No abstract

Objective To develop a fully automated AI system to quantitatively assess the disease severity and disease progression of COVID-19 using thick-section chest CT images. Methods In this retrospective study, an AI system was developed to automatically segment and quantify the COVID-19-infected lung regions on thick-section chest CT images. Five hundred thirty-one CT scans from 204 COVID-19 patients were collected from one appointed COVID-19 hospital. The automatically segmented lung abnormalities were compared with manual segmentation of two experienced radiologists using the Dice coefficient on a randomly selected subset (30 CT scans). Two imaging biomarkers were automatically computed, i.e., the portion of infection (POI) and the average infection HU (iHU), to assess disease severity and disease progression. The assessments were compared with patient status of diagnosis reports and key phrases extracted from radiology reports using the area under the receiver operating characteristic curve (AUC) and Cohen's kappa, respectively. Results The dice coefficient between the segmentation of the AI system and two experienced radiologists for the COVID-19infected lung abnormalities was 0.74 ± 0.28 and 0.76 ± 0.29, respectively, which were close to the inter-observer agreement (0.79 ± 0.25). The computed two imaging biomarkers can distinguish between the severe and non-severe stages with an AUC of 0.97 (p value < 0.001). Very good agreement (κ = 0.8220) between the AI system and the radiologists was achieved on evaluating the changes in infection volumes. Conclusions A deep learning-based AI system built on the thick-section CT imaging can accurately quantify the COVID-19associated lung abnormalities and assess the disease severity and its progressions.

The development of metastasis is the leading cause of death and an enormous therapeutic challenge in cases of non-small cell lung cancer. To better understand the molecular mechanisms underlying the metastasis process and to discover novel potential clinical markers for non-small cell lung cancer, comparative proteomic analysis of two non-small cell lung cancer cell lines with different metastatic potentials, the non-metastatic CL1-0 and highly metastatic CL1-5 cell lines, was carried out using two-dimensional electrophoresis followed by matrix-assisted laser desorption ionization-time of flight mass spectrometry and tandem mass spectrometry. Thirty-three differentially expressed proteins were identified unambiguously, among which 16 proteins were significantly upregulated and 17 proteins were downregulated in highly metastatic CL1-5 cells compared with non-metastatic CL1-0 cells. Subsequently, 8 of 33 identified proteins were selected for further validation at the mRNA level using real-time quantitative polymerase chain reaction, and three identified proteins, S100A11, PGP 9.5 and HSP27, were confirmed by western blotting. The protein S100A11 displaying significant differential expression at both the protein and mRNA levels was further analyzed by immunohistochemical staining in 65 primary non-small cell lung cancer tissues and 10 matched local positive lymph node specimens to explore its relationship with metastasis. The results indicated that the upregulation of S100A11 expression in non-small cell lung cancer tissues was significantly associated with higher tumor-nodemetastasis stage (P = 0.001) and positive lymph node status (P = 0.011), implying that S100A11 might be an important regulatory molecule in promoting invasion and metastasis of non-small cell lung cancer. (Cancer Sci 2007; 98: 1265-1274) L ung cancer is the leading cause of cancer-related mortality worldwide. In some countries it has become the number one cancer killer, accounting for more deaths than prostate cancer, breast cancer and colorectal cancer combined.(1) NSCLC, the most common histological subtype, represents 85% of all lung cancers and often develops metastases resulting in incurable disease at the time of diagnosis. Because of the lack of accurate early stage detection measures and efficient methods for preventing metastasis, the 5-year survival rate for all stages combined is only 15%, and only 16% of lung cancers are diagnosed at an early stage.(2) Therefore, investigations into the mechanisms of metastasis are required urgently for the early diagnosis and therapy of NSCLC.Metastasis is a complex multistep process that includes invasion of tumor cells into the surrounding stroma, passage through the endothelial lining and into the vasculature, escape from blood vessels, and then colonization of distant organs. During the devastating process a series of changes occur in the tumor cells, providing them with the potential for invasion and subsequent localization at a secondary site. It is therefore quite difficult to attribute the m...

No abstract

A highly sensitive and water-soluble "switch-on" fluorescent probe with aggregation-induced emission characteristics was developed for protein quantification and visualization. It offers a rapid, economic and effective way for the assay of complete serum proteins and disease-marker proteins.