Artificial intelligence applied to digestive endoscopy
Journal Title: Applied Medical Informatics - Year 2019, Vol 41, Issue 0
Abstract
Introduction: In recent years, deep learning methods have improved significantly and have beenimplemented in fields such as medical imaging. Applying these techniques to digestiveendoscopy has led diagnosis rates for entities such as polyps similar or even better than humans.Materials and methods: We trained a convolutional neural network to classify medical images intotwo categories – with polyps or with normal mucosa – using about 800 images. For scalabilityand accessibility reasons, the architecture was implemented into a web interface. To ourknowledge, this is the first solution to emphasize the importance of scalability and accessibility.We developed an interface that can be used in real life scenarios and is easy to use, being webenabled and accessible from any device. Results: Experimental results show that our solution isfeasible and can be implemented in clinical practice. The model was evaluated on the test setand under these circumstances the final test accuracy was 100%. One limitation is the numberof images used for training. Whereas 800 images were used in total for training, only 100contained normal mucosa and 700 contained polyps. With future research, the number ofimages used will be increased and data enhancement techniques will be used, alongside withendoscopy videos. Conclusion: In conclusion, deep learning advances can be successfully appliedto biomedical fields such as digestive endoscopy for tasks such as polyp classification, with greatpotential of developing tools for medical professionals.
Authors and Affiliations
Andrei IOANOVICI, Sergiu CHERECHEȘ, Ștefan MĂRUȘTERI
Keywords
Related Articles
- EP ID EP655051
- DOI -
- Views 81
- Downloads 0
Web Application Used in Education for a Healthy Diet
www.anchetainfarfurie.ro is a website that intends to help healthy people maintain, increase or decrease their weight. www.anchetainfarfurie.ro loggs food and activities during day. The program contains a database of 639...
Quality of life measurement instruments for headache and migraine disorders
Introduction: The present study aims to achieve a comprehensive review of existing patient-reported outcome measurement instruments (PROMs) used for assessing the impact of headache disorders and migraine on patients hea...
Structural equation modelling for assessing the psychosocial risk factors of abortion on demand
Introduction: In Romania, an increasing number of women are opting for abortion on demand, despite the large variety of contraceptive methods and their ease of use. Some of the factors that influence the decision of unde...
Satistical Graphical User Interface Plug-In for Survival Analysis in R Statistical and Graphics Language and Environment.
[i][b]Introduction[/b][/i]: R is a statistical and graphics language and environment. Although it is extensively used in command line, graphical user interfaces exist to ease the accommodation with it for new users. Rcmd...
Breast cancer pathology, types of neoplasia and number of cases in a General Surgery Department
Introduction: Quality of Life (QOL) is a complex concept considered a construct with many different facets which has a strong impact in the socio-medical field. Diagnosis of breast cancer or any other type of neoplasm, t...