Automated triaging of head MRI examinations using convolutional neural networks

David A. Wood, Sina Kafiabadi, Aisha Al Busaidi, Emily Guilhem, Antanas Montvila, Siddarth Agarwal, Jeremy Lynch, Matthew Townend, Gareth Barker, Sebastian Ourselin, James H. Cole, Thomas C. Booth
Proceedings of the Fourth Conference on Medical Imaging with Deep Learning, PMLR 143:813-841, 2021.

Abstract

The growing demand for head magnetic resonance imaging (MRI) examinations, along with a global shortage of radiologists, has led to an increase in the time taken to report head MRI scans around the world. For many neurological conditions, this delay can result in increased morbidity and mortality. An automated triaging tool could reduce reporting times for abnormal examinations by identifying abnormalities at the time of imaging and prioritizing the reporting of these scans. In this work, we present a convolutional neural network (CNN) for detecting clinically-relevant abnormalities in T2-weighted head MRI scans. Using a validated neuroradiology report classifier, we generated a labelled dataset of 43,754 scans from two large UK hospitals for model training, and demonstrate accurate classification (area under the receiver operating curve (AUC) = 0.943) on a test set of 800 scans labelled by a team of neuroradiologists. Importantly, when trained on scans from only a single hospital the model generalized to scans from the other hospital (delta AUC <= 0.02). A simulation study demonstrated that our model would reduce the mean reporting time for abnormal scans from 28 days to 14 days and from 9 days to 5 days at the two hospitals, demonstrating feasibility for use in a clinical triage environment.

Cite this Paper

BibTeX
@InProceedings{pmlr-v143-wood21a, title = {Automated triaging of head MRI examinations using convolutional neural networks}, author = {Wood, David A. and Kafiabadi, Sina and Al Busaidi, Aisha and Guilhem, Emily and Montvila, Antanas and Agarwal, Siddarth and Lynch, Jeremy and Townend, Matthew and Barker, Gareth and Ourselin, Sebastian and Cole, James H. and Booth, Thomas C.}, booktitle = {Proceedings of the Fourth Conference on Medical Imaging with Deep Learning}, pages = {813--841}, year = {2021}, editor = {Heinrich, Mattias and Dou, Qi and de Bruijne, Marleen and Lellmann, Jan and Schläfer, Alexander and Ernst, Floris}, volume = {143}, series = {Proceedings of Machine Learning Research}, month = {07--09 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v143/wood21a/wood21a.pdf}, url = {https://proceedings.mlr.press/v143/wood21a.html}, abstract = {The growing demand for head magnetic resonance imaging (MRI) examinations, along with a global shortage of radiologists, has led to an increase in the time taken to report head MRI scans around the world. For many neurological conditions, this delay can result in increased morbidity and mortality. An automated triaging tool could reduce reporting times for abnormal examinations by identifying abnormalities at the time of imaging and prioritizing the reporting of these scans. In this work, we present a convolutional neural network (CNN) for detecting clinically-relevant abnormalities in T2-weighted head MRI scans. Using a validated neuroradiology report classifier, we generated a labelled dataset of 43,754 scans from two large UK hospitals for model training, and demonstrate accurate classification (area under the receiver operating curve (AUC) = 0.943) on a test set of 800 scans labelled by a team of neuroradiologists. Importantly, when trained on scans from only a single hospital the model generalized to scans from the other hospital (delta AUC <= 0.02). A simulation study demonstrated that our model would reduce the mean reporting time for abnormal scans from 28 days to 14 days and from 9 days to 5 days at the two hospitals, demonstrating feasibility for use in a clinical triage environment.} }
Endnote
%0 Conference Paper %T Automated triaging of head MRI examinations using convolutional neural networks %A David A. Wood %A Sina Kafiabadi %A Aisha Al Busaidi %A Emily Guilhem %A Antanas Montvila %A Siddarth Agarwal %A Jeremy Lynch %A Matthew Townend %A Gareth Barker %A Sebastian Ourselin %A James H. Cole %A Thomas C. Booth %B Proceedings of the Fourth Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2021 %E Mattias Heinrich %E Qi Dou %E Marleen de Bruijne %E Jan Lellmann %E Alexander Schläfer %E Floris Ernst %F pmlr-v143-wood21a %I PMLR %P 813--841 %U https://proceedings.mlr.press/v143/wood21a.html %V 143 %X The growing demand for head magnetic resonance imaging (MRI) examinations, along with a global shortage of radiologists, has led to an increase in the time taken to report head MRI scans around the world. For many neurological conditions, this delay can result in increased morbidity and mortality. An automated triaging tool could reduce reporting times for abnormal examinations by identifying abnormalities at the time of imaging and prioritizing the reporting of these scans. In this work, we present a convolutional neural network (CNN) for detecting clinically-relevant abnormalities in T2-weighted head MRI scans. Using a validated neuroradiology report classifier, we generated a labelled dataset of 43,754 scans from two large UK hospitals for model training, and demonstrate accurate classification (area under the receiver operating curve (AUC) = 0.943) on a test set of 800 scans labelled by a team of neuroradiologists. Importantly, when trained on scans from only a single hospital the model generalized to scans from the other hospital (delta AUC <= 0.02). A simulation study demonstrated that our model would reduce the mean reporting time for abnormal scans from 28 days to 14 days and from 9 days to 5 days at the two hospitals, demonstrating feasibility for use in a clinical triage environment.
APA
Wood, D.A., Kafiabadi, S., Al Busaidi, A., Guilhem, E., Montvila, A., Agarwal, S., Lynch, J., Townend, M., Barker, G., Ourselin, S., Cole, J.H. & Booth, T.C.. (2021). Automated triaging of head MRI examinations using convolutional neural networks. Proceedings of the Fourth Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 143:813-841 Available from https://proceedings.mlr.press/v143/wood21a.html.

Related Material