Deep Multiple Instance Learning Model to Predict Outcome of Pancreatic Cancer Following Surgery
Caroline Truntzer, Dina Ouahbi, Titouan Huppé, David Rageot, Alis Ilie, Chloe Molimard, Françoise Beltjens, Anthony Bergeron, Angelique Vienot, Christophe Borg, Franck Monnien, Frédéric Bibeau, Valentin Derangère, François Ghiringhelli, Roberto Piergentili · 2024
Read Deep Multiple Instance Learning Model to Predict Outcome of Pancreatic Cancer Following Surgery by Caroline Truntzer, Dina Ouahbi, Titouan Huppé, David Rageot, Alis Ilie, Chloe Molimard, Françoise Beltjens, Anthony Bergeron, Angelique Vienot, Christophe Borg, Franck Monnien, Frédéric Bibeau, Valentin Derangère, François Ghiringhelli, Roberto Piergentili (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-11673784.txt.
Description
Pancreatic cancer returns often after surgery, and doctors lack good tools to predict whose will. Caroline Truntzer and co-authors train a deep learning model on microscope slides of the removed tumors. The model uses multiple instance learning, judging a whole slide from its many small patches. It was built on 206 surgical patients, then tested on 166 patients from The Cancer Genome Atlas.
The model split patients into two groups with clearly different outlooks. In the training set the better group carried a hazard ratio of 0.72 for progression, and 0.63 in the validation set, both statistically firm. Gene and mutation data showed the worse group matched the squamous subtype of the cancer, a known aggressive form. The authors argue that slide-reading models could help doctors choose who should receive adjuvant treatment after surgery.
Catalog record
| CREATOR | Caroline Truntzer, Dina Ouahbi, Titouan Huppé, David Rageot, Alis Ilie, Chloe Molimard, Françoise Beltjens, Anthony Bergeron, Angelique Vienot, Christophe Borg, Franck Monnien, Frédéric Bibeau, Valentin Derangère, François Ghiringhelli, Roberto Piergentili |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 38 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |