Dawei Zhang

Background: Colorectal cancer (CRC) is a leading cause of mortality in China, with metastasis significantly contributing to poor outcomes. Histopathological growth patterns (HGPs) in colorectal liver metastasis (CRLM) provide vital prognostic insights, yet the limited number of pathologists highlights the need for auxiliary diagnostic tools. Recent advancements in artificial intelligence (AI) have demonstrated potential in enhancing diagnostic precision, prompting the development of specialized AI models like COFFEE to improve the classification and management of HGPs in CRLM patients. Methods: This study developed a Transformer-based deep learning model, COFFEE, for the precise classification of colorectal cancer subtypes using whole-slide images (WSIs) from 431 patients diagnosed with colorectal cancer liver metastasis. The model was pretrained using DINO on 1442 WSIs from the TCGA-COAD cohort, utilizing a Vision Transformer (ViT) architecture to extract 384-dimensional feature vectors from 256 × 256 pixel patches. The proposed model integrates a Transformer-based Multiple Instance Learning (TransMIL) framework, which effectively aggregates spatial and morphological information through multi-head self-attention and Pyramid Position Encoding Generator (PPEG) modules. This design enables efficient handling of large instance sequences within WSIs, allowing for accurate binary and four-class classification. The model was validated on 972 WSIs from a recent dataset, demonstrating its robustness and clinical applicability. After testing the model with internal and prospective cohorts, a direct comparison between conventional and AI-assisted pathology assessment was also performed. Results: A total of 431 patients were included in three cohorts: training ( n = 297), testing ( n = 104), and prospective ( n = 30). Desmoplastic tumors were associated with longer overall survival (OS, 53.6 vs. 31.9 months, P = 0.002) and progression-free survival (PFS, 25.2 vs. 10.7 months, P < 0.001) compared to non-desmoplastic tumors. The COFFEE binary classification model achieved high predictive performance with area under the ROC curve (AUC) values of 0.961 in the training, 0.935 in the testing, and 1.000 in the prospective cohort. The four-class model also showed strong performance, with AUCs of 0.961 and 0.966 in the training and testing cohorts, and 0.985 in the prospective cohort. AI-assisted models helped junior pathologists achieve an accuracy of 94.7% (vs. 85.9%) and reduced diagnostic time by 36%, improving both accuracy and speed. Conclusion: This study developed an AI model for HGP classification in colorectal cancer liver metastasis, achieving high accuracy in both binary classification and four-class classification models. The model demonstrated potential for improving diagnostic precision and guiding post-surgery treatment strategies, with AI-assisted pathologists surpassing traditional methods in a prospective cohort.

Cancer-associated fibroblasts (CAFs) are a kind of stromal cells in the cholangiocarcinoma (CCA) microenvironment, playing crucial roles in cancer development. However, the potential mechanisms of the interaction between CCA cells and CAFs remain obscure. This work investigated the role of circ_0020256 in CAFs activation. We proved circ_0020256 was up-regulated in CCA. High circ_0020256 expression facilitated TGF-β1 secretion from CCA cells, which activated CAFs via the phosphorylation of Smad2/3. Mechanistically, circ_0020256 recruited EIF4A3 protein to stabilize KLF4 mRNA and upregulate its expression, then KLF4 bound to TGF-β1 promoter and induced its transcription in CCA cells. KLF4 overexpression abrogated the inhibition of circ_0020256 silencing in TGF-β1/Smad2/3-induced CAFs activation. Furthermore, CCA cell growth, migration, and epithelial-mesenchymal transition were favored by CAFs-secreted IL-6 via autophagy inhibition. We also found circ_0020256 accelerated CCA tumor growth in vivo. In conclusion, circ_0020256 promoted fibroblast activation to facilitate CCA progression via EIF4A3/KLF4 pathway, providing a potential intervention for CCA progression.

This study investigated the exosomal circular RNAs (CircRNAs) produced by tumor-associated macrophages and delivered into the microenvironment of cholangiocarcinoma cells in order to use them as molecular targets for clinical therapy. Tumor-associated M2 macrophages (TAMs) were induced from THP-1 cells and identified by flow cytometry. The TAM-secreted exosomes were isolated from conditioned medium and a CircRNA microarray assay was performed to identify CircRNAs that were uniquely expressed in the isolated exosomes. Circ_0020256 was especially identified based on having the highest differential expression level among all of the CircRNA candidates. In vitro and in vivo experiments were performed to assess the effects of TAMs, exosomes, and Circ_0020256 on the growth and migration of cholangiocarcinoma (CCA) cells. The induced TAMs promoted the proliferation, migration, and invasion of CCA cells and those effects were mediated by exosomes secreted by the TAMs. In CCA cells (RBE and HCCC-9810), Circ_0020256 significantly promoted cellular activity by interacting with its intra-cellular microRNA target, miR-432-5p. In contrast, overexpression of transcription factor E2F3 in CCA cells restored the CCA cellular activities that were inhibited by miR-432-5p. On the other hand, treatment with small interference RNA (siRNA) for Circ_0020256 inhibited CCA cell proliferation, migration, and invasion both in vitro and in vivo. In conclusion, Circ_0020256 in TAM-secreted exosomes promoted the proliferation, migration, and invasion of CCA cells, and that promotional activity was regulated via a Circ_0020256/miR-432-5p/E2F3 axis.

Glutamine metabolism of tumor cells plays a crucial role in maintaining cell homeostasis and reducing oxidative damage. Herein, a valid strategy of inhibiting glutamine metabolism is proposed to amplify the oxidative damage of photodynamic therapy (PDT) to tumor cells. Specifically, the authors develop a drug co‐delivery system (designated as CeV) based on chlorine e6 (Ce6) and V9302 via the self‐assembly technology. In spite of the strong hydrophobicity of therapeutic agents, the assembled CeV holds a favorable dispersibility in water and an improved cellular uptake capability. Under light irradiation, the internalized CeV is capable of generating abundant reactive oxygen species (ROS) for PDT. More importantly, CeV can reduce the uptake of glutamine through V9302‐mediated alanine‐serine‐cysteine transporter of type‐2 (ASCT2) inhibition, leading to a reduced glutathione (GSH) production and an amplified oxidative stress. As a result, CeV has a robust PDT efficacy on tumor inhibition by the blockade of glutamine transport. Notably, CeV exhibits a superiority on tumor suppression over the single treatment as well as the combined administration of Ce6 and V9302, which indicates the advantage of CeV for synergistic treatment. It may serve as a novel nanoplatform for developing a drug co‐delivery system to improve PDT efficiency by inhibiting cell metabolism.