Objective:To automatically segment diabetic retinal exudation features from deep learning color fundus images.Methods:An applied study. The method of this study is based on the U-shaped network model of the Indian Diabetic Retinopathy Image Dataset (IDRID) dataset, introduces deep residual convolution into the encoding and decoding stages, which can effectively extract seepage depth features, solve overfitting and feature interference problems, and improve the model's feature expression ability and lightweight performance. In addition, by introducing an improved context extraction module, the model can capture a wider range of feature information, enhance the perception ability of retinal lesions, and perform excellently in capturing small details and blurred edges. Finally, the introduction of convolutional triple attention mechanism allows the model to automatically learn feature weights, focus on important features, and extract useful information from multiple scales. Accuracy, recall, Dice coefficient, accuracy and sensitivity were used to evaluate the ability of the model to detect and segment the automatic retinal exudation features of diabetic patients in color fundus images.Results:After applying this method, the accuracy, recall, dice coefficient, accuracy and sensitivity of the improved model on the IDRID dataset reached 81.56%, 99.54%, 69.32%, 65.36% and 78.33%, respectively. Compared with the original model, the accuracy and Dice index of the improved model are increased by 2.35%, 3.35% respectively.Conclusion:The segmentation method based on U-shaped network can automatically detect and segment the retinal exudation features of fundus images of diabetic patients, which is of great significance for assisting doctors to diagnose diseases more accurately.

To summarize the nursing experience of a patient with large skin ulcers caused by EBV positive T/NK-cell lymphoproliferative diseases based on TIME Clinical-Decision-Support-Tool. The main points of nursing care were as follows: early identification of the cause of ulceration and active treatment of the underlying disease; accurate and continuous assessment of patients and their wounds; multidisciplinary consultation to ensure the integrity and comprehensiveness of diagnosis and treatment; active identification of obstacle factors and risk control; providing different dressing change programs according to different wound healing stages; evaluation of treatment effects at any time; timely pain management; improving the nutritional status of patients; providing health education and psychological nursing care. After 367 days of wound dressing, the patient′s wound was fully healed, and EBV-DNA was not detected in genetic examination after hematopoietic stem cell transplantation.

In order to provide basic information for the utilization and development of famous classical formulas containing Bletillae Rhizoma， this article systematically analyzes the historical evolution of the name， origin， harvesting and processing of Bletillae Rhizoma by reviewing the ancient materia medica， prescription books， medical books and modern literature. The research results showed that Baiji（白及） was the main name， some scholars took Baiji（白芨） as its main name， and there were many other names such as Baiji（白给）， Baigen（白根）， Baiji（白苙）. The mainstream source of Bletillae Rhizoma was the tubers of Bletilla striata， and drying， large， white， solid， root-free and skin removed completely were the good quality standards. With the promotion of wild to cultivated medicinal materials， there were certain differences between their traits， and the quality evaluation indexes should be adjusted accordingly. The origin of records in the past dynasties was widely distributed， with Guizhou and Sichuan having high production and good quality in modern times. The harvesting period is mostly in spring and autumn， and harvested in autumn was better. The processing and processing technology is relatively simple， and it was used fresh or powdered in past dynasties， while it is mainly sliced for raw use in modern times. Based on the results， it is suggested that the tubers of Bletilla striata of Orchidaceae should be used in the famous classical formulas， and it should be uniformly written as Baiji（白及）. And if the original formula indicates the requirement of processing， it should be operated according to the requirement， if the requirement of processing is not indicated， it can be used in raw form as medicine.

Objective To evaluate the safety and effectiveness of excessive dynamic airway collapse(EDAC)treated by laser.Methods 13 patients with EDAC confirmed by bronchoscopy from January 2018 to August 2022 were selected and divided into a simple EDAC group(6 cases)and an EDAC combined with tracheobronchomalacia(TBM)group(7 cases)based on whether they were combined with TBM.All patients underwent laser tracheobronchoplasty under bronchoscope.Symptoms,airway collapse,oxygenation index,modified version of British Medical Research Council dyspnoea scale(mMRC)and 6 min walking test before and after treatment were compared to evaluate the therapeutic effect.Results 13 patients underwent 17 times of laser tracheobronchoplasty with laser power of 8～15 W,and 4 patients underwent 2 times of laser tracheobronchoplasty.After treatment,the clinical symptoms of cough,sputum,shortness of breath and dyspnea were improved in all patients.1 week post-treatment,the EDAC group showed a significant improvement in airway lumen stenosis,with a significant statistical difference(P<0.05),1 month post-treatment,enhancements were observed in airway stenosis,oxygenation index,FEV1%,6-minute walk test,and mMRC,which remained stable over a 6 month follow-up.In the EDAC + TBM group,significant enhancements in airway stenosis,oxygenation index,and mMRC were noted 1 week post-treatment,with statistical significance(P<0.05).Between 8 d～6 months post-treatment,some patients exhibited a recurrence of airway stenosis,necessitating comprehensive interventions like balloon dilation,cryotherapy,and stent insertion.Local necrosis and granuloma occurred in some patients after laser therapy,and no serious complications associated with laser intervention were found in all patients.Conclusion Laser tracheobronchoplasty is a safe and effective technique for the treatment of EDAC.For patients with EDAC alone,the therapeutic effect is good,but for patients with EDAC combined with TBM,the long-term effect is not good.

Objective To observe the value of quality control system based on artificial intelligence(AI)for improving imaging quality of chest CT.Methods Totally 1 726 CT images obtained from 415 patients were retrospectively collected,among which 1 414 images were used for convolutional neural network(CNN)training and the rest 312 images were used for validation.Precision,Recall,F1-Score,mean average precision(mAP)and intersection over union(IOU)of quality control system based on AI for chest CT scanning were calculated.Meanwhile,21 patients with unsatisfactory chest CT who would undergo re-examination were prospectively enrolled,and chest CT scanning with quality control system based on AI were performed.The results of 2 examinations were compared.Results Precision,Recall,F1-Score,mAP and IOU of quality control system based on AI for chest CT were all good.All 21 cases were diagnosed correctly with re-examination CT based on quality control system.Among 21 cases,the first CT misdiagnosed 19 cases,the displaying of the area,volume and display quality of pulmonary nodules were not significantly different,but the morphology,boundaries,spiny protrusions,vacuolar signs,inflatable bronchial signs of nodules as well as the thickened and twisted blood vessels were obviously different between 2 times examination.The first CT missed 1 case while correctly diagnosed 1 case.Conclusion The quality control system based on AI was helpful for improving imaging quality of chest CT and increasing diagnostic efficacy.

Objective To investigate the application effects of different myocardial protective solutions in total thoracoscopic minimally invasive aortic valve replacement surgery.Methods The clinical data of 72 patients with total thoracoscopic minimally invasive aortic valve replacement surgery in this hospital from May 2020 to January 2024 were analyzed retrospectively.The patients were divided into the St Thomas cardioplegia group(STH group,n=13),del Nido cardioplegia group(DN group,n=24),histidine tryptophan ketoglutar-ate solution group(HTK group,n=35)according to the different myocardial protective solutions.The levels of lactate(Lac)before and during surgery,the highest levels of myocardial creatine kinase isoenzyme(CK-MB),high-sensitivity troponin T(TnT)and creatinine(Cr)before operation,on the operative day and after surgery as well as the duration of extracorporeal circulation,aortic cross-clamping time,maximum flow rate,minimum bladder temperature,cardioplegia perfusion times,number of defibrillation after aortic de-clamping,postoperative ventilator assisted time,ICU stay duration and postoperative hospitalization duration were com-pared among the three groups.Results Except for 1 case of HTK was discharged automatically after surgery,the other 71 cases recovered and discharged according to the doctor's advice.There were no statistically signif-icant differences in the age,body weight,extracorporeal circulation time,aortic blocking time,maximum flow volume of extracorporeal circulation,minimum bladder temperature of extracorporeal circulation,Lac before extracorporeal circulation,highest Lac during extracorporeal circulation,assistant time of postoperative venti-lator,ICU stay duration,postoperative hospitalization duration,serum Cr before operation,Cr on operative day,preoperative TnT,postoperative TnT on operative day,postoperative highest TnT,preoperative CK-MB,postoperative CK-MB on operative day and postoperative highest CK-MB among the three groups(P＞0.05).There were statistically significant differences in the defibrillation ratio after aortic de-clamping and perfusion frequency of myocardial protective solution(P＜0.05).There was statistically significant difference in the perfusion frequency of myocardial protective solution in pairwise comparison among groups(P＜0.05),and the defibrillation ratio after aortic de-clamping had statistical difference between the DN group and HTK group(P＜0.05).Conclusion DN,STH and HTK all have good myocardial protective effect in total thoraco-scopic minimally invasive aortic valve surgery.HTK has the advantages of less perfusion times and decreasing the operative procedures compared with DN and STH;DN has the advantage of lower use for electrical defib-rillation correcting arrhythmias after aortic opening over HTK.

Objective:To compare and analyze the clinical efficacy of laparoscopic microwave ablation and laparoscopic hepatectomy in the treatment of hepatic hemangioma.Methods:The clinical data of 98 patients with hepatic hemangioma admitted to the Hepatobiliary Center, the First Affiliated Hospital of Nanjing Medical University from June 2019 to June 2023 were retrospectively analyzed, including 20 males and 78 females, aged 24-69 years. According to the surgical method, they were divided into two groups: laparoscopic microwave ablation group (ablation group) with 34 cases, and laparoscopic hepatectomy group (resection group) with 64 cases. The differences in intraoperative and postoperative recovery related indicators, follow-up and prognosis between the two groups were compared and analyzed.Results:The operative time and blood loss in the ablation group were (90.6±21.8) min and (60.3±40.8) ml, respectively, which were lower than those in the resection group (128.7±30.0) min and (165.8±212.7) ml, and the differences were statistically significant ( t=-6.54, -2.86, P<0.001, P=0.005). There were 5 cases (14.71%) of residual lesions in the ablation group and none in the resection group, with a significant difference between the two groups ( χ2=0.01, P=0.003). The ablation group was superior to the resection group in hospital stay, drainage tube removal time and postoperative pain, with statistical significance (all P<0.05). On the 1st and 3rd day after surgery, the levels of alanine aminotransferase, aspartate aminotransferase, total bilirubin and direct bilirubin in ablation group were lower than those in resection group, and the differences were statistically significant (all P<0.05). In the ablation group, there were 14 cases of hemoglobinuria (41.2%), 2 cases of abdominal hemorrhage (5.9%), 0 cases of bile leakage and 6 cases of pleural effusion (17.7%), while in the resection group, these complications were 2 cases (3.1%), 18 cases (28.1%), 11 cases (17.2%) and 32 cases (50.0%), respectively, and there were statistical significance between the two groups (all P<0.05). In terms of prognosis, there was both one recurrence in each group (2.9% vs. 1.6%), with no significant difference ( χ2=1.00, P=0.653). Conclusion:Compared with laparoscopic hepatectomy, laparoscopic microwave ablation has obvious advantages in terms of operation time, intraoperative blood loss, hospital stay, postoperative pain and complications.

Objective:To investigate the risk factor of hepatocellular carcinoma (HCC) with vessels encapsulating tumor clusters (VETC) and the application value of its risk scoring model.Methods:The retrospective cross-sectional study was conducted. The clinicopathological data of 149 patients with HCC who were admitted to two medical centers, including 97 cases in the Jiangnan University Medical Center and 52 cases in the Affiliated Xingtai People′s Hospital of Hebei Medical University, from January 2017 to April 2020 were collected. There were 116 males and 33 females, aged (58±12)years. There were 74 cases with VETC and 75 cases without VETC. Observation indica-tors: (1) clinical characteristics of patients with and without VETC; (2) imaging features of patients with and without VETC; (3) multivariable analysis of HCC patients with VETC; (4) construction of VETC related risk scoring model and its performance evaluation; (5) postoperative early tumor recurrence of patients with and without VETC who were confirmed by risk scoring model and histopathological examination. Measurement data with normal distribution were represented as Mean± SD, and comparison between groups was conducted using the t test. Count data were described as absolutes, and comparison between groups was conducted using the chi-square test and continuous correction chi-square test. Variables of clinical and imaging characteristics with statistically signifi-cant were included in the multivariate analysis. Multivariate analysis was conducted using the Logistic regression model of backward stepwise selection. VETC related risk scoring model was constructed based on the results of Logistic regression model. The receiver operating characteristic (ROC) curve was drawn, and the area under curve (AUC), the sensitivity, specificity, accuracy and their 95% confidence interval ( CI) were calculated. The maximizing Youden index was the optimal cutoff value for VETC prediction. The Hosmer Lemeshow goodness of fit test was used to assess the consistency between VETC risk scoring model predicted VTEC status and the true VETC status. The Kaplan-Meier method was used to calculate survival rates and draw survival curves. The Log-rank test was used for survival analysis. Results:(1) Clinical characteristics of patients with and without VETC. Cases with postoperative albumin <36 g/L were 57 in patients with VETC, versus 68 in patients without VETC, respectively, showing a significant difference between them ( χ2=5.13, P<0.05). (2) Imaging features of patients with and without VETC. Cases with lesion imaging presence as nonperipheral washout, cases with lesion imaging presence as mosaic architecture, cases with lesion imaging presence as intratumoral hemorrhage, cases with lesion imaging presence as corona enhancement, cases with lesion imaging presence as non-smooth tumor margin, cases with lesion imaging presence as peritumoral enhancement in arterial phase, cases with lesion imaging presence as intratumoral arteries, cases with lesion imaging presence as peritumoral hypointensity in hepatobiliary phase, cases with lesion imaging enhancement type as uniform low enhancement, uniform high enhance-ment, heterogeneous enhancement with septations and heterogeneous enhancement with irregular ring-like structures, cases with intratumoral necrosis or ischemic, cases with tumor diameter >5 cm were 73, 35, 33, 15, 39, 28, 42, 27, 4, 5, 27, 38, 45, 46 in patients with VETC, versus 64, 16, 13, 3, 19, 15, 9, 13, 9, 35, 5, 26, 10, 10 in patients without VETC, respectively, showing significant differences in the above indicators between them ( χ2=8.92, 11.15, 12.97, 9.28, 11.74, 5.77, 33.14, 6.96, 41.79, 36.05, 37.86, P<0.05). (3) Multivariable analysis of patients with VETC. Results of multivariable analysis showed that lesion imaging enhancement as heterogeneous enhancement with septations, lesion imaging enhancement as heterogeneous enhancement with irregular ring-like structures, intratumoral necrosis or ischemia and tumor diameter >5 cm were independent risk factors influen-cing patients with VETC ( odds ratio=4.18, 7.62, 4.23, 4.08, 95% CI as 1.60?11.60, 2.00?31.70, 1.71?10.90, 1.60?10.80), P<0.05). (4) Construction of VETC related risk scoring model and its performance evaluation. The VETC related risk scoring model was constructed as (heterogeneous enhancement with septations, presence: 1.0, absence: 0)+(heterogeneous enhancement with irregular ring-like structures, presence: 1.5, absence: 0)+(intratumoral necrosis or ischemia, presence: 1.0, absence: 0)+(main tumor diameter >5 cm, presence: 1.0, absence: 0). The AUC, sensitivity, specificity, and accuracy of VETC related risk scoring model were 0.86 (95% CI as 0.80?0.92), 79.7% (95% CI as 69.2%?87.3%), 80.0% (95% CI as 69.6%?87.5%) and 79.9% (95% CI as 72.7%?85.5%), respectively. Results of Hosmer-Lemeshow goodness of fit test showed a good consistency between VETC risk scoring model predicted VETC status and true VETC status ( P>0.05). (5) Postoperative early tumor recurrence of patients with and without VETC who were confirmed by risk scoring model and histopathological examination. All 149 patients were followed up for 29(range, 26?35)months. The time to tumor recurrence and 2-year cumulative tumor recurrence rate of 149 patients were 29(range, 24?33)months and 43.0%, respectively. The 2-year tumor cumulative recurrence rate of patients with and without VETC predicted by risk scoring model was 47.8% and 37.9%, respectively, showing a significant difference between ( χ2=3.90, P<0.05). The 2-year cumulative tumor recurrence rate of patients with and without VETC confirmed by postoperative histopathological examination was 47.4% and 38.1%, respectively, showing a significant difference between ( χ2=4.20, P<0.05). Conclusions:Lesion imaging enhancement as heterogeneous enhancement with septations or irregular ring-like structures, intratumoral necrosis or ischemia and tumor diameter >5 cm are independent risk factors influen-cing HCC patients with VETC. The proposed risk scoring model based on those three risk factors achieves an optimal preoperative diagnostic performance.

Objective:To investigate the value of the extrahepatic bile duct and main pancreatic duct segment patterns on magnetic resonance cholangiopancreatography (MRCP) for differentiating the periampullary carcinoma (PAC).Methods:The clinicopathologic data of 125 patients with PAC who were admitted to Wuxi No.2 People’s Hospital from June 2013 to December 2021 were retrospectively analyzed, including 72 males and 53 females, aged (64.9±8.6) years. According to its anatomy, the extrahepatic bile duct (B) was divided into suprapancreatic and intrapancreatic (including ampullary) segments, and the main pancreatic duct (P) was divided into tail-body and head segments. MRCP patterns: i. the extrahepatic bile duct or main pancreatic duct visible without dilatation, ii. cutoff of the distal extrahepatic bile duct or main pancreatic duct with upstream dilatation, iii. cutoff of the intrapancreatic or head segment with upstream dilatation and remnant intrapancreatic or head segments invisible, iv. cutoff of the intrapancreatic or head segment with upstream dilatation and nondilated remnant intrapancreatic or head segments, were represented as 0, 1, 2, and 3, respectively. Segment patterns of B1/P0+ B1/P1, B0/P2+ B0/P3+ B2/P2+ B2/P3+ B3/P3, B3/P0, and B0/P0+ B2/P0 on MRCP were compared in PAC patients.Results:Of the 125 patients, there were 57 (45.6%) with pancreatic head carcinoma, 36 (28.8%) with ampullary carcinoma, 20 (16.0%) with distal cholangiocarcinoma, and 12 (9.6%) with periampullary duodenal carcinoma. Segment patterns of B0/P2+ B0/P3+ B2/P2+ B2/P3+ B3/P3 were found in 52 patients with pancreatic head carcinoma (91.2%, 52/57), with a significant difference between PAC (χ 2=110.66, P<0.001). Segment patterns of B1/P0+ B1/P1were found in 36 patients with ampullary carcinoma (100.0%, 36/36), fallowed by 11 (91.7%, 11/12) with periampullary duodenal carcinoma, with a significant difference between PAC (χ 2=129.95, P<0.001). Segment pattern of B3/P0 presented in 16 patients with distal cholangiocarcinoma (80.0%, 16/20), with a significant difference between PAC (χ 2=62.45, P<0.001). The segment patterns of B0/P0+ B2/P0 were only seen in 3 of 57(5.3%) patients with pancreatic head carcinoma. Conclusion:On MRCP, cutoff of the head segment with upstream dilatation and remnant head segment invisible or nondilated indicates the pancreatic head carcinoma. Cutoff of the intrapancreatic segment with upstream dilatation, remnant intrapancreatic segment visible, and main pancreatic duct nondilated, indicates the distal cholangiocarcinoma. And cutoff of the distal extrahepatic segment with upstream dilatation and main pancreatic duct dilatation or not, indicates the ampullary or periampullary duodenal carcinoma.

Objective:To observe the influence of NOD-like receptor thermal protein domain associated protein 6 (NLRP6) on hepatic ischemia-reperfusion injury (IRI), and elucidate the related mechanism.Methods:Thirty C57BL/6 mice with body weight of (18.80±1.99) g, were divided randomly into 5 groups, with 6 mice in each group: the mice that experienced only exploratory laparotomy were Sham group; that only underwent an operation to establish a hepatic IRI model were IRI group; that were treated with tail intravenous injection of clodronate (Clo) liposomes before the establishment of hepatic IRI model were Clo group; that received tail intravenous injection of clodronate liposomes and transfusion of bone marrow derived macrophages (BMDM) before the operation were Clo+ BMDM group; that received preoperative tail intravenous injection of clodronate liposomes and transfusion of BMDM with NLRP6 knockdown were Clo+ NLRP6-knockdown group. Real time quantitative polymerase chain reaction analysis (RT-PCR) and Western blot were performed to analyze the expressions of pyroptosis related proteins and factors. Simulate a hypoxia/reoxygenation (H/R) model in vitro, and set up experimental groups: lipopolysaccharide (LPS) + adenosine triphosphate (ATP), LPS+ ATP+ NLRP6-knockdown, H/R, and H/R+ NLRP6-knockdown. The changes of expressions of pyroptosis related proteins and factors were detected by RT-PCR and Western blot. Expression of NF-κB in vivo and in vitro was measured.Results:Compared with those in Sham group, protein expressions of NLRP6, NLRP3, Caspase-1, gasdermin D (GSDMD), IL-1β and IL-18 were remarkably increased in IRI group, but the levels of these proteins were dramatically decreased in Clo group with the exhaustion of macrophages in comparison with in IRI group, which were significantly different statistically (all P<0.05). The levels of these proteins were enhanced again in Clo+ BMDM group with the reconstruction of macrophages in contrast to those in Clo group, while the enhancements were more obvious in Clo+ NLRP6-knockdown group comparing to those in Clo+ BMDM group, with significant differences (all P<0.05). In vitro, pyroptosis rate for LPS+ ATP group was (16.39±1.06)%, which was lower than (27.34±2.79)% for LPS+ ATP+ NLRP6-knockdown group, with a statistical significance ( P<0.05). Meanwhile, pyroptosis rate for H/R group was (20.59±5.66)%, also much more reduced than (37.76±2.00)% for H/R+ NLRP6-knockdown group ( P<0.05). Expressions of NLRP3, Caspase-1, GSDMD, IL-1β, IL-18 and NF-κB p65 in LPS+ ATP+ NLRP6-knockdown group were more elevated than in LPS+ ATP group, and these indices were also more enhanced in H/R+ NLRP6-knockdown group than which in H/R group. Compared to the Sham group, expression of NF-κB p65 significantly increased in IRI group, which was reversed in Clo group, but enhanced again in Clo+ BMDM group and reached a peak in Clo+ NLRP6-knockdown group. Conclusions:Macrophage plays a critical role in immune response to hepatic IRI, wherein NLRP6 functions specifically. NLRP6 acts to suppress inflammation during hepatic IRI through regulating macrophage pyroptosis via inhibiting NF-κB.