Jonas Ammeling from our group recently presented a paper on the prediction of survival of lung cancer patients from tiny tissue parts (from a tissue micro array) using attention-based multiple instance learning. One key finding was that the prediction of survival worked similarly good to using established methods on tabular clinical data such as smoker status, age, sex, and even stage and grade.

Here is the full video of his presentation for this year’s workshop Bildverarbeitung in der Medizin (image processing in medicine) in Braunschweig, Germany: