Development and Validation of a Deep Learning Model to Predict Distant Metastases in Nasopharyngeal Carcinoma Using Whole Slide Imaging and MRI

Development and Multicenter Validation of a Deep Learning Model Based on Whole Slide Imaging and Magnetic Resonance Imaging of the Nasopharynx and Lymph Nodes to Predict Distant Metastases At Diagnosis in Nasopharyngeal Carcinoma

An AI model was developed to predict the likelihood of distant metastasis in patients with nasopharyngeal cancer based on pathology slides and MRI scans of the primary tumor. The model was validated using data from multiple centers. It was then applied to patients with advanced stages who were recommended to undergo PET/CT scans based on the NCCN or CSCO guidelines. This AI model can accurately screen patients with high risk of distant metastasis at the time of initial diagnosis to receive PET/CT, avoid excessive examination of patients with low risk of distant metastasis, save medical resources and reduce the economic burden on patients.

Study Overview

• Status: Recruiting
• Conditions: Distant Metastasis; Nasopharyngeal Cancinoma (NPC)

Detailed Description

An AI model was constructed based on HE-stained pathological sections of the primary lesion and MRI of the nasopharynx and neck to predict the probability of distant metastasis at the first visit, and the AI model was fully verified by multicenter data; the AI model was applied to T3-4 or N2-3 patients who were recommended to undergo PET/CT examination according to the NCCN and CSCO guidelines, and the threshold of the AI model when the negative predictive value for predicting M0 was not less than 95% was determined, providing theoretical support for patients predicted by AI to be exempted from PET/CT examination.

• Study Type: Observational
• Enrollment (Estimated): 500

Contacts and Locations

• Study Contact: Name: Pu-Yun OuYang; Phone Number: +8618565382769; Email: ouyangpy@sysucc.org.cn

Study Locations

• China
  • Guangdong
    • Guangzhou, Guangdong, China, 510060
      • Recruiting
      • Sun Yat-Sen University Cancer Center
      • Contact: Pu-Yun OuYang; Phone Number: +86 18565382769; Email: ouyangpy@sysucc.org.cn
      • Contact: Pu-Yun OuYang; Email: ouyangpy@sysucc.org.cn
    • Guangzhou, Guangdong, China, 510060
      • Not yet recruiting
      • Department of Radiation Oncology, Sun Yat-sen University Cancer Center
      • Contact: Pu-Yun OuYang; Phone Number: 86+020-87342925; Email: ouyangpy@sysucc.org.cn
      • Contact: Pu-Yun OuYang

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Patients with pathologically confirmed nasopharyngeal carcinoma

Description

Inclusion Criteria:

A. The primary lesion was pathologically confirmed as nasopharyngeal carcinoma (WHO classification is I, II and III); B. The stage was T3-4 or N2-3, and the nasopharynx + neck MRI plain scan and enhanced scan were performed to confirm the nasopharyngeal and cervical lymph node lesions, and PET/CT or conventional examination (chest CT plain scan + enhanced scan, upper abdominal CT or MRI plain scan + enhanced scan or abdominal color Doppler ultrasound or ultrasound angiography, and whole body bone imaging) was performed to screen for distant metastases.

Exclusion Criteria:

Previous history of other malignant tumors (such as other head and neck squamous cell carcinomas, thyroid cancer, breast cancer, esophageal cancer, etc.).

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort
Prospective Validation Cohort; Prospective patient enrollment to validate the diagnostic efficacy of the AI model

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Negative predictive value	NPV measures the proportion of predicted negative cases that are actually negative. It tells us how reliable the model is when it predicts a negative outcome.	through study completion, an average of 2 year

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Sensitivity, specificity, and positive predictive value	Sensitivity, specificity, and positive predictive value of AI in predicting distant metastasis at the threshold corresponding to a negative predictive value of 95%.	through study completion, an average of 2 year

Collaborators and Investigators

• Sponsor: Sun Yat-sen University
• Collaborators: First Affiliated Hospital, Sun Yat-Sen University; Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University; Fifth Affiliated Hospital, Sun Yat-Sen University; Affiliated Cancer Hospital & Institute of Guangzhou Medical University; Qingyuan County People's Hospital; The Affiliated Panyu Center Hospital of Guangzhou Medical University

Publications and helpful links

General Publications

• OuYang PY, He Y, Guo JG, Liu JN, Wang ZL, Li A, Li J, Yang SS, Zhang X, Fan W, Wu YS, Liu ZQ, Zhang BY, Zhao YN, Gao MY, Zhang WJ, Xie CM, Xie FY. Artificial intelligence aided precise detection of local recurrence on MRI for nasopharyngeal carcinoma: a multicenter cohort study. EClinicalMedicine. 2023 Aug 30;63:102202. doi: 10.1016/j.eclinm.2023.102202. eCollection 2023 Sep.
• Zhong L, Dong D, Fang X, Zhang F, Zhang N, Zhang L, Fang M, Jiang W, Liang S, Li C, Liu Y, Zhao X, Cao R, Shan H, Hu Z, Ma J, Tang L, Tian J. A deep learning-based radiomic nomogram for prognosis and treatment decision in advanced nasopharyngeal carcinoma: A multicentre study. EBioMedicine. 2021 Aug;70:103522. doi: 10.1016/j.ebiom.2021.103522. Epub 2021 Aug 11.
• Qiang M, Li C, Sun Y, Sun Y, Ke L, Xie C, Zhang T, Zou Y, Qiu W, Gao M, Li Y, Li X, Zhan Z, Liu K, Chen X, Liang C, Chen Q, Mai H, Xie G, Guo X, Lv X. A Prognostic Predictive System Based on Deep Learning for Locoregionally Advanced Nasopharyngeal Carcinoma. J Natl Cancer Inst. 2021 May 4;113(5):606-615. doi: 10.1093/jnci/djaa149.
• Lin L, Dou Q, Jin YM, Zhou GQ, Tang YQ, Chen WL, Su BA, Liu F, Tao CJ, Jiang N, Li JY, Tang LL, Xie CM, Huang SM, Ma J, Heng PA, Wee JTS, Chua MLK, Chen H, Sun Y. Deep Learning for Automated Contouring of Primary Tumor Volumes by MRI for Nasopharyngeal Carcinoma. Radiology. 2019 Jun;291(3):677-686. doi: 10.1148/radiol.2019182012. Epub 2019 Mar 26.
• OuYang PY, Zhang BY, Guo JG, Liu JN, Li J, Peng QH, Yang SS, He Y, Liu ZQ, Zhao YN, Li A, Wu YS, Hu XF, Chen C, Han F, You KY, Xie FY. Deep learning-based precise prediction and early detection of radiation-induced temporal lobe injury for nasopharyngeal carcinoma. EClinicalMedicine. 2023 Apr 4;58:101930. doi: 10.1016/j.eclinm.2023.101930. eCollection 2023 Apr.
• Sun XS, Liu SL, Luo MJ, Li XY, Chen QY, Guo SS, Wen YF, Liu LT, Xie HJ, Tang QN, Liang YJ, Yan JJ, Lin DF, Bi MM, Liu Y, Liang YF, Ma J, Tang LQ, Mai HQ. The Association Between the Development of Radiation Therapy, Image Technology, and Chemotherapy, and the Survival of Patients With Nasopharyngeal Carcinoma: A Cohort Study From 1990 to 2012. Int J Radiat Oncol Biol Phys. 2019 Nov 1;105(3):581-590. doi: 10.1016/j.ijrobp.2019.06.2549. Epub 2019 Jul 15.
• Tang LQ, Chen QY, Fan W, Liu H, Zhang L, Guo L, Luo DH, Huang PY, Zhang X, Lin XP, Mo YX, Liu LZ, Mo HY, Li J, Zou RH, Cao Y, Xiang YQ, Qiu F, Sun R, Chen MY, Hua YJ, Lv X, Wang L, Zhao C, Guo X, Cao KJ, Qian CN, Zeng MS, Mai HQ. Prospective study of tailoring whole-body dual-modality [18F]fluorodeoxyglucose positron emission tomography/computed tomography with plasma Epstein-Barr virus DNA for detecting distant metastasis in endemic nasopharyngeal carcinoma at initial staging. J Clin Oncol. 2013 Aug 10;31(23):2861-9. doi: 10.1200/JCO.2012.46.0816. Epub 2013 Jul 15. Erratum In: J Clin Oncol. 2016 Feb 10;34(5):519. doi: 10.1200/jco.2015.66.3427.
• Xiao BB, Lin DF, Sun XS, Zhang X, Guo SS, Liu LT, Luo DH, Sun R, Wen YF, Li JB, Lv XF, Han LJ, Yuan L, Liu SL, Tang QN, Liang YJ, Li XY, Guo L, Chen QY, Fan W, Mai HQ, Tang LQ. Nomogram for the prediction of primary distant metastasis of nasopharyngeal carcinoma to guide individualized application of FDG PET/CT. Eur J Nucl Med Mol Imaging. 2021 Jul;48(8):2586-2598. doi: 10.1007/s00259-020-05128-8. Epub 2021 Jan 8.

Study record dates

Study Major Dates

• Study Start (Estimated): February 15, 2025
• Primary Completion (Estimated): December 31, 2026
• Study Completion (Estimated): December 31, 2026

Study Registration Dates

• First Submitted: February 14, 2025
• First Submitted That Met QC Criteria: February 14, 2025
• First Posted (Actual): March 25, 2025

Study Record Updates

• Last Update Posted (Actual): March 25, 2025
• Last Update Submitted That Met QC Criteria: February 21, 2025
• Last Verified: February 1, 2025

More Information

Terms related to this study

• Keywords: MRI; PET/CT; deep learning model; Nasopharyngeal Cancinoma (NPC); Distant Metastasis; whole slide imaging
• Additional Relevant MeSH Terms: Stomatognathic Diseases; Pathologic Processes; Neoplasms by Site; Neoplasms; Neoplasms by Histologic Type; Head and Neck Neoplasms; Neoplasms, Glandular and Epithelial; Neoplastic Processes; Carcinoma; Otorhinolaryngologic Diseases; Pharyngeal Neoplasms; Otorhinolaryngologic Neoplasms; Nasopharyngeal Diseases; Pharyngeal Diseases; Nasopharyngeal Neoplasms; Nasopharyngeal Carcinoma; Neoplasm Metastasis
• Other Study ID Numbers: B2025-062-01

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Individual participant data (IPD) might not be shared due to concerns about patient privacy, ethical considerations, or institutional policies. Restrictions may also arise from data protection regulations, confidentiality agreements, or the potential risk of re-identification. Additionally, if the data includes sensitive medical information, sharing may require special approvals or de-identification processes that are not feasible.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No