Radiographical assessment of tumour stroma and treatment outcomes using deep learning: a retrospective, multicohort study

Bray, 2018, Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries, CA Cancer J Clin, 68, 394, 10.3322/caac.21492 Paoletti, 2010, Benefit of adjuvant chemotherapy for resectable gastric cancer: a meta-analysis, JAMA, 303, 1729, 10.1001/jama.2010.534 Noh, 2014, Adjuvant capecitabine plus oxaliplatin for gastric cancer after D2 gastrectomy (CLASSIC): 5-year follow-up of an open-label, randomised phase 3 trial, Lancet Oncol, 15, 1389, 10.1016/S1470-2045(14)70473-5 Jiang, 2017, Association of adjuvant chemotherapy with survival in patients with stage II or III gastric cancer, JAMA Surg, 152, 10.1001/jamasurg.2017.1087 Cheong, 2018, Predictive test for chemotherapy response in resectable gastric cancer: a multi-cohort, retrospective analysis, Lancet Oncol, 19, 629, 10.1016/S1470-2045(18)30108-6 Valkenburg, 2018, Targeting the tumour stroma to improve cancer therapy, Nat Rev Clin Oncol, 15, 366, 10.1038/s41571-018-0007-1 Kobayashi, 2019, Cancer-associated fibroblasts in gastrointestinal cancer, Nat Rev Gastroenterol Hepatol, 16, 282, 10.1038/s41575-019-0115-0 Quail, 2013, Microenvironmental regulation of tumor progression and metastasis, Nat Med, 19, 1423, 10.1038/nm.3394 Pietras, 2010, Hallmarks of cancer: interactions with the tumor stroma, Exp Cell Res, 316, 1324, 10.1016/j.yexcr.2010.02.045 Ligorio, 2019, Stromal microenvironment shapes the intratumoral architecture of pancreatic cancer, Cell, 178, 160, 10.1016/j.cell.2019.05.012 Torres, 2013, Proteome profiling of cancer-associated fibroblasts identifies novel proinflammatory signatures and prognostic markers for colorectal cancer, Clin Cancer Res, 19, 6006, 10.1158/1078-0432.CCR-13-1130 Huijbers, 2013, The proportion of tumor-stroma as a strong prognosticator for stage II and III colon cancer patients: validation in the VICTOR trial, Ann Oncol, 24, 179, 10.1093/annonc/mds246 Moffitt, 2015, Virtual microdissection identifies distinct tumor- and stroma-specific subtypes of pancreatic ductal adenocarcinoma, Nat Genet, 47, 1168, 10.1038/ng.3398 Calon, 2015, Stromal gene expression defines poor-prognosis subtypes in colorectal cancer, Nat Genet, 47, 320, 10.1038/ng.3225 Mahajan, 2018, Immune Cell and stromal signature associated with progression-free survival of patients with resected pancreatic ductal adenocarcinoma, Gastroenterology, 155, 1625, 10.1053/j.gastro.2018.08.009 Friedman, 2020, Cancer-associated fibroblast compositions change with breast cancer progression linking the ratio of S100A4+ and PDPN+ CAFs to clinical outcome, Nat Can, 1, 692, 10.1038/s43018-020-0082-y Zhi, 2010, Cancer-associated fibroblasts are positively correlated with metastatic potential of human gastric cancers, J Exp Clin Cancer Res, 29, 66, 10.1186/1756-9966-29-66 Wu, 2013, Comprehensive genomic meta-analysis identifies intra-tumoural stroma as a predictor of survival in patients with gastric cancer, Gut, 62, 1100, 10.1136/gutjnl-2011-301373 Uhlik, 2016, Stromal-based signatures for the classification of gastric cancer, Cancer Res, 76, 2573, 10.1158/0008-5472.CAN-16-0022 Zhang, 2020, CAF secreted miR-522 suppresses ferroptosis and promotes acquired chemo-resistance in gastric cancer, Mol Cancer, 19, 43, 10.1186/s12943-020-01168-8 Li, 2020, Natural killer cell and stroma abundance are independently prognostic and predict gastric cancer chemotherapy benefit, JCI Insight, 5, 10.1172/jci.insight.136570 Grunberg, 2021, Cancer-associated fibroblasts promote aggressive gastric cancer phenotypes via heat shock factor 1-mediated secretion of extracellular vesicles, Cancer Res, 10.1158/0008-5472.CAN-20-2756 Zhong, 2019, Overexpression of periostin is positively associated with gastric cancer metastasis through promoting tumor metastasis and invasion, J Cell Biochem, 120, 9927, 10.1002/jcb.28275 Yuan, 2016, Spatial Heterogeneity in the tumor microenvironment, Cold Spring Harb Perspect Med, 6, 10.1101/cshperspect.a026583 Josson, 2010, Tumor-stroma co-evolution in prostate cancer progression and metastasis, Semin Cell Dev Biol, 21, 26, 10.1016/j.semcdb.2009.11.016 Sun, 2018, 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, Lancet Oncol, 19, 1180, 10.1016/S1470-2045(18)30413-3 Jiang, 2020, Noninvasive imaging evaluation of tumor immune microenvironment to predict outcomes in gastric cancer, Ann Oncol, 31, 760, 10.1016/j.annonc.2020.03.295 Vaidya, 2020, CT derived radiomic score for predicting the added benefit of adjuvant chemotherapy following surgery in stage I, II resectable non-small cell lung cancer: a retrospective multi-cohort study for outcome prediction, Lancet Digit Health, 2, e116, 10.1016/S2589-7500(20)30002-9 Gulshan, 2016, Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs, JAMA, 316, 2402, 10.1001/jama.2016.17216 Esteva, 2017, Dermatologist-level classification of skin cancer with deep