1
|
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; 63:102202. [PMID: 37680944 PMCID: PMC10480520 DOI: 10.1016/j.eclinm.2023.102202] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/20/2023] [Revised: 07/31/2023] [Accepted: 08/21/2023] [Indexed: 09/09/2023] Open
Abstract
Background MRI is the routine examination to surveil the recurrence of nasopharyngeal carcinoma, but it has relatively lower sensitivity than PET/CT. We aimed to find if artificial intelligence (AI) could be competent pre-inspector for MRI radiologists and whether AI-aided MRI could perform better or even equal to PET/CT. Methods This multicenter study enrolled 6916 patients from five hospitals between September 2009 and October 2020. A 2.5D convolutional neural network diagnostic model and a nnU-Net contouring model were developed in the training and test cohorts and used to independently predict and visualize the recurrence of patients in the internal and external validation cohorts. We evaluated the area under the ROC curve (AUC) of AI and compared AI with MRI and PET/CT in sensitivity and specificity using the McNemar test. The prospective cohort was randomized into the AI and non-AI groups, and their sensitivity and specificity were compared using the Chi-square test. Findings The AI model achieved AUCs of 0.92 and 0.88 in the internal and external validation cohorts, corresponding to the sensitivity of 79.5% and 74.3% and specificity of 91.0% and 92.8%. It had comparable sensitivity to MRI (e.g., 74.3% vs. 74.7%, P = 0.89) but lower sensitivity than PET/CT (77.9% vs. 92.0%, P < 0.0001) at the same individual-specificities. The AI model achieved moderate precision with a median dice similarity coefficient of 0.67. AI-aided MRI improved specificity (92.5% vs. 85.0%, P = 0.034), equaled PET/CT in the internal validation subcohort, and increased sensitivity (81.9% vs. 70.8%, P = 0.021) in the external validation subcohort. In the prospective cohort of 1248 patients, the AI group had higher sensitivity than the non-AI group (78.6% vs. 67.3%, P = 0.23), albeit nonsignificant. In future randomized controlled trials, a sample size of 3943 patients in each arm would be required to demonstrate the statistically significant difference. Interpretation The AI model equaled MRI by expert radiologists, and AI-aided MRI by expert radiologists equaled PET/CT. A larger randomized controlled trial is warranted to demonstrate the AI's benefit sufficiently. Funding The Sun Yat-sen University Clinical Research 5010 Program (2015020), Guangdong Basic and Applied Basic Research Foundation (2022A1515110356), and Guangzhou Science and Technology Program (2023A04J1788).
Collapse
Affiliation(s)
- Pu-Yun OuYang
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Yun He
- Department of Radiology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Jian-Gui Guo
- Department of Radiation Oncology, The First People's Hospital of Foshan, Foshan, China
| | - Jia-Ni Liu
- Department of Head and Neck Oncology, The Cancer Center of the Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, China
| | - Zhi-Long Wang
- Department of Radiology, Zhongshan City People's Hospital, Zhongshan, China
| | | | | | - Shan-Shan Yang
- Department of Radiation Oncology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, Shandong, China
| | - Xu Zhang
- Department of Nuclear Medicine, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Wei Fan
- Department of Nuclear Medicine, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Yi-Shan Wu
- Department of Nasopharyngeal Carcinoma, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Zhi-Qiao Liu
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Bao-Yu Zhang
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Ya-Nan Zhao
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Ming-Yong Gao
- Department of Radiology, The First People's Hospital of Foshan, Foshan, China
| | - Wei-Jun Zhang
- Department of Radiation Oncology, Affiliated Cancer Hospital & Institute of Guangzhou Medical University, Guangzhou, China
| | - Chuan-Miao Xie
- Department of Radiology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Fang-Yun Xie
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| |
Collapse
|
2
|
Li Z, Li Y, Li N, Shen L. Positron emission tomography/computed tomography outperforms MRI in the diagnosis of local recurrence and residue of nasopharyngeal carcinoma: An update evidence from 44 studies. Cancer Med 2018; 8:67-79. [PMID: 30578604 PMCID: PMC6346220 DOI: 10.1002/cam4.1882] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/14/2018] [Revised: 10/28/2018] [Accepted: 10/29/2018] [Indexed: 12/14/2022] Open
Abstract
Studies on nasopharyngeal carcinoma (NPC) in five electronic databases were systematically searched online from the inception to June 5, 2018. Quality of the included studies was assessed using the updated Quality Assessment of Diagnostic Accuracy Studies 2. Data of sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, diagnostic odds ratio, and the 95% confidence intervals were pooled using a bivariate random‐effect model. Forty‐four studies with 61 groups of data and totally 3369 patients were included in the qualitative and quantitative synthesis analysis. The overall estimated sensitivity and specificity of positron emission tomography/computed tomography/magnetic resonance imaging (PET‐CT/MRI) for local recurrent/residual NPC were 0.90 and 0.85, respectively. The pooled area under the curve of (AUC) of PET‐CT/MRI in the summary receiver operator characteristic curve was 0.94. Subgroup analysis showed MRI vs PET‐CT had lower sensitivity (0.83 vs 0.92) and specificity (0.78 vs 0.89). The AUCs of MRI and PET‐CT were 0.87 and 0.96, respectively. No‐cross of 95% CI was found in MRI vs PET/CT (0.87‐0.90 vs 0.94‐0.98). Meta‐regression showed PET/CT vs MRI was a potential source of heterogeneity. PET/CT and MRI both showed quite high overall ability in diagnosing local recurrent/residual NPC, but the subgroup analysis indicated PET‐CT was superior over MRI in diagnosis of local recurrence and residue of NPC after radiotherapy. The examination methods affected the heterogeneity within studies.
