Ultrasound identification of hepatic echinococcosis using a deep convolutional neural network model in China: a retrospective, large-scale, multicentre, diagnostic accuracy study.

BACKGROUND: Ultrasonography is the most widely used technique to diagnose echinococcosis; however, challenges in using this technique and the demand on medical resources, especially in low-income or remote areas, can delay diagnosis. We aimed to develop a deep convolutional neural network (DCNN) model based on ultrasonography to identify echinococcosis and its types, especially alveolar echinococcosis. METHODS: This retrospective, large-scale, multicentre study used ultrasound images from patients assessed at 84 hospitals in China, obtained between Jan 1, 2002, and Dec 31, 2021. Patients with a diagnosis of cystic echinococcosis, alveolar echinococcosis, or seven other types of focal liver lesions were included. We tested ResNet-50, ResNext-50, and VGG-16 as the backbone network architecture for a classification DCNN model and input the perinodular information from the ultrasound images. We trained and validated the DCNN model to diagnose and classify echinococcosis using still greyscale ultrasound images of focal liver lesions in four stages: differentiating between echinococcosis and other focal liver lesions (stage one); differentiating cystic echinococcosis, alveolar echinococcosis, and other focal liver lesions (stage two); differentiating cystic echinococcosis, alveolar echinococcosis, benign other focal liver lesions, and malignant focal liver lesions (stage three); and differentiating between active and transitional cystic echinococcosis and inactive cystic echinococcosis (stage four). We then tested the algorithm on internal, external, and prospective test datasets. The performance of DCNN was also compared with that of 12 radiologists recruited between Jan 15, 2022, and Jan 28, 2022, from Qinghai, Xinjiang, Anhui, Henan, Xizang, and Beijing, China, with different levels of diagnostic experience for echinococcosis and other focal liver lesions in a subset of ultrasound data that were randomly chosen from the prospective test dataset. The study is registered at ClinicalTrials.gov (NCT03871140). FINDINGS: The study took place between Jan 1, 2002, and Dec 31, 2021. In total, to train and test the DCNN model, we used 9631 liver ultrasound images from 6784 patients (2819 [41·7%] female patients and 3943 [58·3%] male patients) from 87 Chinese hospitals. The DCNN model was trained with 6328 images, internally validated with 984 images, and tested with 2319 images. The ResNet-50 network architecture outperformed VGG-16 and ResNext-50 and was generalisable, with areas under the receiver operating characteristic curve (AUCs) of 0·982 (95% CI 0·960-0·994), 0·984 (0·972-0·992), and 0·913 (0·886-0·935) in distinguishing echinococcosis from other focal liver lesions; 0·986 (0·966-0·996), 0·962 (0·946-0·975), and 0·900 (0·872-0·924) in distinguishing alveolar echinococcosis from cystic echinococcosis and other focal liver lesions; and 0·974 (0·818-1·000), 0·956 (0·875-0·991), and 0·944 (0·844-0·988) in distinguishing active and transitional cystic echinococcosis from inactive echinococcosis in the three test datasets. Specifically, in patients with the hepatitis B or hepatitis C virus, the model could distinguish alveolar echinococcosis from hepatocellular carcinoma with an AUC of 0·892 (0·812-0·946). In identifying echinococcosis, the model showed significantly better performance compared with senior radiologists from a high-endemicity area (AUC 0·942 [0·904-0·967] vs 0·844 [0·820-0·866]; p=0·027) and improved the diagnostic ability of junior, attending, and senior radiologists before and after assistance with AI with comparison of AUCs of 0·743 (0·714-0·770) versus 0·850 (0·826-0·871); p<0·0001, 0·808 (0·782-0·832) versus 0·886 (0·864-0·905); p<0·0001, and 0·844 (0·820-0·866) versus 0·870 (0·847-0·890); p=0·092, respectively. INTERPRETATION: The DCNN model was shown to be accurate and robust, and could improve the ultrasound diagnostic ability of radiologists for echinococcosis and its types for highly endemic and remote regions. FUNDING: National Natural Science Foundation of China and National Key Research & Development Program of China. TRANSLATION: For the Chinese translation of the abstract see Supplementary Materials section.

Effectiveness and safety of ultrasound-guided percutaneous microwave ablation for hepatic alveolar echinococcosis.

BACKGROUND: Microwave ablation (MWA) is a popular therapy for liver malignant tumor in recent years. Few studies have been conducted on its use in the treatment of hepatic alveolar echinococcosis (HAE). The study aims to evaluate the efficacy and safety of MWA in the treatment of HAE. METHODS: This study analyzed the data of 45 patients (mean age, 38 ± 2 years; 24 males) diagnosed with HAE and underwent MWA treatment between June 2014 to December 2019. The patients after MWA were examined by CT or MRI [follow-up: 32 months (IQR 23-48.5)] to determine whether the lesions were relapsed and to evaluate the therapeutic effect of MWA. The safety of MWA was evaluated by monitoring postoperative complications. Clinical data, such as patient demographics, imaging features of the lesions, relevant findings of laboratory tests before and after ablation, and information related to ablation, were collected and analyzed. Paired-sample t tests and paired-sample Wilcoxon signed-rank tests were used to compare relevant laboratory indicators before and after MWA. RESULTS: MWA was applied to 57 HAE lesions in 45 patients. The median size of lesions was 3.42 cm (IQR2.85-4.41). The rate of complete ablation was 100% (57/57). The median follow-up time was 32 months (IQR 23-48.5). The recurrence rate was 13% (6/45), and the median time of recurrence was 22 months. The rate of minor complications was 11.1% (5/45), and there were no major complications and deaths. Compared to preoperative, ALB, RBC, HBG, and PLT were decreased (p < 0.001); ALT, TB, DB, and WBC were increased (p < 0.001); and no statistically difference in PT, APTT, and INR (p > 0.05). CONCLUSIONS: MWA might be a safe and effective way to cure HAE. Meanwhile, it provides a new option and a new way of thinking about treatment for patients with HAE.

Analysis of the efficacy of microwave ablation in the treatment of early hepatic alveolar echinococcosis: A propensity score matching based study.

BACKGROUND: To explore the efficacy of microwave ablation (MWA) in the treatment of hepatic alveolar echinococcosis (HAE) with a diameter of ≤5 cm. METHOD: From June 2014 to January 2020, patients diagnosed with HAE were retrospectively analyzed. After balancing the confounding factors by propensity score matching (PSM) , the patients were divided into MWA group (n = 20) and radical operation group (n = 20) by 1:1 matching. The safety and effectiveness of MWA were assessed by comparing the differences between the two groups in terms of postoperative general laboratory indices, grading of postoperative complications, length of postoperative hospitalization, the outcome of treatment, and disease recurrence. RESULT: After PSM, all confounders were not statistically different (P>0.05) . Compared with the radical surgery group, patients in the MWA group had lower postoperative ALT and WBC elevations (P<0.001) , shorter postoperative hospital stay (P<0.001) ) , lower hospital costs (P<0.001) . The effective rate of the two groups was 100%. There was no statistical difference in the incidence of postoperative complications and recurrence rate (P>0.05). CONCLUSION: MWA is a safe and effective means of treating HAE ≤ 5 cm in diameter.

Parasite Circulating Cell-free DNA in the Blood of Alveolar Echinococcosis Patients as a Diagnostic and Treatment-Status Indicator.

BACKGROUND: Alveolar echinococcosis (AE) is a serious parasitic disease caused by the larvae of Echinococcus multilocularis. It is the less common but substantially more deadly of the 2 major echinococcosis diseases that can occur globally but are concentrated in central Asia. METHODS: We analyzed parasite circulating cell-free DNA (cfDNA) in 149 plasma samples using a DNA sequencing-based method (105 AE, 16 cystic echinococcosis, 4 liver cancer, 4 gallstones, and 20 healthy volunteers). After identifying the Echinococcus-specific cfDNA (Em-cfDNA) sequences in the samples, we determined whether Em-cfDNA could be used for AE diagnosis and as a potential indicator of the effectiveness of surgical treatment. We also examined potential associations between Em-cfDNA levels and clinical features of AE patients. RESULTS: Our work demonstrates that varying reads of Em-cfDNA were detectable in the plasma of 100% of preoperative AE patients and that all of the non-AE patients and healthy volunteers were negative. Em-cfDNA has good sensitivity and specificity for the diagnosis of AE. We also found that Em-cfDNA levels apparently have reference value for evaluating the therapeutic efficacy of surgery interventions for AE lesions. Finally, our analysis revealed that Em-cfDNA levels can reflect meaningful information about lesion size in preoperative AE patients. CONCLUSIONS: We demonstrate that sequencing-based monitoring of Em-cfDNA can be used in the clinic as a powerful diagnostic indicator for AE. We also note that there is a strong potential for use of this liquid-biopsy method to monitor ongoing disease status in postintervention AE patients.

Measurement and bioinformatics analysis of exosomes microRNAs in bile of hepatic alveolar echinococcosis patients with biliary tract invasion / 临床肝胆病杂志

ObjectiveTo investigate the expression of exosome microRNAs (miRNAs) in bile of hepatic alveolar echinococcosis (HAE) patients with biliary tract invasion and the regulatory mechanism of differentially expressed miRNAs on target genes. MethodsBile samples were collected from 12 HAE patients who attended Qinghai University Affiliated Hospital from August 2017 to October 2018, with 6 patients in observation group (with the manifestation of biliary tract invasion) and 6 in control group (without the manifestation of biliary tract invasion). Ultracentrifugation extraction and Western blot were used to identify the structure of exosomes, the Trizol method was used to extract total RNA in exosomes, and miRNA expression profile microarray was used to identify differentially expressed miRNAs. The pathway enrichment analysis was performed to predict the target genes of biliary tract invasion based on differentially expressed miRNAs. ResultsA total of 74 differentially expressed miRNAs were identified between the observation group and the control group, among which 9 were upregulated and 65 were downregulated (｜Fold Change｜＞2). The pathway analysis showed that the target genes were mainly enriched in the pathways for tumorigenesis, phosphatidylinositol signaling system, and PTEN (FDR＜0.05). The GO annotation and enrichment analysis showed that the target genes were mainly enriched in the biological processes such as positive regulation of gene repression and regulation of cell differentiation (FDR＜0.05). ConclusionThe established expression profile of differentially expressed exosome miRNAs in bile of HAE patients with biliary tract invasion can be used as biomarkers for biliary tract invasion of HAE and preliminarily elaborate on the regulatory mechanism of differentially expressed miRNAs on target genes after HAE invades the biliary tract.

Effect of hepatitis B virus infection on patients with hepatic alveolar echinococcoisis after surgical resection / 中华肝胆外科杂志

Objective:To investigate the effect of hepatitis B virus (HBV) infection in patients with hepatic alveolar echinococcoisis after surgical resection and determine the differences of liver function between patients with different HBV-DNA levels.Methods:Patients were selected from January 2014 to July 2018 in the Affiliated Hospital of Qinghai University. Twenty-eight patients with hepatitis B and hepatic alveolar echinococcoisis were included in the experimental group, and 20 patients with hepatic alveolar echinococcoisis but without hepatitis B virus were included in the control group. Based on HBV-DNA level, the experimental group was divided into low-level group (HBV-DNA level<200 IU/ml, n=6), intermediate-level group (HBV-DNA level 200-20 000 IU/ml, n=15) and high level group (HBV-DNA level>20 000 IU/ml, n=7). Comparison of complications and liver function after liver resection in two groups.Univariate and multivariate logistic regression were used to analyze the influential factors of postoperative complications in patients.Comparison of postoperative liver function indexes in patients with different HBV-DNA levels. Results:In the control group, postoperative total bilirubin 10.6(8.3, 16.9) μmol/L, direct bilirubin 5.3(3.4, 10.0) μmol/L, prothrombin time 13.6(13.0, 15.8)s, and the incidence of complications 25.0%(5/20), were better than the experimental group 12.6(8.4, 46.9) μmol/L, 6.7(3.1, 26.4) μmol/L, 15.4(13.5, 18.1)s, 78.6% (22/28), the differences were statistically significant significance (all P<0.05). Multivariate logistic analysis showed that patients with HBV infection ( OR=4.593, 95% CI: 1.128-18.708) and intraoperative blood loss ≥1 000 ml ( OR=2.200, 95% CI: 1.106-4.378) were the hepatic alveolar echinococcoisis independent risk factors for postoperative complications. There were no significant differences in total bilirubin and albumin between the three groups of patients with different HBV-DNA levels ( P>0.05). Conclusion:Patients with HBV and hepatic alveolar echinococcoisis have worse liver function and are more prone to complications after surgical resection, but there is no significant difference in liver function among patients with different HBV-DNA levels.

Experimental study on the effect of radioactive 125I particles on alveolar echinococcosis / 中华肝胆外科杂志

Objective:To investigate the effect of 125I particles in alveolar echinococcosis with the animal model (nude mice and Sprague Dawley rats). Methods:Twenty 10 weeks nude mice with body weight ranged from 20 to 24 g were divided into three groups. Sixteen nude mice were divided into experimental group ( n=8), puncture group ( n=4) and model group ( n=4). There was no intervention in the model group and only particle puncture needle was used in the puncture group. 125I particles were implanted in the experimental group. 14 male Sprague Dawley rats without specific pathogen, with body weight 280-320 g, 12 weeks old, were used to construct the model of hepatic alveolar echinococcosis. Then the rats were divided into intervention group ( n=10) and control group ( n=4). In the intervention group, 125I particles were pushed into the lesions. The abdomen was only open and closed in the control group. All the mice were sacrificed 45 days after intervention. The tumor size was measured. The activity of protoscolex and pathological changes of Echinococcus multilocularis in each group were observed. Results:At the timepoint of 22nd, 30th and 40th day of intervention, the largest diameter of tumor in nude mice experimental group was (10.7±5.2) mm, (10.9±5.0) mm, (8.5±4.3) mm, smaller than that in puncture group (24.5±4.4) mm, (25.4±4.1) mm, (31.4±2.8) mm and model group (22.5±7.3) mm, (25.0±5.4) mm, (26.7±6.3) mm, with statistically significant difference ( P<0.05). The number and activity of protoscoleces in experimental group were lower than those in puncture group and model group. Under the light microscope, the structure of echinococcus vesiculae and its body in the experimental group was obviously destroyed, and the cuticle and germinal layer of echinococcus vesiculae in the puncture group and the model group were normal, with multiple intact protoscoleces. The pathological changes of Sprague Dawley rats in the intervention group and the control group were basically the same as those in the nude mice model. Conclusion:The 125I particle radiation effect can kill Echinococcus multilocularis protoscoleces and inhibit the growth of alveolar echinococcosis.

Efficacy and safety of ultrasound-guided percutaneous microwave ablation for the treatment of hepatic alveolar echinococcosis: A preliminary study.

The present study aims to assess the efficacy and safety of ultrasound-guided percutaneous microwave ablation (MWA) for hepatic alveolar echinococcosis (HAE) preliminarily.Seventeen patients diagnosed to HAE and treated with MWA (80 watts, 4 min) were retrospectively analyzed. The upper abdominal computed tomography (CT) was performed at 1, 6, 12 months after the MWA treatment. The complications were evaluated to assess the safety.The diameters of the lesions in the HAE patients ranged from 1.9 to 4.7 cm. The patients included 10 males and 7 females, aged 26 to 70 (45.82 ±â€Š13.36) years, 5 patients infecting with chronic hepatitis viral B and 8 patients with positive hydatid antibody (IgG). The lesions observed in the postoperative CT (1, 6, 12 months) were calcified compared with those observed in the preoperative CT and without relapse. No serious treatment-related complications occurred after treatment.MWA is a novel and effective therapeutic method for HAE with a single lesion (diameter≤=5 cm). Further studies based on prospective random control trials to confirm our findings are necessary.

Study on the correlation of related cytokines expression to invasion and metastasis of hepatic alveolar echinococcosis / 重庆医学

Objective To investigate the expression of osteopontin (OPN)and matrix metalloproteinase-2(MMP-2)in hepatic alveolar echinococcosis(HAE) ,and explore the role of OPN and MMP-2 in the invasion and metastasis of HAE infection .Methods Expression of OPN and MMP-2 in HAE tissues from 69 patients within12 nomral liver tissues .HAE were detected using SP im-munohistochemical technique ,the correlation between OPN and MMP-2 expression and clinieopahtologic features was analyzed .Re-sults OPN and MMP-2 mainly distributed in the cyst wall about granuloma inflammatory cells of HAE and and the peripheral por-tion of stromal cell and liver cells ,the positive expression rate in HAE focus and normal liver tissue at the juncti-on of the invasive margin the most obvious .The results showed that the positive rates of OPN and MMP-2 in HAE tissue were 72 .5% (50/69)and 59 .4% (41/69) ,respectively ,and in normal liver tissue were 16 .7% (2/12) and 8 .3% (1/12) ,respectively .The positive rates of OPN and MMP-2 in HAE were significantly higher than those in normal liver tissue(P<0 .01) .The positive rates of OPN and P21 in HAE tissues with metastasis were 86 .8% (33/38)and 76 .3% (29/38) ,respectively ,which were significantly higher than those without metastasis of OPN and MMP-2 positive expression rate of 54 .8% (17/31) and 38 .7% (12/31) ,(P<0 .01) .The positive expression of OPN and MMP-2 were not related to the size of tumor bulk ,HBsAg ,gender ,age and nation of tumor .Rank correlated analysis showed that OPN and MMP-2 were positive correlated(r=0 .36 ,P<0 .01) .Conclusion OPN and MMP-2 mainly distrib-utes in the cyst wall about granuloma inflammatory cells of HAE and and the peripheral portion of liver cells ,the positive expres-sion rate in HAE and normal liver tissue at the junction of the invasive margin the most obvious ,which might be invasion and me-tastasis of HAE .