新型海绵胶囊联合人工智能细胞DNA检测在早期食管癌筛查中的价值

doi:10.16150/j.1671-2870.2024.06.004

摘要/Abstract

摘要：

目的： 探讨新型海绵胶囊联合人工智能细胞DNA检测在早期食管癌筛查中的价值。方法： 2021年6月至2022年6月期间，向社会招募年龄>40岁，愿意行食管癌筛查的受试者。首先让受试者行新型海绵细胞胶囊检查，收集细胞标本，采用人工智能 (artificial intelligence，AI) 评测细胞学DNA指数（DNA index，DI），后均行内镜检查，评价细胞学DI值与内镜结果之间的关系。结果： 本研究共纳入1 369名受试者。经内镜确诊食管病变组25例，其中食管低级别上皮内瘤变15例，食管高级别上皮内瘤变1例，食管癌9例。食管正常组1 344例，食管正常组DI值为2.154±0.339，食管病变组DI值为2.832±0.479，食管病变组DI值明显高于食管正常组DI值（P<0.05）。Logistic回归分析显示，食管病变组与食管正常组的DI值比值比（odds ratio，OR）为0.04（95%CI为0.017~0.096）。海绵胶囊DI值诊断食管病变的最佳临界值为2.450，受试者工作特征（receiver operating characteristic，ROC）曲线下面积为0.914，特异度为83.71%，灵敏度为88.00%，准确率为83.78%。结论： 新型海绵胶囊收集细胞行DI检测可用于早期食管癌的筛查，该方法值得临床推广。

关键词: 新型海绵胶囊, 人工智能, 细胞DNA指数, 早期食管癌

Abstract:

Objective To explore the value of novel sponge capsules combined with AI-based cell DNA detectio in early esophageal cancer screening. Methods From June 2021 to June 2022, subjects aged >40 years who were willing to undergo esophageal cancer screening were recruited. Firstly, the subjects underwent a novel sponge cell capsule examination to collect cell specimens. Then the cytological DNA index (DI) was assessed using artificial intelligence (AI). Subsequently, all subjects underwent endoscopy. The relationship between cytologic DI values and endoscopic findings was evaluated. Results A total of 1 369 participants were enrolled. There were 25 cases of esophageal lesions confirmed by endoscopy, including 15 cases of low-grade intraepithelial neoplasia, 1 case of high-grade intraepithelial neoplasia, and 9 cases of esophageal cancer. There were 1 344 cases in the normal esophagus group. DI was 2.154 ± 0.339 in the normal group and 2.832 ± 0.479 in the lesion group. The DI value of the esophageal lesion group was significantly higher than that of the normal esophageal group, and the difference was statistically significant. Logistic regression analysis showed that the odds ratio (OR) of DI values between the esophageal lesion group and the normal esophagus group = 0.04 (95% CI: 0.017-0.096). The sponge capsules combined with DI value diagnosed esophageal lesions with an area under the ROC curve of 0.914, an optimal critical value of 2.450, a specificity of 83.71%, a sensitivity of 88.00%, and an accuracy of 83.78%. Conclusions The novel sponge capsules DI test can be used for screening of early esophageal cancer, and this method should be promoted in clinical practice.

Key words: Novel sponge capsule, Artificial intelligence, Cell DNA index, Early esophageal cancer

中图分类号:

R735.1
R445

徐梦迪, 高峰, 朱剑, 陈蕾, 秦雨萌, 黄越, 唐银萍, 沙杰. 新型海绵胶囊联合人工智能细胞DNA检测在早期食管癌筛查中的价值[J]. 诊断学理论与实践, 2024, 23(06): 580-586.

XU Mengdi, GAO Feng, ZHU Jian, CHEN Lei, QIN Yumeng, HUANG Yue, TANG Yinping, SHA Jie. Value of novel sponge capsules combined with AI-based cell DNA detection in early esophageal cancer screening[J]. Journal of Diagnostics Concepts & Practice, 2024, 23(06): 580-586.

图/表 3

参考文献 27

[1]	WATERS J K, REZNIK S I. Update on management of squamous cell esophageal cancer[J]. Curr Oncol Rep, 2022, 24(3):375-385. doi: 10.1007/s11912-021-01153-4 pmid: 35142974
[2]	YU Z, BAI X, ZHOU R, et al. Differences in the incidence and mortality of digestive cancer between Global Cancer Observatory 2020 and Global Burden of Disease 2019[J]. Int J Cancer, 2024, 154(4):615-625.
[3]	刘琳, 王钟怡, 黄楚殷, 等. 基于Web of Science数据库食管胃结合部腺癌研究的可视化及热点分析[J]. 中华消化外科杂志, 2023, 22(10):1243-1254.
	LIU L, WANG Z Y, HUANG C Y, et al. Visualization and hotspots analysis of research on adenocarcinoma of esophagogastric junction based on Web of Science[J]. Chin J Dig Surg, 2023, 22(10):1243-1254.
[4]	YANG H, HU B. Recent advances in early esophageal cancer: diagnosis and treatment based on endoscopy[J]. Postgrad Med, 2021, 133(6):665-673.
[5]	ROTH M J, LIU S F, DAWSEY S M, et al. Cytologic detection of esophageal squamous cell carcinoma and precursor lesions using balloon and sponge samplers in asymptomatic adults in Linxian, China[J]. Cancer, 1997, 80(11):2047-2059. doi: 10.1002/(sici)1097-0142(19971201)80:11<2047::aid-cncr3>3.0.co;2-u pmid: 9392326
[6]	LIU J, ZHAO H. Application of convolution neural network in medical image processing[J]. Technol Health Care, 2021, 29(2):407-417. doi: 10.3233/THC-202657 pmid: 33386836
[7]	NGUYEN H N, SEVIN B U, AVERETTE H E, et al. The role of DNA index as a prognostic factor in early cervical carcinoma[J]. Gynecol Oncol, 1993, 50(1): 54-59. pmid: 8349165
[8]	国家消化内镜专业质控中心, 国家消化系疾病临床医学研究中心(上海), 国家消化道早癌防治中心联盟, 等. 中国早期食管癌及癌前病变筛查专家共识意见(2019年,新乡)[J]. 中华消化内镜杂志, 2019, 36(11):793-801.
	National Digestive Endoscopy Professional Quality Control Center, National Clinical Research Center for Digestive Diseases (Shanghai), National Alliance of Digestive Early Cancer Prevention and Control Centers, et al. Expert consensus on early esophageal cancer and precancerous lesions screening in China (2019, Xinxiang)[J]. Chin J Dig Endosc, 2019, 36(11):793-801.
[9]	ZHOU M, WANG H, ZENG X, et al. Mortality, morbi-dity, and risk factors in China and its provinces, 1990-2017: a systematic analysis for the Global Burden of Disea-se Study 2017[J]. Lancet, 2019, 394(10204):1145-1158.
[10]	MORGAN E, SOERJOMATARAM I, RUMGAY H, et al. The global landscape of esophageal squamous cell carcinoma and esophageal adenocarcinoma incidence and mortality in 2020 and projections to 2040: new estimates from GLOBOCAN 2020[J]. Gastroenterology, 2022, 163(3):649-658.e2. doi: 10.1053/j.gastro.2022.05.054 pmid: 35671803
[11]	DIJKSTERHUIS W P M, KALFF M C, WAGNER A D, et al. Gender differences in treatment allocation and survival of advanced gastroesophageal cancer: a population-based study[J]. J Natl Cancer Inst, 2021, 113(11):1551-1560. doi: 10.1093/jnci/djab075 pmid: 33837791
[12]	LI R, SUN J, WANG T, et al. Comparison of secular trends in esophageal cancer mortality in China and Japan during 1990-2019: an age-period-cohort analysis[J]. Int J Environ Res Public Health, 2022, 19(16):10302.
[13]	CHAI T, SHEN Z, ZHANG P, et al. Comparison of high risk factors (hot food, hot beverage, alcohol, tobacco, and diet) of esophageal cancer: a protocol for a systematic review and meta-analysis[J]. Medicine (Baltimore), 2019, 98(17):e15176.
