Journal of Digestive Cancer Research

Korean Society of Gastrointestinal Cancer Research (대한소화기암연구학회)
권호 표지
DOI QR코드

DOI QR Code

Application of Artificial Intelligence in Gastric Cancer

위암에서 인공지능의 응용

  • Jung In Lee (Division of Gastroenterology, Department of Internal Medicine, College of Medicine, Chosun University)
  • 이정인 (조선대학교 의과대학 소화기내과)
  • Received : 2023.11.14
  • Accepted : 2023.12.07
  • Published : 2023.12.20
Download PDF
⟨ Previous Next ⟩

Abstract

Gastric cancer (GC) is one of the most common malignant tumors worldwide, with a 5-year survival rate of < 40%. The diagnosis and treatment decisions of GC rely on human experts' judgments on medical images; therefore, the accuracy can be hindered by image condition, objective criterion, limited experience, and interobserver discrepancy. In recent years, several applications of artificial intelligence (AI) have emerged in the GC field based on improvement of computational power and deep learning algorithms. AI can support various clinical practices in endoscopic examination, pathologic confirmation, radiologic staging, and prognosis prediction. This review has systematically summarized the current status of AI applications after a comprehensive literature search. Although the current approaches are challenged by data scarcity and poor interpretability, future directions of this field are likely to overcome the risk and enhance their accuracy and applicability in clinical practice.

