Yiran Li

Therapeutic exosomes loaded with SERPINA5 attenuated endometrial cancer cell migration via the integrin β1/FAK signaling pathway

Metastasis is still the major cause of endometrial cancer (EC)-related death. Because of their biological function and regenerative properties, exosomes have been applied to therapeutic regimens. SERPINA5 expression is downregulated in several tumors and linked to tumor cell migration and invasion. However, the expression and biological functions of SERPINA5 in EC remain unclear. The levels of SERPINA5 in plasma exosomes were determined with ELISAs. SERPINA5 expression in EC and its relationship with survival outcomes were analyzed using the TCGA database and clinical EC tissue samples. The effect of SERPINA5 overexpression or exosomal SERPINA5 on EC metastasis was examined by cell migration and invasion assays in vitro. Mechanistically, overexpression of SERPINA5 or high exosomal SERPINA5 levels mediated the regulation of the integrin β1/FAK signaling pathway in EC cell lines. The therapeutic effect of exosomal SERPINA5 was determined with xenograft models. This study revealed that the level of exosomal SERPINA5 was increased in the circulating plasma of EC patients. In addition, the expression of SERPINA5 was decreased in EC patients with distant metastasis, and low expression of SERPINA5 indicated worse survival. In addition, SERPINA5 was elevated in normal tissues adjacent to EC tumors. Moreover, overexpression of SERPINA5 inhibited metastatic potential of EC cell lines in vitro. Furthermore, SERPINA5 loaded on secreted exosomes reduced the metastatic ability of EC cells. Notably, overexpression of SERPINA5 or high exosomal SERPINA5 levels suppressed EC metastatic potential by suppressing integrin β1/FAK signaling pathway activation. Finally, exosomal SERPINA5 impeded tumor growth and metastasis in xenograft models. Our findings revealed that a low level of SERPINA5 expression indicated poor survival outcomes in EC and that exogenous SERPINA5 loading of exosomes may be a novel therapeutic strategy for metastatic EC.

Clinical-grade AI model for molecular subtyping of endometrial cancer: a multi-center cohort study in China

Abstract Accurate molecular subtyping is essential for guiding precision treatment and prognostic stratification in endometrial cancer (EC). However, current methods, based on Sanger sequencing and immunohistochemistry (IHC), are costly, time-intensive, and difficult to implement widely in routine clinical practice, particularly in resource-limited settings. To overcome these challenges, we developed a deep-learning pipeline that directly infers EC molecular subtypes from routine hematoxylin-and-eosin (H&E) whole-slide images (WSIs). The framework integrates super-resolution enhancement (SRResGAN), transformer-based lesion segmentation (MedSAM), and a ResNet-101 classifier for molecular subtype prediction, with an LSTM module for survival modeling. This retrospective study included 393 Chinese patients diagnosed between 2010 and 2018, all with ≥ 5 years of follow-up. Molecular subtypes—POLE mut , mismatch repair-deficient (MMRd), p53abnormal (p53abn), and no specific molecular profile (NSMP)—were confirmed by Sanger sequencing and immunohistochemistry. The model achieved high classification accuracies (92% for POLE mut and MMRd, 91% for p53abn, and 90% for NSMP), with a strong correlation between predicted and observed survival (R2 = 0.9692; MAE = 123 days). External validation on two independent cohorts ( N  = 35 and N  = 83) confirmed robust generalizability across institutions. This study represents the first large-scale, multicenter, AI-based digital pathology model for EC molecular classification in China. The proposed workflow provides an automated, interpretable, and cost-efficient alternative to conventional molecular testing, supporting precision oncology, fertility-preserving management, and clinical decision-making in real-world practice.