Format

Send to

Choose Destination
See comment in PubMed Commons below
Phys Med Biol. 2014 Apr 7;59(7):1789-800. doi: 10.1088/0031-9155/59/7/1789. Epub 2014 Mar 12.

Automatic classification of DMSA scans using an artificial neural network.

Author information

  • 1Department of Nuclear Medicine, Glasgow Royal Infirmary, NHS Greater Glasgow and Clyde, G4 0SF, UK.

Abstract

DMSA imaging is carried out in nuclear medicine to assess the level of functional renal tissue in patients. This study investigated the use of an artificial neural network to perform diagnostic classification of these scans. Using the radiological report as the gold standard, the network was trained to classify DMSA scans as positive or negative for defects using a representative sample of 257 previously reported images. The trained network was then independently tested using a further 193 scans and achieved a binary classification accuracy of 95.9%. The performance of the network was compared with three qualified expert observers who were asked to grade each scan in the 193 image testing set on a six point defect scale, from 'definitely normal' to 'definitely abnormal'. A receiver operating characteristic analysis comparison between a consensus operator, generated from the scores of the three expert observers, and the network revealed a statistically significant increase (α < 0.05) in performance between the network and operators. A further result from this work was that when suitably optimized, a negative predictive value of 100% for renal defects was achieved by the network, while still managing to identify 93% of the negative cases in the dataset. These results are encouraging for application of such a network as a screening tool or quality assurance assistant in clinical practice.

[PubMed - indexed for MEDLINE]
PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for IOP Publishing Ltd.
    Loading ...
    Write to the Help Desk