Interactive Confidence Thresholding in Virtual Reality for AI-Assisted 3D MRI Segmentation of Mandibular Glands
Applied Sciences · 14.07.2026 · 16 (14) · 7067
DOI: 10.3390/app16147067 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 14.07.2026. Verfasst von Nastaran Rasouli und 7 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research Council of Finland.
Abstract (Originalsprache)
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.
Förderung
- Research Council of Finland
Zitieren
APA
Rasouli, N., Orsmaa, L., Saukkoriipi, M., Kangas, J., Järnstedt, J., Sahlsten, J., Kaski, K., & Raisamo, R. (2026). Interactive Confidence Thresholding in Virtual Reality for AI-Assisted 3D MRI Segmentation of Mandibular Glands. Applied Sciences, 16(14), 7067. https://doi.org/10.3390/app16147067
Vancouver
Rasouli N, Orsmaa L, Saukkoriipi M, Kangas J, Järnstedt J, Sahlsten J, et al. Interactive Confidence Thresholding in Virtual Reality for AI-Assisted 3D MRI Segmentation of Mandibular Glands. Applied Sciences. 2026;16(14):7067. doi:10.3390/app16147067
BibTeX
@article{Rasouli2026,
author = {Rasouli, Nastaran and Orsmaa, Lotta and Saukkoriipi, Mikko and Kangas, Jari and Järnstedt, Jorma and Sahlsten, Jaakko and Kaski, Kimmo and Raisamo, Roope},
title = {Interactive Confidence Thresholding in Virtual Reality for AI-Assisted 3D MRI Segmentation of Mandibular Glands},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {14},
pages = {7067},
doi = {10.3390/app16147067}
}
EUVIMED