Advertisement

Performance of a machine learning-based decision model to help clinicians decide the extent of lymphadenectomy (D1 vs. D2) in gastric cancer before surgical resection

  • Chang Liu
  • Liang Qi
  • Qiu-Xia Feng
  • Shu-Wen Sun
  • Yu-Dong ZhangEmail author
  • Xi-Sheng LiuEmail author
Hollow Organ GI

Abstract

Background

Controversy still exists on the optimal surgical resection for potentially curable gastric cancer (GC). Use of radiologic evaluation and machine learning algorithms might predict extent of lymphadenectomy to limit unnecessary surgical treatment. We purposed to design a machine learning-based clinical decision-support model for predicting extent of lymphadenectomy (D1 vs. D2) in local advanced GC.

Methods

Clinicoradiologic features available from routine clinical assignments in 557 patients with GCs were retrospectively interpreted by an expert panel blinded to all histopathologic information. All patients underwent surgery using standard D2 resection. Decision models were developed with a logistic regression (LR), support vector machine (SVM) and auto-encoder (AE) algorithm in 371 training and tested in 186 test data, respectively. The primary end point was to measure diagnostic performance of decision model and a Japanese gastric cancer treatment guideline version 4th (JPN 4th) criteria for discriminate D1 (pT1 + pN0) versus D2 (≥ pT1 + ≥ pN1) lymphadenectomy.

Results

The decision model with AE analysis produced highest area under ROC curve (train: 0.965, 95% confidence interval (CI) 0.948–0.978; test: 0.946, 95% CI 0.925–0.978), followed by SVM (train: 0.925, 95% CI 0.902–0.944; test: 0.942, 95% CI 0.922–0.973) and LR (train: 0.886, 95% CI 0.858–0.910; test: 0.891, 95% CI 0.891–0.952). By this improvement, overtreatment was reduced from 21.7% (121/557) by treat-all pattern, to 15.1% (84/557) by JPN 4th criteria, and to 0.7–0.9% (4–5/557) by the new approach.

Conclusions

The decision model with machine learning analysis demonstrates high accuracy for identifying patients who are candidates for D1 versus D2 resection. Its approximate 14–20% improvements in overtreatment compared to treat-all pattern and JPN 4th criteria potentially increase the number of patients with local advanced GCs who can safely avoid unnecessary lymphadenectomy.

Keywords

Tomography Gastric cancer Machine learning Lymphadenectomy Decision-support model 

Notes

Funding

This study is supported by a Key Social Development Program for the Ministry of Science and Technology of Jiangsu Province (BE2017756, YDZ)

Compliance with ethical standards

Conflict of interest

The authors have nothing to declare.

Ethical approval

The study was approved by the Institutional Review Board of the First Affiliated Hospital of Nanjing Medical University.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Supplementary material

261_2019_2098_MOESM1_ESM.docx (15 kb)
Supplementary material 1 (DOCX 15 kb)
261_2019_2098_MOESM2_ESM.docx (3.6 mb)
Supplementary material 2 (DOCX 3716 kb)
261_2019_2098_MOESM3_ESM.docx (29 kb)
Supplementary material 3 (DOCX 29 kb)