Keywords

References

  1. Sung H, Ferlay J, Siegel RL, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 2021;71:209-249. https://doi.org/10.3322/caac.21660 
  2. Ajani JA, Bentrem DJ, Besh S, et al.; National Comprehensive Cancer Network. Gastric cancer, version 2.2013: featured updates to the NCCN Guidelines. J Natl Compr Canc Netw 2013;11:531-546. https://doi.org/10.6004/jnccn.2013.0070 
  3. Isobe Y, Nashimoto A, Akazawa K, et al. Gastric cancer treatment in Japan: 2008 annual report of the JGCA nationwide registry. Gastric Cancer 2011;14:301-316. https://doi.org/10.1007/s10120-011-0085-6 
  4. Veitch AM, Uedo N, Yao K, East JE. Optimizing early upper gastrointestinal cancer detection at endoscopy. Nat Rev Gastroenterol Hepatol 2015;12:660-667. https://doi.org/10.1038/nrgastro.2015.128 
  5. Pimentel-Nunes P, Dinis-Ribeiro M, Ponchon T, et al. Endoscopic submucosal dissection: European Society of Gastrointestinal Endoscopy (ESGE) guideline. Endoscopy 2015;47:829-854. https://doi.org/10.1055/s-0034-1392882 
  6. Wagner AD, Syn NL, Moehler M, et al. Chemotherapy for advanced gastric cancer. Cochrane Database Syst Rev 2017;8:CD004064. https://doi.org/10.1002/14651858.CD004064.pub4 
  7. Gravalos C, Jimeno A. HER2 in gastric cancer: a new prognostic factor and a novel therapeutic target. Ann Oncol 2008;19:1523-1529. https://doi.org/10.1093/annonc/mdn169 
  8. Sauerbruch T, Schreiber MA, Schussler P, Permanetter W. Endoscopy in the diagnosis of gastritis. Diagnostic value of endoscopic criteria in relation to histological diagnosis. Endoscopy 1984;16:101-104. https://doi.org/10.1055/s-2007-1018546 
  9. Watanabe K, Nagata N, Shimbo T, et al. Accuracy of endoscopic diagnosis of Helicobacter pylori infection according to level of endoscopic experience and the effect of training. BMC Gastroenterol 2013;13:128. https://doi.org/10.1186/1471-230X-13-128 
  10. Menon S, Trudgill N. How commonly is upper gastrointestinal cancer missed at endoscopy? A meta-analysis. Endosc Int Open 2014;2:E46-E50. https://doi.org/10.1055/s-0034-1365524 
  11. Miyaki R, Yoshida S, Tanaka S, et al. Quantitative identification of mucosal gastric cancer under magnifying endoscopy with flexible spectral imaging color enhancement. J Gastroenterol Hepatol 2013;28:841-847. https://doi.org/10.1111/jgh.12149 
  12. Miyaki R, Yoshida S, Tanaka S, et al. A computer system to be used with laser-based endoscopy for quantitative diagnosis of early gastric cancer. J Clin Gastroenterol 2015;49:108-115. https://doi.org/10.1097/MCG.0000000000000104 
  13. Zhang X, Hu W, Chen F, et al. Gastric precancerous diseases classification using CNN with a concise model. PLoS One 2017;12:e0185508. https://doi.org/10.1371/journal.pone.0185508 
  14. Hirasawa T, Aoyama K, Tanimoto T, et al. Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images. Gastric Cancer 2018;21:653-660. https://doi.org/10.1007/s10120-018-0793-2 
  15. Liu X, Wang C, Hu Y, et al. Transfer learning with convolutional neural network for early gastric cancer classification on magnifiying narrow-band imaging images [abstract]. In: 2018 25th IEEE International Conference on Image Processing (ICIP); 2018 Oct 7-10; Athens, Greece. p.1388-1392. 
  16. Cho BJ, Bang CS, Park SW, et al. Automated classification of gastric neoplasms in endoscopic images using a convolutional neural network. Endoscopy 2019;51:1121-1129. https://doi.org/10.1055/a-0981-6133 
  17. Lee JH, Kim YJ, Kim YW, et al. Spotting malignancies from gastric endoscopic images using deep learning. Surg Endosc 2019;33:3790-3797. https://doi.org/10.1007/s00464-019-06677-2 
  18. Luo H, Xu G, Li C, et al. Real-time artificial intelligence for detection of upper gastrointestinal cancer by endoscopy: a multicentre, case-control, diagnostic study. Lancet Oncol 2019;20:1645-1654. https://doi.org/10.1016/S1470-2045(19)30637-0 
  19. Hsu CC, Ma HT, Lee JY. SSSNet: small-scale-aware siamese network for gastric cancer detection [abstract]. In: 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS); 2019 Sep 18-21; Taipei, Taiwan. p.1-5. 
  20. Yoon HJ, Kim S, Kim JH, et al. A lesion-based convolutional neural network improves endoscopic detection and depth prediction of early gastric cancer. J Clin Med 2019;8:1310. https://doi.org/10.3390/jcm8091310 
  21. Nguyen DT, Lee MB, Pham TD, Batchuluun G, Arsalan M, Park KR. Enhanced image-based endoscopic pathological site classification using an ensemble of deep learning models. Sensors (Basel) 2020;20:5982. https://doi.org/10.3390/s20215982 
  22. Ikenoyama Y, Hirasawa T, Ishioka M, et al. Detecting early gastric cancer: comparison between the diagnostic ability of convolutional neural networks and endoscopists. Dig Endosc 2021;33:141-150. https://doi.org/10.1111/den.13688 
  23. Hu H, Gong L, Dong D, et al. Identifying early gastric cancer under magnifying narrow-band images with deep learning: a multicenter study. Gastrointest Endosc 2021;93:1333-1341.e3. https://doi.org/10.1016/j.gie.2020.11.014 
  24. Kubota K, Kuroda J, Yoshida M, Ohta K, Kitajima M. Medical image analysis: computer-aided diagnosis of gastric cancer invasion on endoscopic images. Surg Endosc 2012;26:1485-1489. https://doi.org/10.1007/s00464-011-2036-z 
