MCU-Net: A framework towards uncertainty representations for decision support system patient referrals in healthcare contexts
This addresses the need for patient-centered trust and reliability in healthcare AI by enabling human-in-the-loop referrals for uncertain cases, though it is incremental as it builds on existing methods like U-Net and Monte Carlo Dropout.
The paper tackles the problem of lacking uncertainty representation in deep learning for healthcare decision support, presenting MCU-Net, a framework combining U-Net with Monte Carlo Dropout and four uncertainty metrics, which maximizes automated performance on a patient level while referring uncertain cases to professionals.
Incorporating a human-in-the-loop system when deploying automated decision support is critical in healthcare contexts to create trust, as well as provide reliable performance on a patient-to-patient basis. Deep learning methods while having high performance, do not allow for this patient-centered approach due to the lack of uncertainty representation. Thus, we present a framework of uncertainty representation evaluated for medical image segmentation, using MCU-Net which combines a U-Net with Monte Carlo Dropout, evaluated with four different uncertainty metrics. The framework augments this by adding a human-in-the-loop aspect based on an uncertainty threshold for automated referral of uncertain cases to a medical professional. We demonstrate that MCU-Net combined with epistemic uncertainty and an uncertainty threshold tuned for this application maximizes automated performance on an individual patient level, yet refers truly uncertain cases. This is a step towards uncertainty representations when deploying machine learning based decision support in healthcare settings.