Segmentation label propagation using deep convolutional neural networks and dense conditional random field

• Main Authors: Mingchen Gao, Ziyue Xu, Le Lu, Wu, Aaron, Nogues, Isabella, Summers, Ronald M., Mollura, Daniel J.
• Format: Conference Proceeding
• Language: English
• Subjects: Accuracy; Annotations; Biomedical imaging; Computed tomography; Convolutional Neural Network; Dense Conditional Random Field; Fields (mathematics); Image segmentation; Interstitial Lung Disease; Labeling; Labels; Level (quantity); Lungs; Medical imaging; Message passing; Multi-class Labeling; Neural networks; Segmentation; Segmentation Label Propagation
• ISSN: 1945-8452
• DOI: 10.1109/ISBI.2016.7493497

Availability and accessibility of large-scale annotated medical image datasets play an essential role in robust supervised learning of medical image analysis. Missed labeling of regions of interest is a common issue on existing medical image datasets due to the labor intensive nature of the annotation task which requires high levels of clinical proficiency. In this paper, we present a segmentation based label propagation method to a publicly available dataset on interstitial lung disease [3], to address the missing annotation challenge. Upon validation from an expert radiologist, the amount of available annotated training data is largely increased. Such a dataset expansion can can potentially increase the accuracy of Computer-aided Detection (CAD) systems. The proposed constrained segmentation propagation algorithm combines the cues from the initial annotations, deep convolutional neural networks and a dense fully-connected Conditional Random Field (CRF) that achieves high quantitative accuracy levels.