Abstract
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.
Similar content being viewed by others
References
E Siegel B Reiner (2002) ArticleTitleWork flow redesign: the key to success when using PACS. AJR Am J Roentgenol 178 563–566
DJ Passadore RA Isoardi PP Ariza et al. (2001) ArticleTitleUse of a low-cost, PC-based image review workstation at a radiology department. J Digit Imaging 14 222–223 Occurrence Handle1:STN:280:DC%2BD38%2Fhs12rsQ%3D%3D Occurrence Handle11442105
AA Twair WC Torreggiani SM Mahmud et al. (2000) ArticleTitleSignificant savings in radiologic report turnaround time after implementation of a complete picture archiving and communication system (PACS). J Digit Imaging 13 175–177 Occurrence Handle1:STN:280:DC%2BD3Mzgtl2lsQ%3D%3D
Y Nakano T Gido S Honda et al. (2002) ArticleTitleImproved computed radiography image quality from a BaFl:Eu photostimulable phosphor plate. Med Phys 29 592–597 Occurrence Handle10.1118/1.1462639 Occurrence Handle1:CAS:528:DC%2BD38XisFymuro%3D Occurrence Handle11991131
M Aoyama Q Li S Katsuragawa et al. (2002) ArticleTitleAutomated computerized scheme for distinction between benign and malignant solitary pulmonary nodules on chest images. Med Phys 29 701–708 Occurrence Handle10.1118/1.1469630 Occurrence Handle12033565
M Freedman (1991) ArticleTitleChest image quality: film-screen vs. computed radiography. Adm Radiol 10 38–40, 42 Occurrence Handle1:STN:280:By6A38flsVQ%3D
JM Boone VG Sigillito GS Shaber (1990) ArticleTitleNeural networks in radiology: an introduction and evaluation in a signal detection task. Med Phys 17 234–241 Occurrence Handle10.1118/1.596501 Occurrence Handle1:STN:280:By%2BB3sfktlc%3D Occurrence Handle2333049
JM Boone GW Gross V Greco-Hunt (1990) ArticleTitleNeural networks in radiologic diagnosis. I. Introduction and illustration. Invest Radiol 25 1012–1016 Occurrence Handle1:STN:280:By6D3cfit1A%3D Occurrence Handle2211042
GW Gross JM Boone V Greco-Hunt et al. (1990) ArticleTitleNeural networks in radiologic diagnosis. II. Interpretation of neonatal chest radiographs. Invest Radiol 25 1017–1023 Occurrence Handle1:STN:280:By6D3cfit1E%3D Occurrence Handle2211043
JM Boone (1994) ArticleTitleSidetracked at the crossroads. Radiology 193 28–30 Occurrence Handle1:STN:280:ByuA2sjmsVI%3D Occurrence Handle8090909
Q Li S Katsuragawa K Doi (2001) ArticleTitleComputer-aided diagnostic scheme for lung nodule detection in digital chest radiographs by use of a multiple-template matching technique. Med Phys 28 2070–2076 Occurrence Handle10.1118/1.1406517 Occurrence Handle1:STN:280:DC%2BD3Mnkt12rsg%3D%3D Occurrence Handle11695768
K Doi ML Giger RM Nishikawa et al. (1997) ArticleTitleComputer-aided diagnosis of breast cancer on mammograms. Breast Cancer 4 228–233 Occurrence Handle11091604
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Boone, J.M., Hurlock, G.S., Seibert, J.A. et al. Automated Recognition of Lateral from PA Chest Radiographs: Saving Seconds in a PACS Environment. J Digit Imaging 16, 345–349 (2003). https://doi.org/10.1007/s10278-003-1662-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10278-003-1662-y