Leveraging Uncertainty in Deep Learning for Pancreatic Adenocarcinoma Grading
This work addresses the need for reliable and explainable AI-based cancer grading to improve diagnosis accuracy and clinician trust in digital pathology, though it is incremental as it applies Bayesian methods to a specific domain.
The paper tackled the problem of automating pancreatic adenocarcinoma grading from stained images to address time-consuming and error-prone manual methods, achieving a system that correlates estimated uncertainty with prediction error and allows adjustable acceptance thresholds for clinical use.
Pancreatic cancers have one of the worst prognoses compared to other cancers, as they are diagnosed when cancer has progressed towards its latter stages. The current manual histological grading for diagnosing pancreatic adenocarcinomas is time-consuming and often results in misdiagnosis. In digital pathology, AI-based cancer grading must be extremely accurate in prediction and uncertainty quantification to improve reliability and explainability and are essential for gaining clinicians trust in the technology. We present Bayesian Convolutional Neural Networks for automated pancreatic cancer grading from MGG and HE stained images to estimate uncertainty in model prediction. We show that the estimated uncertainty correlates with prediction error. Specifically, it is useful in setting the acceptance threshold using a metric that weighs classification accuracy-reject trade-off and misclassification cost controlled by hyperparameters and can be employed in clinical settings.