Wen Yu1, Chad Tang1, Brian P Hobbs2, Xiao Li2, Eugene J Koay1, Ignacio I Wistuba3, Boris Sepesi4, Carmen Behrens5, Jaime Rodriguez Canales3, Edwin Roger Parra Cuentas3, Jeremy J Erasmus6, Laurence E Court7, Joe Y Chang8. 1. Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas. 2. Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, Texas. 3. Department of Translational and Molecular Pathology, The University of Texas MD Anderson Cancer Center, Houston, Texas. 4. Department of Thoracic and Cardiovascular Surgery, The University of Texas MD Anderson Cancer Center, Houston, Texas. 5. Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas. 6. Department of Diagnostic Radiology, The University of Texas MD Anderson Cancer Center, Houston, Texas. 7. Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas. Electronic address: LECourt@mdanderson.org. 8. Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas. Electronic address: jychang@mdanderson.org.
Abstract
PURPOSE: To develop and validate a radiomics signature that can predict the clinical outcomes for patients with stage I non-small cell lung cancer (NSCLC). METHODS AND MATERIALS: We retrospectively analyzed contrast-enhanced computed tomography images of patients from a training cohort (n = 147) treated with surgery and an independent validation cohort (n = 295) treated with stereotactic ablative radiation therapy. Twelve radiomics features with established strategies for filtering and preprocessing were extracted. The random survival forests (RSF) method was used to build models from subsets of the 12 candidate features based on their survival relevance and generate a mortality risk index for each observation in the training set. An optimal model was selected, and its ability to predict clinical outcomes was evaluated in the validation set using predicted mortality risk indexes. RESULTS: The optimal RSF model, consisting of 2 predictive features, kurtosis and the gray level co-occurrence matrix feature homogeneity2, allowed for significant risk stratification (log-rank P < .0001) and remained an independent predictor of overall survival after adjusting for age, tumor volume and histologic type, and Karnofsky performance status (hazard ratio [HR] 1.27; P < 2e-16) in the training set. The resultant mortality risk indexes were significantly associated with overall survival in the validation set (log-rank P = .0173; HR 1.02, P = .0438). They were also significant for distant metastasis (log-rank P < .05; HR 1.04, P = .0407) and were borderline significant for regional recurrence on univariate analysis (log-rank P < .05; HR 1.04, P = .0617). CONCLUSIONS: Our radiomics model accurately predicted several clinical outcomes and allowed pretreatment risk stratification in stage I NSCLC, allowing the choice of treatment to be tailored to each patient's individual risk profile.
PURPOSE: To develop and validate a radiomics signature that can predict the clinical outcomes for patients with stage I non-small cell lung cancer (NSCLC). METHODS AND MATERIALS: We retrospectively analyzed contrast-enhanced computed tomography images of patients from a training cohort (n = 147) treated with surgery and an independent validation cohort (n = 295) treated with stereotactic ablative radiation therapy. Twelve radiomics features with established strategies for filtering and preprocessing were extracted. The random survival forests (RSF) method was used to build models from subsets of the 12 candidate features based on their survival relevance and generate a mortality risk index for each observation in the training set. An optimal model was selected, and its ability to predict clinical outcomes was evaluated in the validation set using predicted mortality risk indexes. RESULTS: The optimal RSF model, consisting of 2 predictive features, kurtosis and the gray level co-occurrence matrix feature homogeneity2, allowed for significant risk stratification (log-rank P < .0001) and remained an independent predictor of overall survival after adjusting for age, tumor volume and histologic type, and Karnofsky performance status (hazard ratio [HR] 1.27; P < 2e-16) in the training set. The resultant mortality risk indexes were significantly associated with overall survival in the validation set (log-rank P = .0173; HR 1.02, P = .0438). They were also significant for distant metastasis (log-rank P < .05; HR 1.04, P = .0407) and were borderline significant for regional recurrence on univariate analysis (log-rank P < .05; HR 1.04, P = .0617). CONCLUSIONS: Our radiomics model accurately predicted several clinical outcomes and allowed pretreatment risk stratification in stage I NSCLC, allowing the choice of treatment to be tailored to each patient's individual risk profile.
Authors: Kyle J Lafata; Michael N Corradetti; Junheng Gao; Corbin D Jacobs; Jingxi Weng; Yushi Chang; Chunhao Wang; Ace Hatch; Eric Xanthopoulos; Greg Jones; Chris R Kelsey; Fang-Fang Yin Journal: Radiol Imaging Cancer Date: 2021-04
Authors: Robert H Press; Hui-Kuo G Shu; Hyunsuk Shim; James M Mountz; Brenda F Kurland; Richard L Wahl; Ella F Jones; Nola M Hylton; Elizabeth R Gerstner; Robert J Nordstrom; Lori Henderson; Karen A Kurdziel; Bhadrasain Vikram; Michael A Jacobs; Matthias Holdhoff; Edward Taylor; David A Jaffray; Lawrence H Schwartz; David A Mankoff; Paul E Kinahan; Hannah M Linden; Philippe Lambin; Thomas J Dilling; Daniel L Rubin; Lubomir Hadjiiski; John M Buatti Journal: Int J Radiat Oncol Biol Phys Date: 2018-06-30 Impact factor: 7.038
Authors: Zhicheng Jiao; Hongming Li; Ying Xiao; Charu Aggarwal; Maya Galperin-Aizenberg; Daniel Pryma; Charles B Simone; Steven J Feigenberg; Gary D Kao; Yong Fan Journal: Int J Radiat Oncol Biol Phys Date: 2021-01-19 Impact factor: 7.038
Authors: Radouane El Ayachy; Nicolas Giraud; Paul Giraud; Catherine Durdux; Philippe Giraud; Anita Burgun; Jean Emmanuel Bibault Journal: Front Oncol Date: 2021-05-05 Impact factor: 6.244
Authors: Sang Ho Lee; Gary D Kao; Steven J Feigenberg; Jay F Dorsey; Melissa A Frick; Samuel Jean-Baptiste; Chibueze Z Uche; Keith A Cengel; William P Levin; Abigail T Berman; Charu Aggarwal; Yong Fan; Ying Xiao Journal: Int J Radiat Oncol Biol Phys Date: 2021-03-01 Impact factor: 8.013