| abstract |
Methods of providing a computational model for predicting an activity of a test agent with respect to a 3D cell structure, such as a spheroid, an organoid, and a tumor sphere. Specifically, an automatic learning algorithm is used to generate a quantitative model of drug response in the 3D cell structure using zone-specific image characteristics, the areas comprising a necrotic zone, a rest and a proliferation zone. The invention also relates to markerless prediction methods using said computational model and a device adapted to implement the methods of the invention. |