体细胞突变与代谢成像表型在非小细胞肺癌中的关系(英文)

2017-04-23 16:02:00 admin 1

Associations Between Somatic Mutations and Metabolic Imaging Phenotypes in Non-Small CellLung Cancer.

J Nucl Med. 2017 Apr

Yip SS1, Kim J2, Coroller TP3, Parmar C3, Velazquez ER3, Huynh E3, Mak RH3, Aerts HJ3,4.

Author information

    1.Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, and Harvard Medical School, Boston, Massachusetts Stephen_Yip@dfci.harvard.edu.

    2.Department of Radiology, University of Michigan Health System, Ann Arbor, Michigan; and.

    3.Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, and Harvard Medical School, Boston, Massachusetts.

    4.Department of Radiology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, and Harvard Medical School, Boston, Massachusetts.

Abstract

PET-based radiomics have been used to noninvasively quantify the metabolic tumor phenotypes; however, little is known about the relationship between these phenotypes and underlying somatic mutations. This study assessed the association and predictive power of 18F-FDG PET-based radiomic features for somatic mutations in non-small cell lung cancer patients. 

Methods 

Three hundred forty-eight non-small cell lung cancer patients underwent diagnostic 18F-FDG PET scans and were tested for genetic mutations. Thirteen percent (44/348) and 28% (96/348) of patients were found to harbor epidermal growth factor receptor (EGFR) or Kristen rat sarcoma viral (KRAS) mutations, respectively. We evaluated 21 imaging features: 19 independent radiomic features quantifying phenotypic traits and 2 conventional features (metabolic tumor volume and maximum SUV). The association between imaging features and mutation status (e.g., EGFR-positive [EGFR+] vs. EGFR-negative) was assessed using the Wilcoxon rank-sum test. The ability of each imaging feature to predict mutation status was evaluated by the area under the receiver operating curve (AUC) and its significance was compared with a random guess (AUC = 0.5) using the Noether test. All P values were corrected for multiple hypothesis testing by controlling the false-discovery rate (FDRWilcoxon, FDRNoether) with a significance threshold of 10%.

Results 

Eight radiomic features and both conventional features were significantly associated with EGFR mutation status (FDRWilcoxon = 0.01-0.10). One radiomic feature (normalized inverse difference moment) outperformed all other features in predicting EGFR mutation status (EGFR+ vs. EGFR-negative, AUC = 0.67, FDRNoether = 0.0032), as well as differentiating between KRAS-positive and EGFR+ (AUC = 0.65, FDRNoether = 0.05). None of the features was associated with or predictive of KRAS mutation status (KRAS-positive vs. KRAS-negative, AUC = 0.50-0.54).

Conclusion 

Our results indicate that EGFR mutations may drive different metabolic tumor phenotypes that are captured in PET images, whereas KRAS-mutated tumors do not. This proof-of-concept study sheds light on genotype-phenotype interactions, using radiomics to capture and describe the phenotype, and may have potential for developing noninvasive imaging biomarkers for somatic mutations.

KEYWORDS


PET imaging; phenotype; radiomics; somatic mutation


慧影医疗科技(北京)有限公司

地点:北京市海淀区中关村东升科技园B2-C103

电话:400-890-9020

邮箱:radcloud@huiyihuiying.com

关闭
图片
图片
  • 人工智能诊断云平台