A Novel Approach to the Technique of Lung Region Segmentation Based on a Deep Learning Model to Diagnose COVID-19 X-ray Images.

BACKGROUND: The novel coronavirus pandemic has caused a global health crisis, placing immense strain on healthcare systems worldwide. Chest X-ray technology has emerged as a critical tool for the diagnosis and treatment of COVID-19. However, the manual interpretation of chest X-ray films has proven to be inefficient and time-consuming, necessitating the development of an automated classification system. OBJECTIVE: In response to the challenges posed by the COVID-19 pandemic, we aimed to develop a deep learning model that accurately classifies chest X-ray images, specifically focusing on lung regions, to enhance the efficiency and accuracy of COVID-19 and pneumonia diagnosis. METHODS: We have proposed a novel deep network called "FocusNet" for precise segmentation of lung regions in chest radiographs. This segmentation allows for the accurate extraction of lung contours from chest X-ray images, which are then input into the classification network, ResNet18. By training the model on these segmented lung datasets, we sought to improve the accuracy of classification. RESULTS: The performance of our proposed system was evaluated on three types of lung regions in normal individuals, COVID-19 patients, and those with pneumonia. The average accuracy of the segmentation model (FocusNet) in segmenting lung regions was found to be above 90%. After reclassification of the segmented lung images, the specificities and sensitivities for normal, COVID-19, and pneumonia were excellent, with values of 98.00%, 99.00%, 99.50%, and 98.50%, 100.00%, and 99.00%, respectively. ResNet18 achieved impressive area under the curve (AUC) values of 0.99, 1.00, and 0.99 for classifying normal, COVID-19, and pneumonia, respectively, on the segmented lung datasets. Moreover, the AUC values of the three groups increased by 0.02, 0.02, and 0.06, respectively, when compared to the direct classification of unsegmented original images. Overall, the accuracy of lung region classification after processing the datasets was 99.3%. CONCLUSION: Our deep learning-based automated chest X-ray classification system, incorporating lung region segmentation using FocusNet and subsequent classification with ResNet18, has significantly improved the accuracy of diagnosing respiratory lung diseases, including COVID-19. The proposed approach has great potential to revolutionize the diagnosis of COVID-19 and other respiratory lung diseases, offering a valuable tool to support healthcare professionals during health crises.

A radiomics model based on magnetic resonance imaging to predict cytokeratin 7/19 expression and liver fluke infection of hepatocellular carcinoma.

Hepatocellular carcinoma (HCC) is the most common type of primary liver cancer. HCC with liver fluke infection could harbor unique biological behaviors. This study was aimed at investigating radiomics features of HCC with liver fluke infection and establishing a model to predict the expression of cytokeratin 7 (CK7) and cytokeratin 19 (CK19) as well as prognosis at the same time. A total of 134 HCC patients were included. Gadoxetic acid-enhanced magnetic resonance imaging (MRI) images of all patients were acquired. Radiomics features of the tumor were extracted and then data dimensionality was reduced. The radiomics model was established to predict liver fluke infection and the radiomics score (Radscore) was calculated. There were 11 features in the four-phase combined model. The efficiency of the combined model increased significantly compared to each single-phase MRI model. Radscore was an independent predictor of liver fluke infection. It was also significantly different between different expression of CK7/ CK19. Meanwhile, liver fluke infection was associated with CK7/CK19 expression. A cut-off value was set up and all patients were divided into high risk and low risk groups of CK7/CK19 positive expression. Radscore was also an independent predictor of these two biomarkers. Overall survival (OS) and recurrence free survival (RFS) of negative liver fluke infection group were significantly better than the positive group. OS and RFS of negative CK7 and CK19 expression were also better, though not significantly. Positive liver fluke infection and CK19 expression prediction groups harbored significantly worse OS and RFS, survival of positive CK7 expression prediction was unsatisfying as well. A radiomics model was established to predict liver fluke infection among HCC patients. This model could also predict CK7 and CK19 expression. OS and RFS could be foreseen by this model at the same time.

Synergistic effects of trans-p-coumaric acid isolated from the ethanol extract of Gynura procumbens in promoting intestinal absorption of chlorogenic acid and reversing alcoholic fatty liver disease.

ETHNOPHARMACOLOGICAL RELEVANCE: Our previous studies found that the ethanol extract of Gynura procumbens (EEGS) reduced hepatic steatosis in alcoholic fatty liver disease (AFLD). AIM OF THE STUDY: To explore the active ingredients from EEGS and their relevant mechanism of action in alleviating alcoholic liver injuries. AIM OF THE STUDY: To explore the active ingredients from EEGS and their intestinal absorption characteristics as an approach for understanding mechanism of action in alleviating alcoholic liver injuries. MATERIALS AND METHODS: Monitored by high-performance liquid chromatography (HPLC) and thin-layer chromatography (TLC), chemical constituents from the prepared EEGS were isolated by means of solvent extraction, repeated column chromatography, preparative HPLC and other methods, and their structures were identified based on spectroscopic methods. The in vivo intestinal absorption rate of chlorogenic acid (CA), the active component of the EEGS, both in a single form and in the EEGS were monitored by the single-pass intestinal perfusion (SPIP) method in rats. The protective effect of EEGS and its active components on alcoholic liver injuries was evaluated in the alcoholic liver injury model of C57BL/6J male mice induced by Lieber-DeCarli alcohol liquid feed. RESULTS: Three noncaffeoyl quinic acid components were isolated and identified from the EEGS, namely, 3-trans-p-coumaroyl quinic acid (0.9%), 3-cis-p-coumaroyl quinic acid (2.7%), and trans-p-coumaric acid (0.6%). In vivo intestinal absorption of CA decreased with the increase of pH value of perfusion solution in the range of 5.5-7.8. The maximum absorption percentage of CA alone was 6.7 ± 2.4%, while the maximum absorption percentage of CA in the EEGS was 16.0 ± 2.2%, which was 2.4 times higher than that of CA alone. The results of animal experiments showed that the degree of fatty liver of mice treated with EEGS was significantly lower than that of the CA, trans-p-coumaric acid, and the combination group of CA and trans-p-coumaric acid alone. CONCLUSION: The above results indicated that trans-p-coumaric acid isolated from the dried stems of Gynura procumbens assisted CA being absorbed into the body and worked together with CA to improve the function of liver lipid metabolism, reduce hepatic lipid accumulation in a mouse model of AFLD and effectively counteract alcohol-induced fatty liver disease.

Establishment of a Stable Acute Drug-Induced Liver Injury Mouse Model by Sodium Cyclamate.

Objective: To establish a stable acute DILI mouse model and explore its possible pathogenesis. Methods: Mice were randomly divided into control, low-dose, middle-dose and high-dose sodium cyclamate groups. Mice in the model group were intraperitoneally injected with corresponding doses of sodium cyclamate, and in the control group intraperitoneally injected with 0.9% normal saline. The toxic effects of sodium cyclamate on liver, heart, kidney were evaluated by biochemical index level and histomorphologically observed. The expression of TNF-α and IL-1ß were measured by immunohistochemistry. Results: 1. The level of ALT in the low-dose and middle-dose groups at 24h, 72h, 120h and 168h were increased, also in the high-dose group at 24h, 72h and 120h. The level of AST in the low-dose group at 72h, 120h, 168h and in the middle-dose group at 168h were increased, also in the middle-dose and high-dose groups at 24h, 72h and 120h. The levels of CK, CK-MB and cTnT in the low-dose and middle-dose groups at 168h were increased, also in the high-dose group at 24h, 72h and 120h. 2. The damage of hepatocytes increased with the increase of sodium cyclamate dosage and treated time. 3. At 120h, the IOD/Area of TNF-α and IL-1ß positive expression increased in the liver tissues with the increase of the dosage. In the heart and kidney tissues, the IOD/Area of TNF-α and IL-1ß positive expression in the high-dose group increased significantly. In the kidney tissues, the IOD/Area of IL-1ß positive expression in the middle-dose group increased significantly. Conclusion: Sodium cyclamate-induced acute DILI mouse model can be established by intraperitoneal injection of 6000 mg/kg/day sodium cyclamate for 5 days successfully. The toxicity of sodium cyclamate to liver showed a dose-response and time-response relationship. Sodium cyclamate induced liver, heart and kidney injury closely related to the inflammatory response mediated by TNF-α and IL-1ß.

Highly Suspected COVID-19 Cluster with Multiple Negative SARS-CoV-2 RNA Tests: A Case Report.

The patient had several close contacts with friends from Wuhan, the epicenter of the epidemic. His mother and father had close contact with him. His father was later diagnosed with COVID-19 infection after a positive reverse transcription PCR test for SARS-CoV-2 RNA. The patient and his mother were diagnosed as suspected cases of COVID-19 based on a history of exposure, clinical manifestation, and imaging examination. However, the patient was tested more than three times with the reverse transcription PCR test for SARS-CoV-2 RNA, and the results were negative each time. COVID-19 should be suspected, regardless of SARS-CoV-2 test negativity, for recent close contact with a confirmed case and respiratory symptoms.

Value of radiomics in differential diagnosis of chromophobe renal cell carcinoma and renal oncocytoma.

PURPOSE: To explore the value of CT-enhanced quantitative features combined with machine learning for differential diagnosis of renal chromophobe cell carcinoma (chRCC) and renal oncocytoma (RO). METHODS: Sixty-one cases of renal tumors (chRCC = 44; RO = 17) that were pathologically confirmed at our hospital between 2008 and 2018 were retrospectively analyzed. All patients had undergone preoperative enhanced CT scans including the corticomedullary (CMP), nephrographic (NP), and excretory phases (EP) of contrast enhancement. Volumes of interest (VOIs), including lesions on the images, were manually delineated using the RadCloud platform. A LASSO regression algorithm was used to screen the image features extracted from all VOIs. Five machine learning classifications were trained to distinguish chRCC from RO by using a fivefold cross-validation strategy. The performance of the classifier was mainly evaluated by areas under the receiver operating characteristic (ROC) curve and accuracy. RESULTS: In total, 1029 features were extracted from CMP, NP, and EP. The LASSO regression algorithm was used to screen out the four, four, and six best features, respectively, and eight features were selected when CMP and NP were combined. All five classifiers had good diagnostic performance, with area under the curve (AUC) values greater than 0.850, and support vector machine (SVM) classifier showed a diagnostic accuracy of 0.945 (AUC 0.964 ± 0.054; sensitivity 0.999; specificity 0.800), showing the best performance. CONCLUSIONS: Accurate preoperative differential diagnosis of chRCC and RO can be facilitated by a combination of CT-enhanced quantitative features and machine learning.

Comparison of Imaging and Clinically Relevant Features of Combined Hepatocellular Carcinoma and Cholangiocarcinoma with Hepatocellular Carcinoma.

BACKGROUND The aim of this study was to compare the clinical, imaging, pathological, and prognostic characteristics of combined hepatocellular carcinoma and cholangiocarcinoma (cHCC-CC) and hepatocellular carcinoma (HCC). MATERIAL AND METHODS Medical records of 21 patients with cHCC-CC and 21 patients with HCC were retrospectively reviewed. Patients underwent a computed tomography (CT) examination within 1 month before surgery and did not receive preoperative interventional therapy. Clinical, imaging, pathological, and prognostic characteristics of cHCC-CC and HCC were compared. RESULTS On multi-phase contrast-enhanced CT, cHCC-CC could be differentiated from HCC based on the presence of a pseudocapsule (p<0.0001; χ²=14.538) and extensive necrosis (p=0.009; χ²=8.400). The changes in the arterial phase and venous phase (V>A) and arterial phase and delayed phase (D>A) of CT enhanced scanning in HCC and cHCC-CC were statistically significant (both p<0.0001, χ²=28.560 and 25.846). Immunohistochemistry showed more HCC were positive for VEGF (P=0.012, χ²=7.785). A Kaplan-Meier survival analysis showed no statistically significant difference in progression-free survival (PFS) after treatment between patients with cHCC-CC and those with HCC (p=0.526). CONCLUSIONS Multi-phase contrast-enhanced CT may be useful for preoperative diagnosis of cHCC-CC in tumors with a diffuse boundary, no pseudocapsule, extensive necrosis (>50%), and a dilated bile duct, and when the CT value in the delayed phase is higher than in the arterial phase. VEGF expression is more likely to be positive in HCC than cHCC-CC. There was no significant difference between cHCC-CC and HCC in prognosis, but cHCC-CC was more likely to recur after treatment than HCC.

Radiomics for diagnosis of dual-phenotype hepatocellular carcinoma using Gd-EOB-DTPA-enhanced MRI and patient prognosis.

PURPOSE: To describe the clinical characteristics and outcomes of patients with dual-phenotype hepatocellular carcinoma (DPHCC) and investigate the use of radiomics to establish an image-based signature for preoperative differential diagnosis. METHODS: This study included 50 patients with a postoperative pathological diagnosis of DPHCC (observation group) and 50 patients with CK7- and CK19-negative HCC (control group) who attended our hospital between January 2015 and December 2018. All patients underwent Gd-EOB-DTPA-enhanced MRI within 1 month before surgery. Arterial phase (AP), portal venous phase (PVP), delayed phase (DP) and hepatobiliary phase (HBP) images were transferred into a radiomics platform. Volumes of interest covered the whole tumor. The dimensionality of the radiomics features were reduced using LASSO. Four classifiers, including multi-layer perceptron (MLP), support vector machines (SVM), logistic regression (LR) and K-nearest neighbor (KNN) were used to distinguish DPHCC from CK7- and CK19-negative HCC. Kaplan-Meier survival analysis was used to assess 1-year disease-free survival (DFS) and overall survival (OS) in the observation and control groups. RESULTS: The best preoperative diagnostic power for DPHCC will likely be derived from a combination of different phases and classifiers. The sensitivity, specificity and accuracy of LR in PVP (0.740, 0.780, 0.766), DP (0.893, 0.700, 0.798), HBP (0.800, 0.720, 0.756) and MLP in PVP (0.880, 0.720, 0.798) were better performance. The 1-year DFS and OS of the patients in the observation group were 69% and 78%, respectively. The 1-year DFS and OS of the patients in the control group were 83% and 85%, respectively. Kaplan-Meier survival analysis showed no statistical difference in DFS and OS between groups (P = 0.231 and 0.326), but DFS and OS were numerically lower in patients with DPHCC. CONCLUSION: The radiomics features extracted from Gd-EOB-DTPA-enhanced MR images can be used to diagnose preoperative DPHCC. DPHCC is more likely to recur and cause death than HCC, suggesting that active postoperative management of patients with DPHCC is required.

Quantification of pancreatic proton density fat fraction in diabetic pigs using MR imaging and IDEAL-IQ sequence.

BACKGROUND: Recent studies have highlighted the correlation between diabetes and pancreatic fat infiltration. Notably, pancreatic fat content (PFC) is a potential biomarker in diabetic patients, and magnetic resonance imaging (MRI) provides an effective method for noninvasive assessment of pancreatic fat infiltration. However, most reports of quantitative measurement of pancreatic fat have lacked comparisons of pathology results. The primary objective of this study was to determine the feasibility and accuracy of pancreatic MRI by using pancreatic fat fraction (PFF) measurements with the IDEAL-IQ sequence; the secondary objective was to explore changes in PFC between pigs with and without diabetes. METHODS: In this prospective study, 13 Bama Mini-pigs (7 females, 6 males; median age, 2 weeks) were randomly assigned to diabetes (n = 7) or control (n = 6) groups. Pigs in the diabetes group received high fat/high sugar feed, combined with streptozotocin injections. At the end of 15 months, biochemical changes were evaluated. All pigs underwent axial MRI with the IDEAL-IQ sequence to measure PFF; PFC of fresh pancreatic parenchyma was measured by the Soxhlet extraction method; and pancreatic fat distribution was observed by histopathology. Results of all analyses were compared between the diabetes and control groups by using the Mann-Whitney U-test. Correlations of PFF and PFC, fasting blood glucose (GLU), and serum insulin (INS) were calculated by using the Spearman correlation coefficient. Single-measure intraclass correlation coefficient (ICC) was used to assess interreader agreement. RESULTS: There were significant differences between diabetes and control groups: GLU (mmol/L) was 18.06 ± 6.03 and 5.06 ± 1.41 (P < 0.001); INS (mU/L) was 21.59 ± 2.93 and 29.32 ± 3.27 (P = 0.003); PFC (%) was 34.60 ± 3.52 and 28.63 ± 3.25 (P = 0.027); and PFF (%) was 36.51 ± 4.07 and 27.75 ± 3.73 (P = 0.003). There was a strongly positive correlation between PFF and PFC (r = 0.934, P < 0.001); there were moderate correlations between PFF and GLU (r = 0.736, P = 0.004; positive correlation), and between PFF and INS (r = - 0.747, P = 0.003; negative correlation). Excellent interreader agreement was observed for PFF measurements (ICC, 0.954). CONCLUSIONS: Pancreatic fat infiltration shows a clear association with diabetes. MRI with the IDEAL-IQ sequence can be used to accurately and reproducibly quantify PFC.

Anti-inflammatory and antinociceptive effects of active ingredients in the essential oils from Gynura procumbens, a traditional medicine and a new and popular food material.

ETHNOPHARMACOLOGICAL RELEVANCE: Gynura procumbens is applied topically for the treatment of traumatic injuries in South China. MATERIALS AND METHODS: This study was conducted to identify the active ingredients in the essential oils from Gynura procumbens (GPEO) by Gas Chromatography-Mass Spectrometer (GC-MS) and to elucidate the mechanisms underlying the anti-inflammatory and antinociceptive effects in vivo and in vitro. RESULTS: A reduction in dswelling and pain were observed in mice treated with GPEO or its active ingredients (α-pinene, 3-carene, and limonene) compared with mice treated with a solvent control. GPEO or its three active ingredients had potent pharmacological effects on COX-2 overexpression and LPS-induced migration of Raw264.7 macrophages. All three ingredients inhibited nociceptive stimulus-induced inflammatory infiltrates and COX-2 overexpression, which could be responsible for the anti-inflammatory effect of GPEO. However, only 3-carene produced an antinociceptive effect. CONCLUSION: Consistent with the traditional usage in Southern China, GPEO may serve as a promising potent external therapeutic agent for the treatment of chronic pain.