Automated detection and segmentation of pleural effusion on ultrasound images using an Attention U-net.

BACKGROUND: Ultrasonic for detecting and evaluating pleural effusion is an essential part of the Extended Focused Assessment with Sonography in Trauma (E-FAST) in emergencies. Our study aimed to develop an Artificial Intelligence (AI) diagnostic model that automatically identifies and segments pleural effusion areas on ultrasonography. METHODS: An Attention U-net and a U-net model were used to detect and segment pleural effusion on ultrasound images of 848 subjects through fully supervised learning. Sensitivity, specificity, precision, accuracy, F1 score, the receiver operating characteristic (ROC) curve, and the area under the curve (AUC) were used to assess the model's effectiveness in classifying the data. The dice coefficient was used to evaluate the segmentation performance of the model. RESULTS: In 10 random tests, the Attention U-net and U-net 's average sensitivity of 97% demonstrated that the pleural effusion was well detectable. The Attention U-net performed better at identifying negative images than the U-net, which had an average specificity of 91% compared to 86% for the U-net. Additionally, the Attention U-net was more accurate in predicting the pleural effusion region because its average dice coefficient was 0.86 as opposed to the U-net's average dice coefficient of 0.82. CONCLUSIONS: The Attention U-net showed excellent performance in detecting and segmenting pleural effusion on ultrasonic images, which is expected to enhance the operation and application of E-FAST in clinical work.

Role of env gene and LTR sequence in the pathogenesis of subgroup K avian leukosis virus.

Avian leukosis virus (ALV) is a retrovirus that induces tumours in infected birds; ALV is divided into different subgroups according to the env gene and cellular tropism. In general, ALV subgroup J (ALV-J) is considered to be the most pathogenic and prevalent subgroup while subgroup K (ALV-K), a newly identified subgroup, only causes mild symptoms. To illuminate the roles of the env viral gene and LTR sequence in pathogenic differences between ALV-J and ALV-K, rescued ALV-J strain rSDAU1005, rescued ALV-K strain rJS11C1, and recombinant strains rENV(J)-LTR(K) and rENV(K)-LTR(J) were characterized and investigated in this study. Among rescued viruses, rSDAU1005 had the highest replication efficiency while rJS11C1 replicated the slowest (replication efficiency rankings were rSDAU1005 >rENV(K)-LTR(J)>rENV(J)-LTR(K)>rJS11 C1). The luciferase reporter gene assay results showed that the promoter activity of ALV-K LTR was lower than that of the ALV-J LTR promoter, which may have accounted for the slower replication efficiency of ALV-K. Pathogenicity of the four rescued viruses was determined via inoculating the yolk sacs of specific-pathogen-free chickens. The results demonstrated that all four viruses were pathogenic; rSDAU1005 caused the most severe growth retardation and immunosuppression. rENV(J)-LTR(K) was more pathogenic when compared to rENV(K)-LTR(J), indicating that env and the LTR sequence play important roles in pathogenicity between ALV-K and ALV-J. Additionally, env seemed to especially play a role in ALV-K pathogenesis. This study provided scientific data and insight to improve detection methods and judgement criteria in ALV clearance and surveillance.

Deep learning for emergency ascites diagnosis using ultrasonography images.

PURPOSE: The detection of abdominal free fluid or hemoperitoneum can provide critical information for clinical diagnosis and treatment, particularly in emergencies. This study investigates the use of deep learning (DL) for identifying peritoneal free fluid in ultrasonography (US) images of the abdominal cavity, which can help inexperienced physicians or non-professional people in diagnosis. It focuses specifically on first-response scenarios involving focused assessment with sonography for trauma (FAST) technique. METHODS: A total of 2985 US images were collected from ascites patients treated from 1 January 2016 to 31 December 2017 at the Shenzhen Second People's Hospital. The data were categorized as Ascites-1, Ascites-2, or Ascites-3, based on the surrounding anatomy. A uniform standard for regions of interest (ROIs) and the lack of obstruction from acoustic shadow was used to classify positive samples. These images were then divided into training (90%) and test (10%) datasets to evaluate the performance of a U-net model, utilizing an encoder-decoder architecture and contracting and expansive paths, developed as part of the study. RESULTS: Test results produced sensitivity and specificity values of 94.38% and 68.13%, respectively, in the diagnosis of Ascites-1 US images, with an average Dice coefficient of 0.65 (standard deviation [SD] = 0.21). Similarly, the sensitivity and specificity for Ascites-2 were 97.12% and 86.33%, respectively, with an average Dice coefficient of 0.79 (SD = 0.14). The accuracy and area under the curve (AUC) were 81.25% and 0.76 for Ascites-1 and 91.73% and 0.91 for Ascites-2. CONCLUSION: The results produced by the U-net demonstrate the viability of DL for automated ascites diagnosis. This suggests the proposed technique could be highly valuable for improving FAST-based preliminary diagnoses, particularly in emergency scenarios.

Ultrasound-Guided Lauromacrogol Injection for the Treatment of Active Bleeding After Renal Biopsy.

Background: This study aimed to describe the technique and outcomes of hemostasis for ultrasound-guided lauromacrogol injection for active bleeding after renal biopsy. Methods: Data from patients with active bleeding after renal biopsy between January 2018 and December 2020 were retrospectively collected. Patients who still had active bleeding after 30 min of compression were then injected with lauromacrogol under ultrasound guidance. The patient's symptoms before and after operation were collected to assess whether they had severe complications. Changes in hemoglobin and serum creatinine values were collected. Results: Data from a total of 15 patients with active bleeding after renal biopsy were collected, including data of 6 men and 9 women. After the operation, there were 11 cases of mild back pain; 1 case of chills, cold sweats, and back pain; 1 case of cold sweats and blood pressure reduction, and 2 cases with no obvious symptoms. No severe complications occurred in this study, and active bleeding was stopped in all patients. After the operation, compared with before the operation, there was no statistically significant difference in the hemoglobin value and serum creatinine value (p = 0.10 > 0.05, p = 0.78 > 0.05). Conclusion: Ultrasound-guided lauromacrogol injection is a relatively simple, safe and feasible method, which could be helpful in treating active bleeding in the immediate post-procedure period after renal biopsy.

Complete Genome Sequence of Genotype Psittacine Beak and Feather Disease Virus, a Strain Identified from Budgerigars in China.

Psittacine beak and feather disease virus (PBFDV) has been reported in many countries, such as Australia, Poland, the United States, South Africa, etc. In this study, the complete genome of a PBFDV isolate was determined and characterized from budgerigars in China.