Collapse
Affiliation(s)
- Zhanzhan Li
- Department of Oncology, Xiangya Hospital, Central South University, Changsha, Hunan Province, China
| | - Yanyan Li
- Xiangya Hospital, Central South University, Changsha, Hunan Province, China
| | - Na Li
- Department of Oncology, Xiangya Hospital, Central South University, Changsha, Hunan Province, China
| | - Liangfang Shen
- Department of Oncology, Xiangya Hospital, Central South University, Changsha, Hunan Province, China
| |
Collapse
|
3
|
Hines JP, Howard BE, Hoxworth JM, Lal D. Positive and Negative Predictive Value of PET-CT in Skull Base Lesions: Case Series and Systematic Literature Review. J Neurol Surg Rep 2016; 77:e39-45. [PMID: 26937333 PMCID: PMC4773825 DOI: 10.1055/s-0035-1570387] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/20/2022] Open
Abstract
Objectives To study positive (PPV) and negative predictive value (NPV) of positron emission tomography with computed tomography (PET-CT) scans in determining malignancy in skull base lesions and perform a systematic literature review for optimal PET-CT interpretation. Design Retrospective case series and systematic literature review of the current English literature. Setting Tertiary referral academic medical center. Participants All patients with skull base lesions that underwent PET-CT and tissue biopsy from 2010 to 2013. Main Outcome Measures PPV and NPV of radiologist's report and standardized uptake value (SUV) cutoff of 2.5 and 3, biopsy with pathologic interpretation, clinical follow-up. Results A total of 31 PET-CT scans of 16 patients were studied; 10 PET-CT were performed upfront for diagnostic purposes and 21 were post-treatment surveillance scans. The PPV of radiologist's interpretation, SUV cutoff of 2.5, and SUV cutoff of 3.0 was 80%, 60%, and 68.4%, with a NPV of 100%, 83.3%, and 75%, respectively. Literature search yielded 500 abstracts; 7 studies met inclusion criteria for detailed review. No consensus or guidelines for optimal SUV cutoff value was found. Conclusions PET-CT based on SUV cutoff criteria alone has high NPV but low PPV in determining malignancy in skull base lesions. Interpretation by a radiologist experienced in nuclear medicine and neuroradiology, synthesizing clinical, SUV, and radiologic data are of superior value.
