2024 | OriginalPaper | Buchkapitel
Multi-organ Segmentation in CT from Partially Annotated Datasets using Disentangled Learning
verfasst von : Tianyi Wang, Chang Liu, Leonhard Rist, Andreas Maier
Erschienen in: Bildverarbeitung für die Medizin 2024
Verlag: Springer Fachmedien Wiesbaden
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
While deep learning models are known to be able to solve the task of multi-organ segmentation, the scarcity of fully annotated multi-organ datasets poses a significant obstacle during training. The 3D volume annotation of such datasets is expensive, time-consuming and varies greatly in the variety of labeled structures. To this end, we propose a solution that leverages multiple partially annotated datasets using disentangled learning for a single segmentation model. Dataset-specific encoder and decoder networks are trained, while a joint decoder network gathers the encoders’ features to generate a complete segmentation mask. We evaluated our method using two simulated partially annotated datasets: one including the liver, lungs and kidneys, the other bones and bladder. Our method is trained to segment all five organs achieving a dice score of 0.78 and an IoU of 0.67. Notably, this performance is close to a model trained on the fully annotated dataset, scoring 0.80 in dice score and 0.70 in IoU respectively.