[14]	HUANG F L, YU S J. Esophageal cancer: risk factors, genetic association, and treatment[J]. Asian J Surg, 2018, 41(3):210-215.
[15]	LI B, LIU Y, PENG J, et al. Trends of esophageal cancer incidence and mortality and its influencing factors in China[J]. Risk Manag Healthc Policy, 2021, 14:4809-4821.
[16]	MMBAGA B T, MWASAMWAJA A, MUSHI G, et al. Missing and decayed teeth, oral hygiene and dental stai-ning in relation to esophageal cancer risk: ESCCAPE case-control study in Kilimanjaro, Tanzania[J]. Int J Cancer, 2021, 148(10):2416-2428.
[17]	陈克能. 管饲要素营养在食管癌全程治疗中的特殊地位[J]. 中华消化外科杂志, 2023, 22(1):61-64.
	CHEN K N. The special role of enteral nutrition in the comprehensive treatment of esophageal cancer[J]. Chin J Dig Surg, 2023, 22(1):61-64.
[18]	SU Z, ZOU G R, MAO Y P, et al. Prognostic impact of family history of cancer in Southern Chinese patients with esophageal squamous cell cancer[J]. J Cancer, 2019, 10(6):1349-1357. doi: 10.7150/jca.26511 pmid: 31031844
[19]	VISAGGI P, BARBERIO B, GHISA M, et al. Modern dia-gnosis of early esophageal cancer: from blood biomarkers to advanced endoscopy and artificial intelligence[J]. Cancers (Basel), 2021, 13(13):3162
[20]	DEISSOVÁ T, KALA Z, SLABÝ O, et al. Biomarkers for non-endoscopic examination of esophageal mucosa[J]. Vnitr Lek, 2020, 66(7):13-19. pmid: 33380129
[21]	GAO Y, XIN L, FENG Y D, et al. Feasibility and accuracy of artificial intelligence-assisted sponge cytology for community-based esophageal squamous cell carcinoma screening in China[J]. Am J Gastroenterol, 2021, 116(11):2207-2215. doi: 10.14309/ajg.0000000000001499 pmid: 34546186
[22]	RAI V, ABDO J, AGRAWAL D K. Biomarkers for early detection, prognosis, and therapeutics of esophageal cancers[J]. Int J Mol Sci, 2023, 24(4):3316.
[23]	YUAN Z, WANG X, GENG X, et al. Liquid biopsy for esophageal cancer: Is detection of circulating cell-free DNA as a biomarker feasible?[J] Cancer Commun (Lond), 2021, 41(1):3-15.
[24]	SHAHEEN N J, KOMANDURI S, MUTHUSAMY V R, et al. Acceptability and adequacy of a non-endoscopic cell collection device for diagnosis of barrett's esophagus: lessons learned[J]. Dig Dis Sci, 2022, 67(1):177-186.
[25]	FITZGERALD R C, DI PIETRO M, O'DONOVAN M, et al. Cytosponge-trefoil factor 3 versus usual care to identify Barrett's oesophagus in a primary care setting: a multicentre, pragmatic, randomised controlled trial[J]. Lancet, 2020, 396(10247):333-344. doi: S0140-6736(20)31099-0 pmid: 32738955
[26]	YAO B, FENG Y, ZHAO K, et al. Artificial intelligence assisted cytological detection for early esophageal squamous epithelial lesions by using low-grade squamous intraepithelial lesion as diagnostic threshold[J]. Cancer Med, 2023, 12(2):1228-1236.
[27]	MIDDLETON D R S, MMBAGA B T, O'DONOVAN M, et al. Minimally invasive esophageal sponge cytology sampling is feasible in a Tanzanian community setting[J]. Int J Cancer, 2021, 148(5):1208-1218. doi: 10.1002/ijc.33366 pmid: 33128785

Group	Lesion group （n = 25）	Normal group （n = 75）	P
Sex			0.640
Female	9	33
Male	16	42
Age	66.16±5.77	66.35±6.06	0.891
Registered permanent residence			1.000
City	22	65
Village	3	10
Smoking			1.000
Yes	2	5
No	23	70
Tipple			1.000
Yes	4	11
No	21	64
Hot diet			1.000
Yes	10	30
No	15	45
Anodontia			0.819
Yes	13	36
No	12	39
Number of missing teeth			0.954
0	12	39
1-4	5	14
>5	8	22
Family history			0.732
Yes	4	9
No	21	66