TY - JOUR
T1 - Diffusion histology imaging combining diffusion basis spectrum imaging (DBSI) and machine learning improves detection and classification of glioblastoma pathology
AU - Ye, Zezhong
AU - Price, Richard L.
AU - Liu, Xiran
AU - Lin, Joshua
AU - Yang, Qingsong
AU - Sun, Peng
AU - Wu, Anthony T.
AU - Wang, Liang
AU - Han, Rowland H.
AU - Song, Chunyu
AU - Yang, Ruimeng
AU - Gary, Sam E.
AU - Mao, Diane D.
AU - Wallendorf, Michael
AU - Campian, Jian L.
AU - Li, Jr Shin
AU - Dahiya, Sonika
AU - Kim, Albert H.
AU - Song, Sheng Kwei
N1 - Publisher Copyright:
© 2020 American Association for Cancer Research.
PY - 2020/10/15
Y1 - 2020/10/15
N2 - Purpose: Glioblastoma (GBM) is one of the deadliest cancers with no cure. While conventional MRI has been widely adopted to examine GBM clinically, accurate neuroimaging assessment of tumor histopathology for improved diagnosis, surgical planning, and treatment evaluation remains an unmet need in the clinical management of GBMs. Experimental Design: We employ a novel diffusion histology imaging (DHI) approach, combining diffusion basis spectrum imaging (DBSI) and machine learning, to detect, differentiate, and quantify areas of high cellularity, tumor necrosis, and tumor infiltration in GBM. Results: Gadolinium-enhanced T1-weighted or hyperintense fluid-attenuated inversion recovery failed to reflect the morphologic complexity underlying tumor in patients with GBM. Contrary to the conventional wisdom that apparent diffusion coefficient (ADC) negatively correlates with increased tumor cellularity, we demonstrate disagreement between ADC and histologically confirmed tumor cellularity in GBM specimens, whereas DBSI-derived restricted isotropic diffusion fraction positively correlated with tumor cellularity in the same specimens. By incorporating DBSI metrics as classifiers for a supervised machine learning algorithm, we accurately predicted high tumor cellularity, tumor necrosis, and tumor infiltration with 87.5%, 89.0%, and 93.4% accuracy, respectively. Conclusions: Our results suggest that DHI could serve as a favorable alternative to current neuroimaging techniques in guiding biopsy or surgery as well as monitoring therapeutic response in the treatment of GBM.
AB - Purpose: Glioblastoma (GBM) is one of the deadliest cancers with no cure. While conventional MRI has been widely adopted to examine GBM clinically, accurate neuroimaging assessment of tumor histopathology for improved diagnosis, surgical planning, and treatment evaluation remains an unmet need in the clinical management of GBMs. Experimental Design: We employ a novel diffusion histology imaging (DHI) approach, combining diffusion basis spectrum imaging (DBSI) and machine learning, to detect, differentiate, and quantify areas of high cellularity, tumor necrosis, and tumor infiltration in GBM. Results: Gadolinium-enhanced T1-weighted or hyperintense fluid-attenuated inversion recovery failed to reflect the morphologic complexity underlying tumor in patients with GBM. Contrary to the conventional wisdom that apparent diffusion coefficient (ADC) negatively correlates with increased tumor cellularity, we demonstrate disagreement between ADC and histologically confirmed tumor cellularity in GBM specimens, whereas DBSI-derived restricted isotropic diffusion fraction positively correlated with tumor cellularity in the same specimens. By incorporating DBSI metrics as classifiers for a supervised machine learning algorithm, we accurately predicted high tumor cellularity, tumor necrosis, and tumor infiltration with 87.5%, 89.0%, and 93.4% accuracy, respectively. Conclusions: Our results suggest that DHI could serve as a favorable alternative to current neuroimaging techniques in guiding biopsy or surgery as well as monitoring therapeutic response in the treatment of GBM.
UR - http://www.scopus.com/inward/record.url?scp=85092086916&partnerID=8YFLogxK
U2 - 10.1158/1078-0432.CCR-20-0736
DO - 10.1158/1078-0432.CCR-20-0736
M3 - Article
C2 - 32694155
AN - SCOPUS:85092086916
SN - 1078-0432
VL - 26
SP - 5388
EP - 5399
JO - Clinical Cancer Research
JF - Clinical Cancer Research
IS - 20
ER -