Pathologic stratification of operable lung adenocarcinoma using radiomics features extracted from dual energy CT images

// Jung Min Bae 1, * , Ji Yun Jeong 2, * , Ho Yun Lee 1 , Insuk Sohn 3 , Hye Seung Kim 3 , Ji Ye Son 1 , O Jung Kwon 4 , JoonYoung Choi 5 , Kyung Soo Lee 1 , Young Mog Shim 6 1 Department of Radiology and Center for Imaging Science, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul 135-710, Korea 2 Department of Pathology, Kyungpook National University Medical Center, Kyungpook National University School of Medicine, Daegu 702-210, Korea 3 Biostatisticsand Clinical Epidemiology Center, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul 135-710, Korea 4 Division of Respiratory and Critical Medicine of the Department of Internal Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul 135-710, Korea 5 Department of Nuclear Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul 135-710, Korea 6 Department of Thoracic and Cardiovascular Surgery, Samsung Medical Center, Sungkyunkwan University School of Medicine, Gangnam-gu, Seoul 135-710, Korea * These authors contributed equally to this work Correspondence to: Ho Yun Lee, email: hoyunlee96@gmail.com Young Mog Shim, email: youngmog.shim@samsung.com Keywords: lung adenocarcinoma, heterogeneity, radiomics, texture analysis, dual energy CT Received: June 29, 2016 Accepted: November 14, 2016 Published: November 21, 2016 ABSTRACT Purpose: To evaluate the usefulness of surrogate biomarkers as predictors of histopathologic tumor grade and aggressiveness using radiomicsdata from dual-energy computed tomography (DECT), with the ultimate goal of accomplishing stratification of early-stage lung adenocarcinoma for optimal treatment. Results: Pathologic grade was divided into grades 1, 2, and 3. Multinomial logistic regressionanalysis revealed i -uniformity and 97.5th percentile CT attenuation value as independent significant factors to stratify grade 2 or 3 from grade 1. The AUC value calculated from leave-one-out cross-validation procedure for discriminating grades 1, 2, and 3 was 0.9307 (95% CI: 0.8514–1), 0.8610 (95% CI: 0.7547–0.9672), and 0.8394 (95% CI: 0.7045–0.9743), respectively. Materials and Methods: A total of 80 patients with 91 clinically and radiologically suspected stage I or II lung adenocarcinoma were prospectively enrolled. All patients underwent DECT and F-18-fluorodeoxyglucose (FDG) positron emission tomography (PET)/CT, followed by surgery. Quantitative CT and PET imaging characteristics were evaluated using a radiomicsapproach. Significant features for a tumor aggressiveness prediction model were extracted and used to calculate diagnostic performance for predicting all pathologic grades. Conclusions: Quantitative radiomicsvalues from DECT imaging metrics can help predict pathologic aggressiveness of lung adenocarcinoma.