1. Adversarial Graph Learning and Deep Learning Techniques for improving diagnosis within CT and Ultrasound images
- Author
-
Badea Radu, Mitrea Delia-Alexandrina, Nedevschi Sergiu, and Bacea Dan-Sebastian
- Subjects
Treatment response ,medicine.diagnostic_test ,Coronavirus disease 2019 (COVID-19) ,business.industry ,Computer science ,Deep learning ,Ultrasound ,Pattern recognition ,Computed tomography ,02 engineering and technology ,030218 nuclear medicine & medical imaging ,03 medical and health sciences ,0302 clinical medicine ,Binary classification ,0202 electrical engineering, electronic engineering, information engineering ,medicine ,Graph (abstract data type) ,020201 artificial intelligence & image processing ,In patient ,Artificial intelligence ,business - Abstract
Computed tomography (CT) examination has an important role in diagnosing, monitoring, and evaluating treatment response in patients infected with COVID-19. Chest CT images provide a reliable alternative to the reverse transcription polymerase chain reaction (RT-PCR). Ultrasonography provides a non-invasive and low-cost solution for diagnosing liver tumors. Recognition of hepatocellular carcinoma (HCC) in ultrasound images can provide a suitable alternative to the more invasive and dangerous method of doing a biopsy. Significant effort has been dedicated to the development of automated ways of diagnosing COVID-19 based on CT scans and on diagnosing liver tumors based on ultrasound images, some of them use deep learning methods. This paper proposes a method for training deep neural networks for performing binary classification, which is called Adversarial Graph Learning. Improved classification performance and reliability is achieved by using our method for both target tasks, recognizing COVID-19 in CT images and recognizing HCC in ultrasound images.
- Published
- 2020