{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T04:37:21Z","timestamp":1790743041325,"version":"4.1.0"},"reference-count":48,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2021,3,2]],"date-time":"2021-03-02T00:00:00Z","timestamp":1614643200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Checkpoint inhibitors provided sustained clinical benefit to metastatic lung cancer patients. Nonetheless, prognostic markers in metastatic settings are still under research. Imaging offers distinctive advantages, providing whole-body information non-invasively, while routinely available in most clinics. We hypothesized that more prognostic information can be extracted by employing artificial intelligence (AI) for treatment monitoring, superior to 2D tumor growth criteria.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A cohort of 152 stage-IV non-small-cell lung cancer patients (NSCLC) (73 discovery, 79 test, 903CTs), who received nivolumab were retrospectively collected. We trained a neural network to identify morphological changes on chest CT acquired during patients\u2019 follow-ups. A classifier was employed to link imaging features learned by the network with overall survival.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Our results showed significant performance in the independent test set to predict 1-year overall survival from the date of image acquisition, with an average area under the curve (AUC) of 0.69 (<jats:italic>p &amp;lt;<\/jats:italic> 0.01), up to AUC 0.75 (<jats:italic>p<\/jats:italic> &amp;lt; 0.01) in the first 3 to 5 months of treatment, and 0.67 AUC (<jats:italic>p<\/jats:italic> = 0.01) for durable clinical benefit (6 months progression-free survival). We found the AI-derived survival score to be independent of clinical, radiological, PDL1, and histopathological factors. Visual analysis of AI-generated prognostic heatmaps revealed relative prognostic importance of morphological nodal changes in the mediastinum, supraclavicular, and hilar regions, lung and bone metastases, as well as pleural effusions, atelectasis, and consolidations.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>Our results demonstrate that deep learning can quantify tumor- and non\u2013tumor-related morphological changes important for prognostication on serial imaging. Further investigation should focus on the implementation of this technique beyond thoracic imaging.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fonc.2021.609054","type":"journal-article","created":{"date-parts":[[2021,3,2]],"date-time":"2021-03-02T14:36:31Z","timestamp":1614695791000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":44,"title":["Prognostic Value of Deep Learning-Mediated Treatment Monitoring in Lung Cancer Patients Receiving Immunotherapy"],"prefix":"10.3389","volume":"11","author":[{"given":"Stefano","family":"Trebeschi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuhir","family":"Bodalal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thierry N.","family":"Boellaard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Teresa M.","family":"Tareco Bucho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Silvia G.","family":"Drago","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ieva","family":"Kurilova","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adriana M.","family":"Calin-Vainak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Delli Pizzi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mirte","family":"Muller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karlijn","family":"Hummelink","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Koen J.","family":"Hartemink","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thi Dan Linh","family":"Nguyen-Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Egbert F.","family":"Smit","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hugo J. W. L.","family":"Aerts","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Regina G. H.","family":"Beets-Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2021,3,2]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1126\/science.271.5256.1734","article-title":"Enhancement of antitumor immunity by CTLA-4 blockade","volume":"271","author":"Leach","year":"1996","journal-title":"Science"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1002\/j.1460-2075.1992.tb05481.x","article-title":"Induced expression of PD-1, a novel member of the immunoglobulin gene superfamily, upon programmed cell death","volume":"11","author":"Ishida","year":"1992","journal-title":"EMBO J"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1507643","article-title":"Nivolumab versus Docetaxel in Advanced Nonsquamous Non-Small-Cell Lung Cancer","volume":"373","author":"Borghaei","year":"2015","journal-title":"N Engl J Med"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1504627","article-title":"Nivolumab versus Docetaxel in Advanced Squamous-Cell Non-Small-Cell Lung Cancer","volume":"373","author":"Brahmer","year":"2015","journal-title":"N Engl J Med"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(15)01281-7","article-title":"Pembrolizumab versus docetaxel for previously treated, PD-L1-positive, advanced non-small-cell lung cancer (KEYNOTE-010): a randomised controlled trial","volume":"387","author":"Herbst","year":"2016","journal-title":"Lancet"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.canlet.2017.11.014","article-title":"Progress and challenges of predictive biomarkers of anti PD-1\/PD-L1 immunotherapy: A systematic review","volume":"414","author":"Teng","year":"2018","journal-title":"Cancer Lett"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1038\/s41568-019-0116-x","article-title":"The evolving landscape of biomarkers for checkpoint inhibitor immunotherapy","volume":"19","author":"Havel","year":"2019","journal-title":"Nat Rev