TY - JOUR
T1 - Deep learning application engine (DLAE)
T2 - Development and integration of deep learning algorithms in medical imaging
AU - Sanders, Jeremiah W.
AU - Fletcher, Justin R.
AU - Frank, Steven J.
AU - Liu, Ho Ling
AU - Johnson, Jason M.
AU - Zhou, Zijian
AU - Chen, Henry Szu Meng
AU - Venkatesan, Aradhana M.
AU - Kudchadker, Rajat J.
AU - Pagel, Mark D.
AU - Ma, Jingfei
N1 - Funding Information:
Jeremiah Sanders would like to acknowledge the generous donors of the Pauline Altman-Goldstein Foundation Discovery Fellowship. We thank MD Anderson Research Medical Library Scientific Publication Services for their help in editing this paper. We also acknowledge the Github repository at https://github.com/pierluigiferrari/ssd_keras, from which we adapted some of our code for implementing SSDs in DLAE.
Publisher Copyright:
© 2019 The Authors
PY - 2019/7/1
Y1 - 2019/7/1
N2 - Herein we introduce a deep learning (DL) application engine (DLAE) system concept, present potential uses of it, and describe pathways for its integration in clinical workflows. An open-source software application was developed to provide a code-free approach to DL for medical imaging applications. DLAE supports several DL techniques used in medical imaging, including convolutional neural networks, fully convolutional networks, generative adversarial networks, and bounding box detectors. Several example applications using clinical images were developed and tested to demonstrate the capabilities of DLAE. Additionally, a model deployment example was demonstrated in which DLAE was used to integrate two trained models into a commercial clinical software package.
AB - Herein we introduce a deep learning (DL) application engine (DLAE) system concept, present potential uses of it, and describe pathways for its integration in clinical workflows. An open-source software application was developed to provide a code-free approach to DL for medical imaging applications. DLAE supports several DL techniques used in medical imaging, including convolutional neural networks, fully convolutional networks, generative adversarial networks, and bounding box detectors. Several example applications using clinical images were developed and tested to demonstrate the capabilities of DLAE. Additionally, a model deployment example was demonstrated in which DLAE was used to integrate two trained models into a commercial clinical software package.
KW - Algorithm development
KW - Deep learning
KW - Medical imaging
KW - Software
UR - http://www.scopus.com/inward/record.url?scp=85074166468&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85074166468&partnerID=8YFLogxK
U2 - 10.1016/j.softx.2019.100347
DO - 10.1016/j.softx.2019.100347
M3 - Article
C2 - 34113706
AN - SCOPUS:85074166468
SN - 2352-7110
VL - 10
JO - SoftwareX
JF - SoftwareX
M1 - 100347
ER -