Collapse
Affiliation(s)
- John Peyton Hines
- Department of Otolaryngology-Head and Neck Surgery, Mayo Clinic, Phoenix, Arizona, United States
| | - Brittany E Howard
- Department of Otolaryngology-Head and Neck Surgery, Mayo Clinic, Phoenix, Arizona, United States
| | - Joseph M Hoxworth
- Department of Radiology, Mayo Clinic, Phoenix, Arizona, United States
| | - Devyani Lal
- Department of Otolaryngology-Head and Neck Surgery, Mayo Clinic, Phoenix, Arizona, United States
| |
Collapse
|
5
|
Zhou H, Shen G, Zhang W, Cai H, Zhou Y, Li L. 18F-FDG PET/CT for the Diagnosis of Residual or Recurrent Nasopharyngeal Carcinoma After Radiotherapy: A Metaanalysis. J Nucl Med 2015; 57:342-7. [PMID: 26541775 DOI: 10.2967/jnumed.115.165407] [Citation(s) in RCA: 17] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/11/2015] [Accepted: 10/21/2015] [Indexed: 02/05/2023] Open
Abstract
UNLABELLED The aim of this work was to assess the overall value of (18)F-FDG PET/CT in the diagnosis of residual or recurrent nasopharyngeal carcinoma using a metaanalysis. METHODS The literature published between January 1990 and September 2014 was searched in the PubMed, EMBASE, Cochrane Library, EBSCO, VIP, CNKI, and Wanfang databases to identify eligible studies on PET/CT of residual or recurrent lesions. The methodologic quality of the included studies was evaluated using the "quality assessment for studies of diagnostic accuracy" tool. Summary sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, diagnostic odds ratio, and receiver-operating characteristic curve were obtained using Meta-DiSc freeware. Subgroups were also analyzed. RESULTS A total of 23 studies, involving 1,253 subjects, were included in the metaanalysis. Pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and diagnostic odds ratio, with 95% confidence intervals in parentheses, for (18)F-FDG PET or PET/CT were 0.93 (0.91-0.95), 0.87 (0.84-0.89), 5.52 (3.96-7.71), 0.12 (0.09-0.15), and 55.31 (34.94-87.57), respectively. The area under the receiver-operating characteristic curve and Q* index estimate of PET/CT were 0.9473 and 0.8869, respectively. There was no significant difference between the area under the curve of PET and PET/CT (P > 0.05). CONCLUSION Our study has confirmed that (18)F-FDG PET/CT has high sensitivity and specificity but significant heterogeneity in the diagnosis of residual or recurrent nasopharyngeal carcinoma.
Collapse
Affiliation(s)
- Huijun Zhou
- Department of Nuclear Medicine, West China Hospital of Sichuan University, Chengdu, Sichuan, China
| | - Guohua Shen
- Department of Nuclear Medicine, West China Hospital of Sichuan University, Chengdu, Sichuan, China
| | - Wenjie Zhang
- Department of Nuclear Medicine, West China Hospital of Sichuan University, Chengdu, Sichuan, China
| | - Huawei Cai
- Department of Nuclear Medicine, West China Hospital of Sichuan University, Chengdu, Sichuan, China
| | - Yue Zhou
- Department of Nuclear Medicine, West China Hospital of Sichuan University, Chengdu, Sichuan, China
| | - Lin Li
- Department of Nuclear Medicine, West China Hospital of Sichuan University, Chengdu, Sichuan, China
| |
Collapse
|
6
|
Liang FY, Sun W, Han P, Lu X, Lian YN, Huang XM. Detecting plasma Epstein-Barr virus DNA to diagnose postradiation nasopharyngeal skull base lesions in nasopharyngeal carcinoma patients: a prospective study. Chin J Cancer 2012; 31:142-9. [PMID: 22237037 PMCID: PMC3777480 DOI: 10.5732/cjc.011.10279] [Citation(s) in RCA: 16] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
Abstract
The diagnosis of postradiation nasopharyngeal skull base lesions in petients with nasopharyngeal carcinoma (NPC) is still a tough problem in clinical practice. An early and accurate diagnosis is important for subsequent management. We prospectively evaluated the diagnostic value of plasma Epstein-Barr virus(EBV) DNA in detecting postradiation nasopharyngeal skull base lesions in NPC patients. From July 2006 to September 2010, 90 patients with postradiation NPC (34 women and 56 men; median age: 42 years) met the selection criteria and were recruited in this study. All postradiation nasopharyngeal skull base lesions were found in the latest magnetic resonance imaging (MRI) examinations before endoscopic surgery, and the nasopharyngeal cavity was normal under flexible nasopharyngoscopy. Plasma EBV DNA detection was performed within 2 weeks before endoscopic surgery. A total of 90 endoscopic operations were successfully performed without any postoperative complications. Recurrences confirmed by postoperative pathology were found in 30 patients. The specificity, positive and negative predictive values of plasma EBV DNA detection were better than those of MRI. In addition, combining plasma EBV DNA detection with MRI improved the specificity and positive predictive values of MRI. Plasma EBV DNA detection followed by MRI would help to diagnose recurrence whereas MRI was unable. These results indicate that plasma EBV DNA is an effective and feasible biomarker for detecting postradiation nasopharyngeal skull base lesions in NPC patients.
Collapse
Affiliation(s)
- Fa-Ya Liang
- Department of Head and Neck Surgery, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, Guangdong 510120, P. R. China
| | | | | | | | | | | |
Collapse
|