Codeless Deep Learning of COVID-19 Chest X-Ray Image Dataset with KNIME Analytics Platform
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Objectives: This paper proposes a method for computer-assisted diagnosis of coronavirus disease 2019 (COVID-19) throughchest X-ray imaging using a deep learning model without writing a single line of code using the Konstanz Information Miner(KNIME) analytics platform. Methods: We obtained 155 samples of posteroanterior chest X-ray images from COVID-19open dataset repositories to develop a classification model using a simple convolutional neural network (CNN). All of theimages contained diagnostic information for COVID-19 and other diseases. The model would classify whether a patient wasinfected with COVID-19 or not. Eighty percent of the images were used for model training, and the rest were used for testing. The graphic user interface-based programming in the KNIME enabled class label annotation, data preprocessing, CNNmodel training and testing, performance evaluation, and so on. Results: 1,000 epochs training were performed to test thesimple CNN model. The lower and upper bounds of positive predictive value (precision), sensitivity (recall), specificity, andf-measure are 92.3% and 94.4%. Both bounds of the model’s accuracies were equal to 93.5% and 96.6% of the area under thereceiver operating characteristic curve for the test set. Conclusions: In this study, a researcher who does not have basic knowledgeof python programming successfully performed deep learning analysis of chest x-ray image dataset using the KNIME independently. The KNIME will reduce the time spent and lower the threshold for deep learning research applied to healthcare.
Abstract
Objectives: This paper proposes a method for computer-assisted diagnosis of coronavirus disease 2019 (COVID-19) throughchest X-ray imaging using a deep learning model without writing a single line of code using the Konstanz Information Miner(KNIME) analytics platform. Methods: We obtained 155 samples of posteroanterior chest X-ray images from COVID-19open dataset repositories to develop a classification model using a simple convolutional neural network (CNN). All of theimages contained diagnostic information for COVID-19 and other diseases. The model would classify whether a patient wasinfected with COVID-19 or not. Eighty percent of the images were used for model training, and the rest were used for testing. The graphic user interface-based programming in the KNIME enabled class label annotation, data preprocessing, CNNmodel training and testing, performance evaluation, and so on. Results: 1,000 epochs training were performed to test thesimple CNN model. The lower and upper bounds of positive predictive value (precision), sensitivity (recall), specificity, andf-measure are 92.3% and 94.4%. Both bounds of the model’s accuracies were equal to 93.5% and 96.6% of the area under thereceiver operating characteristic curve for the test set. Conclusions: In this study, a researcher who does not have basic knowledgeof python programming successfully performed deep learning analysis of chest x-ray image dataset using the KNIME independently. The KNIME will reduce the time spent and lower the threshold for deep learning research applied to healthcare.
참고문헌 (17)
- "Artificial intelligence in healthcare market size, share & trends analysis report by component (hardware, software, services), by application, by region, competitive insights, and segment forecasts, 2019-2025" (2019)[URL]
- Guo Y, "Artificial intelligence in health care : bibliometric analysis", J Med Internet Res, 22(7), pp.e18228~ (2020)
- Jiang F, "Artificial intelligence in healthcare : past, present and future", Stroke Vasc Neurol, 2(4), pp.230~243 (2017)
- "Keras UI: a GUI to manage image classification" (2019)[URL]
- Blume PA, "The LabVIEW style book" (2011), Prentice-Hall
- Frank E, "Data mining and knowledge discovery handbook", pp.1269~1277 (2009), Springer
- "KNIME Analytics Platform" (2020)[URL]
- Lin Q, "A conceptual model for the coronavirus disease 2019(COVID-19)outbreak in Wuhan, China with individual reaction and governmental action", Int J Infect Dis, 93, pp.211~216 (2020)
- "RSNA pneumonia detection challenge" (2018)[URL]
- "Covid-19 image data collection: prospective predictions are the future" (2020)[URL]
- Shaheen F, "Impact of automatic feature extraction in deep learning architecture", Proceedings of 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA), pp.1~8 (2016)
- Vinayakumar R, "Applying convolutional neural network for network intrusion detection", Proceedings of 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), pp.1222~1228 (2017)
- Swapna G, "Automated detection of diabetes using CNN and CNN-LSTM network and heart rate signals", Procedia computer science, 132, pp.1253~1262 (2018)
- Gao T, "Chest X-ray image analysis and classification for COVID-19 pneumonia detection using deep CNN" (2020)[DOI]
- Ismael AM, "Deep learning approaches for COVID-19 detection based on chest X-ray images", Expert Syst Appl, 164, pp.114054~ (2021)
- "Diagnosing COVID-19 pneumonia from X-ray and CT images using deep learning and transfer learning algorithms" (2020)[URL]
- "Chexphoto: 10,000+ smartphone photos and synthetic photographic transformations of chest xrays for benchmarking deep learning robustness" (2020)[URL]