Chinese Guideline for the Application of Rectal Cancer Staging Recognition Systems Based on Artificial Intelligence Platforms (2021 Edition)

0
0
0

Chinese Guideline for the Application of Rectal Cancer Staging Recognition Systems Based on Artificial Intelligence Platforms (2021 Edition)

Equal Contribution Authors: Yuan Gao, Yun Lu, Shuai Li
Authors: Yong Dai, Bo Feng, Fang-Hai Han, Jia-Gang Han, Jing-Jing He, Xin-Xiang Li, Guo-Le Lin, Qian Liu, Gui-Ying Wang, Quan Wang, Zhen-Ning Wang, Zheng Wang, Ai-Wen Wu, Bin Wu, Ying-Chi Yang, Hong-Wei Yao, Wei Zhang, Jian-Ping Zhou, Ai-Min Hao, Zhong-Tao Zhang
Affiliations: Colorectal Surgery Group of the Surgery Branch in the Chinese Medical Association; Beihang University State Key Laboratory of Virtual Reality Technology and Systems; and departments of general surgery, gastrointestinal surgery, and oncology at 21 major hospitals and research institutions across China (full affiliations listed at the end of this article).

Why AI Matters for Rectal Cancer Staging

Rectal cancer is one of the most common cancers globally, and accurate staging (knowing how far the cancer has spread) is critical to choosing the right treatment—whether surgery, chemotherapy, radiation, or a combination. Imaging (like MRI) is the gold standard for pre-operative staging, but reading these scans requires highly trained radiologists. Unfortunately, many regions face shortages of experienced radiologists, leading to delays, inconsistent results, and even treatment errors.

Artificial intelligence (AI) offers a solution. By learning from thousands of MRI scans, AI systems can quickly and consistently analyze images to identify key staging factors—helping doctors make faster, more reliable decisions. This 2021 guideline from Chinese medical experts outlines how AI can be used to stage rectal cancer, focusing on four critical parameters: T staging (tumor depth), N staging (lymph node spread), circumferential resection margin (CRM) (the safety margin around the tumor), and extramural vascular invasion (EMVI) (cancer in blood vessels outside the rectum).

Key Staging Parameters AI Evaluates

The guideline uses established medical standards to train AI systems, so results align with global best practices:

  1. T Staging (How Deep the Tumor Has Grown):

    • T1: Cancer is in the inner lining (submucosa) of the rectum.
    • T2: Cancer has reached the muscle layer (muscularis propria).
    • T3: Cancer has broken through the muscle layer into the surrounding tissue (mesorectum).
    • T4: Cancer has spread to nearby organs (like the bladder or uterus) or the lining of the abdomen (peritoneal reflection).
      Based on the AJCC TNM system and MRI research by Horvat et al.

  2. N Staging (Lymph Node Metastasis):
    AI flags lymph nodes as cancerous if they:

    • Are ≥5mm in the smallest dimension on MRI.
    • Have irregular shapes or unclear edges.
    • Show high signal on contrast-enhanced scans.
    • Appear discontinuous across image layers.
      Based on international consensus from the MERCURY Study Group and others.

  3. CRM (Circumferential Resection Margin):
    A “positive” CRM means the tumor is within 1mm of the edge of the tissue that will be removed during surgery—raising the risk of cancer remaining. AI measures this distance using MRI.

  4. EMVI (Extramural Vascular Invasion):
    AI detects cancer cells in blood vessels outside the rectum, which is a strong predictor of recurrence.

How the AI System Was Built

To ensure reliability, the AI was trained on high-quality MRI scans (3.0T machines from GE, Siemens, and Philips—used in most hospitals) and validated by a team of:

  • 2 senior radiologists
  • 1 colorectal surgery expert
  • A 4th radiologist to resolve disagreements

The core technology is a Faster Region-Based Convolutional Neural Network (FR-CNN)—a type of AI that:

  1. Scans MRI images to find “suspected” areas (e.g., tumors, abnormal lymph nodes).
  2. Analyzes these areas in detail to calculate the probability of cancer.
  3. Outputs results with bounding boxes (to show where the issue is) and confidence scores.

To test accuracy, the team used ROC curves (a tool to measure how well AI distinguishes between normal and abnormal) and AUC scores (a 0–1 scale where higher = better). Only AI systems with an AUC ≥90% (excellent accuracy) are approved for clinical use.

How Doctors Use the AI System

The AI doesn’t replace doctors—it supports them by providing fast, data-driven insights. Here’s how it works in practice:

Step 1: Interpret AI Results

Doctors use three confidence levels to guide decisions:

  • Highly reliable: T staging ≥90% confidence; N/CRM/EMVI ≥80% confidence.
  • Possible compliance: T staging 70–89%; N/CRM/EMVI 60–79%.
  • Poor compliance: T staging <70%; N/CRM/EMVI <60% (needs further testing).