neural networks, Nature, 542, 115, 10.1038/nature21056 Ehteshami Bejnordi, 2017, Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer, JAMA, 318, 2199, 10.1001/jama.2017.14585 Chilamkurthy, 2018, Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study, Lancet, 392, 2388, 10.1016/S0140-6736(18)31645-3 Coudray, 2018, Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning, Nat Med, 24, 1559, 10.1038/s41591-018-0177-5 Ardila, 2019, End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography, Nat Med, 25, 954, 10.1038/s41591-019-0447-x Kikuchi, 2014, The niche component periostin is produced by cancer-associated fibroblasts, supporting growth of gastric cancer through ERK activation, Am J Pathol, 184, 859, 10.1016/j.ajpath.2013.11.012 Zhou, 2015, Periostin secreted by glioblastoma stem cells recruits M2 tumour-associated macrophages and promotes malignant growth, Nat Cell Biol, 17, 170, 10.1038/ncb3090 Ryner, 2015, Upregulation of periostin and reactive stroma is associated with primary chemoresistance and predicts clinical outcomes in epithelial ovarian cancer, Clin Cancer Res, 21, 2941, 10.1158/1078-0432.CCR-14-3111 Oh, 2017, Overexpression of POSTN in tumor stroma is a poor prognostic indicator of colorectal cancer, J Pathol Transl Med, 51, 306, 10.4132/jptm.2017.01.19 Yang, 2020, Prognostic value of periostin in multiple solid cancers: a systematic review with meta-analysis, J Cell Physiol, 235, 2800, 10.1002/jcp.29184 Li, 2013, Upregulation of periostin prevents P53-mediated apoptosis in SGC-7901 gastric cancer cells, Mol Biol Rep, 40, 1677, 10.1007/s11033-012-2218-3 Yu, 2019, Effect of laparoscopic vs open distal gastrectomy on 3-year disease-free survival in patients with locally advanced gastric cancer: the CLASS-01 randomized clinical trial, JAMA, 321, 1983, 10.1001/jama.2019.5359 2011, Japanese gastric cancer treatment guidelines 2010 (ver. 3), Gastric Cancer, 14, 113, 10.1007/s10120-011-0042-4 Haejin, 2017, Validation of the 8th edition of the AJCC TNM staging system for gastric cancer using the national cancer database, Ann Surg Oncol, 24, 3683, 10.1245/s10434-017-6078-x Jiang, 2018, ImmunoScore signature: a prognostic and predictive tool in gastric cancer, Ann Surg, 267, 504, 10.1097/SLA.0000000000002116 Jiang, 2018, Immunomarker support vector machine classifier for prediction of gastric cancer survival and adjuvant chemotherapeutic benefit, Clin Cancer Res, 24, 5574, 10.1158/1078-0432.CCR-18-0848 He KM, Zhang XY, Ren SQ, Sun J. Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition; Las Vegas NV; June 26–July 1, 2016: 770–78. Russakovsky, 2015, ImageNet large scale visual recognition challenge, Int J Comput Vis, 115, 211, 10.1007/s11263-015-0816-y Selvaraju, 2020, Grad-CAM: visual explanations from deep networks via gradient-based localization, Int J Comput Vis, 128, 336, 10.1007/s11263-019-01228-7 Tsujino, 2007, Stromal myofibroblasts predict disease recurrence for colorectal cancer, Clin Cancer Res, 13, 2082, 10.1158/1078-0432.CCR-06-2191 Segal, 2007, Decoding global gene expression programs in liver cancer by noninvasive imaging, Nat Biotechnol, 25, 675, 10.1038/nbt1306 Wu, 2018, Magnetic resonance imaging and molecular features associated with tumor-infiltrating lymphocytes in breast cancer, Breast Cancer Res, 20, 101, 10.1186/s13058-018-1039-2 Tang, 2018, Development of an immune-pathology informed radiomics model for non-small cell lung cancer, Sci Rep, 8 Sun, 2020, Radiomics to predict outcomes and abscopal response of patients with cancer treated with immunotherapy combined with radiotherapy using a validated signature of CD8 cells, J Immunother Cancer, 8, 10.1136/jitc-2020-001429 Zinn, 2018, A coclinical radiogenomic validation study: conserved magnetic resonance radiomic appearance of periostin-expressing glioblastoma in patients and xenograft models, Clin Cancer Res, 24, 6288, 10.1158/1078-0432.CCR-17-3420 Mu, 2020, Non-invasive decision support for NSCLC treatment using PET/CT radiomics, Nat Commun, 11, 10.1038/s41467-020-19116-x Lou, 2019, An image-based deep learning framework for individualising radiotherapy dose: a retrospective analysis of outcome prediction, Lancet Digit Health, 1, e136, 10.1016/S2589-7500(19)30058-5 Shitara, 2020, Efficacy and safety of pembrolizumab or pembrolizumab plus chemotherapy vs chemotherapy alone for patients with first-line, advanced gastric cancer: the KEYNOTE-062 phase 3 randomized clinical trial, JAMA Oncol, 6, 1571, 10.1001/jamaoncol.2020.3370 Cunningham, 2006, Perioperative chemotherapy versus surgery alone for resectable gastroesophageal cancer, N Engl J Med, 355, 11, 10.1056/NEJMoa055531 Tauriello, 2018, TGFβ drives immune evasion in genetically reconstituted colon cancer metastasis, Nature, 554, 538, 10.1038/nature25492 Mariathasan, 2018, TGFβ attenuates tumour response to PD-L1 blockade by contributing to exclusion of T cells, Nature, 554, 544, 10.1038/nature25501