Quality Assessment Based on PCJO for Low-dose CT Images

Tianjie Xu, Lu Zhang, Yang Chen, Huazhong Shu, Limin Luo


Published in:Fully3D 2017 Proceedings


PCJO, LDCT, image reconstruction
The anthropomorphic model observer (MO) has played an important role in the assessment of medical imaging systems due to its tasked-based features. In this paper, an improved clinical-relevant anthropomorphic MO is proposed for the task of detecting and locating lesions based on low-dose computerized tomography (LDCT) and the perceptually relevant channelized joint observer (PCJO). During our former study, PCJO has been proposed for detecting and locating multiple hyposignals and hypersignals of conventional dose with unknown amplitude, orientation, size and location. In this paper, we extend PCJO to LDCT field to explore its generality. Experiments were conducted using different image sets obtained by two LDCT image reconstruction algorithms: filtered back projection (FBP) and adaptive statistical iterative reconstruction (ASIR), and seek to compare their advantages and disadvantages. Preliminary results show that the extended PCJO can detect and locate multiple lesions with unknown amplitude, orientation, size and location in LDCT reconstruction images and approach experts’ performance under certain VDP threshold and combinations of channels.
Tianjie Xu
Laboratory of Image Science and Technology, Southeast University, China
Lu Zhang
IETR, CNRS UMR 6164, INSA Rennes, France
Yang Chen
Laboratory of Image Science and Technology, Southeast University, China
Huazhong Shu
Laboratory of Image Science and Technology, Southeast University, China
Limin Luo
Laboratory of Image Science and Technology, Southeast University, China
  1. Rusinek H, Naidich D P, McGuinness G, et al. Pulmonary nodule detection: low-dose versus conventional CT. Radiology, 209(1): 243-249, 1998
  2. Yang Chen, Xindao Yin, Luyao Shi, et al. Improving abdomen tumor low-dose CT images using a fast dictionary learning based processing, Physics in Medicine and Biology, 58(16):5803–5820, 2013.
  3. G. Mather, Foundations of Sensation and Perception. Hove and New York, USA: Psychology Press Ltd., Talor & Francis Inc., 2009.
  4. Barrett Harrison H., Myers Kyle J. Foundations of image science. John Wiley & Sons, 2013.
  5. He X., Park S. Model observers in medical imaging research. Theranostics. 2013.
  6. Zhang Lu, Goossens Bart, Cavaro-Menard Christine, et al. Channelized model observer for the detection and estimation of signals with unknown amplitude, orientation, and size. JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 30(11): 2422-2432, 2013.
  7. Zhang Lu, Cavaro-Ménard Christine, Le Callet Patrick, et al. A perceptually relevant channelized joint observer (PCJO) for the detection-localization of parametric signals. IEEE transactions on medical imaging. 31(10): 1875-1888, 2012.
  8. S. Daly, The visible differences predictor: an algorithm for the assessment of image fidelity, Digital Image and Human Vision, A. B. Watson, Ed. Cambridge, MA: MIT Press, 1993.
  9. Zhang Lu. Numerical observers for the objective quality assessment of medical images. Université d'Angers, 2012.
  10. Goossens Bart. Multiresolution image models and estimation techniques. Ghent University, 2010.
  11. DP Chakraborty, KS Berbaum, Observer studies involving detection and localization: Modeling, analysis and validation. Medical Physics, 31(8): 2313-2330, 2004.
  12. Chakraborty Dev P. New developments in observer performance methodology in medical imaging. Seminars in nuclear medicine. Elsevier,401-418,2011.