Objective:To explore the clinical application value of convolutional neural network（CNN）based on deep learning in the automatic measurement of dynamic pelvic floor ultrasound video parameters and the diagnosis and classification of cystocele.Methods:A retrospective analysis was conducted on dynamic pelvic floor ultrasound videos from 398 postpartum women who underwent examinations at the First People's Hospital of Foshan between June 2020 and June 2022. The lowest point of the posterior bladder wall（PWB），urethral rotation angle（URA），and retrovesical angle（RVA）were manually measured by a senior radiologist（R1）and a junior radiologist（R2），and cystocele was classified according to the Green standard. The CNN model was employed to automatically extract the above parameters and to diagnose and classify cystocele. Using R1 measurements as a reference，intraclass correlation coefficient（ICC）was used to evaluate the consistency between the CNN model and R1，as well as between R2 and R1. The Kappa value was used to assess the agreement between the CNN model，R2，and R1 in the diagnosis and classification of cystocele. Additionally，the time consumption of the three measurement methods was compared.Results:The CNN model showed good consistency with R1 in measuring PWB and URA（ICC = 0.983，0.894），while its consistency in measuring RVA was moderate（ICC = 0.614）. The ICC between R2 and R1 in measuring PWB，URA，and RVA was 0.979，0.815，and 0.627，respectively. In the measurement of PWB and URA，the consistency between the CNN model and R1 was superior to that between R2 and R1. For cystocele diagnosis，the Kappa value between the CNN model and R1 was 0.924，which was higher than that between R2 and R1（0.904）. In cystocele classification，the Kappa value between the CNN model and R1 was 0.503，also higher than that between R2 and R1（0.426）. The CNN model processed a single video in 2.5（0.6）s，significantly faster than R1［59.9（16.9）s］and R2［56.8（11.2）s］（all P < 0.001）. Conclusions:The CNN model demonstrates high accuracy and efficiency in the measurement，diagnosis，and classification of cystocele，outperforming a junior radiologist and showing potential for clinical application.

Objective:To explore the clinical application value of convolutional neural network（CNN）based on deep learning in the automatic measurement of dynamic pelvic floor ultrasound video parameters and the diagnosis and classification of cystocele.Methods:A retrospective analysis was conducted on dynamic pelvic floor ultrasound videos from 398 postpartum women who underwent examinations at the First People's Hospital of Foshan between June 2020 and June 2022. The lowest point of the posterior bladder wall（PWB），urethral rotation angle（URA），and retrovesical angle（RVA）were manually measured by a senior radiologist（R1）and a junior radiologist（R2），and cystocele was classified according to the Green standard. The CNN model was employed to automatically extract the above parameters and to diagnose and classify cystocele. Using R1 measurements as a reference，intraclass correlation coefficient（ICC）was used to evaluate the consistency between the CNN model and R1，as well as between R2 and R1. The Kappa value was used to assess the agreement between the CNN model，R2，and R1 in the diagnosis and classification of cystocele. Additionally，the time consumption of the three measurement methods was compared.Results:The CNN model showed good consistency with R1 in measuring PWB and URA（ICC = 0.983，0.894），while its consistency in measuring RVA was moderate（ICC = 0.614）. The ICC between R2 and R1 in measuring PWB，URA，and RVA was 0.979，0.815，and 0.627，respectively. In the measurement of PWB and URA，the consistency between the CNN model and R1 was superior to that between R2 and R1. For cystocele diagnosis，the Kappa value between the CNN model and R1 was 0.924，which was higher than that between R2 and R1（0.904）. In cystocele classification，the Kappa value between the CNN model and R1 was 0.503，also higher than that between R2 and R1（0.426）. The CNN model processed a single video in 2.5（0.6）s，significantly faster than R1［59.9（16.9）s］and R2［56.8（11.2）s］（all P < 0.001）. Conclusions:The CNN model demonstrates high accuracy and efficiency in the measurement，diagnosis，and classification of cystocele，outperforming a junior radiologist and showing potential for clinical application.

Objective:To explore the effect of early intermittent enteral nutrition (EN) in critically ill patients after cardiac surgery.Methods:We developed an early EN feeding regimen for critically ill patients after cardiac surgery. A prospective analysis was conducted on 178 critically ill patients admitted to the Cardiothoracic Surgery Intensive Care Unit of a tertiary hospital in Shanghai from May 2022 to May 2023. They were divided into the control group ( n=88) and the observation group ( n=90) using a random number table method. The control group received routine EN feeding, while the observation group received early intermittent EN feeding. Comparison between groups was performed in terms of the tolerability and interruption of EN administration, nutrition related outcome indicators, and prognosis indicators. Results:The observation group had significantly lower rates of abdominal distension, diarrhea, nausea and vomiting (or reflux), and EN interruption, as well as shorter duration of EN interruption, compared to the control group ( P<0.05). After 7 days of early EN, 87.8% of patients in the observation group met the calorie goal, which was significantly higher than that of 22.5% in the observation group ( P<0.05). The nutritional related indicators (serum prealbumin, hemoglobin, actual intake of nutritional fluids) were also better in the observation group patients compared to the control group ( P<0.05). The duration of mechanical ventilation and length of ICU stay in the observation group were significantly shorter than those in the control group, with statistical significance ( P<0.05). There was no significant difference in the length of hospital stay between the two groups. Conclusion:Early EN program can improve the symptoms of feeding intolerance in patients, reduce the occurrence and duration of feeding interruption, increase the rate of calorie goal fulfillment, improve nutritional status,and promote patient recovery and outcome in critically ill patients after cardiac surgery.

Objective To compare the clinical efficacy of abdominal ultrasound-guided endoscopic retrograde appendicitis therapy(ERAT)with laparoscopic appendectomy(LA)for acute uncomplicated appendicitis using propensity score matching.Methods The clinical data of 441 patients with acute uncomplicated appendicitis admitted to the Third People's Hospital of Yunnan Province from March 2020 to April 2023 were collected.The cases were classified based on the differences in surgical method and divided into the ERAT group(n = 30)and LA group(n = 411).The clinical efficacy of patients was compared between the two groups after reducing confounding bias by propensity score matching(PSM).Results After PSM,a total of 30 pairs of patients in the two groups were successfully matched,and the baseline data of the two groups met the requirements for comparability.At 24 hours after the operation,the ERAT group exhibited lower white blood cells,neutrophil counts,and C-reactive protein levels compared to the LA group,and these differences were statistically significant(P<0.05).There was no significant difference in the operation time and total effective rate between the ERAT group and the LA group(P>0.05).However,the ERAT group had lower intraoperative blood loss and shorter pain relief time compared to the LA group,and these differences were statistically significant(P<0.05).Conclusion Abdominal ultrasound-guided endoscopic retrograde appendicitis treatment is an effective,safe,and feasible technique with good prospects for the treatment of acute uncomplicated appendicitis.

Objective:To explore the value of a nomogram model based on the CT enterography (CTE) signs for prediction of intestinal penetrating lesions in patients with Crohn disease (CD).Methods:The clinical and CTE data of CD patients who underwent at least two CTE examinations from January 2010 to June 2020 in the First Affiliated Hospital of Sun Yat-sen University were retrospectively collected. A total of 112 patients were enrolled, and according to whether there was intestinal wall penetration in the last CTE observation were divided into non-penetration group (84 cases) and penetration group (28 cases). First, the clinical and CTE data for the first examination was analyzed by using univariate and multivariate Cox proportional hazards regression to screen out high-risk factors that could effectively predict intestinal wall penetrating lesions in CD patients and established a nomogram model. Then the change trend of CTE data (ΔCTE) between the first and last clinical and CTE signs was analyzed by using univariate and multivariate Cox proportional hazards regression, and built a nomogram model to sort out ΔCTE that may accompany the development of penetrating lesions in CD patients. The Harrell concordance index was used to evaluate the discriminative ability of the nomogram model.Results:In the first time clinical and CTE signs, multivariate Cox proportional hazards regression results showed that numbers of diseased bowel segments (HR=0.686, 95%CI 0.475-0.991, P=0.045) and the shortest diameter of the largest lymph node (HR=0.751, 95%CI 0.593-0.949, P=0.017) were independent protection factors for penetrating lesions, and rough bowel wall surface (HR=5.626, 95%CI 2.466-12.839, P<0.001) was an independent risk factor for penetrating lesions. The specificity and sensitivity of the nomogram model to predict non-penetration lesions were 82.1% and 59.5% respectively, and the Harrell concordance index was 0.810 (95%CI 0.732-0.888). In the ΔCTE signs, multivariate Cox proportional hazards regression showed that Δrough bowel wall surface (always rough bowel wall surface HR=12.344, 95%CI 2.042-74.625, P=0.006; slide bowel wall surface becomes rough bowel wall surface HR=28.720, 95%CI 4.580-180.112, P<0.001) and Δthe shortest diameter of the largest lymph node (HR=1.534, 95%CI 1.091-2.157, P=0.014) were independent risk factors for penetrating lesions. The specificity and sensitivity of the nomogram model were 89.3% and 79.2% respectively, and the Harrell concordance index was 0.876 (95%CI 0.818-0.934). Conclusion:The nomogram based on CTE signs of numbers of diseased bowel segments, the shortest diameter of the largest lymph node and rough bowel wall surface and ΔCTE can effectively predict the intestinal wall penetrating lesions of CD patients.

Objective:To explore the classification performance of combined model constructed from CT signs combined with radiomics for discriminating COVID-19 pneumonia and other viral pneumonia.Methods:The clinical and CT imaging data of 181 patients with viral pneumonia confirmed by reverse transcription-polymerase chain reaction in 15 hospitals of Yunnan Province from March 2015 to March 2020 were analyzed retrospectively. The 181 patients were divided into COVID-19 group (89 cases) and non-COVID-19 group (92 cases), which were further divided into training cohort (126 cases) and test cohort (55 cases) at a ratio of 7∶3 using random stratified sampling. The CT signs of pneumonia were determined and the radiomics features were extracted from the initial unenhanced chest CT images to build independent and combined models for predicting COVID-19 pneumonia. The diagnostic performance of the models were evaluated using receiver operating characteristic (ROC) analysis, continuous net reclassification index (NRI) calibration curve and decision curve analysis.Results:The combined models consisted of 3 significant CT signs and 14 selected radiomics features. For the radiomics model alone, the area under the ROC curve (AUC) were 0.904 (sensitivity was 85.5%, specificity was 84.4%, accuracy was 84.9%) in the training cohort and 0.866 (sensitivity was 77.8%, specificity was 78.6%, accuracy 78.2%) in the test cohort. After combining CT signs and radiomics features, AUC of the combined model for the training cohort was 0.956 (sensitivity was 91.9%, specificity was 85.9%, accuracy was 88.9%), while that for the test cohort was 0.943 (sensitivity was 88.9%, specificity was 85.7%, accuracy was 87.3%). The AUC values of the combined model and the radiomics model in the differentiation of COVID-19 group and the non-COVID-19 group were significantly different in the training cohort ( Z=-2.43, P=0.015), but difference had no statistical significance in the test cohort ( Z=-1.73, P=0.083), and further analysis using the NRI showed that the combined model in both the training cohort and the test cohort had a positive improvement ability compared with radiomics model alone (training cohort: continuous NRI 1.077, 95 %CI 0.783-1.370; test cohort: continuous NRI 1.421, 95 %CI 1.051-1.790). The calibration curve showed that the prediction probability of COVID-19 predicted by the combined model was in good agreement with the observed value in the training and test cohorts; the decision curve showed that a net benefit greater than 0.6 could be obtained when the threshold probability of the combined model was 0-0.75. Conclusion:The combination of CT signs and radiomics might be a potential method for distinguishing COVID-19 and other viral pneumonia with good performance.

Objective:To explore the value of multiphasic CT-based radiomics signature in predicting the invasive behavior of pancreatic solid pseudopapillary neoplasm (pSPN).Methods:The multiphasic CT images of patients with pSPN confirmed by postoperative pathology in the First Affiliated Hospital of Zhengzhou University from January 2012 to January 2021 were analyzed retrospectively. There were 23 cases of invasiveness and 59 cases of non-invasiveness. The region of interest(ROI) was artificially delineated layer by layer in the plain scan, arterial-phase and venous-phase images, respectively. The 1 316 image features were extracted from each ROI. The data set was divided into training and validation sets with a ratio of 7∶3 by stratified random sampling, and synthetic minority oversampling technique (SMOTE) algorithm was used for oversampling in the training set to generate invasive and non-invasive balanced data for building the training model. The constructed model was validated in the validation set. The receiver operating characteristic(ROC) analysis was used to evaluate model performance and the Delong′s test was applied to compare the area under the ROC curve (AUC) of different predict models. The improvement for classification efficiency of each independent model or their combinations were also assessed by net reclassification improvement (NRI) and integrated discrimination improvement (IDI) indices.Results:After feature extraction, 2, 6 and 3 features were retained to construct plain-scanned model, arterial-phase and venous-phase models, respectively. Seven independent-phase and combined-phase models were established. Except the plain-scanned model, the AUC values of other models were greater than 0.800. The arterial-phase model had the best efficiency for classification among all independent-phase models. The AUC values of arterial-phase model in the SMOTE training and validation sets were 0.913 and 0.873, respectively. By combining the radiomics signature of the arterial-phase and venous-phase models, the AUC values of training and validation sets increased to 0.934 and 0.913 respectively. There were no significant differences of the AUC values between the scan-arterial venous-phase model and arterial venous-phase model in both training and validation sets (both P>0.05). The NRI and IDI indexes showed that the combined form of plain-scan model and arterial-venous-phase model could not significantly improve the classification efficiency in the validation set (both NRI and IDI<0). Conclusions:The arterial-phase CT-based radiomics model has a good predictive performance in the invasive behavior of pSPN, and the combination with a venous-phase radiomics model can further improve the model performance.

Objective:To develop a mesenteric creeping fat index (MCFI) based on CT enterography (CTE) to characterize the degree of creeping fat wrapping around the inflamed gut in Crohn disease (CD), and to assess the relationship between MCFI and the inflammatory intestinal stricture.Methods:From December 2018 to July 2019, the patients with CD who underwent surgery in the First Affiliated Hospital of Sun Yat-Sen University were prospectively collected. The extent of perienteric mesenteric vessels wrapping around the gut was reconstructed to develop MCFI based on CTE images. The intestinal stricture index was obtained by calculating the ratio of the maximal upstream luminal diameter divided by the minimum luminal diameter apparent within the stricturing region. Using region-by-region correlation between CTE and surgical specimen, creeping fat score in intestinal specimen was obtained by assessing the extent of creeping fat wrapping around the resected bowel segment, and HE staining was performed on the bowel specimen corresponding to creeping fat to obtain the pathological inflammatory score. The Spearman correlation analysis was used to evaluate the correlation between MCFI, creeping fat score in intestinal specimen, and inflammatory score, intestinal stricture index. The ROC curve analysis was used to assess the accuracy of MCFI in distinguishing moderate-severe and mild inflammatory bowel walls.Results:Totally 30 CD patients were enrolled. The creeping fat score in intestinal specimen positively correlated with pathological inflammatory score ( r s=0.403, P=0.027) and with intestinal stricture index ( r s=0.642, P<0.001). MCFI positively correlated with creeping fat score in intestinal specimen ( r s=0.840, P<0.001), with pathological inflammatory score ( r s=0.497, P=0.005), and with intestinal stricture index ( r s=0.599, P<0.001). ROC analysis showed that the area under the curve of MCFI for differentiating moderate-severely from mildly inflammatory bowel walls was 0.718 (95%CI 0.522-0.913). Using MCFI≥4 as a cutoff value, the sensitivity and specificity were 81.8% and 47.4%, respectively. Conclusions:There was a correlation between creeping fat and inflammatory intestinal strictures in CD. MCFI can non-invasively depict the degree of creeping fat wrapping around the gut and assess the inflammatory intestinal stricture.

Inflammatory bowel disease (IBD) mainly includes Crohn′s disease (CD) and ulcerative colitis (UC) . The imaging diagnosis of CD is difficult because of its complex disease and varied imaging manifestations. Standardizations of imaging techniques and reports are helpful to improve the imaging diagnosis level of CD. This article aims to provide guideline for the imaging technique selection, scanning scheme formulation, imaging features interpretation and imaging report writing of CD in China.

Inflammatory bowel disease (IBD) mainly includes Crohn′s disease (CD) and ulcerative colitis (UC) . The imaging diagnosis of CD is difficult because of its complex disease and varied imaging manifestations. Standardizations of imaging techniques and reports are helpful to improve the imaging diagnosis level of CD. This article aims to provide guideline for the imaging technique selection, scanning scheme formulation, imaging features interpretation and imaging report writing of CD in China.