  25. Zhu Y, Wang QC, Xu MD, et al. Application of convolutional neural network in the diagnosis of the invasion depth of gastric cancer based on conventional endoscopy. Gastrointest Endosc 2019;89:806-815.e1. https://doi.org/10.1016/j.gie.2018.11.011 
  26. Nagao S, Tsuji Y, Sakaguchi Y, et al. Highly accurate artificial intelligence systems to predict the invasion depth of gastric cancer: efficacy of conventional whitelight imaging, nonmagnifying narrow-band imaging, and indigo-carmine dye contrast imaging. Gastrointest Endosc 2020;92:866-873.e1. https://doi.org/10.1016/j.gie.2020.06.047 
  27. An P, Yang D, Wang J, et al. A deep learning method for delineating early gastric cancer resection margin under chromoendoscopy and white light endoscopy. Gastric Cancer 2020;23:884-892. https://doi.org/10.1007/s10120-020-01071-7 
  28. Ling T, Wu L, Fu Y, et al. A deep learning-based system for identifying differentiation status and delineating the margins of early gastric cancer in magnifying narrowband imaging endoscopy. Endoscopy 2021;53:469-477. https://doi.org/10.1055/a-1229-0920 
  29. Li Y, Li X, Xie X, Shen L. Deep learning based gastric cancer identification [abstract]. In: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018); 2018 Apr 4-7; Washington, D.C., USA. p.182-185. 
  30. Li Y, Xie X, Liu S, Li X, Shen L. GT-Net: a deep learning network for gastric tumor diagnosis [abstract]. In: 2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI); 2018 Nov 5-7; Volos, Greece. p.20-24. 
  31. Sun M, Zhang G, Dang H, et al. Accurate gastric cancer segmentation in digital pathology images using deformable convolution and multi-scale embedding networks. IEEE Access 2019;7:75530-75541. https://doi.org/10.1109/ACCESS.2019.2918800 
  32. Wang S, Zhu Y, Yu L, et al. RMDL: recalibrated multiinstance deep learning for whole slide gastric image classification. Med Image Anal 2019;58:101549. https://doi.org/10.1016/j.media.2019.101549 
  33. Sharma H, Zerbe N, Heim D, et al. Cell nuclei attributed relational graphs for efficient representation and classification of gastric cancer in digital histopathology. In: Gurcan MN, Madabhushi A, eds. Medical imaging 2016: digital pathology. Bellingham: SPIE, 2016:97910X. 
  34. Sharma H, Zerbe N, Klempert I, Hellwich O, Hufnagl P. Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology. Comput Med Imaging Graph 2017;61:2-13. https://doi.org/10.1016/j.compmedimag.2017.06.001 
  35. Kather JN, Pearson AT, Halama N, et al. Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer. Nat Med 2019;25:1054-1056. https://doi.org/10.1038/s41591-019-0462-y 
  36. Valieris R, Amaro L, Osorio CABT, et al. Deep learning predicts underlying features on pathology images with therapeutic relevance for breast and gastric cancer. Cancers (Basel) 2020;12:3687. https://doi.org/10.3390/cancers12123687 
  37. Chen Y, Sun Z, Chen W, et al. The immune subtypes and landscape of gastric cancer and to predict based on the whole-slide images using deep learning. Front Immunol 2021;12:685992. https://doi.org/10.3389/fimmu.2021.685992 
  38. Wang Y, Liu W, Yu Y, et al. Prediction of the depth of tumor invasion in gastric cancer: potential role of CT radiomics. Acad Radiol 2020;27:1077-1084. https://doi.org/10.1016/j.acra.2019.10.020 
  39. Sun RJ, Fang MJ, Tang L, et al. CT-based deep learning radiomics analysis for evaluation of serosa invasion in advanced gastric cancer. Eur J Radiol 2020;132:109277.https://doi.org/10.1016/j.ejrad.2020.109277 
  40. Dong D, Fang MJ, Tang L, et al. Deep learning radiomic nomogram can predict the number of lymph node metastasis in locally advanced gastric cancer: an international multicenter study. Ann Oncol 2020;31:912-920. https://doi.org/10.1016/j.annonc.2020.04.003 
  41. Li J, Dong D, Fang M, et al. Dual-energy CT-based deep learning radiomics can improve lymph node metastasis risk prediction for gastric cancer. Eur Radiol 2020;30:2324-2333. https://doi.org/10.1007/s00330-019-06621-x 
  42. Jin C, Jiang Y, Yu H, et al. Deep learning analysis of the primary tumour and the prediction of lymph node metastases in gastric cancer. Br J Surg 2021;108:542-549. https://doi.org/10.1002/bjs.11928 
  43. Dong D, Tang L, Li ZY, et al. Development and validation of an individualized nomogram to identify occult peritoneal metastasis in patients with advanced gastric cancer. Ann Oncol 2019;30:431-438. https://doi.org/10.1093/annonc/mdz001 
  44. Huang Z, Liu D, Chen X, et al. Deep convolutional neural network based on computed tomography images for the preoperative diagnosis of occult peritoneal metastasis in advanced gastric cancer. Front Oncol 2020;10:601869. https://doi.org/10.3389/fonc.2020.601869 
  45. Jiang Y, Liang X, Wang W, et al. Noninvasive prediction of occult peritoneal metastasis in gastric cancer using deep learning. JAMA Netw Open 2021;4:e2032269. https://doi.org/10.1001/jamanetworkopen.2020.32269 
  46. Lai YC, Yeh TS, Wu RC, et al. Acute tumor transition angle on computed tomography predicts chromosomal instability status of primary gastric cancer: radiogenomics analysis from TCGA and independent validation. Cancers (Basel) 2019;11:641. https://doi.org/10.3390/cancers11050641 
  47. Tan JW, Wang L, Chen Y, et al. Predicting chemotherapeutic response for far-advanced gastric cancer by radiomics with deep learning semi-automatic segmentation. J Cancer 2020;11:7224-7236. https://doi.org/10.7150/jca.46704 
  48. Joo M, Park A, Kim K, et al. A deep learning model for cell growth inhibition IC50 prediction and its application for gastric cancer patients. Int J Mol Sci 2019;20:6276. https://doi.org/10.3390/ijms20246276 
  49. Hyung WJ, Son T, Park M, et al. Superior prognosis prediction performance of deep learning for gastric cancer compared to Yonsei prognosis prediction model using Cox regression. J Clin Oncol 2017;35:164. https://doi.org/10.1200/JCO.2017.35.4_suppl.164 
  50. Zhang L, Dong D, Zhang W, et al. A deep learning risk prediction model for overall survival in patients with gastric cancer: a multicenter study. Radiother Oncol 2020;150:73-80. https://doi.org/10.1016/j.radonc.2020.06.010 
  51. Jiang Y, Jin C, Yu H, et al. Development and validation of a deep learning CT signature to predict survival and chemotherapy benefit in gastric cancer: a multicenter, retrospective study. Ann Surg 2021;274:e1153-e1161. https://doi.org/10.1097/SLA.0000000000003778 
  52. Meier A, Nekolla K, Hewitt LC, et al. Hypothesis-free deep survival learning applied to the tumour microenvironment in gastric cancer. J Pathol Clin Res 2020;6:273-282. https://doi.org/10.1002/cjp2.170 
  53. Wang X, Chen Y, Gao Y, et al. Predicting gastric cancer outcome from resected lymph node histopathology images using deep learning. Nat Commun 2021;12:1637. https://doi.org/10.1038/s41467-021-21674-7 
  54. Correa P. A human model of gastric carcinogenesis. Cancer Res 1988;48:3554-3560. 
  55. de Vries AC, van Grieken NC, Looman CW, et al. Gastric cancer risk in patients with premalignant gastric lesions: a nationwide cohort study in the Netherlands. Gastroenterology 2008;134:945-952. https://doi.org/10.1053/j.gastro.2008.01.071 
  56. Amin A, Gilmour H, Graham L, Paterson-Brown S, Terrace J, Crofts TJ. Gastric adenocarcinoma missed at endoscopy. J R Coll Surg Edinb 2002;47:681-684. 
  57. Yalamarthi S, Witherspoon P, McCole D, Auld CD. Missed diagnoses in patients with upper gastrointestinal cancers. Endoscopy 2004;36:874-879. https://doi.org/10.1055/s-2004-825853 
  58. Voutilainen ME, Juhola MT. Evaluation of the diagnostic accuracy of gastroscopy to detect gastric tumours: clinicopathological features and prognosis of patients with gastric cancer missed on endoscopy. Eur J Gastroenterol Hepatol 2005;17:1345-1349. https://doi.org/10.1097/00042737-200512000-00013 
  59. Robbins SL, Cotran RS. Pathologic basis of disease. 2nd ed. Philadelphia: Saunders, 1979. 
  60. Behrens HM, Warneke VS, Boger C, et al. Reproducibility of Her2/neu scoring in gastric cancer and assessment of the 10% cut-off rule. Cancer Med 2015;4:235-244. https://doi.org/10.1002/cam4.365 
  61. Warneke VS, Behrens HM, Boger C, et al. Her2/neu testing in gastric cancer: evaluating the risk of sampling errors. Ann Oncol 2013;24:725-733. https://doi.org/10.1093/annonc/mds528 
  62. Ba-Ssalamah A, Prokop M, Uffmann M, Pokieser P, Teleky B, Lechner G. Dedicated multidetector CT of the stomach: spectrum of diseases. Radiographics 2003;23:625-644. https://doi.org/10.1148/rg.233025127 
  63. Kim JW, Shin SS, Heo SH, et al. Diagnostic performance of 64-section CT using CT gastrography in preoperative T staging of gastric cancer according to 7th edition of AJCC cancer staging manual. Eur Radiol 2012;22:654-662. https://doi.org/10.1007/s00330-011-2283-3 
  64. Hwang SW, Lee DH, Lee SH, et al. Preoperative staging of gastric cancer by endoscopic ultrasonography and multidetector-row computed tomography. J Gastroenterol Hepatol 2010;25:512-518. https://doi.org/10.1111/j.1440-1746.2009.06106.x 
  65. Amin MB, Greene FL, Edge SB, et al. The eighth edition AJCC cancer staging manual: continuing to build a bridge from a population-based to a more "personalized" approach to cancer staging. CA Cancer J Clin 2017;67:93-99. https://doi.org/10.3322/caac.21388 
  66. Kim HJ, Kim AY, Oh ST, et al. Gastric cancer staging at multi-detector row CT gastrography: comparison of transverse and volumetric CT scanning. Radiology 2005;236:879-885. https://doi.org/10.1148/radiol.2363041101 
  67. Smyth EC, Verheij M, Allum W, Cunningham D, Cervantes A, Arnold D; ESMO Guidelines Committee. Gastric cancer: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up. Ann Oncol 2016;27(suppl 5):v38-v49. https://doi.org/10.1093/annonc/mdw350 
  68. Cancer Genome Atlas Research Network. Comprehensive molecular characterization of gastric adenocarcinoma. Nature 2014;513:202-209. https://doi.org/10.1038/nature13480 
  69. Wagner AD, Grothe W, Haerting J, Kleber G, Grothey A, Fleig WE. Chemotherapy in advanced gastric cancer: a systematic review and meta-analysis based on aggregate data. J Clin Oncol 2006;24:2903-2909. https://doi.org/10.1200/JCO.2005.05.0245