Biochemical Prostate Cancer Recurrence Prediction: Thinking Fast & Slow
This work addresses prognostic monitoring for prostate cancer patients, but it is incremental as it applies a known method to a specific medical domain.
The paper tackled predicting time to biochemical recurrence in prostate cancer after prostatectomy using a two-stage multiple instance learning strategy, achieving a mean C-index of 0.733 on internal validation and 0.603 on an external challenge set.
Time to biochemical recurrence in prostate cancer is essential for prognostic monitoring of the progression of patients after prostatectomy, which assesses the efficacy of the surgery. In this work, we proposed to leverage multiple instance learning through a two-stage ``thinking fast \& slow'' strategy for the time to recurrence (TTR) prediction. The first (``thinking fast'') stage finds the most relevant WSI area for biochemical recurrence and the second (``thinking slow'') stage leverages higher resolution patches to predict TTR. Our approach reveals a mean C-index ($Ci$) of 0.733 ($θ=0.059$) on our internal validation and $Ci=0.603$ on the LEOPARD challenge validation set. Post hoc attention visualization shows that the most attentive area contributes to the TTR prediction.