Joint Multi Organ and Tumor Segmentation from Partial Labels Using Federated Learning

Chen Shen, Pochuan Wang, Dong Yang, Daguang Xu, Masahiro Oda, Po-Ting Chen, Kao-Lang Liu, Wei-Chih Liao, Chiou-Shann Fuh, Kensaku Mori, Weichung Wang, Holger R. Roth

Abstract

Segmentation studies in medical image analysis are always associated with a particular task scenario. However, building datasets to train models to segment multiple types of organs and pathologies is challenging. For example, a dataset annotated for the pancreas and pancreatic tumors will result in a model that cannot segment other organs, like the liver and spleen, visible in the same abdominal computed tomography image. The lack of a well-annotated dataset is one limitation resulting in a lack of universal segmentation models. Federated learning (FL) is ideally suited for addressing this issue in the real-world context. In this work, we show that each medical center can use training data for distinct tasks to collaboratively build more generalizable segmentation models for multiple segmentation tasks without the requirement to centralize datasets in one place. The main challenge of this research is the heterogeneity of training data from various institutions and segmentation tasks. In this paper, we propose a multi-task segmentation framework using FL to learn segmentation models using several independent datasets with different annotations of organs or tumors. We include experiments on four publicly available single-task datasets, including MSD liver (w/ tumor), MSD spleen, MSD pancreas (w/ tumor), and KITS19. Experimental results on an external validation set to highlight the advantages of employing FL in multi-task organ and tumor segmentation.
BibTeX
@inproceedings{shen2022joint,
  author = {Chen Shen and Pochuan Wang and Dong Yang and Daguang Xu and Masahiro Oda and Po-Ting Chen and Kao-Lang Liu and Wei-Chih Liao and Chiou-Shann Fuh and Kensaku Mori and Weichung Wang and Holger R. Roth},
  title = {{Joint Multi Organ and Tumor Segmentation from Partial Labels Using Federated Learning}},
  booktitle = {DeCaF/FAIR @ MICCAI},
  year = {2022},
  doi = {10.1007/978-3-031-18523-6\_6},
}

Loading related content...

Figure