Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2017:2017:2727686.
doi: 10.1155/2017/2727686. Epub 2017 Sep 17.

Automatic Radiographic Position Recognition from Image Frequency and Intensity

Ning-Ning Ren  1   2 , An-Ran Ma  1   2 , Li-Bo Han  1   2 , Yong Sun  1 , Yan Shao  1   3 , Jian-Feng Qiu  1
Affiliations

Automatic Radiographic Position Recognition from Image Frequency and Intensity

Ning-Ning Ren et al. J Healthc Eng. 2017.

Abstract

Purpose: With the development of digital X-ray imaging and processing methods, the categorization and analysis of massive digital radiographic images need to be automatically finished. What is crucial in this processing is the automatic retrieval and recognition of radiographic position. To address these concerns, we developed an automatic method to identify a patient's position and body region using only frequency curve classification and gray matching.

Methods: Our new method is combined with frequency analysis and gray image matching. The radiographic position was determined from frequency similarity and amplitude classification. The body region recognition was performed by image matching in the whole-body phantom image with prior knowledge of templates. The whole-body phantom image was stitched by radiological images of different parts.

Results: The proposed method can automatically retrieve and recognize the radiographic position and body region using frequency and intensity information. It replaces 2D image retrieval with 1D frequency curve classification, with higher speed and accuracy up to 93.78%.

Conclusion: The proposed method is able to outperform the digital X-ray image's position recognition with a limited time cost and a simple algorithm. The frequency information of radiography can make image classification quicker and more accurate.

PubMed Disclaimer

Figures

Figure 1
Figure 1
The whole-body phantom's X-ray mask and the examples of partial anatomical definition.
Figure 2
Figure 2
Frequency curves and the AUCs for various anatomical regions.
Figure 3
Figure 3
(a) From top to bottom: the chest X-ray image, the image frequency curve, and the chest X-ray image with inversed gray scale. (b) From top to bottom: chest X-ray image by Butterworth filtering, the image frequency curve, and the chest X-ray image with inversed gray scale. (c) From top to bottom: lung texture image reconstructed by the filtered frequency information, the frequency curve, and the lung texture image with inversed gray scale.
Figure 4
Figure 4
(a) From top to bottom: the knee X-ray image and the knee image frequency curve. (b) From top to bottom: the knee X-ray image by Butterworth filtering and the image frequency curve by filtering. (c) From top to bottom: the trabeculae texture image reconstructed by the filtered frequency information and the frequency curve.
Figure 5
Figure 5
The reciprocal of mean-variance between 6 organs and the standard frequency curve.
Figure 6
Figure 6
Workflow.
Figure 7
Figure 7
The automatic recognition results for three cervical spine images.
See this image and copyright information in PMC

References

    1. Hwang K. H., Lee H., Choi D. Medical image retrieval: past and present. Healthcare Informatics Research. 2012;18(1):3–9. doi: 10.4258/hir.2012.18.1.3. - DOI - PMC - PubMed
    1. van de Sande K. E., Gevers T., Snoek C. G. Evaluating color descriptors for object and scene recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2010;32(9):1582–1596. doi: 10.1109/TPAMI.2009.154. - DOI - PubMed
    1. Kajimura J., Ito R., Manley N. R., Hale L. P. Optimization of single- and dual-color immunofluorescence protocols for formalin-fixed, paraffin-embedded archival tissues. Journal of Histochemistry & Cytochemistry. 2016;64(2):112–124. doi: 10.1369/0022155415610792. - DOI - PMC - PubMed
    1. Zhang X., Gao X., Liu B. J., Ma K., Yan W., Fujita H. Effective staging of fibrosis by the selected texture features of liver: which one is better, CT or MR imaging? Computerized Medical Imaging & Graphics the Official Journal of the Computerized Medical Imaging Society. 2015;46(Part 2):227–236. doi: 10.1016/j.compmedimag.2015.09.003. - DOI - PubMed
    1. Jain A. K., Vailaya A. Image retrieval using color and shape. Pattern Recognition. 1996;29(8):1233–1244. doi: 10.1016/0031-3203(95)00160-3. - DOI

Publication types

MeSH terms

LinkOut - more resources