Automated Labelling using an Attention model for Radiology reports of MRI scans (ALARM)

David A. Wood, Jeremy Lynch, Sina Kafiabadi, Emily Guilhem, Aisha Al Busaidi, Antanas Montvila, Thomas Varsavsky, Juveria Siddiqui, Naveen Gadapa, Matthew Townend, Martin Kiik, Keena Patel, Gareth Barker, Sebastian Ourselin, James H. Cole, Thomas C. Booth
Proceedings of the Third Conference on Medical Imaging with Deep Learning, PMLR 121:811-826, 2020.

Abstract

Labelling large datasets for training high-capacity neural networks is a major obstacle to the development of deep learning-based medical imaging applications. Here we present a transformer-based network for magnetic resonance imaging (MRI) radiology report classification which automates this task by assigning image labels on the basis of free-text expert radiology reports. Our model�s performance is comparable to that of an expert radiologist, and better than that of an expert physician, demonstrating the feasibility of this approach. We make our code available for researchers to label their own MRI datasets for medical imaging applications.

Cite this Paper

BibTeX
@InProceedings{pmlr-v121-wood20a, title = {Automated Labelling using an Attention model for Radiology reports of MRI scans (ALARM)}, author = {Wood, David A. and Lynch, Jeremy and Kafiabadi, Sina and Guilhem, Emily and Al Busaidi, Aisha and Montvila, Antanas and Varsavsky, Thomas and Siddiqui, Juveria and Gadapa, Naveen and Townend, Matthew and Kiik, Martin and Patel, Keena and Barker, Gareth and Ourselin, Sebastian and Cole, James H. and Booth, Thomas C.}, booktitle = {Proceedings of the Third Conference on Medical Imaging with Deep Learning}, pages = {811--826}, year = {2020}, editor = {Arbel, Tal and Ben Ayed, Ismail and de Bruijne, Marleen and Descoteaux, Maxime and Lombaert, Herve and Pal, Christopher}, volume = {121}, series = {Proceedings of Machine Learning Research}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v121/wood20a/wood20a.pdf}, url = {https://proceedings.mlr.press/v121/wood20a.html}, abstract = {Labelling large datasets for training high-capacity neural networks is a major obstacle to the development of deep learning-based medical imaging applications. Here we present a transformer-based network for magnetic resonance imaging (MRI) radiology report classification which automates this task by assigning image labels on the basis of free-text expert radiology reports. Our model�s performance is comparable to that of an expert radiologist, and better than that of an expert physician, demonstrating the feasibility of this approach. We make our code available for researchers to label their own MRI datasets for medical imaging applications.} }
Endnote
%0 Conference Paper %T Automated Labelling using an Attention model for Radiology reports of MRI scans (ALARM) %A David A. Wood %A Jeremy Lynch %A Sina Kafiabadi %A Emily Guilhem %A Aisha Al Busaidi %A Antanas Montvila %A Thomas Varsavsky %A Juveria Siddiqui %A Naveen Gadapa %A Matthew Townend %A Martin Kiik %A Keena Patel %A Gareth Barker %A Sebastian Ourselin %A James H. Cole %A Thomas C. Booth %B Proceedings of the Third Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2020 %E Tal Arbel %E Ismail Ben Ayed %E Marleen de Bruijne %E Maxime Descoteaux %E Herve Lombaert %E Christopher Pal %F pmlr-v121-wood20a %I PMLR %P 811--826 %U https://proceedings.mlr.press/v121/wood20a.html %V 121 %X Labelling large datasets for training high-capacity neural networks is a major obstacle to the development of deep learning-based medical imaging applications. Here we present a transformer-based network for magnetic resonance imaging (MRI) radiology report classification which automates this task by assigning image labels on the basis of free-text expert radiology reports. Our model�s performance is comparable to that of an expert radiologist, and better than that of an expert physician, demonstrating the feasibility of this approach. We make our code available for researchers to label their own MRI datasets for medical imaging applications.
APA
Wood, D.A., Lynch, J., Kafiabadi, S., Guilhem, E., Al Busaidi, A., Montvila, A., Varsavsky, T., Siddiqui, J., Gadapa, N., Townend, M., Kiik, M., Patel, K., Barker, G., Ourselin, S., Cole, J.H. & Booth, T.C.. (2020). Automated Labelling using an Attention model for Radiology reports of MRI scans (ALARM). Proceedings of the Third Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 121:811-826 Available from https://proceedings.mlr.press/v121/wood20a.html.

Related Material