Standard Three-dimensional (3D) Magnetic Resonance Imaging (MRI) segmentation models typically rely on a fixed threshold or argmax-based class selection, providing little or no insight into model uncertainty, which can limit clinician trust. In this work, we developed a framework that integrates a calibrated 3D U-Net into a Virtual Reality (VR) system, enabling clinicians to manipulate confidence thresholds in real time and observe how the segmentation changes. The network was trained to segment mandibular structures (submandibular glands and mandibular canal) on 55 T2-weighted MRI scans from the AAPM RT-MAC 2019 dataset and post hoc calibrated using temperature scaling. The VR application, built in Unity with OpenXR, offers two interaction modes: a single upper-threshold mode and a range mode that controls both lower and upper bounds. A user study with six clinicians was conducted to evaluate both modes using the UMUX-Lite questionnaire (from which a System Usability Scale (SUS)-equivalent score was derived), interaction logs, and qualitative feedback. Both modes were rated as highly usable, and narrower confidence intervals, focusing on the most reliable predictions, were more popular among users. The results suggest that enabling real-time adjustment of confidence thresholds improves the clarity of segmentation outputs and may support clinicians’ perceived confidence, as indicated by participants’ qualitative feedback and stated preferences.
Rasouli et al. (Tue,) studied this question.