Deep learning based tissue analysis predicts outcome in colorectal cancer.
Bychkov D, Linder N, Turkki R, Nordling S, Kovanen PE, Verrill C, Walliander M, Lundin M, Haglund C, Lundin J. · 2018
Read Deep learning based tissue analysis predicts outcome in colorectal cancer. by Bychkov D, Linder N, Turkki R, Nordling S, Kovanen PE, Verrill C, Walliander M, Lundin M, Haglund C, Lundin J. (2018) 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/europmc-pmc5821847.txt.
Description
Bychkov and co-authors teach a deep network to predict colon cancer outcomes. Pathologists judge tumor tissue by eye to grade risk. Image algorithms have lately matched expert skill at such tasks. The team skips tissue labels and aims straight at outcome.
The network trained on stained tissue spots from 420 patients. It split patients into low and high risk groups. Its calls beat expert visual grading on the same spots. Whole-slide expert grading also fell short of the network. Hazard ratios reached 2.3 for the network against 1.67 for experts. Readers get proof that tissue images hold more outcome clues than eyes can see.
Catalog record
| CREATOR | Bychkov D, Linder N, Turkki R, Nordling S, Kovanen PE, Verrill C, Walliander M, Lundin M, Haglund C, Lundin J. |
|---|---|
| YEAR | 2018 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |