No abstract

Objective. To analyze and identify the core genes related to the expression and prognosis of lung cancer including lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC) by bioinformatics technology, with the aim of providing a reference for clinical treatment. Methods. Five sets of gene chips, GSE7670, GSE151102, GSE33532, GSE43458, and GSE19804, were obtained from the Gene Expression Omnibus (GEO) database. After using GEO2R to analyze the differentially expressed genes (DEGs) between lung cancer and normal tissues online, the common DEGs of the five sets of chips were obtained using a Venn online tool and imported into the Database for Annotation, Visualization, and Integrated Discovery (DAVID) database for Gene Ontology (GO) enrichment and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analyses. The protein–protein interaction (PPI) network was constructed by STRING online software for further study, and the core genes were determined by Cytoscape software and KEGG pathway enrichment analysis. The clustering heat map was drawn by Excel software to verify its accuracy. In addition, we used the University of Alabama at Birmingham Cancer (UALCAN) website to analyze the expression of core genes in P53 mutation status, confirmed the expression of crucial core genes in lung cancer tissues with Gene Expression Profiling Interactive Analysis (GEPIA) and GEPIA2 online software, and evaluated their prognostic value in lung cancer patients with the Kaplan–Meier online plotter tool. Results. CHEK1, CCNB1, CCNB2, and CDK1 were selected. The expression levels of these four genes in lung cancer tissues were significantly higher than those in normal tissues. Their increased expression was negatively correlated with lung cancer patients (including LUAD and LUSC) prognosis and survival rate. Conclusion. CHEK1, CCNB1, CCNB2, and CDK1 are the critical core genes of lung cancer and are highly expressed in lung cancer. They are negatively correlated with the prognosis of lung cancer patients (including LUAD and LUSC) and closely related to the formation and prediction of lung cancer. They are valuable predictors and may be predictive biomarkers of lung cancer.

No abstract

Purpose Coronavirus disease 2019 (COVID‐19) has become a global pandemic and is still posing a severe health risk to the public. Accurate and efficient segmentation of pneumonia lesions in computed tomography (CT) scans is vital for treatment decision‐making. We proposed a novel unsupervised approach using a cycle consistent generative adversarial network (cycle‐GAN) which automates and accelerates the process of lesion delineation. Method The workflow includes lung volume segmentation, healthy lung image synthesis, infected and healthy image subtraction, and binary lesion mask generation. The lung volume was first delineated using a pre‐trained U‐net and worked as the input for the following network. A cycle‐GAN was trained to generate synthetic healthy lung CT images from infected lung images. After that, the pneumonia lesions were extracted by subtracting the synthetic healthy lung CT images from the infected lung CT images. A median filter and k‐means clustering were then applied to contour the lesions. The auto segmentation approach was validated on three different datasets. Results The average Dice coefficient reached 0.666 ± 0.178 on the three datasets. Especially, the dice reached 0.748 ± 0.121 and 0.730 ± 0.095, respectively, on two public datasets Coronacases and Radiopedia. Meanwhile, the average precision and sensitivity for lesion segmentation on the three datasets were 0.679 ± 0.244 and 0.756 ± 0.162. The performance is comparable to existing supervised segmentation networks and outperforms unsupervised ones. Conclusion The proposed label‐free segmentation method achieved high accuracy and efficiency in automatic COVID‐19 lesion delineation. The segmentation result can serve as a baseline for further manual modification and a quality assurance tool for lesion diagnosis. Furthermore, due to its unsupervised nature, the result is not influenced by physicians’ experience which otherwise is crucial for supervised methods.

Lesion segmentation is critical for clinicians to accurately stage the disease and determine treatment strategy. Deep learning based automatic segmentation can improve both the segmentation efficiency and accuracy. However, training a robust deep learning segmentation model requires sufficient training examples with sufficient diversity in lesion location and lesion size. This study is to develop a deep learning framework for generation of synthetic lesions with various locations and sizes that can be included in the training dataset to enhance the lesion segmentation performance. The lesion synthesis network is a modified generative adversarial network (GAN). Specifically, we innovated a partial convolution strategy to construct a U‐Net‐like generator. The discriminator is designed using Wasserstein GAN with gradient penalty and spectral normalization. A mask generation method based on principal component analysis (PCA) was developed to model various lesion shapes. The generated masks are then converted into liver lesions through a lesion synthesis network. The lesion synthesis framework was evaluated for lesion textures, and the synthetic lesions were used to train a lesion segmentation network to further validate the effectiveness of the lesion synthesis framework. All the networks are trained and tested on the LITS public dataset. Our experiments demonstrate that the synthetic lesions generated by our approach have very similar distributions for the two parameters, GLCM‐energy and GLCM‐correlation. Including the synthetic lesions in the segmentation network improved the segmentation dice performance from 67.3% to 71.4%. Meanwhile, the precision and sensitivity for lesion segmentation were improved from 74.6% to 76.0% and 66.1% to 70.9%, respectively. The proposed lesion synthesis approach outperforms the other two existing approaches. Including the synthetic lesion data into the training dataset significantly improves the segmentation performance.