References

  1. 1.
    Siegel RL, Miller KD, Jemal A (2018) Cancer statistics, 2018. CA: a cancer journal for clinicians; 68(1): 7–30.Google Scholar
  2. 2.
    Wu CW, Hsiung CA, Lo SS et al (2006) Nodal dissection for patients with gastric cancer: a randomised controlled trial. The Lancet Oncol 7(4): 309–315.CrossRefGoogle Scholar
  3. 3.
    Sasako M, Sano T, Yamamoto S et al (2008) D2 lymphadenectomy alone or with para-aortic nodal dissection for gastric cancer. N. Engl. J. Med 359(5): 453–462.CrossRefGoogle Scholar
  4. 4.
    Songun I, Putter H, Kranenbarg EM et al (2010) Surgical treatment of gastric cancer: 15-year follow-up results of the randomised nationwide Dutch D1D2 trial. The Lancet Oncol 11(5): 439–449.CrossRefGoogle Scholar
  5. 5.
    Cuschieri A, Weeden S, Fielding J et al (1999) Patient survival after D1 and D2 resections for gastric cancer: long-term results of the MRC randomized surgical trial. Surgical Co-operative Group. Br. J. Cancer 79(9–10): 1522–1530.CrossRefGoogle Scholar
  6. 6.
    Japanese Gastric Cancer A. Japanese gastric cancer treatment guidelines 2014 (ver. 4). Gastric cancer: official journal of the International Gastric Cancer Association and the Japanese Gastric Cancer Association 2017; 20(1): 1–19.Google Scholar
  7. 7.
    Ahn HS, Kim SH, Kodera Y, Yang HK (2013) Gastric cancer staging with radiologic imaging modalities and UICC staging system. Dig. Surg 30(2): 142–9.CrossRefGoogle Scholar
  8. 8.
    Kim JW, Shin SS, Heo SH et al (2012) 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 22(3): 654–662.Google Scholar
  9. 9.
    Lee SL, Ku YM, Jeon HM, Lee HH (2017) Impact of the Cross-Sectional Location of Multidetector Computed Tomography Scans on Prediction of Serosal Exposure in Patients with Advanced Gastric Cancer. Ann Surg Oncol 24(4): 1003–1009.CrossRefGoogle Scholar
  10. 10.
    Hur J, Park MS, Lee JH et al (2006) Diagnostic accuracy of multidetector row computed tomography in T- and N staging of gastric cancer with histopathologic correlation. J Comput Assist Tomo 30(3): 372–377.CrossRefGoogle Scholar
  11. 11.
    Kim SH, Kim JJ, Lee JS et al (2013) Preoperative N staging of gastric cancer by stomach protocol computed tomography. J Gastric Cancer 13(3): 149–156.CrossRefGoogle Scholar
  12. 12.
    Stabile Ianora AA, Telegrafo M, Lucarelli NM et al(2017) Comparison between CT Net enhancement and PET/CT SUV for N staging of gastric cancer: A case series. Ann Med Surg 21: 1–6.CrossRefGoogle Scholar
  13. 13.
    Kim HJ, Kim AY, Oh ST et al (2005) Gastric cancer staging at multi-detector row CT gastrography: comparison of transverse and volumetric CT scanning. Radiology 236(3): 879–885.CrossRefGoogle Scholar
  14. 14.
    Maccioni F, Marcelli G, Al Ansari N et al (2010) Preoperative T and N staging of gastric cancer: magnetic resonance imaging (MRI) versus multi detector computed tomography (MDCT). Clin Ter 161(2): e57–62.Google Scholar
  15. 15.
    Huang CM, Xu M, Wang JB et al (2014) Is tumor size a predictor of preoperative N staging in T2-T4a stage advanced gastric cancer? Surg Oncol 23(1): 5–10.CrossRefGoogle Scholar
  16. 16.
    Hwang SH, Kim HI, Song JS, Lee MH, Kwon SJ, Kim MG (2016) The Ratio-Based N Staging System Can More Accurately Reflect the Prognosis of T4 Gastric Cancer Patients with D2 Lymphadenectomy Compared with the 7th American Joint Committee on Cancer/Union for International Cancer Control Staging System. J Gastric Cancer 16(4): 207–214.CrossRefGoogle Scholar
  17. 17.
    Dorfman RE, Alpern MB, Gross BH, Sandler MA (1991). Upper abdominal lymph nodes: criteria for normal size determined with CT. Radiology 180(2): 319–322.CrossRefGoogle Scholar
  18. 18.
    Chen CY, Hsu JS, Wu DC et al (2007) Gastric cancer: preoperative local staging with 3D multi-detector row CT–correlation with surgical and histopathologic results. Radiology 242(2): 472–482.CrossRefGoogle Scholar
  19. 19.
    Peng CW, Wang LW, Zeng WJ, Yang XJ, Li Y (2013) Evaluation of the staging systems for gastric cancer. J Surg Oncol 108(2): 93–105.CrossRefGoogle Scholar
  20. 20.
    Washington K (2010) 7th edition of the AJCC cancer staging manual: stomach. Ann Surg Oncol 17(12): 3077–3079.CrossRefGoogle Scholar
  21. 21.
    Kumano S, Okada M, Shimono T et al (2012) T-staging of gastric cancer of air-filling multidetector-row CT: comparison with hydro-multidetector-row CT. Eur J Radiol 81(11): 2953–2960.CrossRefGoogle Scholar
  22. 22.
    Lee IJ, Lee JM, Kim SH et al (2009) Helical CT evaluation of the preoperative staging of gastric cancer in the remnant stomach. AJR Am J Roentgenol 192(4): 902–908.CrossRefGoogle Scholar
  23. 23.
    Kumano S, Murakami T, Kim T et al (2005) T staging of gastric cancer: role of multi-detector row CT. Radiology 237(3): 961–966.CrossRefGoogle Scholar
  24. 24.
    Fairweather M, Jajoo K, Sainani N, Bertagnolli MM, Wang J (2015) Accuracy of EUS and CT imaging in preoperative gastric cancer staging. J Surg Oncol 111(8): 1016–1020.CrossRefGoogle Scholar
  25. 25.
