ABSTRACT
Objective To explore the clinical efficacy and safety of low-intensity pulse ultrasound in the treatment of medial painful knee osteoarthritis.Methods A total of 10 patients with medial painful knee osteoar-thritis were collected and treated with low-intensity pulsed ultrasound.VAS visual analogue scores,WOMAC and Lysholm knee osteoarthritis rehabilitation scale scores were performed before treatment,immediately after treatment,1 week,2 weeks and 4 weeks after treatment.The efficacy and safety were compared before and after treatment.The ultrasound images before and after treatment were compared to verify its safety.Result VAS,WOMAC and Lysholm scores were statistically significant before and immediately after treatment,1 week and 2 weeks after treat-ment(P<0.05),but there was no statistically significant difference between them and 4 weeks after treatment(P>0.05).VAS decreased significantly before treatment,immediately after treatment,1 week after treatment and 2 weeks after treatment,and were(5.26±1.12),(2.76±0.92),(2.74±1.26),(3.42±0.93),respectively.The secondary outcome indicators of WOMAC and Lysholm were significantly changed before treatment,immediately after treatment,1 week after treatment and 2 weeks after treatment.They were(24.03±4.43)and(66.93±14.14),(12.75±1.63)and(79.86±10.82),(12.76±1.82)and(81.93±7.67),(15.17±2.73)and(77.08±9.73),respectively.No significant abnormality was found in the ultrasound images before and after treatment.Conclusion low-intensity pulsed ultrasound safely and effectively regulates the peripheral knee nerve in the treatment of painful knee osteoarthritis,providing a new idea for the intervention and treatment of clinical knee osteoarthritis.
ABSTRACT
italic>Atractylodes chinensis has important medicinal and economic values. In this study, the chloroplast genome sequences of four A. chinensis samples from different producing areas were sequenced using the Illumina platform. The specific DNA barcodes were screened and the germplasm resources of A. chinensis samples from different producing areas and the genetic diversity of the population were analyzed basing on the specific barcodes. The whole chloroplast genomes of the four A. chinensis samples had a typical cyclic tetrad structure, with 112 genes annotated. The comparative genomics results indicated that ccsA and trnC-GCA_petN were potential specific DNA barcodes for intraspecific identification of A. chinensis. Polymerase chain reaction (PCR) analysis of ccsA and trnC-GCA_petN was performed on 256 samples from 14 areas in 9 provinces, and the amplification efficiency was 100%. Sequence analysis showed that ccsA and trnC-GCA_petN had 11 and 22 variant positions, which could identify 16 and 22 haplotypes, respectively. The combined sequence analysis identified 39 haplotypes, named Hap1-Hap39, of which the most abundant and widely distributed genotype was Hap9. Haplotype diversity (Hd) = 0.896 and nucleotide diversity (Pi) = 0.002 22 indicated high genetic diversity at the species level in A. chinensis. The genetic distances of the haplotypes were 0.000 00-0.004 88, indicating that there were small genetic differences among the haplotypes. The results of phylogenetic tree analysis showed that 39 haplotypes had very close genetic relationship, and formed two obvious branches with other groups of the same genus except Atractylodes macrocephala. This study plays an important role in the identification of the origin of A. chinensis and the protection and breeding of germplasm resources.
ABSTRACT
Objective:To construct an artificial intelligence-assisted diagnosis system to recognize the characteristics of Helicobacter pylori ( HP) infection under endoscopy, and evaluate its performance in real clinical cases. Methods:A total of 1 033 cases who underwent 13C-urea breath test and gastroscopy in the Digestive Endoscopy Center of Renmin Hospital of Wuhan University from January 2020 to March 2021 were collected retrospectively. Patients with positive results of 13C-urea breath test (which were defined as HP infertion) were assigned to the case group ( n=485), and those with negative results to the control group ( n=548). Gastroscopic images of various mucosal features indicating HP positive and negative, as well as the gastroscopic images of HP positive and negative cases were randomly assigned to the training set, validation set and test set with at 8∶1∶1. An artificial intelligence-assisted diagnosis system for identifying HP infection was developed based on convolutional neural network (CNN) and long short-term memory network (LSTM). In the system, CNN can identify and extract mucosal features of endoscopic images of each patient, generate feature vectors, and then LSTM receives feature vectors to comprehensively judge HP infection status. The diagnostic performance of the system was evaluated by sensitivity, specificity, accuracy and area under receiver operating characteristic curve (AUC). Results:The diagnostic accuracy of this system for nodularity, atrophy, intestinal metaplasia, xanthoma, diffuse redness + spotty redness, mucosal swelling + enlarged fold + sticky mucus and HP negative features was 87.5% (14/16), 74.1% (83/112), 90.0% (45/50), 88.0% (22/25), 63.3% (38/60), 80.1% (238/297) and 85.7% (36 /42), respectively. The sensitivity, specificity, accuracy and AUC of the system for predicting HP infection was 89.6% (43/48), 61.8% (34/55), 74.8% (77/103), and 0.757, respectively. The diagnostic accuracy of the system was equivalent to that of endoscopist in diagnosing HP infection under white light (74.8% VS 72.1%, χ2=0.246, P=0.620). Conclusion:The system developed in this study shows noteworthy ability in evaluating HP status, and can be used to assist endoscopists to diagnose HP infection.
ABSTRACT
Objective:To construct a real-time artificial intelligence (AI)-assisted endoscepic diagnosis system based on YOLO v3 algorithm, and to evaluate its ability of detecting focal gastric lesions in gastroscopy.Methods:A total of 5 488 white light gastroscopic images (2 733 images with gastric focal lesions and 2 755 images without gastric focal lesions) from June to November 2019 and videos of 92 cases (288 168 clear stomach frames) from May to June 2020 at the Digestive Endoscopy Center of Renmin Hospital of Wuhan University were retrospectively collected for AI System test. A total of 3 997 prospective consecutive patients undergoing gastroscopy at the Digestive Endoscopy Center of Renmin Hospital of Wuhan University from July 6, 2020 to November 27, 2020 and May 6, 2021 to August 2, 2021 were enrolled to assess the clinical applicability of AI System. When AI System recognized an abnormal lesion, it marked the lesion with a blue box as a warning. The ability to identify focal gastric lesions and the frequency and causes of false positives and false negatives of AI System were statistically analyzed.Results:In the image test set, the accuracy, the sensitivity, the specificity, the positive predictive value and the negative predictive value of AI System were 92.3% (5 064/5 488), 95.0% (2 597/2 733), 89.5% (2 467/ 2 755), 90.0% (2 597/2 885) and 94.8% (2 467/2 603), respectively. In the video test set, the accuracy, the sensitivity, the specificity, the positive predictive value and the negative predictive value of AI System were 95.4% (274 792/288 168), 95.2% (109 727/115 287), 95.5% (165 065/172 881), 93.4% (109 727/117 543) and 96.7% (165 065/170 625), respectively. In clinical application, the detection rate of local gastric lesions by AI System was 93.0% (6 830/7 344). A total of 514 focal gastric lesions were missed by AI System. The main reasons were punctate erosions (48.8%, 251/514), diminutive xanthomas (22.8%, 117/514) and diminutive polyps (21.4%, 110/514). The mean number of false positives per gastroscopy was 2 (1, 4), most of which were due to normal mucosa folds (50.2%, 5 635/11 225), bubbles and mucus (35.0%, 3 928/11 225), and liquid deposited in the fundus (9.1%, 1 021/11 225).Conclusion:The application of AI System can increase the detection rate of focal gastric lesions.
ABSTRACT
Objective@#To analyze physical fitness and health status and gender differences of middle school students among 5 minorities (Mongolian, Hui, Uyghur, Zhuang and Korean), and to provide the theoretical basis for the strategy formulation.@*Methods@#The present data came from 3 waves of Chinese National Survey on Students Constitution and Health (2010, 2014, and 2019). According to National Standards for Students Physical Health (2014 Revision), excellent, and excellent good physical fitness and health status were defined. Cochran Armitage test was used to examine the trends of physical fitness and health status. Chi square test and Logistic regression were used to analyze the difference of physical fitness and health status by sex and survey year.@*Results@#From 2010 to 2019, the excellent physical fitness and health status rate of Mongolian, Hui, Uyghur, Zhuang and Korean students increased from 1.8%, 0.7%, 0.3%, 0.5% and 1.3% to 4.3%, 2.8%, 1.2%, 1.3% and 3.5%, respectively. The excellent good physical fitness and health status rate of Mongolian, Hui, Uyghur and Zhuang students increased from 12.9%, 8.0%, 7.2 % and 8.4% to 24.7%, 20.1%, 12.6% and 19.8%( Z =6.15,6.71,4.12,3.06,5.26;11.88,13.42,6.70,11.08, P <0.05), respectively. In 2019, students aged 13 to 15 years showed higher proportion of excellent/excellent good physical fitness and health status than that of students aged 16 to 18. Boys were more likely to be in excellent/excellent good physical fitness and health status than girls from 2010 to 2019. The sex difference in excellent/excellent good physical fitness and health status narrowed during 2010 and 2019.@*Conclusion@#Physical fitness and health status of minority students improved while sex difference narrowed during last decade, but there is still a long way to reach the goal proposed by China. Targeted intervention should be proposed to promote physical fitness and health status in accordance with the developmental characteristics, especially for girls and students aged 16 to 18 years.
ABSTRACT
Eleutherococcus senticosus is one of the Dao-di herbs in northeast China. In this study, the chloroplast genomes of three E. senticosus samples from different genuine producing areas were sequenced and then used for the screening of specific DNA barcodes. The germplasm resources and genetic diversity of E. senticosus were analyzed basing on the specific DNA barcodes. The chloroplast genomes of E. senticosus from different genuine producing areas showed the total length of 156 779-156 781 bp and a typical tetrad structure. Each of the chloroplast genomes carried 132 genes, including 87 protein-coding genes, 37 tRNAs, and 8 rRNAs. The chloroplast genomes were relatively conserved. Sequence analysis of the three chloroplast genomes indicated that atpI, ndhA, ycf1, atpB-rbcL, ndhF-rpl32, petA-psbJ, psbM-psbD, and rps16-psbK can be used as specific DNA barcodes of E. senticosus. In this study, we selected atpI and atpB-rbcL which were 700-800 bp and easy to be amplified for the identification of 184 E. senticosus samples from 13 genuine producing areas. The results demonstrated that 9 and 10 genotypes were identified based on atpI and atpB-rbcL sequences, respectively. Furthermore, the two barcodes identified 23 genotypes which were named H1-H23. The haplotype with the highest proportion and widest distribution was H10, followed by H2. The haplotype diversity and nucleotide diversity were 0.94 and 1.82×10~(-3), respectively, suggesting the high genetic diversity of E. senticosus. The results of the median-joining network analysis showed that the 23 genotypes could be classified into 4 categories. H2 was the oldest haplotype, and it served as the center of the network characterized by starlike radiation, which suggested that population expansion of E. senticosus occurred in the genuine producing areas. This study lays a foundation for the research on the genetic quality and chloroplast genetic engineering of E. senticosus and further research on the genetic mechanism of its population, providing new ideas for studying the genetic evolution of E. senticosus.
Subject(s)
DNA Barcoding, Taxonomic , Eleutherococcus/genetics , Base Sequence , Chloroplasts/genetics , Genetic Variation , PhylogenyABSTRACT
Scutellaria baicalensis is a commonly used Chinese medicinal herb. In this study, we identified the germplasm resources of commercial S. baicalensis samples based on trnH-psbA, petA-psbJ, and ycf4-cemA sequences according to the available chloroplast genome sequencing results, and measured the content of baicalin by HPLC. Through the above means we determined the best DNA barcode that can be used to detect the germplasm resources and evaluate the quality of commercial S. baicalensis samples. A total of 104 samples were collected from 24 provinces, from which DNA was extracted for PCR amplification. The amplification efficiencies of trnH-psbA, petA-psbJ, and ycf4-cemA sequences were 100%, 59.62%, and 25.96%, respectively. The results of sequence analysis showed that 5, 4, and 2 haplotypes were identified based on trnH-psbA, petA-psbJ, and ycf4-cemA sequences, respectively. However, the sequences of haplotypes in commercial samples were different from that of the wild type, and the joint analysis of three fragments of S. baicalensis only identified 6 haplotypes. Furthermore, the phylogenetic analysis and genetic distance analysis indicated that trnH-psbA could be used to identify S. baicalensis from adulterants. The above analysis showed that trnH-psbA was the best fragment for identifying the germplasm resources of commercial S. baicalensis samples. We then analyzed the haplotypes(THap1-THap5) of commercial S. baicalensis samples based on trnH-psbA and found that THap2 was the main circulating haplotype of the commercial samples, accounting for 86.55% of the total samples, which indicated the scarce germplasm resources of commercial S. baicalensis samples. The content of baicalin in all the collected commercial S. baicalensis samples exceeded the standard in Chinese Pharmacopoeia and had significant differences(maximum of 12.21%) among samples, suggesting that the quality of commercial S. baicalensis samples varied considerably. However, there was no significant difference in baicalin content between different provinces or between different haplotypes. This study facilitates the establishment of the standard identification system for S. baicalensis, and can guide the commercial circulation and reasonable medication of S. baicalensis.
Subject(s)
Chromatography, High Pressure Liquid , DNA Barcoding, Taxonomic/methods , DNA, Plant/genetics , Phylogeny , Scutellaria baicalensis/geneticsABSTRACT
Vaccination is an effective way to reduce the morbidity and mortality of infectious diseases. As a needle-free transcutaneous immunization (NF-TCI) vaccination technology, microneedles (MNs), composed of multiple micro-needles orderly attached to a substrate, can overcome the problems of low immune efficiency, poor compliance and waste of resources that exists in the conventional vaccination by injection, thus becoming a research hotspot in biomedicine. The microneedle vaccine can directly break through the stratum corneum barrier of the skin without touching nerves and blood vessels in the dermis, and effectively delivers the vaccine to the immune cells in the skin tissue to initiate the immune response of the body, thus triggering strong humoral and cellular immune processes. Vaccine delivery via the MNs system possesses the advantages of high safety, satisfying immune effect and practical economy, and shows great prospect in the prevention and treatment of infectious diseases and antineoplastic therapy. This article reviews the development background of MNs in transcutaneous immunization, the types of vaccine delivery, the factors affecting the immune effect, the problems to be solved and development direction in the future.
ABSTRACT
Objective: To analyze the Staphylococcal enterotoxins, Staphylococcal enterotoxin genes, drug resistance and molecular typing of 41 Staphylococcus aureus isolates from 2 food-borne illness outbreaks on 21 August and 27 September 2020 in Guangzhou. Methods: A total of 41 Staphylococcus aureus isolates from 2 outbreaks were analyzed by multilocus sequence typing (MLST) and spa typing. The Staphylococcal enterotoxins typing and the Staphylococcal enterotoxin genes of the isolates were analyzed by ELISA and PCR, respectively. The antimicrobial susceptibility of the isolates was performed by disc diffusion. 21 Staphylococcus aureus isolates were characterized using whole genome sequencing (WGS). Based on the whole genome single nucleotide polymorphism (SNP), the phylogenetic tree was constructed by Snippy. Results: 41 Staphylococcus aureus isolates were divided into 2 types by MLST and spa typing: ST6-t701 and ST7-t091. 2 ST7-t091 isolates were identified as methicillin-resistant Staphylococcus aureus (MRSA). 25 ST7-t091 isolates and 14 ST6-t701 isolates were methicillin-sensitive Staphylococcus aureus (MSSA), and were resistant to 7 and 6 antibiotics, respectively. All isolates were positive for sea by PCR. WGS revealed all 21 isolates carried scn, sak, sea, hla, hld, hlgA, hlgB, hlgC, lukD virulence genes. The results showed the isolates contained an immune evasion cluster type D which located in bacteriophage ϕSa3. The SNP phylogenetic tree showed 2 MRSA ST7-t091 were constituted a separate clade from the 12 MSSA ST7-t091 isolates and 7 ST6-t701 isolates showed high similarity to each other. Conclusion: Base on the results of phylogenetic analysis, the 2 food-borne illness outbreaks occurred on 21 August and 27 September 2020 are caused by the combination of the MRSA ST7-t091 strain and the MSSA ST7-t091 strain, and the MSSA ST6-t701 strain, respectively. All isolates have high level of antibiotic resistance and carry high virulent genes.
Subject(s)
Humans , Anti-Bacterial Agents/pharmacology , Disease Outbreaks , Foodborne Diseases/epidemiology , Methicillin-Resistant Staphylococcus aureus/genetics , Microbial Sensitivity Tests , Multilocus Sequence Typing/methods , Phylogeny , Staphylococcal Infections/epidemiology , Staphylococcus aureus/geneticsABSTRACT
Objective:To develop an accurate, specific and rapid and non-destructive technique for the identification of Candida auris and its relatives without destroying the cell wall. Methods:The study was conducted in Beijing Institute of Radiation Medicine in 2021. Surface-enhanced Raman spectroscopy (SERS) substrates were prepared by sodium citrate reduction. Through SERS, the collected SERS fingerprint spectra were analyzed by orthogonal partial least-squares-discrimination analysis (OPLS-DA) using SIMCA 14.1 (Umetrics, Sweden). Four strains of Candida auris, 4 strains of Candida heamulonii, 3 strains of Candida pseudohaemulonii and 4 strains of Candida duobushaemulonii were effectively identified and distinguished. Results:Within the 95% confidence interval, the sample analysis results presented an oval. The four Candida species detected in this study could be well separated. R2X(cum)=0.629, R2Y(cum)=0.947, Q2(cum)=0.915. R2X, R2Y and Q2 all>0.5 and closed to 1, suggesting that the model in this study was well established, and had good prediction ability. The results of the 10-fold-cross validation showed that the accuracy of both the model training data and test data are 100%, indicating that the model established in this research had good classification capabilities. Conclusions:This research has developed a new technique that can identify Candida auris and its relatives in a highly accuracy, specific and rapid way without destroying the cell wall. Being cost-effective and easy to operate, this technique has great potential to be applied in clinical fungal testing.
ABSTRACT
OBJECTIVES@#To investigate the changes in the rate and volume of mother's own milk (MOM) feeding for very low birth weight infants (VLBWIs) hospitalized during the prevention and control of the coronavirus disease 2019 (COVID-19) pandemic.@*METHODS@#A retrospective analysis was performed on the medical data of the VLBWIs with a gestational age of <32 weeks who were born and admitted to the Neonatal Intensive Care Unit of Nanjing Maternal and Child Health Hospital from January 2019 to December 2020. The changes in the rate and volume of MOM feeding for VLBWIs during hospitalization were examined.@*RESULTS@#A total of 301 VLBWIs were enrolled. According to the timing of COVID-19 outbreak, these infants were divided into a pre-CIVID-19 group with 205 VLBWIs and a post-COVID-19 group with 96 VLBWIs. Compared with the pre-CIVID-19 group, the post-COVID-19 group had a significantly lower rate of MOM feeding within 28 days after birth and during hospitalization (P<0.05), a significantly lower volume of MOM feeding within 0-7 days, 0-14 days, and 0-28 days after birth (P<0.05), and significantly higher incidence rates of moderate-to-severe bronchopulmonary dysplasia and feeding intolerance (P<0.05).@*CONCLUSIONS@#The COVID-19 pandemic has a significant impact on MOM feeding for VLBWIs, and there are significant reductions in the rate and volume of MOM feeding for VLBWIs within 28 days after birth, as well as a significant reduction in the rate of MOM feeding during hospitalization.
Subject(s)
Child , Female , Humans , Infant , Infant, Newborn , Breast Feeding , COVID-19 , Infant, Very Low Birth Weight , Pandemics , Retrospective StudiesABSTRACT
Flexible variable stiffness actuator is divided into four categories including elastic element, pneumatic element, electric-magnetic element and intelligent material. It is gradually applied in rehabilitation robot. It could adapt the change of patient's impedance in the upper and lower limb rehabilitation robots, ensure the safety of the wearer in the exoskeleton, and improve the biomimetics in the prosthesis. Variable stiffness driving mechanism for rehabilitation robot still has some disadvantages. It is proposed to have compact structure, low power consumption, good stiffness characteristics, high response rate and progressive output torque curve, etc.
ABSTRACT
Objective:To evaluate the effect of preoperative respiratory muscle exercise combined with intraoperative lung protective ventilation strategy on atelectasis in elderly patients undergoing robot-assisted radical prostatectomy.Methods:In the prospective study, a total of 45 patients aged 65-80 years undergoing scheduled robot-assisted radical prostatectomy in First Hospital of Shanxi Medical University from August 2020 to November 2020 were divided into three groups( N=15, each): respiratory muscle exercise combined with lung protective ventilation strategy group(combined group), lung protective ventilation strategy group(pulmonary protective group)and conventional ventilation strategy(control group). Heart rate, systolic blood pressure, diastolic pressure, and pulse oxygen saturation as well as blood gas analysis of arterial blood and the calculated oxygenation index were measured and recorded immediately after establishing invasive artery monitoring in operating room, 10 min after endotracheal intubation, 1 h after the flexitic position, 30 min after tracheal extubation, 24 h after operation in all three groups of patients.The lung compliance values, peak airway pressure, and end-tidal carbon dioxide were recorded at 10 minutes after tracheal intubation, 30 minutes after tracheal extubation, 1 hour after succession position.A single-slice chest CT scan was performed at 1 h after surgery while satisfying the anesthesia recovery steward score ≥ 5.And the percentage of atelectasis area was calculated. Results:The American Society of Anesthesiologisits(ASA)classification of patients was 11/4, 12/3, and 11/4 in the combination group, lung protection group and control group respectively, and the difference was not statistically significant( χ2=0.127, P>0.05). Oxygenation index(mmHg)(1 mmHg=0.133 kPa)at 24 h after surgery was significantly higher in the combined group(351.1±11.2)than in lung protection group(337.0±13.4)( t=3.287, P<0.05). Atelectasis area(Median, Interquartile range)assessed by CT imaging at 30 min after tracheal extubation was 1.92(0.77)% in the combination group, 2.09(1.13)% in lung protection group, and 3.01(1.01)% in control group, with statistically significant difference( χ2 values, 26.036, 12.313, both P<0.05). Atelectasis area at 30 minutes after tracheal extubation was statistically significant smaller in the combination group than in lung protection group( χ2=6.240, P<0.05). Conclusions:Preoperative respiratory muscle exercise combined with intraoperative lung protective ventilation strategy can achieve the better effect of lung protection, reduce the degree of perioperative atelectasis in elderly patients, and improve oxygenation function.
ABSTRACT
Objective:To evaluate deep learning in improving the diagnostic rate of adenomatous and non-adenomatous polyps.Methods:Non-magnifying narrow band imaging (NBI) polyp images obtained from Endoscopy Center of Renmin Hospital, Wuhan University were divided into three datasets. Dataset 1 (2 699 adenomatous and 1 846 non-adenomatous non-magnifying NBI polyp images from January 2018 to October 2020) was used for model training and validation of the diagnosis system. Dataset 2 (288 adenomatous and 210 non-adenomatous non-magnifying NBI polyp images from January 2018 to October 2020) was used to compare the accuracy of polyp classification between the system and endoscopists. At the same time, the accuracy of 4 trainees in polyp classification with and without the assistance of this system was compared. Dataset 3 (203 adenomatous and 141 non-adenomatous non-magnifying NBI polyp images from November 2020 to January 2021) was used to prospectively test the system.Results:The accuracy of the system in polyp classification was 90.16% (449/498) in dataset 2, superior to that of endoscopists. With the assistance of the system, the accuracy of colorectal polyp diagnosis was significantly improved. In the prospective study, the accuracy of the system was 89.53% (308/344).Conclusion:The colorectal polyp classification system based on deep learning can significantly improve the accuracy of trainees in polyp classification.
ABSTRACT
Objective:To preliminarily evaluate the feasibility of ultra-wide-angle fundus imaging (UWFI) to observe the Weiss ring (vitreous floats) and the effectiveness and safety of neodymium-doped yttrium aluminum garnet (Nd: YAG) laser ablation in the treatment of symptomatic Weiss ring.Methods:A retrospective clinical study. From March 2016 to December 2019, 80 eyes of 68 patients with symptomatic Weiss ring who were diagnosed and treated at Guangzhou Aier Eye Hospital were included in the study. Among them, there were 39 eyes in 32 males and 41 eyes in 36 females; the average age was 53.7±10.8 years old. All the affected eyes were examined by slit lamp microscope combined with 90 D front lens and UWFI. The position and shape of the vitreous floating objects by drawing pictures were recorded. All the affected eyes underwent Nd: YAG laser ablation treatment. Three months after treatment, a questionnaire survey was conducted on the patients to assess the improvement of subjective symptoms. Those with a total score of 10, 7-9, 3-6, and ≤2 points were defined as cured, significant improvement, partial improvement, and no improvement, respectively. The measurement software Gauge 1.0 was used to manually measure the long diameter, circumference and area of the vitreous float on the UWFI image. The diameter of the optic disc to 1 Unit (U) was set as a standardized reference value. Those who did not show UWFI and no floating objects were found on the front mirror were recorded as 0. The changes of vitreous floats before and after treatment were compared by Wilcoxon rank sum test; the changes in their size before and after treatment and the patients' subjective symptom improvement scores after treatment were analyzed by Spearman rank correlation.Results:After treatment, in 80 eyes, there were no vitreous floats in 59 eyes (73.8%, 59/80) on UWFI. Before treatment, the circumference of the vitreous float was 1.84 (1.07, 2.64) U, the long diameter was 1.17 (0.84, 1.66) U, and the area was 0.18 (0.08, 0.30) U2; after treatment, the circumference was 0.00 (0.00, 0.23) U, The long diameter is 0.00 (0.00, 0.23) U, and the area was 0.00 (0.00, 0.01) U2. There were statistically significant differences in the perimeter, diameter, and area of floating objects before and after treatment ( Z=-7.722, -7.560, -7.655; P<0.001). The results of the questionnaire survey showed that the patient's subjective symptoms were cured, significantly improved, and partially improved in 49 (61.3%, 49/80), 25 (31.2%, 25/80), and 6 (7.5%, 6/80) eyes, respectively. The results of correlation analysis showed that the degree of improvement of the patient's subjective symptoms was related to the circumference ( r=0.812), long diameter ( r=0.796), and area ( r=0.791) of the vitreous float on UWFI before and after treatment ( P<0.01). During the follow-up period, no complications such as increased intraocular pressure or decreased vision occurred. Conclusions:UWFI can objectively image the Weiss ring, and its size can be quantified relatively to the measurement software. Nd: YAG laser ablation treatment of symptomatic Weiss ring is safe and effective.
ABSTRACT
Objective:To construct an intelligent performance measurement system of gastrointestinal endoscopy and to analyze its value for endoscopic quality improvement.Methods:The intelligent gastrointestinal endoscopy performance measurement system was developed by using the deep convolutional neural network (DCNN) and deep reinforcement learning, based on the Digital Imaging and Communications in Medicine. Images were acquired of patients undergoing gastrointestinal endoscopy at Digestive Endoscopy Center of Renmin Hospital of Wuhan University from December 2016 to October 2018. The system applied cecum recognition model (DCNN1), images in vitro and in vivo recognition model (DCNN2), and identification model at 26 gastric sites (DCNN3) to monitor indices such as cecal intubation rate, colonoscopic withdrawal time, gastroscopic inspection time, and gastroscopic coverage. Images of 83 gastroscopies and 205 colonoscopies acquired at Digestive Endoscopy Center of Renmin Hospital of Wuhan University from March to November 2019 were randomly selected to examine the effectiveness of the system. Results:The intelligent gastrointestinal endoscopy performance measurement system consisted of quality analysis of both gastroscopy and colonoscopy, including all indices, and could be generated automatically at any time. The accuracy for cecal intubation rate, colonoscopic withdrawal time, gastroscopic inspection time, and gastroscopic coverage were 92.5% (172/186), 91.7% (188/205), 100.0% (83/83), 89.3% (1 928/2 158), respectively.Conclusion:The intelligent performance measurement system for gastrointestinal endoscopy can be recommended for the quality control of gastrointestinal endoscopy, from which endoscopists can get feedback and improve the quality of gastrointestinal endoscopy.
ABSTRACT
Objective:To explore the clinical value of a diagnostic system of ophthalmic B-scan ultrasound images based on deep convolutional neural network.Methods:A total of 3 600 ophthalmic B-scan ultrasound images of 1 278 patients with an average age of (49.32±7.69) years at the Eye Center of Renmin Hospital of Wuhan University from January 2018 to October 2020 were collected to build an image database.These B-scan images were labeled by three ophthalmologists.The database was divided into the training dataset of 2 812 images and the testing dataset of 788 images.The deep learning algorithm was used to build a diagnostic model, which can identify retinal detachment (RD), vitreous hemorrhage (VH) and posterior vitreous detachment (PVD), and the accuracy of the model was evaluated.Another 120 B-scan ultrasound images were collected for the human-computer comparison between the model and 3 senior ophthalmologists.Eight junior clinicians were selected to evaluate another 150 B-scan images with and without the assistance of the model, and the accuracy was analyzed to evaluate the effect of the model.This study adhered to the Declaration of Helsinki and the study protocol was approved by Renmin Hospital of Wuhan University (No.WDRY2020K-192).Results:The accuracy of the model for identifying normal fundus, RD, VH, PVD and other diseases were 0.954, 0.909, 0.881, 0.990 and 0.920, respectively.The accuracy of the model was similar to that of senior doctors, and the time the model used was almost half that of doctors.With the assistance of the model, the diagnostic accuracy of the 8 junior clinicians who participated in the training was significantly improved ( P<0.01). Conclusions:The accuracy of RD, VH and PVD identification of the intelligent evaluation system is good, and the system can improve the accuracy and efficiency of clinical examinations, and can better assist clinicians in clinical evaluation.
ABSTRACT
Objective:To construct a real-time monitoring system based on computer vision for monitoring withdrawal speed of colonoscopy and to validate its feasibility and performance.Methods:A total of 35 938 images and 63 videos of colonoscopy were collected in endoscopic database of Renmin Hospital of Wuhan University from May to October 2018. The images were divided into two datasets, one dataset included in vitro, in vivo and unqualified colonoscopy images, and another dataset included ileocecal and non-cecal area images. And then 3 594 and 2 000 images were selected respectively from the two datasets for testing the deep learning model, and the remaining images were used to train the model. Three colonoscopy videos were selected to evaluate the feasibility of real-time monitoring system, and 60 colonoscopy videos were used to evaluate its performance.Results:The accuracy rate of the deep learning model for classification for in vitro, in vivo, and unqualified colonoscopy images was 90.79% (897/988), 99.92% (1 300/1 301), and 99.08% (1 293/1 305), respectively, and the overall accuracy rate was 97.11% (3 490/3 594). The accuracy rate of identifying ileocecal and non-cecal area was 96.70% (967/1 000) and 94.90% (949/1 000), respectively, and the overall accuracy rate was 95.80% (1 916/2 000). In terms of feasibility evaluation, 3 colonoscopy videos data showed a linear relationship between the retraction speed and the image processing interval, which indicated that the real-time monitoring system automatically monitored the retraction speed during the colonoscopy withdrawal process. In terms of performance evaluation, the real-time monitoring system correctly predicted entry time and withdrawal time of all 60 examinations, and the results showed that the withdrawal speed and withdrawal time was significantly negative-related ( R=-0.661, P<0.001). The 95% confidence interval of withdrawal speed for the colonoscopy with withdrawal time of less than 5 min, 5-6 min, and more than 6 min was 43.90-49.74, 40.19-45.43, and 34.89-39.11 respectively. Therefore, 39.11 was set as the safe withdrawal speed and 45.43 as the alarm withdrawal speed. Conclusion:The real-time monitoring system we constructed can be used to monitor real-time withdrawal speed of colonoscopy and improve the quality of endoscopy.
ABSTRACT
Objective:To construct an artificial intelligence-assisted diagnosis system to detect gastric ulcer lesions and identify benign and malignant gastric ulcers automatically.Methods:A total of 1 885 endoscopy images were collected from November 2016 to April 2019 in the Digestive Endoscopy Center of Renmin Hospital of Wuhan University. Among them, 636 were normal images, 630 were with benign gastric ulcers, and 619 were with malignant gastric ulcers. A total of 1 735 images belonged to training data set and 150 images were used for validation. These images were input into the Res-net50 model based on the fastai framework, the Res-net50 model based on the Keras framework, and the VGG-16 model based on the Keras framework respectively. Three separate binary classification models of normal gastric mucosa and benign ulcers, normal gastric mucosa and malignant ulcers, and benign and malignant ulcers were constructed.Results:The VGG-16 model showed the best ability of classification. The accuracy of the validation set was 98.0%, 98.0% and 85.0%, respectively, for distinguishing normal gastric mucosa from benign ulcers, normal gastric mucosa from malignant ulcers, and benign ulcers from malignant ulcers.Conclusion:The artificial intelligence-assisted diagnosis system obtained in this study shows noteworthy ability of detection of ulcerous lesions, and is expected to be used in clinical to assist doctors to detect ulcer and identify benign and malignant ulcers.
ABSTRACT
Objective:To establish a deep convolutional neural network (DCNN) model based on YOLO and ResNet algorithm for automatic detection of colorectal polyps and to test its function.Methods:Colonoscopy images and videos collected from the database of Digestive Endoscopy Center of Renmin Hospital of Wuhan University from January 2018 to March 2019 were divided into three databases (database 1, 3, 4). The public database CVC-ClinicDB (composed of 612 polyp images extracted from 29 colonoscopy videos provided by Barcelona Hospital, Spain) was used as the database 2. Database 1 (4 700 colonoscopy images from January 2018 to November 2018, including 3 700 intestinal polyp images and 1 000 non-polyp images) was used for establishing training and verifying the DCNN model. Database 2 (CVC-ClinicDB) and database 3 (720 colonoscopy images from January 2019 to March 2019, including 320 intestinal polyp images and 400 non-polyp images) were used for testing the DCNN model on image detection. Database 4 (15 colonoscopy videos in December 2019, containing 33 polyps) was used for testing the DCNN model on video detection. The sensitivity, specificity, accuracy and false positive rate of the DCNN model for detecting intestinal polyps were calculated.Results:The sensitivity of the DCNN model for detecting intestinal polyps in database 2 was 93.19% (602/646). In database 3, the DCNN model showed the accuracy of 95.00% (684/720), sensitivity of 98.13% (314/320), specificity of 92.50% (370/400), and false positive rate of 7.50% (30/400) for detecting intestinal polyps. In database 4, the DCNN model achieved a per-polyp-sensitivity of 100.00% (33/33), a per-image-accuracy of 96.29% (133 840/138 998), a per-image-sensitivity of 90.24% (4 066/4 506), a per-image-specificity of 96.49% (129 774/134 492), and a per-image-false positive rate of 3.51% (4 718/134 492).Conclusion:The DCNN model constructed in the study has a high sensitivity and specificity for automatic detection of colorectal polyps both in the colonoscopy images and videos, has a low false positive rate in the videos, and has the potential to assist endoscopists in diagnosis of colorectal polyps.