Ling Qiu

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

Abstract Background The role of artificial intelligence (AI) in enhancing the accuracy of lymphovascular space invasion (LVSI) detection in cervical cancer remains debated. Objective This meta-analysis aimed to evaluate the diagnostic accuracy of imaging-based AI for predicting LVSI in cervical cancer. Methods 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. Results 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). Conclusions 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.

Characterization of the Genomic Landscape in Cervical Cancer by Next Generation Sequencing

Cervical cancer is the fourth leading cause of cancer-related deaths in women worldwide. Although many sequencing studies have been carried out, the genetic characteristics of cervical cancer remain to be fully elucidated, especially in the Asian population. Herein, we investigated the genetic landscape of Chinese cervical cancer patients using a validated multigene next generation sequencing (NGS) panel. We analyzed 64 samples, consisting of 32 tumors and 32 blood samples from 32 Chinese cervical cancer patients by performing multigene NGS with a panel targeting 571 cancer-related genes. A total of 810 somatic variants, 2730 germline mutations and 701 copy number variations (CNVs) were identified. FAT1, HLA-B, PIK3CA, MTOR, KMT2D and ZFHX3 were the most mutated genes. Further, PIK3CA, BRCA1, BRCA2, ATM and TP53 gene loci had a higher frequency of CNVs. Moreover, the role of PIK3CA in cervical cancer was further highlighted by comparing with the ONCOKB database, especially for E545K and E542K, which were reported to confer radioresistance to cervical cancer. Notably, analysis of potential therapeutic targets suggested that cervical cancer patients could benefit from PARP inhibitors. This multigene NGS analysis revealed several novel genetic alterations in Chinese patients with cervical cancer and highlighted the role of PIK3CA in cervical cancer. Overall, this study showed that genetic variations not only affect the genetic susceptibility of cervical cancer, but also influence the resistance of cervical cancer to radiotherapy, but further studies involving a larger patient population should be undertaken to validate these findings.