Skip to Main content Skip to Navigation
Conference papers

Comparative validation of graphical models for learning tumor segmentations from noisy manual annotations

Abstract : Classification-based approaches for segmenting medical images commonly suffer from missing ground truth: often one has to resort to manual labelings by human experts, which may show considerable intra-rater and inter-rater variability. We experimentally evaluate several latent class and latent score models for tumor classification based on manual segmentations of different quality, using approximate variational techniques for inference. For the first time, we also study models that make use of image feature information on this specific task. Additionally, we analyze the outcome of hybrid techniques formed by combining aspects of different models. Benchmarking results on simulated MR images of brain tumors are presented: while simple baseline techniques already gave very competitive performance, significant improvements could be made by explicitly accounting for rater quality. Furthermore, we point out the transfer of these models to the task of fusing manual tumor segmentations derived from different imaging modalities on real-world data.
Complete list of metadata

https://hal.inria.fr/hal-00813770
Contributor : Project-Team Asclepios <>
Submitted on : Tuesday, April 16, 2013 - 11:06:42 AM
Last modification on : Friday, January 18, 2019 - 1:20:05 AM

Links full text

Identifiers

Collections

Citation

Frederik O. Kaster, Bjoern H. Menze, Marc-André Weber, Fred A. Hamprecht. Comparative validation of graphical models for learning tumor segmentations from noisy manual annotations. MICCAI Workshop on Medical Computer Vision (MICCAI-MCV'10), 2010, Beijing, China. pp.74-85, ⟨10.1007/978-3-642-18421-5_8⟩. ⟨hal-00813770⟩

Share

Metrics

Record views

313