Imaging-Based AI for Predicting Lymphovascular Space Invasion in Cervical Cancer: Systematic Review and Meta-Analysis

• Published in: Journal of medical Internet research Vol. 27; no. 2; p. e71091
• Main Authors: She, Lizhen, Li, Yunfeng, Wang, Hongyong, Zhang, Jun, Zhao, Yuechen, Cui, Jie, Qiu, Ling
• Format: Journal Article
• Language: English
• Published: Canada Journal of Medical Internet Research 16.06.2025; Gunther Eysenbach MD MPH, Associate Professor; JMIR Publications
• Subjects: Accuracy; Algorithms; Artificial Intelligence; Bias; Cancer; Cancer invasiveness; Cancer Prognosis Models and Machine Learning; Cancer therapies; Case reports; Cervical cancer; Clinical Information and Decision Making; Clinical medicine; Complications and side effects; Data mining; Deep learning; Diagnostic tests; Digital Health Reviews; Female; Humans; Imaging Informatics; Innovations in Cancer Diagnostic and Decision Support; Lymphatic Metastasis - diagnostic imaging; Lymphatic system; Machine learning; Magnetic resonance imaging; Medical Imaging; Medical prognosis; Meta-analysis; Metastasis; Methods; Neoplasm Invasiveness - diagnostic imaging; Obstetrics, Gynecology, and Reproductive Medicine; Oncology, Experimental; Positron emission tomography; Prognosis; Review; Risk factors; Statistical analysis; Systematic review; Tomography; Tumors; Uterine Cervical Neoplasms - diagnostic imaging; Uterine Cervical Neoplasms - pathology; China; meta-analysis; diagnostic performance; lymphovascular space invasion; uterine cervical neoplasms; artificial intelligence
• ISSN: 1438-8871; 1439-4456; 1438-8871
• DOI: 10.2196/71091

The role of artificial intelligence (AI) in enhancing the accuracy of lymphovascular space invasion (LVSI) detection in cervical cancer remains debated. This meta-analysis aimed to evaluate the diagnostic accuracy of imaging-based AI for predicting LVSI in cervical cancer. We conducted a comprehensive literature search across multiple databases, including PubMed, Embase, and Web of Science, identifying studies published up to November 9, 2024. Studies were included if they evaluated the diagnostic performance of imaging-based AI models in detecting LVSI in cervical cancer. We used a bivariate random-effects model to calculate pooled sensitivity and specificity with corresponding 95% confidence intervals. Study heterogeneity was assessed using the I2 statistic. Of 403 studies identified, 16 studies (2514 patients) were included. For the interval validation set, the pooled sensitivity, specificity, and area under the curve (AUC) for detecting LVSI were 0.84 (95% CI 0.79-0.87), 0.78 (95% CI 0.75-0.81), and 0.87 (95% CI 0.84-0.90). For the external validation set, the pooled sensitivity, specificity, and AUC for detecting LVSI were 0.79 (95% CI 0.70-0.86), 0.76 (95% CI 0.67-0.83), and 0.84 (95% CI 0.81-0.87). Using the likelihood ratio test for subgroup analysis, deep learning demonstrated significantly higher sensitivity compared to machine learning (P=.01). Moreover, AI models based on positron emission tomography/computed tomography exhibited superior sensitivity relative to those based on magnetic resonance imaging (P=.01). Imaging-based AI, particularly deep learning algorithms, demonstrates promising diagnostic performance in predicting LVSI in cervical cancer. However, the limited external validation datasets and the retrospective nature of the research may introduce potential biases. These findings underscore AI's potential as an auxiliary diagnostic tool, necessitating further large-scale prospective validation.