TY - JOUR
T1 - Automatic assessment of glioma burden
T2 - A deep learning algorithm for fully automated volumetric and bidimensional measurement
AU - Chang, Ken
AU - Beers, Andrew L.
AU - Bai, Harrison X.
AU - Brown, James M.
AU - Ina Ly, K.
AU - Li, Xuejun
AU - Senders, Joeky T.
AU - Kavouridis, Vasileios K.
AU - Boaro, Alessandro
AU - Su, Chang
AU - Bi, Wenya Linda
AU - Rapalino, Otto
AU - Liao, Weihua
AU - Shen, Qin
AU - Zhou, Hao
AU - Xiao, Bo
AU - Wang, Yinyan
AU - Zhang, Paul J.
AU - Pinho, Marco C.
AU - Wen, Patrick Y.
AU - Batchelor, Tracy T.
AU - Boxerman, Jerrold L.
AU - Arnaout, Omar
AU - Rosen, Bruce R.
AU - Gerstner, Elizabeth R.
AU - Yang, Li
AU - Huang, Raymond Y.
AU - Kalpathy-Cramer, Jayashree
N1 - Publisher Copyright:
© 2019 The Author(s).
PY - 2019/11/4
Y1 - 2019/11/4
N2 - Background: Longitudinal measurement of glioma burden with MRI is the basis for treatment response assessment. In this study, we developed a deep learning algorithm that automatically segments abnormal fluid attenuated inversion recovery (FLAIR) hyperintensity and contrast-enhancing tumor, quantitating tumor volumes as well as the product of maximum bidimensional diameters according to the Response Assessment in Neuro-Oncology (RANO) criteria (AutoRANO). Methods: Two cohorts of patients were used for this study. One consisted of 843 preoperative MRIs from 843 patients with low-or high-grade gliomas from 4 institutions and the second consisted of 713 longitudinal postoperative MRI visits from 54 patients with newly diagnosed glioblastomas (each with 2 pretreatment "baseline" MRIs) from 1 institution. Results: The automatically generated FLAIR hyperintensity volume, contrast-enhancing tumor volume, and AutoRANO were highly repeatable for the double-baseline visits, with an intraclass correlation coefficient (ICC) of 0.986, 0.991, and 0.977, respectively, on the cohort of postoperative GBM patients. Furthermore, there was high agreement between manually and automatically measured tumor volumes, with ICC values of 0.915, 0.924, and 0.965 for preoperative FLAIR hyperintensity, postoperative FLAIR hyperintensity, and postoperative contrast-enhancing tumor volumes, respectively. Lastly, the ICCs for comparing manually and automatically derived longitudinal changes in tumor burden were 0.917, 0.966, and 0.850 for FLAIR hyperintensity volume, contrast-enhancing tumor volume, and RANO measures, respectively. Conclusions: Our automated algorithm demonstrates potential utility for evaluating tumor burden in complex posttreatment settings, although further validation in multicenter clinical trials will be needed prior to widespread implementation.
AB - Background: Longitudinal measurement of glioma burden with MRI is the basis for treatment response assessment. In this study, we developed a deep learning algorithm that automatically segments abnormal fluid attenuated inversion recovery (FLAIR) hyperintensity and contrast-enhancing tumor, quantitating tumor volumes as well as the product of maximum bidimensional diameters according to the Response Assessment in Neuro-Oncology (RANO) criteria (AutoRANO). Methods: Two cohorts of patients were used for this study. One consisted of 843 preoperative MRIs from 843 patients with low-or high-grade gliomas from 4 institutions and the second consisted of 713 longitudinal postoperative MRI visits from 54 patients with newly diagnosed glioblastomas (each with 2 pretreatment "baseline" MRIs) from 1 institution. Results: The automatically generated FLAIR hyperintensity volume, contrast-enhancing tumor volume, and AutoRANO were highly repeatable for the double-baseline visits, with an intraclass correlation coefficient (ICC) of 0.986, 0.991, and 0.977, respectively, on the cohort of postoperative GBM patients. Furthermore, there was high agreement between manually and automatically measured tumor volumes, with ICC values of 0.915, 0.924, and 0.965 for preoperative FLAIR hyperintensity, postoperative FLAIR hyperintensity, and postoperative contrast-enhancing tumor volumes, respectively. Lastly, the ICCs for comparing manually and automatically derived longitudinal changes in tumor burden were 0.917, 0.966, and 0.850 for FLAIR hyperintensity volume, contrast-enhancing tumor volume, and RANO measures, respectively. Conclusions: Our automated algorithm demonstrates potential utility for evaluating tumor burden in complex posttreatment settings, although further validation in multicenter clinical trials will be needed prior to widespread implementation.
KW - RANO
KW - deep learning
KW - glioma
KW - longitudinal response assessment
KW - segmentation
UR - http://www.scopus.com/inward/record.url?scp=85074554240&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85074554240&partnerID=8YFLogxK
U2 - 10.1093/neuonc/noz106
DO - 10.1093/neuonc/noz106
M3 - Article
C2 - 31190077
AN - SCOPUS:85074554240
SN - 1522-8517
VL - 21
SP - 1412
EP - 1422
JO - Neuro-oncology
JF - Neuro-oncology
IS - 11
ER -