    Hong ZL, Chen QY, Zheng CH et al (2017) A preoperative scoring system to predict the risk of No. 10 lymph node metastasis for advanced upper gastric cancer: a large case report based on a single-center study. Oncotarget 8(45): 80050–80060.Google Scholar
  26. 26.
    Xu S, Feng L, Chen Y et al (2017) Consistency mapping of 16 lymph node stations in gastric cancer by CT-based vessel-guided delineation of 255 patients. Oncotarget 8(25): 41465–41473.CrossRefGoogle Scholar
  27. 27.
    Peng C, Liu J, Yang G, Li Y (2018) The tumor-stromal ratio as a strong prognosticator for advanced gastric cancer patients: proposal of a new TSNM staging system. J Gastroenterol 53(5):606–617CrossRefGoogle Scholar
  28. 28.
    Choi YY, An JY, Katai H et al (2016) A Lymph Node Staging System for Gastric Cancer: A Hybrid Type Based on Topographic and Numeric Systems. PloS one 11(3): e0149555.CrossRefGoogle Scholar
  29. 29.
    Chen J, Chen C, He Y, Wu K, Wu H, Cai S (2014) A new pN staging system based on both the number and anatomic location of metastatic lymph nodes in gastric cancer. J Gastrointest Surg 18(12): 2080–2088.CrossRefGoogle Scholar
  30. 30.
    Aerts HJ, Velazquez ER, Leijenaar RT et al (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Na Commun 5: 4006.CrossRefGoogle Scholar
  31. 31.
    Kermany DS, Goldbaum M, Cai W et al (2018) Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning. Cell 172(5): 1122–31 e9.Google Scholar
  32. 32.
    Huang YQ, Liang CH, He L et al (2016) Development and Validation of a Radiomics Nomogram for Preoperative Prediction of Lymph Node Metastasis in Colorectal Cancer. J Clin Oncol 34(18): 2157–2164.CrossRefGoogle Scholar
  33. 33.
    Kim AY, Kim HJ, Ha HK (2005) Gastric cancer by multidetector row CT: preoperative staging. Abdom Imaging 30(4): 465–472.CrossRefGoogle Scholar
  34. 34.
    Makino T, Fujiwara Y, Takiguchi S et al (2011) Preoperative T staging of gastric cancer by multi-detector row computed tomography. Surgery 149(5): 672–679.CrossRefGoogle Scholar
  35. 35.
    Vickers AJ, Elkin EB (2006) Decision curve analysis: a novel method for evaluating prediction models. Med Decis Making 26(6): 565–574.CrossRefGoogle Scholar
  36. 36.
    Zhang CD, Ning FL, Zeng XT, Dai DQ (2018) Lymphovascular invasion as a predictor for lymph node metastasis and a prognostic factor in gastric cancer patients under 70 years of age: A retrospective analysis. Int J Surg 53:214–220CrossRefGoogle Scholar
  37. 37.
    Ozawa Y, Chiba N, Hikita K et al (2017) Long-Term Survival of a Gastric Neuroendocrine Carcinoma Patient with Extra-Regional Lymph Node Metastases. Gan To Kagaku Ryoho 44(4): 333–336.Google Scholar
  38. 38.
    Naffouje SA, Salti GI (2017) Extensive Lymph Node Dissection Improves Survival among American Patients with Gastric Adenocarcinoma Treated Surgically: Analysis of the National Cancer Database. J Gastric Cancer 17(4): 319–330.CrossRefGoogle Scholar
  39. 39.
    Marin Cordova NE, Yan-Quiroz EF, Diaz Plasencia J, Churango Barreto K, Calvanapon Prado P, Salazar Abad S (2017) Prognostic significance of the ratio of lymph node metastatic in 5-year survival after curative gastrectomy for advanced gastric carcinoma. Rev Gastroenterol Peru 37(3): 217–224.Google Scholar
  40. 40.
    Lu J, Wang W, Zheng CH et al (2017) Influence of Total Lymph Node Count on Staging and Survival After Gastrectomy for Gastric Cancer: An Analysis From a Two-Institution Database in China. Ann Surg Oncol 24(2): 486–493.CrossRefGoogle Scholar
  41. 41.
    Polkowski M, Palucki J, Wronska E, Szawlowski A, Nasierowska-Guttmejer A, Butruk E (2004) Endosonography versus helical computed tomography for locoregional staging of gastric cancer. Endoscopy 36(7): 617–623.CrossRefGoogle Scholar
  42. 42.
    Botet JF, Lightdale CJ, Zauber AG et al (1991) Preoperative staging of gastric cancer: comparison of endoscopic US and dynamic CT. Radiology 181(2): 426–432.CrossRefGoogle Scholar
  43. 43.
    Pereira MA, Ramos M, Dias AR et al (2018) Risk Factors for Lymph Node Metastasis in Western Early Gastric Cancer After Optimal Surgical Treatment. J Gastrointest Surg 22(1): 23–31.CrossRefGoogle Scholar
  44. 44.
    Chen L, Wang YH, Cheng YQ et al (2017) Risk factors of lymph node metastasis in 1620 early gastric carcinoma radical resections in Jiangsu Province in China: A multicenter clinicopathological study. J Dig Dis 18(10): 556–565.CrossRefGoogle Scholar
  45. 45.
    Miles KA (1999) Tumour angiogenesis and its relation to contrast enhancement on computed tomography: a review. Eur J Radiol 30(3): 198–205.CrossRefGoogle Scholar
  46. 46.
    Fukuya T, Honda H, Hayashi T et al (1995) Lymph-node metastases: efficacy for detection with helical CT in patients with gastric cancer. Radiology 197(3): 705–711.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of RadiologyTongDe Hospital of ZheJiang ProvinceHangzhouChina
  2. 2.Department of RadiologyThe First Affiliated Hospital of Nanjing Medical UniversityNanjingChina

Personalised recommendations