TY - JOUR
T1 - Computer-aided diagnosis of isocitrate dehydrogenase genotypes in glioblastomas from radiomic patterns
AU - Lo, Chung Ming
AU - Weng, Rui Cian
AU - Cheng, Sho Jen
AU - Wang, Hung Jung
AU - Hsieh, Kevin Li Chun
AU - Ding, Jianxun
N1 - Publisher Copyright:
© 2020 the Author(s). Published by Wolters Kluwer Health, Inc.
PY - 2020/2
Y1 - 2020/2
N2 - World Health Organization tumor classifications of the central nervous system differentiate glioblastoma multiforme (GBM) into wild-type (WT) and mutant isocitrate dehydrogenase (IDH) genotypes. This study proposes a noninvasive computer-aided diagnosis to interpret the status of IDH in glioblastomas from transformed magnetic resonance imaging patterns. The collected image database was composed of 32 WT and 7 mutant IDH cases. For each image, a ranklet transformation which changed the original pixel values into relative coefficients was 1st applied to reduce the effects of different scanning parameters and machines on the underlying patterns. Extracting various textural features from the transformed ranklet images and combining them in a logistic regression classifier allowed an IDH prediction. We achieved an accuracy of 90%, a sensitivity of 57%, and a specificity of 97%. Four of the selected textural features in the classifier (homogeneity, difference entropy, information measure of correlation, and inverse difference normalized) were significant (P<.05), and the other 2 were close to being significant (P=.06). The proposed computer-aided diagnosis system based on radiomic textural features from ranklet-transformed images using relative rankings of pixel values as intensity-invariant coefficients is a promising noninvasive solution to provide recommendations about the IDH status in GBM across different healthcare institutions.
AB - World Health Organization tumor classifications of the central nervous system differentiate glioblastoma multiforme (GBM) into wild-type (WT) and mutant isocitrate dehydrogenase (IDH) genotypes. This study proposes a noninvasive computer-aided diagnosis to interpret the status of IDH in glioblastomas from transformed magnetic resonance imaging patterns. The collected image database was composed of 32 WT and 7 mutant IDH cases. For each image, a ranklet transformation which changed the original pixel values into relative coefficients was 1st applied to reduce the effects of different scanning parameters and machines on the underlying patterns. Extracting various textural features from the transformed ranklet images and combining them in a logistic regression classifier allowed an IDH prediction. We achieved an accuracy of 90%, a sensitivity of 57%, and a specificity of 97%. Four of the selected textural features in the classifier (homogeneity, difference entropy, information measure of correlation, and inverse difference normalized) were significant (P<.05), and the other 2 were close to being significant (P=.06). The proposed computer-aided diagnosis system based on radiomic textural features from ranklet-transformed images using relative rankings of pixel values as intensity-invariant coefficients is a promising noninvasive solution to provide recommendations about the IDH status in GBM across different healthcare institutions.
KW - computer-aided diagnosis
KW - glioblastoma
KW - isocitrate dehydrogenase
KW - magnetic resonance imaging
KW - ranklet transformation
KW - Predictive Value of Tests
KW - Brain Neoplasms/diagnostic imaging
KW - Humans
KW - Middle Aged
KW - Genotype
KW - Magnetic Resonance Imaging/methods
KW - Male
KW - Isocitrate Dehydrogenase/genetics
KW - Diagnosis, Computer-Assisted/methods
KW - Glioblastoma/diagnostic imaging
KW - Algorithms
KW - Sensitivity and Specificity
KW - Adult
KW - Female
KW - Aged
KW - Mutation
KW - Preoperative Period
UR - http://www.scopus.com/inward/record.url?scp=85079829363&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85079829363&partnerID=8YFLogxK
U2 - 10.1097/MD.0000000000019123
DO - 10.1097/MD.0000000000019123
M3 - Article
C2 - 32080088
AN - SCOPUS:85079829363
SN - 0025-7974
VL - 99
JO - Medicine (United States)
JF - Medicine (United States)
IS - 8
M1 - e19123
ER -