Coarse-to-Fine Adversarial Networks and Zone-Based Uncertainty Analysis for NK/T-Cell Lymphoma Segmentation in CT/PET Images.

Hu, Xiaobin; Guo, Rui; Chen, Jieneng; Li, Hongwei; Waldmannstetter, Diana; Zhao, Yu; Li, Biao; Shi, Kuangyu; Menze, Bjoern (2020). Coarse-to-Fine Adversarial Networks and Zone-Based Uncertainty Analysis for NK/T-Cell Lymphoma Segmentation in CT/PET Images. IEEE journal of biomedical and health informatics, 24(9), pp. 2599-2608. Institute of Electrical and Electronics Engineers 10.1109/JBHI.2020.2972694

Text 08988186__002_.pdf - Published Version Restricted to registered users only Available under License Publisher holds Copyright. Download (3MB) | Request a copy

Extranodal natural killer/T cell lymphoma (ENKL), nasal type is a kind of rare disease with a low survival rate that primarily affects Asian and South American populations. Segmentation of ENKL lesions is crucial for clinical decision support and treatment planning. This paper is the first study on computer-aided diagnosis systems for the ENKL segmentation problem. We propose an automatic, coarse-to-fine approach for ENKL segmentation using adversarial networks. In the coarse stage, we extract the region of interest bounding the lesions utilizing a segmentation neural network. In the fine stage, we use an adversarial segmentation network and further introduce a multi-scale L1 loss function to drive the network to learn both global and local features. The generator and discriminator are alternately trained by backpropagation in an adversarial fashion in a min-max game. Furthermore, we present the first exploration of zone-based uncertainty estimates based on Monte Carlo dropout technique in the context of deep networks for medical image segmentation. Specifically, we propose the uncertainty criteria based on the lesion and the background, and then linearly normalize them to a specific interval. This is not only the crucial criterion for evaluating the superiority of the algorithm, but also permits subsequent optimization by engineers and revision by clinicians after quantitatively understanding the main source of uncertainty from the background or the lesion zone. Experimental results demonstrate that the proposed method is more effective and lesion-zone stable than state-of-the-art deep-learning based segmentation model.

Interest & Impact

Downloads

1 since deposited on 05 Jan 2021
0 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item