Journal of Digital Imaging

, Volume 16, Issue 4, pp 345–349 | Cite as

Automated Recognition of Lateral from PA Chest Radiographs: Saving Seconds in a PACS Environment

  • John M. BooneEmail author
  • Greg S. Hurlock
  • J. Anthony Seibert
  • Richard L. Kennedy


Images acquired in a two-view digital chest examination are frequently not electronically distinguishable. As a result the lateral and posterioanterio (PA) images are often improperly positioned on a PACS work station. A series of 1998 chest radiographs (999 lateral, 999 PA or AP) were used to develop a neural network classifier. The images were down-sampled to 16 × 16 matrices, and a feed-forward neural network was trained and tested using the “leave-one-out” method. Using five nodes in the hidden layer, the neural network correctly identified 987 of the 999 test cases (98.8%) (average of six runs). The simple architecture and speed of this technique suggests that it would be a useful addition to PACS work station software. The accumulated time saved by correctly positioning the lateral and PA chest images on the work station monitors in accordance with each radiologist’s hanging protocols was estimated to be about 1 week of radiologist time per year.


Chest radiography picture archiving and communication system (PACS) pattern recognition neural networks 


  1. 1.
    Siegel, E, Reiner, B 2002Work flow redesign: the key to success when using PACS.AJR Am J Roentgenol178563566Google Scholar
  2. 2.
    Passadore, DJ, Isoardi, RA, Ariza, PP,  et al. 2001Use of a low-cost, PC-based image review workstation at a radiology department.J Digit Imaging14222223PubMedGoogle Scholar
  3. 3.
    Twair, AA, Torreggiani, WC, Mahmud, SM,  et al. 2000Significant savings in radiologic report turnaround time after implementation of a complete picture archiving and communication system (PACS).J Digit Imaging13175177Google Scholar
  4. 4.
    Nakano, Y, Gido, T, Honda, S,  et al. 2002Improved computed radiography image quality from a BaFl:Eu photostimulable phosphor plate.Med Phys29592597CrossRefPubMedGoogle Scholar
  5. 5.
    Aoyama, M, Li, Q, Katsuragawa, S,  et al. 2002Automated computerized scheme for distinction between benign and malignant solitary pulmonary nodules on chest images.Med Phys29701708CrossRefPubMedGoogle Scholar
  6. 6.
    Freedman, M 1991Chest image quality: film-screen vs. computed radiography.Adm Radiol103840, 42Google Scholar
  7. 7.
    Boone, JM, Sigillito, VG, Shaber, GS 1990Neural networks in radiology: an introduction and evaluation in a signal detection task.Med Phys17234241CrossRefPubMedGoogle Scholar
  8. 8.
    Boone, JM, Gross, GW, Greco-Hunt, V 1990Neural networks in radiologic diagnosis. I. Introduction and illustration.Invest Radiol2510121016PubMedGoogle Scholar
  9. 9.
    Gross, GW, Boone, JM, Greco-Hunt, V,  et al. 1990Neural networks in radiologic diagnosis. II. Interpretation of neonatal chest radiographs.Invest Radiol2510171023PubMedGoogle Scholar
  10. 10.
    Boone, JM 1994Sidetracked at the crossroads.Radiology1932830PubMedGoogle Scholar
  11. 11.
    Li, Q, Katsuragawa, S, Doi, K 2001Computer-aided diagnostic scheme for lung nodule detection in digital chest radiographs by use of a multiple-template matching technique.Med Phys2820702076CrossRefPubMedGoogle Scholar
  12. 12.
    Doi, K, Giger, ML, Nishikawa, RM,  et al. 1997Computer-aided diagnosis of breast cancer on mammograms.Breast Cancer4228233PubMedGoogle Scholar

Copyright information

© by SCAR (Society for Computer Applications in Radiology) 2004

Authors and Affiliations

  • John M. Boone
    • 1
    Email author
  • Greg S. Hurlock
    • 1
  • J. Anthony Seibert
    • 1
  • Richard L. Kennedy
    • 1
  1. 1.Department of RadiologyUniversity of California, Davis Medical CenterSacramentoUSA

Personalised recommendations