The Lancet: Digital Health (Jul 2023)
Predicting benefit from immune checkpoint inhibitors in patients with non-small-cell lung cancer by CT-based ensemble deep learning: a retrospective study
- Maliazurina B Saad, PhD,
- Lingzhi Hong, MD,
- Muhammad Aminu, MD,
- Natalie I Vokes, MD,
- Pingjun Chen, PhD,
- Morteza Salehjahromi, PhD,
- Kang Qin, MD,
- Sheeba J Sujit, PhD,
- Xuetao Lu, PhD,
- Elliana Young, MS,
- Qasem Al-Tashi, PhD,
- Rizwan Qureshi, PhD,
- Carol C Wu, ProfMD,
- Brett W Carter, ProfMD,
- Steven H Lin, ProfMD,
- Percy P Lee, ProfMD,
- Saumil Gandhi, MD,
- Joe Y Chang, ProfMD,
- Ruijiang Li, PhD,
- Michael F Gensheimer, MD,
- Heather A Wakelee, ProfMD,
- Joel W Neal, MD,
- Hyun-Sung Lee, MD,
- Chao Cheng, PhD,
- Vamsidhar Velcheti, ProfMD,
- Yanyan Lou, MD,
- Milena Petranovic, MD,
- Waree Rinsurongkawong, PhD,
- Xiuning Le, MD,
- Vadeerat Rinsurongkawong, PhD,
- Amy Spelman, PhD,
- Yasir Y Elamin, MD,
- Marcelo V Negrao, MD,
- Ferdinandos Skoulidis, MD,
- Carl M Gay, MD,
- Tina Cascone, MD,
- Mara B Antonoff, MD,
- Boris Sepesi, MD,
- Jeff Lewis, BS,
- Ignacio I Wistuba, ProfMD,
- John D Hazle, ProfPhD,
- Caroline Chung, MD,
- David Jaffray, ProfPhD,
- Don L Gibbons, ProfMD,
- Ara Vaporciyan, ProfMD,
- J Jack Lee, ProfPhD,
- John V Heymach, ProfMD,
- Jianjun Zhang, MD,
- Jia Wu, PhD
Affiliations
- Maliazurina B Saad, PhD
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Lingzhi Hong, MD
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Muhammad Aminu, MD
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Natalie I Vokes, MD
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; Department of Genomic Medicine, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Pingjun Chen, PhD
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Morteza Salehjahromi, PhD
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Kang Qin, MD
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Sheeba J Sujit, PhD
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Xuetao Lu, PhD
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Elliana Young, MS
- Department of Enterprise Data Engineering and Analytics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Qasem Al-Tashi, PhD
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Rizwan Qureshi, PhD
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Carol C Wu, ProfMD
- Department of Thoracic Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Brett W Carter, ProfMD
- Department of Thoracic Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Steven H Lin, ProfMD
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Percy P Lee, ProfMD
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; Department of Radiation Oncology, City of Hope National Medical Center, Los Angeles, CA, USA
- Saumil Gandhi, MD
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Joe Y Chang, ProfMD
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Ruijiang Li, PhD
- Department of Radiation Oncology, Stanford University School of Medicine, Palo Alto, CA, USA
- Michael F Gensheimer, MD
- Department of Radiation Oncology, Stanford University School of Medicine, Palo Alto, CA, USA
- Heather A Wakelee, ProfMD
- Department of Medicine, Division of Oncology, Stanford University School of Medicine, Stanford, CA, USA; Stanford Cancer Institute, Stanford, CA, USA
- Joel W Neal, MD
- Department of Medicine, Division of Oncology, Stanford University School of Medicine, Stanford, CA, USA; Stanford Cancer Institute, Stanford, CA, USA
- Hyun-Sung Lee, MD
- Systems Onco-Immunology Laboratory, David J Sugarbaker Division of Thoracic Surgery, Michael E DeBakey Department of Surgery, Baylor College of Medicine, Houston, TX, USA
- Chao Cheng, PhD
- Institute for Clinical and Translational Research, Baylor College of Medicine, Houston, TX, USA
- Vamsidhar Velcheti, ProfMD
- Department of Hematology and Oncology, New York University Langone Health, New York, NY, USA
- Yanyan Lou, MD
- Division of Hematology and Oncology, Mayo Clinic, Jacksonville, FL, USA
- Milena Petranovic, MD
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA
- Waree Rinsurongkawong, PhD
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Xiuning Le, MD
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Vadeerat Rinsurongkawong, PhD
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Amy Spelman, PhD
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Yasir Y Elamin, MD
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Marcelo V Negrao, MD