Step 2: Guide Treatment

  • Early-stage (T1N0): For small, non-spreading tumors, doctors may choose local surgery (e.g., transanal endoscopic microsurgery).
  • Advanced-stage: For tumors with possible lymph node spread or high CRM/EMVI risk, doctors use neoadjuvant chemoradiation (chemo + radiation before surgery) to shrink the tumor. The AI is then re-run to check if the cancer has responded:
    • If the cancer is gone (clinical complete response, cCR), doctors may use a “watch and wait” approach or local surgery.
    • If not, radical surgery (total mesorectal excision, TME) is recommended.
  • Lateral lymph node metastasis: If AI still finds cancer in side lymph nodes after treatment, doctors perform targeted dissection to remove them.

Trust and Transparency

  • Registration: The guideline is registered with the International Practice Guideline Registry (IPGRP-2020CN175).
  • Conflicts of Interest: No authors report financial or personal conflicts related to this work.

Full Author Affiliations

  1. Department of General Surgery, The Affiliated Hospital of Qingdao University, Qingdao, Shandong 266555, China;
  2. Beihang University State Key Laboratory of Virtual Reality Technology and Systems, Beijing 100191, China;
  3. Department of General Surgery, Qilu Hospital of Shandong University, Jinan, Shandong 250012, China;
  4. Department of General Surgery, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China;
  5. Shanghai Minimally Invasive Surgery Center, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China;
  6. Department of Gastrointestinal Surgery, Sun Yat-sen University, Guangzhou, Guangdong 510120, China;
  7. Department of General Surgery, Beijing Chaoyang Hospital, Capital Medical University, Beijing 100020, China;
  8. Institute of International Law, Chinese Academy of Social Sciences, Beijing 100732, China;
  9. Department of Colorectal Surgery, Fudan University Shanghai Cancer Center, Shanghai 201321, China;
  10. Department of Oncology, Shanghai Medical College, Fudan University, Shanghai 201321, China;
  11. Department of General Surgery, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing 100730, China;
  12. National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences, Peking Union Medical College, Beijing 100021, China;
  13. Third Hospital of Hebei Medical University, Shijiazhuang, Hebei 050051, China;
  14. Department of Colon and Rectum Surgery, The First Hospital of Jilin University, Changchun, Jilin 130021, China;
  15. Department of Surgical Oncology and General Surgery, Key Laboratory of Precision Diagnosis and Treatment of Gastrointestinal Tumors, Ministry of Education, The First Affiliated Hospital of China Medical University, Shenyang, Liaoning 110001, China;
  16. Department of Gastrointestinal Surgery, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei 430022, China;
  17. Department of Unit III & Ostomy Service, Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education), Gastrointestinal Cancer Center, Peking University Cancer Hospital & Institute, Beijing 100142, China;
  18. Department of General Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Peking Union Medical College, Beijing 100730, China;
  19. Department of General Surgery, Beijing Friendship Hospital, Capital Medical University, Beijing 100050, China;
  20. Beijing Key Laboratory of Cancer Invasion and Metastasis Research, National Clinical Research Center of Digestive Diseases, Beijing 100050, China;
  21. Colorectal Surgery Department, Changhai Hospital, Naval Medical University, Shanghai 200433, China;
  22. Department of Gastrointestinal Surgery & Hernia and Abdominal Wall Surgery, The First Hospital, China Medical University, Shenyang, Liaoning 110001, China;
  23. Beijing Advanced Innovation Center for Biomedical Engineering, Beijing 100191, China.

Correspondence

For questions about the guideline:

  • Dr. Zhong-Tao Zhang (Beijing Friendship Hospital, Capital Medical University): zhangzht@ccmu.edu.cn
  • Dr. Ai-Min Hao (Beihang University): ham@buaa.edu.cn

