Construction of CXCR4 Receptor-Targeted CuFeSe2 Nano Theranostic Platform and Its Application in MR/CT Dual Model Imaging and Photothermal Therapy.

Introduction: Targeting, imaging, and treating tumors represent major clinical challenges. Developing effective theranostic agents to address these issues is an urgent need. Methods: We introduce an "all-in-one" tumor-targeted theranostic platform using CuFeSe2-based composite nanoparticles (CuFeSe2@PA) for magnetic resonance (MR) and computed tomography (CT) dual model imaging-guided hyperthermia tumor ablation. Plerixafor (AMD3100) is bonded to the surface of CuFeSe2 as a targeting unit. Due to the robust interaction between AMD3100 and the overexpressed Chemokine CXC type receptor 4 (CXCR4) on the membrane of 4T1 cancer cells, CuFeSe2@PA specifically recognizes 4T1 cancer cells, enriching the tumor region. Results: CuFeSe2@PA serves as a contrast agent for T2-weighted MR imaging (relaxivity value of 1.61 mM-1 s-1) and CT imaging. Moreover, it effectively suppresses tumor growth through photothermal therapy (PTT) owing to its high photothermal conversion capability and stability, with minimized side effects demonstrated both in vitro and in vivo. Discussion: CuFeSe2@PA nanoparticles show potential as dual-mode imaging contrast agents for MR and CT and provide an effective means of tumor treatment through photothermal therapy. The surface modification with Plerixafor enhances the targeting ability of the nanoparticles, performing more significant efficacy and biocompatibility in the 4T1 cancer cell model. The study demonstrates that CuFeSe2@PA is a promising multifunctional theranostic platform with clinical application potential.

Prediction of angiogenesis in extrahepatic cholangiocarcinoma using MRI-based machine learning.

Purpose: Reliable noninvasive method to preoperative prediction of extrahepatic cholangiocarcinoma (eCCA) angiogenesis are needed. This study aims to develop and validate machine learning models based on magnetic resonance imaging (MRI) for predicting vascular endothelial growth factor (VEGF) expression and the microvessel density (MVD) of eCCA. Materials and methods: In this retrospective study from August 2011 to May 2020, eCCA patients with pathological confirmation were selected. Features were extracted from T1-weighted, T2-weighted, and diffusion-weighted images using the MaZda software. After reliability testing and feature screening, retained features were used to establish classification models for predicting VEGF expression and regression models for predicting MVD. The performance of both models was evaluated respectively using area under the curve (AUC) and Adjusted R-Squared (Adjusted R2). Results: The machine learning models were developed in 100 patients. A total of 900 features were extracted and 77 features with intraclass correlation coefficient (ICC) < 0.75 were eliminated. Among all the combinations of data preprocessing methods and classification algorithms, Z-score standardization + logistic regression exhibited excellent ability both in the training cohort (average AUC = 0.912) and the testing cohort (average AUC = 0.884). For regression model, Z-score standardization + stochastic gradient descent-based linear regression performed well in the training cohort (average Adjusted R2 = 0.975), and was also better than the mean model in the test cohort (average Adjusted R2 = 0.781). Conclusion: Two machine learning models based on MRI can accurately predict VEGF expression and the MVD of eCCA respectively.