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.

MRI of the epidural cavernous hemangioma showed the characteristic lobulated contour, which encircled the spinal cord. T(1)WI on the MRI presented as isointense and T(2)WI presented as hyperintense and a homogeneously strong enhancement, so we first proposed the sign of wafting silk. The widening of the intervertebral neural foramen and erosion of the adjacent bones can easily be observed. MR imaging has an important role in the detection and diagnosis of pure spinal epidural cavernous hemangioma.

Background: Investigations of disease incidence, mortality, and disability-adjusted life years (DALYs) are valuable for facilitating preventive measures and health resource planning. We examined the tracheal, bronchus, and lung (TBL) cancer burdens worldwide according to sex, age, and social development index (SDI) at the global, regional, and national levels. Methods: We assessed the TBL cancer burden using data from the Global Burden of Disease (GBD) database, including 21 regions, 195 countries, and territories in the diagnostic period 1990-2017. The data of TBL cancer-related mortality and DALYs attributable to all known risk factors were also analyzed. Age-standardized rates (ASRs) and their estimated annual percentage changes (EAPCs) were calculated. Results: Incident cases, deaths, and DALYs of TBL cancer increased worldwide (100.44%, 82.30%, and 61.27%, respectively). The age-standardized incidence rate (ASIR) was stable (EAPC = 0.02, 95% confidence interval [CI] − 0.03 to 0.08), but the agestandardized death (EAPC = − 0.34, 95%CI − 0.38 to − 0.3) and DALY rate decreased generally (EAPC = − 0.74, 95%CI − 0.8 to − 0.68). However, the change trend of ASIR and ASDR among sexes was on the contrary. China and the USA always had the highest incidence, mortality, and DALYs of TBL cancer. Significant positive correlations between ASRs and SDI were observed, especially among females. High (36.86%), high-middle (28.78%), and middle SDI quintiles (24.91%) carried the majority burden of TBL cancer. Tobacco remained the top cause of TBL cancer death and DALYs, followed by air pollution, the leading cause in the low-middle and low-SDI quintiles. Metabolic risk-related TBL cancer mortality and DALYs among females increased but was stable among males. The main ages of TBL cancer onset and death were > 50 years, and the DALYs concentrated in 50 − 69 years.

No abstract

Metastasis/recurrence has been the most fundamental characteristic of hepatocellular cancer (HCC) and the ultimate cause of most HCC-related deaths. However, there are still a limited number of reliable tumor markers that can be used to predict the possibility of metastasis/recurrence in an HCC patient after operation. Recently, much evidence has shown that glypican-3 (GPC3) can be a useful tool to identify the early development of HCC, but little research has been done to test its usefulness as a prognostic marker related to post-operative metastasis/recurrence in HCC patients. In this study, the expression of GPC3 and its relationship with clinicopathological factors were determined by immunohistochemical analysis in 61 primary HCC patients. The potential prognostic value of GPC3 was investigated by comparing the survival time between HCC patients with high and low GPC3 expression. The results demonstrated that GPC3 expression was closely related with metastasis/recurrence in an HCC patient who can receive the operation. The risk of metastasis/recurrence after surgery in an HCC patient with high GPC3 expression was increased to 3.214 as compared to that of an HCC patient with low GPC3 expression. Survival analysis showed that HCC patients with high GPC3 expression had a significantly shorter overall survival time than HCC patients with low GPC3 expression (P=0.003). Further, multivariate analysis showed that GPC3 expression was a significant, independent prognostic parameter (P=0.030) for HCC patients. Overall, the study indicates that GPC3 might be a valuable marker closely related with prognosis and post-operative metastasis/recurrence in HCC patients.

Background The epidemiology of esophageal cancer (EC) can elucidate its causes and risk factors and help develop prevention strategies. We aimed to provide an overview of the burden, trends, and risk factors of EC in China from 1990 to 2017. We also investigated the differences between China, Japan, and South Korea and discussed the possible causes of the disparities. Methods We used the Global Burden of Disease Study 2017 to obtain data on incident cases, deaths, disability-adjusted life-year (DALY) cases, age-standardized incidence rate (ASIR), age-standardized death rate (ASDR), and age-standardized DALY rate of EC in China, Japan, and South Korea from 1990 to 2017. Trend analysis was performed using joinpoint analysis. We measured the associations between ASIR, ASDR, and age-standardized DALY rate and the socio-demographic index (SDI) for 1990–2017. We also analyzed the risk factors associated with EC deaths and DALYs. Results China recorded 234,624 (95% uncertainty intervals: 223,240–246,036) incident cases of and 212,586 (202,673–222,654) deaths from EC in 2017. The ASIR and ASDR declined from 1990 to 2017. Until 2017, the ASIR was 12.23, and ASDR was 11.25 per 100,000 persons. The DALYs were 4,464,980 (4,247,816–4,690,846) with an age-standardized rate of 222.58 per 100,000 persons in 2017. The ASIR, ASDR, and age-standardized DALY rate in China were twice those of Japan and South Korea. These three indicators showed a decreasing trend, whereas SDI increased, in all three countries from 1990 to 2017. Tobacco and alcohol use remained the major risk factors for EC death and DALYs, especially for men in China and women in Japan and South Korea. High body mass index (BMI) and low-fruit diet were the main risk factors for women in China. Conclusions The incident cases and deaths of EC in China, Japan, and South Korea increased from 1990 to 2017, whereas the ASIR, ASDR, and age-standardized DALY rate declined. China had the greatest burden of EC among three countries. SDI and aging along with tobacco use, alcohol use, high BMI, and low-fruit diet were the main risk factors of death and DALYs and should be paid more attention.

The lesions of the NK/T-cell lymphoma are F-FDG avid and PET/CT seems to be useful in the staging of this disease.

Abbreviations: AUC = area under the receiver operating characteristic curve CI = confidence interval COVID-19 = coronavirus disease 2019 POI = portion of infection iHU = average infection Hounsfield unit Key Results: A deep learning based AI system was able to accurately segment the infected lung regions by COVID-19 using the thick-section CT scans (Dice coefficient ≥ 0.74).The computed imaging bio-markers were able to distinguish between the non-severe and severe COVID-19 stages (area under the receiver operating characteristic curve 0.968).The infection volume changes computed by the AI system was able to assess the COVID-19 progression (Cohen's kappa 0.8220). Summary Statement:A deep learning based AI system built on the thick-section CT imaging can accurately quantify the COVID-19 infected lung regions, assess patients disease severity and their disease progressions. AbstractBackground: Thick-section CT scanners are more affordable for the developing countries. Considering the widely spread COVID-19, it is of great benefit to develop an automated and accurate system for quantification of COVID-19 associated lung abnormalities using thick-section chest CT images.Purpose: To develop a fully automated AI system to quantitatively assess the disease severity and disease progression using thick-section chest CT images.