Abstract
The three-dimensional information in CT scans reveals notorious findings in the medical context, also for detecting symptoms of COVID-19 in chest CT scans. However, due to the lack of availability of large-scale datasets in 3D, the use of attention-based models in this field is proven to be difficult. With transfer learning, this work tackles this problem, investigating the performance of a pre-trained TimeSformer model, which was originally developed for video classification, on COVID-19 classification of three-dimensional chest CT scans. The attention-based model outperforms a DenseNet baseline. Furthermore, we propose three new attention schemes for TimeSformer improving the accuracy of the model by 1.5% and reducing runtime by almost 25% compared to the original attention scheme.
Original language | English |
---|---|
Title of host publication | Artificial Intelligence in Medicine |
Subtitle of host publication | AIME 2023 |
Editors | Jose M. Juarez, Mar Marcos, Gregor Stiglic, Allan Tucker |
Publisher | Springer, Cham |
Pages | 229-238 |
Number of pages | 10 |
Volume | 13897 |
ISBN (Electronic) | 978-3-031-34344-5 |
ISBN (Print) | 978-3-031-34343-8 |
DOIs | |
Publication status | Published - 2023 |
Event | International Conference on Artificial Intelligence in Medicine - Singapore, Singapore, Singapore Duration: 5 Aug 2023 → 7 Aug 2023 https://iaim2023.sg/ |
Publication series
Series | Lecture Notes in Computer Science |
---|---|
Volume | 13897 |
ISSN | 0302-9743 |
Conference
Conference | International Conference on Artificial Intelligence in Medicine |
---|---|
Abbreviated title | iAIM 2023 |
Country/Territory | Singapore |
City | Singapore |
Period | 5/08/23 → 7/08/23 |
Internet address |