Objective: To develop an imaging-derived biomarker for prediction of overall survival (OS) of pancreatic cancer by analyzing preoperative multiphase contrast-enhanced computed topography (CECT) using deep learning. Background: Exploiting prognostic biomarkers for guiding neoadjuvant and adjuvant treatment decisions may potentially improve outcomes in patients with resectable pancreatic cancer. Methods: This multicenter, retrospective study included 1516 patients with resected pancreatic ductal adenocarcinoma (PDAC) from 5 centers located in China. The discovery cohort (n=763), which included preoperative multiphase CECT scans and OS data from 2 centers, was used to construct a fully automated imaging-derived prognostic biomarker—DeepCT-PDAC—by training scalable deep segmentation and prognostic models (via self-learning) to comprehensively model the tumor-anatomy spatial relations and their appearance dynamics in multiphase CECT for OS prediction. The marker was independently tested using internal (n=574) and external validation cohorts (n=179, 3 centers) to evaluate its performance, robustness, and clinical usefulness. Results: Preoperatively, DeepCT-PDAC was the strongest predictor of OS in both internal and external validation cohorts [hazard ratio (HR) for high versus low risk 2.03, 95% confidence interval (CI): 1.50–2.75; HR: 2.47, CI: 1.35–4.53] in a multivariable analysis. Postoperatively, DeepCT-PDAC remained significant in both cohorts (HR: 2.49, CI: 1.89–3.28; HR: 2.15, CI: 1.14–4.05) after adjustment for potential confounders. For margin-negative patients, adjuvant chemoradiotherapy was associated with improved OS in the subgroup with DeepCT-PDAC low risk (HR: 0.35, CI: 0.19–0.64), but did not affect OS in the subgroup with high risk. Conclusions: Deep learning-based CT imaging-derived biomarker enabled the objective and unbiased OS prediction for patients with resectable PDAC. This marker is applicable across hospitals, imaging protocols, and treatments, and has the potential to tailor neoadjuvant and adjuvant treatments at the individual level.
The role of transforming growth factorβ (TGF-β)-induced tumor progression in advanced malignancy is well established, but the involvement of long non-coding RNAs (lncRNAs) in TGF-β signaling remains unclear. This study aimed to identify TGF-β-associated lncRNAs in head and neck squamous cell carcinoma (HNSCC). Expression profiling of lncRNAs was obtained using Gene Expression Omnibus and The Cancer Genome Atlas. Real-time quantitative PCR was used to analyze the expression of EPB41L4A-AS2 in HNSCC cell line. We used bioinformatics resources (DAvID) to conduct Gene Ontology biological processes and KEGG pathways at the significant level. Wound healing assay, cell migration and invasion assays, were used to examine the effects of EPB41L4A-AS2 on tumor cell metastasis in vivo. Protein levels of EPB41L4A-AS2 targets were determined by western blot. A novel TGF-β-associated lncRNA, EPB41L4A-AS2, was found downregulated by TGF-β and associated with invasion and metastasis. The relationship of EPB41L4A-AS2 with the clinicopathological features and prognosis of HNSCC patients was evaluated. Bioinformatic analyses revealed that EPB41L4A-AS2 may be involved in processes associated with the tumor-associated signaling pathway, especially the TGF-β signaling pathway. Furthermore, a TGF-β-induced epithelial-to-mesenchymal transition (EMT) model was established. Low EPB41L4A-AS2 expression was determined, and overexpression of this gene inhibited cell migration and invasion in the EMT model. Moreover, EPB41L4A-AS2 suppressed TGFBR1 expression. EPB41L4A-AS2 might serve as a negative regulator of TGF-β signaling and as an effective prognostic biomarker and important target in anti-metastasis therapies of HNSCC patients.
21 October 2022 in Nanomedicine: Nanotechnology, Biology and Medicine
Purpose: Investigate the ability of using complementary information provided by the fusion of PET/CT images to predict immunotherapy response in non-small cell lung cancer (NSCLC) patients. Materials and methods: We collected 64 patients diagnosed with primary NSCLC treated with anti PD-1 checkpoint blockade. Using PET/CT images, fused images were created following multiple methodologies, resulting in up to 7 different images for the tumor region. Quantitative image features were extracted from the primary image (PET/CT) and the fused images, which included 195 from primary images and 1235 features from the fusion images. Three clinical characteristics were also analyzed. We then used support vector machine (SVM) classification models to identify discriminant features that predict immunotherapy response at baseline. Results: A SVM built with 87 fusion features and 13 primary PET/CT features on validation dataset had an accuracy and area under the ROC curve (AUROC) of 87.5% and 0.82, respectively, compared to a model built with 113 original PET/CT features on validation dataset 78.12% and 0.68. Conclusion: The fusion features shows better ability to predict immunotherapy response prediction compared to individual image features.
18 April 2023 in Breast Cancer Research and Treatment