TY - JOUR
T1 - Usefulness of deep learning-assisted identification of hyperdense MCA sign in acute ischemic stroke
T2 - comparison with readers’ performance
AU - Shinohara, Yuki
AU - Takahashi, Noriyuki
AU - Lee, Yongbum
AU - Ohmura, Tomomi
AU - Umetsu, Atsushi
AU - Kinoshita, Fumiko
AU - Kuya, Keita
AU - Kato, Ayumi
AU - Kinoshita, Toshibumi
N1 - Publisher Copyright:
© 2020, Japan Radiological Society.
PY - 2020/9/1
Y1 - 2020/9/1
N2 - Purpose: To evaluate the usefulness of deep learning-assisted diagnosis for identifying hyperdense middle cerebral artery sign (HMCAS) on non-contrast computed tomography in comparison with the diagnostic performance of neuroradiologists. Materials and methods: We obtained 46 HMCAS-positive and 52 HMCAS-negative test samples extracted using 50-pixel-diameter circular regions of interest. Five neuroradiologists undertook an initial diagnostic performance test by describing the HMCAS-positive prediction rate in each sample. Their diagnostic performance was compared with that of a deep convolutional neural network (DCNN) model that had been trained using another dataset in our previous study. In the second test, readers could reference the prediction rate of the DCNN model in each sample. Results: The diagnostic performance of the DCNN for HMCAS showed an accuracy of 81.6% and area under the receiver-operating characteristic curve (AUC) of 0.869, whereas the initial diagnostic performance of neuroradiologists showed an accuracy of 78.8% and AUC of 0.882. The second diagnostic test of neuroradiologists with reference to the results of the DCNN model showed an accuracy of 84.7% and AUC of 0.932. In all readers, AUC values were higher in the second test than the initial test. Conclusion: The ability of DCNN to identify HMCAS is comparable with the diagnostic performance of neuroradiologists.
AB - Purpose: To evaluate the usefulness of deep learning-assisted diagnosis for identifying hyperdense middle cerebral artery sign (HMCAS) on non-contrast computed tomography in comparison with the diagnostic performance of neuroradiologists. Materials and methods: We obtained 46 HMCAS-positive and 52 HMCAS-negative test samples extracted using 50-pixel-diameter circular regions of interest. Five neuroradiologists undertook an initial diagnostic performance test by describing the HMCAS-positive prediction rate in each sample. Their diagnostic performance was compared with that of a deep convolutional neural network (DCNN) model that had been trained using another dataset in our previous study. In the second test, readers could reference the prediction rate of the DCNN model in each sample. Results: The diagnostic performance of the DCNN for HMCAS showed an accuracy of 81.6% and area under the receiver-operating characteristic curve (AUC) of 0.869, whereas the initial diagnostic performance of neuroradiologists showed an accuracy of 78.8% and AUC of 0.882. The second diagnostic test of neuroradiologists with reference to the results of the DCNN model showed an accuracy of 84.7% and AUC of 0.932. In all readers, AUC values were higher in the second test than the initial test. Conclusion: The ability of DCNN to identify HMCAS is comparable with the diagnostic performance of neuroradiologists.
KW - Acute ischemic stroke
KW - Deep learning
KW - Hyperdense MCA sign
KW - Hyperdense artery sign
KW - Non-contrast CT
UR - http://www.scopus.com/inward/record.url?scp=85084585436&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85084585436&partnerID=8YFLogxK
U2 - 10.1007/s11604-020-00986-6
DO - 10.1007/s11604-020-00986-6
M3 - Article
C2 - 32399602
AN - SCOPUS:85084585436
VL - 38
SP - 870
EP - 877
JO - Japanese Journal of Radiology
JF - Japanese Journal of Radiology
SN - 1867-1071
IS - 9
ER -