Home > Oncology > ESMO 2022 > Deep learning models predict risk of relapse and mutational profile in GIST

Deep learning models predict risk of relapse and mutational profile in GIST

Presented By
Dr Raul Perret, Institut Bergonié, France
Conference
ESMO 2022
An algorithm developed by deep learning from digitalised haematoxylin and eosin-stained whole tumour slide images outperformed classical Miettinen relapse risks prediction in patients with gastrointestinal stromal tumour (GIST). A second algorithm predicted mutations with high accuracy. GIST, the most frequent mesenchymal tumour of the GI tract, shows a variable clinical behaviour ranging from benign to malignant. Risk assessment according to the AFIP/Miettinen classification (high, intermediate, or low risk of relapse) and mutational profiling are major tools for patient management. AFIP/Miettinen classification includes size of the tumour, localisation, and mitotic count [1]. However, Miettinen classification comes with subjectivity (mitotic count) and is time-consuming. In addition, mutational profiling is costly, time-consuming, and not yet available in all countries (or centres). Therefore, Dr Raul Perret (Institut Bergonié, France) and colleagues eva...


Please login to read the full text of the article.


If you have no account yet, please register now.





Posted on