Objective To explore the value of CT images in distinguishing perihematomal edema in basal ganglia intracerebral hemorrhage with normal brain tissue,and its significance in assessing patients' conditions and prognoses.Methods CT images and clinical data of 120 patients with basal ganglia intracerebral hemorrhage admitted to our hospital from January 2017 to September 2018 were collected,and these 120 patients were randomly assigned to group of training data set (n=90) and group of test data set (n=30) at a ratio of 3∶l.The texture analysis software Mazda was used to preprocess the CT images and manually sketch the regions of interest (ROIs) to extract the texture parameters in patients from the group of training data set;Mazda software provides texture feature selection methods including mutual information (MI),Fisher coefficients (Fisher),classification error probability combined with average correlation coefficients (POE+ACC),and texture feature analysis including raw data analysis (RDA),principal component analysis (PCA),linear classification analysis (LDA) and nonlinear classification analysis (NDA);texture feature selection methods and texture feature analysis were grouped by pairs to establish different image omics labels;the error rate was used to evaluate the performance of different labels.Random forest model,support vector machine model and neural network model were built for texture parameters in patients from the group of test data set,and texture parameters extracted from patients from group of training data set were imported into these models;receiver operating characteristics curve was used to assess the performance of models.According to the maximum diameter of the hematomas,Glasgow coma scale (GCS) scores at admission,median of National Institute of Health Stroke Scale (NIHSS) scores 3 months after follow up,all patients were divided into two groups;Mazda software was used repeatedly for dimension reduction and establishment of different images omics labels;the sum of error rates from the two groups was taken as total error rate to evaluate the significance of different labels in predicting patients' conditions and prognoses.Results A total of 295 texture parameters were extracted from the ROIs of the best CT images of 90 patients from group of training data set,and 10 characteristic texture parameters were obtained by each of the three dimensionality reduction methods.Among all texture post-processing methods,the lowest error rate was 2.22％ for POE+ACC/NDA;AUCs were 0.87 (95％ CI:0.76-0.97),0.81 (95％ CI:0.72-0.93) and 0.76 (95％CI:0.67-0.89) for random forest model,support vector machine model and neural network model in the test dataset,respectively,which indicated that random forest model had the best forecast performance.The imaging omics labels established based on POE+ACC/NDA had the lowest total error rate for analysis of maximum diameter ofhematoma and GCS scores at admission (26.66％,23.33％);the imaging omics labels established based on Fishers coefficient method and NDA had the lowest total error rate(33.33％) for analysis of NIHSS scores at 3 months of follow up.Conclusion Radiomicmethod with proper model is of certain value in distinguishing erihematomal edema in basal ganglia intracerebral hemorrhage with normal brain tissue,and also has certain significance in evaluating the patienfs conditions and prognoses.

Based on the breast ultrasound database of West China Hospital from January 1, 2002 to December 31, 2007, a study of data mining techniques for utilizing the diagnostic information of breast ultrasound and breast pathology was carried out. An innovative computerized retrieval system was invented. With the visual user interface of the system, the data of benignancy or malignancy diagnosed by ultrasound and pathologic examination, and the data on the diagnostic correlation of ultrasound and pathology were obtained, respectively. The qualities of data mining were 99. 98%-100%. By means of the retrieval system, the users can secure numerous data from the breast ultrasound database rapidly and accurately; so it contributes to the rational utilization of information from medical database for serving various medical studies. This method may also be helpful for doctors to utilize ultrasound database in other fields.
Breast Neoplasms ; diagnostic imaging ; pathology ; Data Mining ; Databases, Factual ; Female ; Humans ; Information Storage and Retrieval ; methods ; Medical Records Systems, Computerized ; Ultrasonography

