Gastrointestinal Cancer

PV QA 1 - Poster Viewing Q&A 1

SU_5_2041 - MRI radiomics signature as a potential biomarker to predict different KRAS status in colorectal cancer patients and tumor cells

Sunday, October 21
1:15 PM - 2:45 PM
Location: Innovation Hub, Exhibit Hall 3

MRI radiomics signature as a potential biomarker to predict different KRAS status in colorectal cancer patients and tumor cells
L. Shen1, Y. Wang1, G. Qing2, J. Zhang1, Y. Sun2, P. Hu2, W. Hu1, J. Wang1, and Z. Zhang1; 1Department of Radiation Oncology, Fudan University Shanghai Cancer Center, Shanghai, China, 2Fudan University Shanghai Cancer Center, Shanghai, China

Purpose/Objective(s): In metastatic colorectal cancer (mCRC), KRAS mutation status is associated with effect of anti-EGFR therapy and prognosis. Radiomics as a potential tumor biomarker exhibit strong phenotypic differences between patients. The purpose of this study is to analyze the potential of MRI radiomics to predict different KRAS status in colorectal cancer patients and tumor cells.

Materials/Methods: This study was performed both in human and mice. In all, 46 metastatic rectal or sigmoid colon cancer patients with primary cancer MRI image and KRAS mutation status were included. Colorectal cell line SW620 cells ectopic expressing KRAS G12V and the corresponding control cells were subcutaneously injected into BALB/c nude mice (6 mice for each cell line). Radiomics features were extracted from MRI T2 images in patients and mice. A ranksum test was preformed to find significant features.

Results: A total of 202 radiomics features were extracted from both patients and mice. Seven features were significantly different between KRAS wild and mutant patients, meanwhile 48 features were difference between KRAS wild and mutant mice. One overlapped feature named HH_GLRLMS.RLN identified from patients and mice set.

Conclusion: MRI radiomics showed its potential to predict different KRAS status in colorectal cancer patients and tumor cells. Further validation in larger dataset is necessary in the future.

Author Disclosure: L. Shen: None. J. Zhang: None. Y. Sun: None. P. Hu: None. Z. Zhang: Independent Contractor; Varian Medical System.

Send Email for Lijun Shen


Assets

SU_5_2041 - MRI radiomics signature as a potential biomarker to predict different KRAS status in colorectal cancer patients and tumor cells



Attendees who have favorited this

Please enter your access key

The asset you are trying to access is locked. Please enter your access key to unlock.

Send Email for MRI radiomics signature as a potential biomarker to predict different KRAS status in colorectal cancer patients and tumor cells