2 results match your criteria: "Institut Optique Graduate School[Affiliation]"
Multi-View Learning for Material Classification.
J Imaging
July 2022
Univ Lyon, UJM-Saint-Etienne, CNRS, Institut Optique Graduate School, Laboratoire Hubert Curien UMR 5516, F-42023 Saint-Etienne, France.
Material classification is similar to texture classification and consists in predicting the material class of a surface in a color image, such as wood, metal, water, wool, or ceramic. It is very challenging because of the intra-class variability. Indeed, the visual appearance of a material is very sensitive to the acquisition conditions such as viewpoint or lighting conditions.
View Article and Find Full Text PDFNatural Language Processing for Patient Selection in Phase I or II Oncology Clinical Trials.
JCO Clin Cancer Inform
June 2021
Drug Development Department (DITEP), Gustave Roussy, Villejuif, France.
Article Synopsis
- Early discontinuation in early-phase oncology trials impacts over one third of patients and complicates study timelines and costs; the research aims to predict successful completion of screening and dose-limiting toxicity periods using automated report analysis.
- A machine learning model was developed using a large dataset of consultation reports to predict patient outcomes, achieving solid performance metrics (F1 score 0.80, recall 0.81) and demonstrating potential to significantly reduce screening failure rates from 39.8% to 12.8%.
- The study highlights the importance of using machine learning with semantic analysis as a promising approach for improving patient selection in clinical trials, focusing on key terms related to disease characteristics and laboratory findings