TY - GEN
T1 - Graph-Radiomics Learning (GrRAiL)
T2 - 21st IEEE International Symposium on Biomedical Imaging, ISBI 2024
AU - Battalapalli, Dheerendranath
AU - Safai, Apoorva
AU - Ismail, Marwa
AU - Hill, Virginia
AU - Statsevych, Volodymyr
AU - Huang, Raymond
AU - Ahluwalia, Manmeet Singh
AU - Tiwari, Pallavi
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - A significant challenge in managing aggressive cancers is the ability to quantify the intra-tumoral heterogeneity that contributes to poor prognostic outcomes. While radiomics approaches have previously attempted to characterize tumor heterogeneity, they have primarily focused on utilizing textural- and morphological-based features from the tumor confines on imaging. In this work, we seek to go beyond textural intensity patterns and present a new Graph-Radiomics Learning (GrRAiL) approach that utilizes graph patterns to capture the spatial interactions in radiomic features. The rationale for this work is that the spatial interactions in radiomic expressions when mapped via connected graphs, can model the extensive heterogeneity of the tumor. GrRAiL involves (a) extracting radiomic expression maps from the segmented lesion, (b) clustering the sub-regions within the expression maps, (c) graph construction and feature extraction, followed by using machine learning approaches to quantify the tumor regions. We assess the efficacy of GrRAiL in accurately quantifying lesion heterogeneity to address a challenging clinical dilemma in Glioblastoma (GB), the most aggressive brain tumor. In this context, we seek to utilize GrRAiL to differentiate GB true progression (TP) from pseudo-progression (PsP), a benign radiation-induced treatment effect that often mimics the appearance of TP on MRI scans. Our study included n = 106 GB patients from Cleveland Clinic (TP: 38, PsP: 22 for training) and Dana-Farber Cancer Center (TP: 33, PsP: 13 for testing). After extracting GrRAiL features, a Random Forest classifier was employed to distinguish TP from PsP. Further, GrRAiL's performance was compared with radiomic features as well as intensity-based graph features, in distinguishing TP from PsP. GrRAiL achieved a test accuracy of 0.76 and outperformed radiomics (accuracy = 0.69) and intensity-based graph approaches (accuracy = 0.61).
AB - A significant challenge in managing aggressive cancers is the ability to quantify the intra-tumoral heterogeneity that contributes to poor prognostic outcomes. While radiomics approaches have previously attempted to characterize tumor heterogeneity, they have primarily focused on utilizing textural- and morphological-based features from the tumor confines on imaging. In this work, we seek to go beyond textural intensity patterns and present a new Graph-Radiomics Learning (GrRAiL) approach that utilizes graph patterns to capture the spatial interactions in radiomic features. The rationale for this work is that the spatial interactions in radiomic expressions when mapped via connected graphs, can model the extensive heterogeneity of the tumor. GrRAiL involves (a) extracting radiomic expression maps from the segmented lesion, (b) clustering the sub-regions within the expression maps, (c) graph construction and feature extraction, followed by using machine learning approaches to quantify the tumor regions. We assess the efficacy of GrRAiL in accurately quantifying lesion heterogeneity to address a challenging clinical dilemma in Glioblastoma (GB), the most aggressive brain tumor. In this context, we seek to utilize GrRAiL to differentiate GB true progression (TP) from pseudo-progression (PsP), a benign radiation-induced treatment effect that often mimics the appearance of TP on MRI scans. Our study included n = 106 GB patients from Cleveland Clinic (TP: 38, PsP: 22 for training) and Dana-Farber Cancer Center (TP: 33, PsP: 13 for testing). After extracting GrRAiL features, a Random Forest classifier was employed to distinguish TP from PsP. Further, GrRAiL's performance was compared with radiomic features as well as intensity-based graph features, in distinguishing TP from PsP. GrRAiL achieved a test accuracy of 0.76 and outperformed radiomics (accuracy = 0.69) and intensity-based graph approaches (accuracy = 0.61).
KW - graph theory
KW - Radiomics
KW - tumor heterogeneity
UR - http://www.scopus.com/inward/record.url?scp=85203344968&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85203344968&partnerID=8YFLogxK
U2 - 10.1109/ISBI56570.2024.10635456
DO - 10.1109/ISBI56570.2024.10635456
M3 - Conference contribution
AN - SCOPUS:85203344968
T3 - Proceedings - International Symposium on Biomedical Imaging
BT - IEEE International Symposium on Biomedical Imaging, ISBI 2024 - Conference Proceedings
PB - IEEE Computer Society
Y2 - 27 May 2024 through 30 May 2024
ER -