the efficacy of different treatments for each patient through using CXRs and clinical data in the early stages of the disease. This use of AI to assess the severity and possibly predicting the future stages of the disease early on, will be essential in dealing with the upcoming waves of COVID-19 and optimizing resource allocation and treatment.

scholarly journals Using Artificial Intelligence System for Pattern Identification Based on Features Extracted from Gel Electrophoresis Images

2020 ◽  
Vol 11 (2) ◽  
pp. 1944-1952
Author(s):  
Sarmad M. Hadi ◽  
Al-Faiz M Z ◽  
Ali A. Ibrahim
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Gel Electrophoresis ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Artificial Intelligence System ◽  
Average Standard Deviation ◽  
Learning Time ◽  
Intelligence System ◽  
Error Back Propagation

Artificial intelligence has many branches of image processing-based applications in terms of classification and identification, error back-propagation neural network is a great match for such applications as long as linear vector quantization (LVQ) and pattern recognition is another great match for recognition of digital images based on their features. The dataset used in this paper are gel electrophoresis images where 6 features had been extracted from the images and used as input to a neural network for learning and then checked for recognition purposed and the system managed to recognize all the 6 images. Six features had been used: average, standard deviation, smoothness, skewness, uniformity, and entropy. A tiny error rate where allowed in the recognition program to cover the variation of the dataset and the test data (gel-electrophoresis images). The proposed system had successfully managed to identify all of the learned data in both LVQ and error-back-propagation. Error-back-propagation proved itself as a great tool in terms of learning time compared with LVQ, which was very slow in terms of learning time and recognition.

Sign in / Sign up

Export Citation Format

Share Document