Attention-based Multiple Instance Learning for Survival Prediction on Lung Cancer Tissue Microarrays
This work addresses survival prediction for lung cancer patients, but it is incremental as it extends an existing AMIL approach to a new task with similar performance.
The authors tackled survival prediction for lung cancer patients using attention-based multiple instance learning (AMIL) on tissue microarray slides, achieving a C-index performance similar to established methods that rely on clinical factors like age and cancer stage.
Attention-based multiple instance learning (AMIL) algorithms have proven to be successful in utilizing gigapixel whole-slide images (WSIs) for a variety of different computational pathology tasks such as outcome prediction and cancer subtyping problems. We extended an AMIL approach to the task of survival prediction by utilizing the classical Cox partial likelihood as a loss function, converting the AMIL model into a nonlinear proportional hazards model. We applied the model to tissue microarray (TMA) slides of 330 lung cancer patients. The results show that AMIL approaches can handle very small amounts of tissue from a TMA and reach similar C-index performance compared to established survival prediction methods trained with highly discriminative clinical factors such as age, cancer grade, and cancer stage