Cancer"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.4103\/jipo.jipo_19_19","article-title":"Review of immunogenomics and the role of tumor mutational burden as a biomarker for immunotherapy response","author":"Ros","year":"2019","journal-title":"J Immunother Precis Oncol"},{"key":"B9","doi-asserted-by":"publisher","first-page":"696","DOI":"10.1001\/jamaoncol.2018.7098","article-title":"Assessment of Blood Tumor Mutational Burden as a Potential Biomarker for Immunotherapy in Patients With Non-Small Cell Lung Cancer With Use of a Next-Generation Sequencing Cancer Gene Panel","volume":"5","author":"Wang","year":"2019","journal-title":"JAMA Oncol"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2008.10.026","article-title":"New response evaluation criteria in solid tumours: revised RECIST guideline (version 1.1)","volume":"45","author":"Eisenhauer","year":"2009","journal-title":"Eur J Cancer"},{"key":"B11","doi-asserted-by":"publisher","first-page":"998","DOI":"10.1093\/annonc\/mdz108","article-title":"Predicting response to cancer immunotherapy using noninvasive radiomic biomarkers","volume":"30","author":"Trebeschi","year":"2019","journal-title":"Ann Oncol"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(18)30413-3","article-title":"A radiomics approach to assess tumour-infiltrating CD8 cells and response to anti-PD-1 or anti-PD-L1 immunotherapy: an imaging biomarker, retrospective multicohort study","volume":"19","author":"Sun","year":"2018","journal-title":"Lancet Oncol"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1186\/s13244-019-0703-0","article-title":"How clinical imaging can assess cancer biology","volume":"10","author":"Garc\u00eda-Figueiras","year":"2019","journal-title":"Insights Imaging"},{"key":"B14","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1148\/radiol.2018181349","article-title":"Imaging of Cancer Immunotherapy: Current Approaches and Future Directions","volume":"290","author":"Nishino","year":"2019","journal-title":"Radiology"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1158\/2326-6066.CIR-15-0102","article-title":"Radiographic Profiling of Immune-Related Adverse Events in Advanced Melanoma Patients Treated with Ipilimumab","volume":"3","author":"Tirumani","year":"2015","journal-title":"Cancer Immunol Res"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1007\/s00261-019-01935-2","article-title":"Frequency and imaging features of abdominal immune-related adverse events in metastatic lung cancer patients treated with PD-1 inhibitor","volume":"44","author":"Alessandrino","year":"2019","journal-title":"Abdom Radiol (NY)"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1609214","article-title":"Fulminant Myocarditis with Combination Immune Checkpoint Blockade","volume":"375","author":"Johnson","year":"2016","journal-title":"N Engl J Med"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.21037\/jtd.2017.02.88","article-title":"Prognostic effects of preoperative obstructive pneumonitis or atelectasis and comparison with tumor size in non-small cell lung cancer","volume":"9","author":"Pang","year":"2017","journal-title":"J Thorac Dis"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21552","article-title":"Artificial intelligence in cancer imaging: Clinical challenges and applications","volume":"69","author":"Bi","year":"2019","journal-title":"CA Cancer J Clin"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-020-01060-x","article-title":"Deep learning in medical image registration: a survey","volume":"31","author":"Haskins","year":"2020","journal-title":"Mach Vision Appl"},{"key":"B21","doi-asserted-by":"crossref","DOI":"10.1109\/ISBI.2017.7950587","article-title":"Self supervised deep representation learning for fine-grained body part recognition","volume-title":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","author":"Zhang","year":"2017"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1788","DOI":"10.1109\/TMI.2019.2897538","article-title":"VoxelMorph: A Learning Framework for Deformable Medical Image Registration","volume":"8","author":"Balakrishnan","year":"2019","journal-title":"IEEE Trans Med Imaging"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1394","DOI":"10.1109\/JBHI.2019.2951024","article-title":"Unsupervised 3D End-to-End Medical Image Registration with Volume Tweening Network","author":"Zhao","year":"2019","journal-title":"IEEE J BioMed Health Inform"},{"key":"B24","article-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"Ronneberger","year":""},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1117\/12.713754","article-title":"The Lung Image Database Consortium (LIDC) data collection process for nodule detection and annotation","author":"McNitt-Gray","year":"2007","journal-title":"Med Imaging 2007: Computer-Aided Diagnosis"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1118\/1.3528204","article-title":"The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A Completed Reference Database of Lung Nodules on CT Scans","volume":"38","author":"Armato","year":"2011","journal-title":"Med Phys"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-013-9622-7","article-title":"The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository","volume":"26","author":"Clark","year":"2013","journal-title":"J Digit Imaging"},{"key":"B28","article-title":"Random forests","volume-title":"Machine learning","year":"2001"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53","article-title":"Visualizing and Understanding Convolutional Networks","volume":"8689","author":"Zeiler","year":"2014","journal-title":"Comput Vision \u2013 ECCV 2014"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1117\/12.2513648","article-title":"Quantitative vessel tortuosity radiomics on baseline non-contrast lung CT predict response to immunotherapy and are prognostic of overall survival","volume":"10950","author":"Alilou","year":"2019","journal-title":"Med