Predicting the response of a patient to a cancer treatment is of high interest. Nonetheless, this task is still challenging from a medical point of view due to the complexity of the interaction between the patient organism and the considered treatment.
Recent works on foundation models pre-trained with self-supervised learning on large-scale unlabeled histopathology datasets have opened a new direction towards the development of new methods for cancer diagnosis related tasks. Our method exploits several foundation models as feature extractors to obtain a local representation of the image corresponding to a small region of the tissue, then, a global representation of the image is obtained by aggregating these local representations using attention-based Multiple Instance Learning.
Our experimental study conducted on a dataset of patients, shows the promising results of our methodology, notably by highlighting the advantage of using foundation models compared to conventional ImageNet pre-training.
Moreover, the obtained results clearly demonstrates the potential of foundation models for characterizing histopathology images and generating more suited semantic representation for this task. It has been shown that patients who failed to complete the treatment are associated with a low survival rate [ 18 ].
Therefore, identifying theses patients could allow to adapt their treatment and lead to a better outcome [ 3 ]. In this sense, predicting the response to a treatment is of high interest, nonetheless, this task is still challenging from a medical point of view. Currently, post-treatment response of DLBCL cases is evaluated through the Deauville score [ 13 ] , that permits to categorize patients into two classes, namely, positive response i.
