A1 Journal article (refereed)
Prediction of major torso organs in low-contrast micro-CT images of mice using a two-stage deeply supervised fully convolutional network (2019)

Wang, H., Han, Y., Chen, Z., Hu, R., Chatziioannou, A. F., & Zhang, B. (2019). Prediction of major torso organs in low-contrast micro-CT images of mice using a two-stage deeply supervised fully convolutional network. Physics in Medicine and Biology, 64(24), Article 245014. https://doi.org/10.1088/1361-6560/ab59a4

JYU authors or editors

Publication details

All authors or editors: Wang, Hongkai; Han, Ye; Chen, Zhonghua; Hu, Ruxue; Chatziioannou, Arion F.; Zhang, Bin

Journal or series: Physics in Medicine and Biology

ISSN: 0031-9155

eISSN: 1361-6560

Publication year: 2019

Volume: 64

Issue number: 24

Article number: 245014

Publisher: Institute of Physics

Publication country: United Kingdom

Publication language: English

DOI: https://doi.org/10.1088/1361-6560/ab59a4

Publication open access: Not open

Publication channel open access: 

Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/93715

Abstract

Delineation of major torso organs is a key step of mouse micro-CT image analysis. This task is challenging due to low soft tissue contrast and high image noise, therefore anatomical prior knowledge is needed for accurate prediction of organ regions. In this work, we develop a deeply supervised fully convolutional network which uses the organ anatomy prior learned from independently acquired contrast-enhanced micro-CT images to assist the segmentation of non-enhanced images. The network is designed with a two-stage workflow which firstly predicts the rough regions of multiple organs and then refines the accuracy of each organ in local regions. The network is trained and evaluated with 40 mouse micro-CT images. The volumetric prediction accuracy (Dice score) varies from 0.57 for the spleen to 0.95 for the heart. Compared to a conventional atlas registration method, our method dramatically improves the Dice of the abdominal organs by 18~26%. Moreover, the incorporation of anatomical prior leads to more accurate results for small-sized low-contrast organs (e.g. the spleen and kidneys). We also find that the localized stage of the network has better accuracy than the global stage, indicating that localized single organ prediction is more accurate than global multiple organ prediction. With this work, the accuracy and efficiency of mouse micro-CT image analysis are greatly improved and the need for using contrast agent and high X-ray dose is potentially reduced.

Keywords: imaging; computed tomography; anatomy; automated pattern recognition; neural networks (information technology)

Free keywords: deeply supervised network; fully convolutional network; micro-CT; mouse image; organ segmentation

Contributing organizations

Ministry reporting: Yes

Reporting Year: 2019

JUFO rating: 2