Practical applications of deep learning: classifying the most common categories of plain radiographs in a PACS using a neural network

Dratsch, Thomas, Korenkov, Michael, Zopfs, David, Brodehl, Sebastian, Baessler, Bettina, Giese, Daniel, Brinkmann, Sebastian, Maintz, David and dos Santos, Daniel Pinto . Practical applications of deep learning: classifying the most common categories of plain radiographs in a PACS using a neural network. Eur. Radiol.. NEW YORK: SPRINGER. ISSN 1432-1084

Full text not available from this repository.

DOI:10.1007/s00330-020-07241-6

Abstract

Objectives The goal of the present study was to classify the most common types of plain radiographs using a neural network and to validate the network's performance on internal and external data. Such a network could help improve various radiological workflows. Methods All radiographs from the year 2017 (n = 71,274) acquired at our institution were retrieved from the PACS. The 30 largest categories (n = 58,219, 81.7% of all radiographs performed in 2017) were used to develop and validate a neural network (MobileNet v1.0) using transfer learning. Image categories were extracted from DICOM metadata (study and image description) and mapped to the WHO manual of diagnostic imaging. As an independent, external validation set, we used images from other institutions that had been stored in our PACS (n = 5324). Results In the internal validation, the overall accuracy of the model was 90.3% (95%CI: 89.2-91.3%), whereas, for the external validation set, the overall accuracy was 94.0% (95%CI: 93.3-94.6%). Conclusions Using data from one single institution, we were able to classify the most common categories of radiographs with a neural network. The network showed good generalizability on the external validation set and could be used to automatically organize a PACS, preselect radiographs so that they can be routed to more specialized networks for abnormality detection or help with other parts of the radiological workflow (e.g., automated hanging protocols; check if ordered image and performed image are the same). The final AI algorithm is publicly available for evaluation and extension.

Item Type:

Journal Article

Creators:

Creators	Email	ORCID	ORCID Put Code
Dratsch, Thomas	UNSPECIFIED	UNSPECIFIED	UNSPECIFIED
Korenkov, Michael	UNSPECIFIED	UNSPECIFIED	UNSPECIFIED
Zopfs, David	UNSPECIFIED	UNSPECIFIED	UNSPECIFIED
Brodehl, Sebastian	UNSPECIFIED	UNSPECIFIED	UNSPECIFIED
Baessler, Bettina	UNSPECIFIED	UNSPECIFIED	UNSPECIFIED
Giese, Daniel	UNSPECIFIED	UNSPECIFIED	UNSPECIFIED
Brinkmann, Sebastian	UNSPECIFIED	UNSPECIFIED	UNSPECIFIED
Maintz, David	UNSPECIFIED	UNSPECIFIED	UNSPECIFIED
dos Santos, Daniel Pinto	UNSPECIFIED	UNSPECIFIED	UNSPECIFIED