Objective:To compare the clinical effects of minimally invasive reduction through a bone tunnel combined with Jail screwing and those of posterolateral locking plating in the treatment of simple posterolateral tibial plateau fractures.Methods:A retrospective analysis was conducted of the data of 48 patients who had been operatively treated and completely followed up at Department of Orthopedics, Suqian Hospital of Nanjing Drum Tower Hospital Group for simple posterolateral tibial plateau fractures from October 2016 to October 2020. There were 26 males and 22 females, aged from 35 to 68 years. They were divided into a minimally invasive group (25 cases subjected to minimally invasive reduction through a bone tunnel combined with Jail screwing) and an incision group (23 cases subjected to posterolateral locking plating) according to their surgical methods. The operation time, incision length, intraoperative blood loss, fracture healing time, cumulative fluoroscopy time, hospital stay and posterior inclination angles of the tibial plateau and Hospital for Special Surgery (HSS) knee function scores at 1, 3, 6, 9, and 12 months after operation were compared between the 2 groups. Complications in the 2 groups of patients were recorded.Results:There was no significant difference in the preoperative general data between the 2 groups, showing comparability ( P>0.05). The 48 patients were followed up for 12 to 36 months (average 16.5 months). The minimally invasive group was significantly better than the incision group in operation time [(42.6±9.1) min versus (65.7±11.5) min], incision length [(4.0±0.4) cm versus (15.0±1.5) cm], intraoperative blood loss[(22.6±5.8) mL versus (31.5±8.8) mL], hospital stay [(7.6±1.4) d versus (11.1±2.4) d], and HSS score one month after operation [(84.8±1.9) points versus (72.9±4.1) points], but the cumulative fluoroscopy time in the incision group [(4.1±1.4) s]was significantly less than that in the minimally invasive group [(22.3±4.2) s] ( P<0.05). There were no significant differences in fracture healing time, HSS scores at 3, 6, 9, or 12 months after operation, or posterior inclination angle of the tibial plateau between the 2 groups ( P>0.05). There were no such complications as wound infection, vascular injury, internal fixation failure, nonunion or malunion of fractures in either of the 2 groups. Two cases in the incision group presented with symptoms of common peroneal nerve injury but recovered 3 months after operation. Conclusions:Although both minimally invasive reduction through a bone tunnel combined with Jail screwing and posterolateral locking plating can achieve satisfactory outcomes in the treatment of simple posterolateral tibial plateau fractures, the minimally invasive technique is preferable because it shows the advantages of a smaller incision, less bleeding, shorter operation time, a lower operation risk, quicker postoperative recovery and shorter hospital stay.

Objective:To explore the efficacy of the proximal tibial lateral locking plate with rafting screws combined with Jail screws in the treatment of collapse fracture of the lateral tibial plateau.Methods:A retrospective case series study was performed on clinical data of 36 patients with collapse fracture of the lateral tibial plateau admitted to Suqian Hospital of Nanjing Drum Tower Hospital Group from January 2016 to January 2020, including 19 males and 17 females, aged 34-68 years [(48.6±5.8)years]. Schatzker classification was type II in 28 patients and type III in 8 patients. All patients were treated using the proximal tibial lateral locking plate with raft screws combined with Jail screws. The operation time, intraoperative blood loss and fracture healing were detected. The distance of articular surface collapse of the tibial plateau, posterior inclination angle (PSA) of the tibial plateau, tibial plateau varus angle (TPVA) and Rasmussen anatomical score were compared before operation and at day 2 and 1 year after operation. The Hospital for Special Surgery (HSS) score was used to evaluate knee function at day 2 and 1 year after operation. Complications were also recorded.Results:All patients were followed up for 12-32 months [(19.5±3.1)months]. The operation time was 56-82 minutes [(68.5±9.1)minutes]. The intraoperative blood loss was 40-100 ml [(75.6±10.2)ml]. The fracture was clinically healed by first-stage, with the healing time of 8 to 15 weeks [(12.5±1.3)weeks]. The distance of articular surface collapse of the tibial plateau was improved from (15.5±4.2)mm before operation to (0.7±0.3)mm at day 2 after operation and (1.0±0.2)mm at 1 year after operation (all P<0.01). The PSA was improved from (21.2±2.1)° before operation to (8.9±0.8)° at day 2 after operation and (9.2±0.6)° at 1 year after operation (all P<0.01). The TPA was improved from (100.2±3.7)° before operation to (88.9±1.8)° at day 2 after operation and (87.2±1.6)° at 1 year after operation (all P<0.05). The Rasmussen anatomical score changed from (7.8±1.8)points before operation to (17.1±0.9)points at day 2 after operation and (16.3±0.7)points at 1 year after operation (all P<0.01). There were no significant difference in the distance of articular surface collapse of the tibial plateau, PSA, TPVA and Rasmussen anatomical score at day 2 and 1 year after operation (all P>0.05). The HSS score was (92.8±3.2)points at 1 year after operation, significantly higher than (74.8±3.5) points at day 2 after operation ( P<0.01). Two patients sustained superficial wound infection after operation, which healed after debridement and dressing change. No deep infection occurred. Conclusion:For patients with collapse fracture of the lateral tibial plateau, the proximal tibial lateral locking plate with rafting screws combined with Jail screws can effectively prevent secondary collapse of the articular surface and obtain satisfactory anatomical reduction, good functional recovery and few postoperative complications.