Carregant...
Tipus de document
Objecte de conferènciaVersió
Versió acceptadaData de publicació
Tots els drets reservats
Si us plau utilitzeu sempre aquest identificador per citar o enllaçar aquest document: https://hdl.handle.net/2445/219964
Leveraging epistemic uncertainty to improve tumour segmentation in breast MRI: an exploratory analysis
Títol de la revista
Director/Tutor
ISSN de la revista
Títol del volum
Recurs relacionat
Resum
Medical image segmentation has improved with deep-learning methods, especially for tumor segmentation. However, variability in tumor shapes, sizes, and enhancement remains a challenge. Breast MRI adds further uncertainty due to anatomical differences. Informing clinicians about result reliability and using model uncertainty to improve predictions are essential. We study Monte-Carlo Dropout for generating multiple predictions and finding consensus segmentation. Our approach reduces false positives using per-pixel uncertainty and improves segmentation metrics. In addition, we study the correlation of model performance to the perceived ease of manual segmentation. Finally, we compare the per-pixel uncertainty with the inter-rater variability as segmented by six different radiologists. Our code is available at https://github.com/smriti-joshi/uncertainty-segmentation-mcdropout.git.
Matèries (anglès)
Citació
Citació
JOSHI, Smriti, OSUALA, Richard, GARRUCHO, Lidia, TSIRIKOGLOU, Apostolia, RIEGO, Javier del, GWOŹDZIEWICZ, Katarzyna, KUSHIBAR, Kaisar, DÍAZ, Oliver, LEKADIR, Karim. Leveraging epistemic uncertainty to improve tumour segmentation in breast MRI: an exploratory analysis. _Comunicació a: Proc. SPIE 12926_. Medical Imaging 2024: Image Processing. Vol. 1292616 (2 April 2024). [consulta: 9 de gener de 2026]. [Disponible a: https://hdl.handle.net/2445/219964]