References

  1. Zhang ZT, Yang YC. Promoting the colorectal surgery in virtue of new theories and techniques (in Chinese). Chin J Surg 2020;58:586–588. doi: doi.org/10.3760/cma.j.cn112139-20200521-00404.
  2. Benson AB, Venook AP, AI-Hawary MM, Arain MA, Chen YJ, Ciombor KK, et al. NCCN guidelines insights: rectal cancer, version 6. 2020. J Natl Compr Canc Netw 2020;18:806–815. doi: doi.org/10.6004/jnccn.2020.0032.
  3. Lu Y, Yu Q, Gao Y, Zhou Y, Liu G, Dong Q, et al. Identification of metastatic lymph nodes in MR imaging with faster region-based convolutional neural network. Cancer Res 2018;78:5135–5143. doi: doi.org/10.1158/0008-5472.CAN-18-0494.
  4. Wang D, Xu J, Zhang Z, Li S, Zhang X, Zhou Y, et al. Evaluation of rectal cancer circumferential resection margin using faster region-based convolutional neural network (R-CNN) in high-resolution magnetic resonance images. Dis Colon Rectum 2020;63:143–151. doi: doi.org/10.1097/DCR.0000000000001519.
  5. Stephen BE, Carolyn CC. The American Joint Committee on Cancer: the 7th edition of the AJCC cancer staging manual and the future of TNM. Ann Surg Oncol 2010;17:1471–1474. doi: doi.org/10.1245/s10434-010-0985-4.
  6. Horvat N, Rocha CCT, Oliveira BC, Petkovska I, Gollub MJ. MRI of rectal cancer: tumor staging, imaging techniques, and management. Radiographics 2019;39:367–387. doi: doi.org/10.1148/rg.2019180114.
  7. Furey E, Jhaveri KS. Magnetic resonance imaging in rectal cancer. Magn Reson Imaging Clin N Am 2014;22:165–190. doi: doi.org/10.1016/j.mric.2014.01.004.
  8. Brown G, Richards CJ, Bourne MW, Newcombe RG, Radcliffe AG, Dallimore NS, et al. Morphologic predictors of lymph node status in rectal cancer with use of high-spatial-resolution MR imaging with histopathologic comparison. Radiology 2003;227:371–377. doi: doi.org/10.1148/radiol.2272011747.
  9. MERCURY Study Group. Diagnostic accuracy of preoperative magnetic resonance imaging in predicting curative resection of rectal cancer: prospective observational study. BMJ 2006;333:779. doi: doi.org/10.1136/bmj.38937.646400.55.
  10. Smith NJ, Barbachano Y, Norman AR, Swift RI, Abulafi AM, Brown G. Prognostic significance of magnetic resonance imaging-detected extramural vascular invasion in rectal cancer. Br J Surg 2008;95:229–236. doi: doi.org/10.1002/bjs.5917.
  11. Ding L, Liu GW, Zhao BC, Zhou YP, Li S, Zhang ZD, et al. Artificial intelligence system of faster region-based convolutional neural network surpassing senior radiologists in evaluation of metastatic lymph nodes of rectal cancer. Chin Med J 2019;132:379–387. doi: doi.org/10.1097/CM9.0000000000000095.
  12. Gao Y, Zhang ZD, Li S, Guo YT, Wu QY, Liu SH, et al. Deep neural network-assisted computed tomography diagnosis of metastatic lymph nodes from gastric cancer. Chin Med J 2019;132:2804–2811. doi: doi.org/10.1097/CM9.0000000000000532.
  13. Liu SL, Li S, Guo YT, Zhou YP, Zhang ZD, Li S, et al. Establishment and application of an artificial intelligence diagnosis system for pancreatic cancer with a faster region-based convolutional neural network. Chin Med J 2019;132:2795–2803. doi: doi.org/10.1097/CM9.0000000000000544.
  14. Zhou YP, Li S, Zhang XX, Zhang ZD, Gao YX, Ding L, et al. High definition MRI rectal lymph node aided diagnostic system based on deep neural network (in Chinese). Chin J Surg 2019;57:108–113. doi: doi.org/10.3760/cma.j.issn.0529-5815.2019.02.007.
  15. Xu JH, Zhou XM, Ma JL, Liu SS, Zhang MS, Zheng XF, et al. Application of convolutional neural network to risk evaluation of positive circumferential resection margin of rectal cancer by magnetic resonance imaging (in Chinese). Chin J Gastrointest Surg 2020;23:572–577. doi: doi.org/10.3760/cma.j.cn.441530-20191023-00460.
  16. Wang SZ, Wang JG, Lu Y, Zhang YJ, Xin FJ, Liu SL, et al. Clinical application of convolutional neural network in pathological diagnosis of metastatic lymph nodes of gastric cancer (in Chinese). Chin J Surg 2019;57:934–938. doi: doi.org/10.3760/cma.j.issn.0529-5815.2019.12.012.
  17. Liu GW, Li S, Chen YJ. Integration of production-university-research based on artificial intelligence for technological innovation and transformation in gastrointestinal surgery (in Chinese). Chin J Gastrointest Surg 2020;23:557–561. doi: doi.org/10.3760/cma.j.cn.441530-20200305-00118.

How to Cite This Article

Gao Y, Lu Y, Li S, Dai Y, Feng B, Han FH, Han JG, He JJ, Li XX, Lin GL, Liu Q, Wang GY, Wang Q, Wang ZN, Wang Z, Wu AW, Wu B, Yang YC, Yao HW, Zhang W, Zhou JP, Hao AM, Zhang ZT; Colorectal Surgery Group of the Surgery Branch in the Chinese Medical Association; Beihang University State Key Laboratory of Virtual Reality Technology and Systems. Chinese guideline for the application of rectal cancer staging recognition systems based on artificial intelligence platforms (2021 edition). Chin Med J 2021;134:1261–1263. doi: doi.org/10.1097/CM9.0000000000001483

Copyright © 2021 The Chinese Medical Association

Was this helpful?

0 / 0