HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Journal articles

Iterative Confidence Relabeling with Deep ConvNets for Organ Segmentation with Partial Labels

Olivier Petit 1 Nicolas Thome 1 Luc Soler 2
1 CEDRIC - VERTIGO - CEDRIC. Données complexes, apprentissage et représentations
CEDRIC - Centre d'études et de recherche en informatique et communications
Abstract : Training deep ConvNets requires large labeled datasets. However, collecting pixel-level labels for medical image segmentation is very expensive and requires a high level of expertise. In addition, most existing segmentation masks provided by clinical experts focus on specific anatomical structures. In this paper, we propose a method dedicated to handle such partially labeled medical image datasets. We propose a strategy to identify pixels for which labels are correct, and to train Fully Convolutional Neural Networks with a multi-label loss adapted to this context. In addition, we introduce an iterative confidence self-training approach inspired by curriculum learning to relabel missing pixel labels, which relies on selecting the most confident prediction with a specifically designed confidence network that learns an uncertainty measure which is leveraged in our relabeling process. Our approach, INERRANT for Iterative coNfidencE Relabeling of paRtial ANnoTations, is thoroughly evaluated on two public datasets (TCAI and LITS), and one internal dataset with seven abdominal organ classes. We show that INERRANT robustly deals with partial labels, performing similarly to a model trained on all labels even for large missing label proportions. We also highlight the importance of our iterative learning scheme and the proposed confidence measure for optimal performance. Finally we show a practical use case where a limited number of completely labeled data are enriched by publicly available but partially labeled data.
Document type :
Journal articles
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03243619
Contributor : Olivier Petit Connect in order to contact the contributor
Submitted on : Monday, May 31, 2021 - 4:56:25 PM
Last modification on : Thursday, March 10, 2022 - 9:44:02 PM

File

CMIG_INERRANT.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Olivier Petit, Nicolas Thome, Luc Soler. Iterative Confidence Relabeling with Deep ConvNets for Organ Segmentation with Partial Labels. Computerized Medical Imaging and Graphics, Elsevier, 2021, pp.101938. ⟨10.1016/j.compmedimag.2021.101938⟩. ⟨hal-03243619⟩

Share

Metrics

Record views

45

Files downloads

84