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Ferdinandos Skoulidis, MD
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Carl M Gay, MD
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Tina Cascone, MD
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Mara B Antonoff, MD
- Department of Thoracic and Cardiovascular Surgery, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Boris Sepesi, MD
- Department of Thoracic and Cardiovascular Surgery, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Jeff Lewis, BS
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Ignacio I Wistuba, ProfMD
- Department of Translational Molecular Pathology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- John D Hazle, ProfPhD
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Caroline Chung, MD
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; Department of Neuroradiology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- David Jaffray, ProfPhD
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Don L Gibbons, ProfMD
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Ara Vaporciyan, ProfMD
- Department of Thoracic and Cardiovascular Surgery, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- J Jack Lee, ProfPhD
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- John V Heymach, ProfMD
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; Prof John V Heymach, Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Jianjun Zhang, MD
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; Department of Genomic Medicine, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; Dr Jianjun Zhang, Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Jia Wu, PhD
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; Correspondence to: Dr Jia Wu, Department of Imaging Physics, Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Journal volume & issue
-
Vol. 5,
no. 7
pp. e404 – e420
Abstract
Summary: Background: Only around 20–30% of patients with non-small-cell lung cancer (NCSLC) have durable benefit from immune-checkpoint inhibitors. Although tissue-based biomarkers (eg, PD-L1) are limited by suboptimal performance, tissue availability, and tumour heterogeneity, radiographic images might holistically capture the underlying cancer biology. We aimed to investigate the application of deep learning on chest CT scans to derive an imaging signature of response to immune checkpoint inhibitors and evaluate its added value in the clinical context. Methods: In this retrospective modelling study, 976 patients with metastatic, EGFR/ALK negative NSCLC treated with immune checkpoint inhibitors at MD Anderson and Stanford were enrolled from Jan 1, 2014, to Feb 29, 2020. We built and tested an ensemble deep learning model on pretreatment CTs (Deep-CT) to predict overall survival and progression-free survival after treatment with immune checkpoint inhibitors. We also evaluated the added predictive value of the Deep-CT model in the context of existing clinicopathological and radiological metrics. Findings: Our Deep-CT model demonstrated robust stratification of patient survival of the MD Anderson testing set, which was validated in the external Stanford set. The performance of the Deep-CT model remained significant on subgroup analyses stratified by PD-L1, histology, age, sex, and race. In univariate analysis, Deep-CT outperformed the conventional risk factors, including histology, smoking status, and PD-L1 expression, and remained an independent predictor after multivariate adjustment. Integrating the Deep-CT model with conventional risk factors demonstrated significantly improved prediction performance, with overall survival C-index increases from 0·70 (clinical model) to 0·75 (composite model) during testing. On the other hand, the deep learning risk scores correlated with some radiomics features, but radiomics alone could not reach the performance level of deep learning, indicating that the deep learning model effectively captured additional imaging patterns beyond known radiomics features. Interpretation: This proof-of-concept study shows that automated profiling of radiographic scans through deep learning can provide orthogonal information independent of existing clinicopathological biomarkers, bringing the goal of precision immunotherapy for patients with NSCLC closer. Funding: National Institutes of Health, Mark Foundation Damon Runyon Foundation Physician Scientist Award, MD Anderson Strategic Initiative Development Program, MD Anderson Lung Moon Shot Program, Andrea Mugnaini, and Edward L C Smith.
