Novel large empirical study of deep transfer learning for COVID-19 classification based on CT and X-ray images
Mansour Almutaani, Turki Turki, Y.-H. Taguchi · 2024
Read Novel large empirical study of deep transfer learning for COVID-19 classification based on CT and X-ray images by Mansour Almutaani, Turki Turki, Y.-H. Taguchi (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11532342.txt.
Description
Mansour Almutaani and two co-authors run a very large test of AI models for spotting COVID-19 in medical images in this 2024 paper. Fast, accurate reading of lung scans can speed up diagnosis and slow spread. The team wanted to find which model setup works best by trying thousands of them.
They gathered over four thousand CT and X-ray images of COVID and non-COVID patients. Four pretrained image models were adapted to the task, then combined by majority vote in many mixes. From about ten thousand built models, the best were picked by cross-checks. The best combined model scored well on CT images, while a single model edged it on X-rays. The authors promote building models at large scale as a path to better tools.
Catalog record
| CREATOR | Mansour Almutaani, Turki Turki, Y.-H. Taguchi |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 71 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |