Objective·To compare the performance of various deep learning methods in the segmentation and classification of colorectal polyp endoscopic images,and identify the most effective approach.Methods·Four colorectal polyp datasets were collected from three hospitals,encompassing 1 534 static images and 15 videos.All samples were pathologically validated and categorized into two types:serrated lesions and adenomatous polyps.Polygonal annotations were performed by using the LabelMe tool,and the annotated results were converted into integer mask formats.These data were utilized to train various architectures of deep neural networks,including convolutional neural network(CNN),Transformers,and their fusion,aiming to develop an effective semantic segmentation model.Multiple performance indicators for automatic diagnosis of colon polyps by different architecture models were compared,including mIoU,aAcc,mAcc,mDice,mFscore,mPrecision and mRecall.Results·Four different architectures of semantic segmentation models were developed,including two deep CNN architectures(Fast-SCNN and DeepLabV3plus),one Transformer architecture(Segformer),and one hybrid architecture(KNet).In a comprehensive performance evaluation of 291 test images,KNet achieved the highest mIoU of 84.59％,significantly surpassing Fast-SCNN(75.32％),DeepLabV3plus(78.63％),and Segformer(80.17％).Across the categories of"background","serrated lesions"and"adenomatous polyps",KNet's intersection over union(IoU)were 98.91％,74.12％,and 80.73％,respectively,all exceeding other models.Additionally,KNet performed excellently in key performance metrics,with aAcc,mAcc,mDice,mFscore,and mRecall reaching 98.59％,91.24％,91.31％,91.31％,and 91.24％,respectively,all superior to other models.Although its mPrecision of 91.46％was not the most outstanding,KNet's overall performance remained leading.In inference testing on 80 external test images,KNet maintained an mIoU of 81.53％,demonstrating strong generalization capabilities.Conclusion·The semantic segmentation model of colorectal polyp endoscopic images constructed by deep neural network based on KNet hybrid architecture,exhibits superior predictive performance,demonstrating its potential as an efficient tool for detecting colorectal polyps.

ObjectiveTo develop a predictive model and application for spontaneous passage of common bile duct stones using automated machine learning algorithms given the complexity of treatment decision-making for patients with common bile duct stones， and to reduce unnecessary endoscopic retrograde cholangiopancreatography （ERCP） procedures. MethodsA retrospective analysis was performed for the data of 835 patients who were scheduled for ERCP after a confirmed diagnosis of common bile duct stones based on imaging techniques in Changshu First People’s Hospital （dataset 1） and Changshu Traditional Chinese Medicine Hospital （dataset 2）. The dataset 1 was used for the training and internal validation of the machine learning model and the development of an application， and the dataset 2 was used for external testing. A total of 22 potential predictive variables were included for the establishment and internal validation of the LASSO regression model and various automated machine learning models. The area under the receiver operating characteristic curve （AUC）， sensitivity， specificity， and accuracy were used to assess the performance of models and identify the best model. Feature importance plots， force plots， and SHAP plots were used to interpret the model. The Python Dash library and the best model were used to develop a web application， and external testing was conducted using the dataset 2. The Kolmogorov-Smirnov test was used to examine whether the data were normally distributed， and the Mann-Whitney U test was used for comparison between two groups， while the chi-square test or the Fisher’s exact test was used for comparison of categorical data between groups. ResultsAmong the 835 patients included in the study， 152 （18.20%） experienced spontaneous stone passage. The LASSO model achieved an AUC of 0.875 in the training set （n=588） and 0.864 in the validation set （n=171）， and the top five predictive factors in terms of importance were solitary common bile duct stones， non-dilated common bile duct， diameter of common bile duct stones， a reduction in serum alkaline phosphatase （ALP）， and a reduction in gamma-glutamyl transpeptidase （GGT）. A total of 55 models were established using automated machine learning， among which the gradient boosting machine （GBM） model had the best performance， with an AUC of 0.891 （95% confidence interval： 0.859‍ ‍—‍ ‍0.927）， outperforming the extreme randomized tree mode， the deep learning model， the generalized linear model， and the distributed random forest model. The GBM model had an accuracy of 0.855， a sensitivity of 0.846， and a specificity of 0.857 in the test set （n=76）. The variable importance analysis showed that five factors had important influence on the prediction of spontaneous stone passage， i.e.， were solitary common bile duct stones， non-dilated common bile duct， a stone diameter of <8 mm， a reduction in serum ALP， and a reduction in GGT. The SHAP analysis of the GBM model showed a significant increase in the probability of spontaneous stone passage in patients with solitary common bile duct stones， non-dilated common bile duct， a stone diameter of <8 mm， and a reduction in serum ALP or GGT. ConclusionThe GBM model and application developed using automated machine learning algorithms exhibit excellent predictive performance and user-friendliness in predicting spontaneous stone passage in patients with common bile duct stones. This application can help avoid unnecessary ERCP procedures， thereby reducing surgical risks and healthcare costs.

ObjectiveTo investigate the independent risk factors for poor prognosis in patients with acute pancreatitis （AP） by analyzing inflammatory factors， lung ultrasound （LUS） scores， and CT scores， to establish a nomogram prediction model， and to provide a basis for early clinical intervention. MethodsA total of 409 patients with AP who were admitted to Changshu Hospital Affiliated to Soochow University from January 2021 to October 2023 were enrolled as subjects， and they were divided into modeling group with 288 patients and validation group with 121 patients using the simple random sampling method at a ratio of 7∶3. According to the prognosis， each group was further divided into poor prognosis group and good prognosis group. The levels of C-reactive protein （CRP）， procalcitonin （PCT）， interleukin-6 （IL-6）， interleukin-10 （IL-10）， and tumor necrosis factor-α （TNF-α） were measured for both groups within 72 hours after admission， and LUS scores， modified CT severity index （MCTSI）， and extrapancreatic inflammation on computed tomography （EPIC） scores were assessed within 48‍ ‍—‍ ‍72 hours after admission. The independent-samples t test was used for comparison of normally distributed continuous data between groups， and the Mann-Whitney U rank sum test was used for comparison of non-normally distributed continuous data between groups； the chi-square test was used for comparison of categorical data between groups. A LASSO regression analysis was used to screen for the variables that were included in the multivariate logistic regression model to identify the independent risk factors for the poor prognosis of AP， and then a nomogram prediction model was established. The receiver operating characteristic （ROC） curve and the calibration curve were used to assess the discriminatory ability and goodness of fit of the nomogram model， and a decision curve analysis was used to assess the clinical applicability of the model. ResultsAmong the 288 patients with AP in the modeling group， there were 33 （11.46%） in the poor prognosis group and 255 （88.54%） in the good prognosis group； among the 121 patients with AP in the validation group， there were 13 （10.74%） in the poor prognosis group and 108 （89.26%） in the good prognosis group. Compared with the good prognosis group， the poor prognosis group had significantly higher levels of CRP （Z=3.607， P<0.05）， IL-6 （Z=4.189， P<0.05）， and TNF-α （t=2.584， P<0.05）， and significantly higher scores of LUS （t=8.075， P<0.05）， MCTSI （t=5.929， P<0.05）， and EPIC （t=8.626， P<0.05）. The multivariate logistic regression analysis showed that CRP （odds ratio ［OR］=3.592， 95% confidence interval ［CI］： 1.272‍ ‍—‍ ‍10.138， P<0.05）， IL-6 （OR=4.225， 95%CI： 1.468‍ ‍—‍ ‍12.156， P<0.05）， TNF-α （OR=3.540， 95%CI： 1.205‍ ‍—‍ ‍10.401， P<0.05）， LUS （OR=7.094， 95%CI： 2.398‍ ‍—‍ ‍20.986， P<0.05）， MCTSI （OR=7.612， 95%CI： 2.832‍ ‍—‍ ‍20.462， P<0.05）， and EPIC （OR=11.915， 95%CI： 4.007‍ ‍—‍ ‍35.432， P<0.05） were independent risk factor for poor prognosis in patients with AP. A nomogram prediction model was established based on the above 6 indicators， which had an area under the ROC curve of 0.924 （95%CI： 0.883‍ ‍—‍ ‍0.964）， and the Youden index for the optimal cut-off value was 0.670， with a sensitivity of 0.909 and a specificity of 0.761. The calibration curve showed good consistency between the predicted and observed results in both the modeling group and the validation group. The decision curve analysis showed that the predictive model had certain clinical effectiveness. ConclusionThe nomogram model for predicting the risk of poor prognosis in AP patients based on CRP， IL-6， TNF-α， LUS score， MCTSI score， and EPIC score has relatively good predictive performance and can provide important strategic guidance for developing early intensified treatment regimens for AP patients in clinical practice.