The path towards improving oncological outcomes and quality of life while reducing costs in cancer care is directly linked to personlized medicine. Since some imaging-relevant features are not discernible to the human eye, machine learning (ML) systems are the last resort to identify prognostic and predictive features, allowing clinicians to select the best treatment for a particular patient and oncological characteristics. However, current ML systems have considerable limitations. Simple radiomics approaches might require manual segmentations, depend on hand-crafted features, and risk missing clinically-relevant information. On the other hand, more complex deep learning approaches overcome the previous limitations by performing task-related representation learning, but have difficulties generalizing to new datasets and lack interpretability. Thus, this workshop aims at calling the attention of the MICCAI community, fostering discussions and the presentation of ideas and algorithms to tackle the many current challenges related to the implementation of ML systems for treatment response assessment and prediction. AI4Treat is a joint effort of the MICCAI community and the European Society of Radiology (ESR).

NEWS: The workshop program is now available! Don’t forget to register for the workshop day at this link!