Imaging 2019: Computer-Aided Diagnosis"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1101\/2020.04.02.020859","article-title":"Hypoxia-related radiomics predict immunotherapy response of non-small cell lung cancer patients","author":"Tunali","year":"2020","journal-title":"Proceedings: AACR Annual Meeting"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1117\/12.2293376","article-title":"Radiomic biomarkers from PET\/CT multi-modality fusion images for the prediction of immunotherapy response in advanced non-small cell lung cancer patients","volume":"10575","author":"Mu","year":"2018","journal-title":"Med Imaging 2018: Computer-Aided Diagnosis"},{"key":"B33","doi-asserted-by":"publisher","first-page":"036501","DOI":"10.1117\/1.JMI.5.3.036501","article-title":"DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning","volume":"5","author":"Yan","year":"2018","journal-title":"J\u00a0Med Imaging (Bellingham)"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2016.03.081","article-title":"RECIST 1.1\u2014Update and clarification: From the RECIST committee","volume":"62","author":"Schwartz","year":"2016","journal-title":"Eur J Cancer"},{"key":"B35","doi-asserted-by":"publisher","first-page":"S211","DOI":"10.1016\/j.ijrobp.2019.06.286","article-title":"Predictors of Early Response to Immunotherapy in Head and Neck Cancer: A Secondary Clinical and Radiomic Analysis of a Prospective Randomized Trial with Nivolumab","volume":"105","author":"Yu","year":"2019","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B36","doi-asserted-by":"publisher","first-page":"101056","DOI":"10.1101\/664912","article-title":"Chemotherapy but not the tumor-draining lymph nodes determine the immunotherapy response in secondary tumors","author":"Zhao","year":"2020","journal-title":"iScience"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1172\/jci.insight.132286","article-title":"Multipanel mass cytometry reveals anti\u2013PD-1 therapy\u2013mediated B and T cell compartment remodeling in tumor-draining lymph nodes","volume":"5","author":"Ho","year":"2020","journal-title":"JCI Insight"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2018.00036","article-title":"Growth and Immune Evasion of Lymph Node Metastasis","volume":"8","author":"Jones","year":"2018","journal-title":"Front Oncol"},{"key":"B39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10278-019-00309-w","article-title":"Classifying Neck Lymph Nodes of Head and Neck Squamous Cell Carcinoma in MRI Images with Radiomic Features","volume":"16","author":"Ho","year":"2020","journal-title":"J Digit Imaging"},{"key":"B40","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/s12880-020-0416-3","article-title":"Discrimination of mediastinal metastatic lymph nodes in NSCLC based on radiomic features in different phases of CT imaging","volume":"20","author":"Sha","year":"2020","journal-title":"BMC Med Imaging"},{"key":"B41","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1007\/s00330-018-5581-1","article-title":"Radiomics nomogram outperforms size criteria in discriminating lymph node metastasis in resectable esophageal squamous cell carcinoma","volume":"29","author":"Tan","year":"2019","journal-title":"Eur Radiol"},{"key":"B42","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1186\/s12967-020-02215-0","article-title":"A clinical-radiomics nomogram for the preoperative prediction of lymph node metastasis in colorectal cancer","volume":"18","author":"Li","year":"2020","journal-title":"J Transl Med"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-15027-z","article-title":"Deep learning radiomics can predict axillary lymph node status in early-stage breast cancer","volume":"11","author":"Zheng","year":"2020","journal-title":"Nat Commun"},{"key":"B44","doi-asserted-by":"publisher","first-page":"20190558","DOI":"10.1259\/bjr.20190558","article-title":"Noninvasive CT radiomic model for preoperative prediction of lymph node metastasis in early cervical carcinoma","volume":"93","author":"Chen","year":"2020","journal-title":"Br J Radiol"},{"key":"B45","doi-asserted-by":"publisher","first-page":"1922","DOI":"10.1038\/s41598-018-20471-5","article-title":"Development of an Immune-Pathology Informed Radiomics Model for Non-Small Cell Lung Cancer","volume":"8","author":"Tang","year":"2018","journal-title":"Sci Rep"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1016\/j.lungcan.2019.01.010","article-title":"Novel clinical and radiomic predictors of rapid disease progression phenotypes among lung cancer patients treated with immunotherapy: An early report","volume":"129","author":"Tunali","year":"2019","journal-title":"Lung Cancer"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.3233\/xst-200642","article-title":"Radiomics study for predicting the expression of PD-L1 in non-small cell lung cancer based on CT images and clinicopathologic features","author":"Sun","year":"2020","journal-title":"J Xray Sci Technol"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1117\/12.2513001","article-title":"A combination of intra- and peritumoral features on baseline CT scans is associated with overall survival in non-small cell lung cancer patients treated with immune checkpoint inhibitors: a multi-agent multi-site study","volume":"10950","author":"Patil","year":"2019","journal-title":"Med Imaging 2019: Computer-Aided Diagnosis"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2021.609054\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,2]],"date-time":"2021-03-02T14:36:37Z","timestamp":1614695797000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2021.609054\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,2]]},"references-count":48,"alternative-id":["10.3389\/fonc.2021.609054"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2021.609054","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,2]]},"article-number":"609054"}}