BMC Cancer最新文献

Background: To investigate the potential of apparent diffusion coefficient (ADC) map-based deep learning and dose distribution-based dosiomics in predicting radiation-induced temporal lobe injury (RTLI) in nasopharyngeal carcinoma (NPC).

Methods: This retrospective study included 3578 NPC patients from Jiangsu Cancer Hospital receiving intensity-modulated radiation therapy (IMRT). Ninety-four RTLI patients were recruited based on inclusion criteria and matched 1:1 with 97 control subjects using propensity scores. Patients were randomly assigned to the training cohort (n = 135) and the validation cohort (n = 59). Deep transfer learning (DTL) features and dosiomics features were extracted from ADC map and three-dimensional dose distribution, respectively. Pearson's correlation coefficient and the least absolute shrinkage and selection operator (LASSO) regression were employed to identify predictive features. Subsequently, eight machine learning classification models were trained to establish a prediction framework, encompassing Support Vector Machine, K-Nearest Neighbor, Random Forest, Extremely Randomized Trees, eXtreme Gradient Boosting, Light Gradient Boosting Machine, Adaptive Boosting and Multilayer Perceptron. The performance of clinical, DTL, dosiomics and feature fusion model was compared by the area under the curve (AUC).

Results: We constructed six pre-trained transfer learning networks and extracted DTL features, respectively. The results showed that pre-trained WideResNet 101 exhibited superior performance with an AUC of 0.786 in the validation cohort. The clinical model based on D_1cc and induction chemotherapy demonstrated an AUC of 0.794 and the dosiomics model demonstrated an AUC of 0.903. Features fusion model demonstrated the highest AUC values in both the training (0.988) and validation (0.940) cohorts.

Conclusions: The fusion model based on pretreatment ADC map and dose distribution provided a promising way to predict RTLI in NPC patients receiving IMRT, which can support clinicians in making decisions to develop individualized treatment plans and implement preventive measures.

Paclitaxel has been a cornerstone of ovarian cancer chemotherapy for over two decades. However, its clinical application is constrained by poor solubility and non-specific delivery, resulting in systemic toxicity and inconsistent therapeutic outcomes. Nanotechnology-based drug delivery systems have emerged as a promising strategy to address these limitations. In this study, we employed elastin-like polypeptide (ELP) nanocarriers, precisely modified with the tumor-targeting AP1 peptide, to deliver paclitaxel in ovarian cancer. ELPs are biologically inspired, genetically engineered polymers that can form nano-sized structures with controlled physicochemical properties, facilitating passive tumor targeting. The integration of the AP1 peptide, which specifically binds to the IL-4 receptor overexpressed in numerous cancers, enables active targeting of these nanocarriers, complementing the passive delivery approach. This investigation focused on the synthesis and characterization of paclitaxel delivery vehicles based on modified (A60) and unmodified (E60) ELPs. Paclitaxel (PTX) was conjugated to ELPs via a thiol-maleimide Michael-addition strategy. Both ELP-PTX formulations formed stable, monodisperse micelles, with A60-PTX nanoparticles measuring 28 ± 2.8 nm and E60-PTX nanoparticles measuring 46.8 ± 6.6 nm, as determined by TEM. DLS analysis further confirmed the narrow size distribution, evidenced by a single, narrow peak in the size distribution profile, indicating near homogeneity of the micellar population. In vitro binding analysis in SKOV-3 and OVCAR-3 ovarian cancer cells demonstrated significantly enhanced targeting capability with A60, exhibiting ~ 8.6-fold and ~ 2.7-fold higher cell binding than E60, respectively. Consistently, A60-PTX demonstrated superior cytotoxicity, with ~ 2.6-fold and ~ 1.4-fold lower IC50 values than E60-PTX in SKOV-3 (47 nM vs. 120 nM) and OVCAR-3 (45 nM vs. 62 nM), respectively. The relevance of the active targeting was further validated in agarose-based 3D spheroid models of the two cell lines with A60-PTX demonstrating approximately ~ 3-fold (SKOV-3) and ~ 2.5-fold (OVCAR-3) higher cytotoxicity compared to E60-PTX. Overall, this study highlights the potential of AP1-functionalized ELP nanocarriers to enhance the precision and therapeutic efficacy of paclitaxel delivery, offering a promising strategy for targeted ovarian cancer therapy.