BACKGROUND:MRI is important for the diagnosis of early knee osteoarthritis.MRI image recognition and intelligent segmentation of knee osteoarthritis using deep learning method is a hot topic in image diagnosis of artificial intelligence. OBJECTIVE:Through deep learning of MRI images of knee osteoarthritis,the segmentation of femur,tibia,patella,cartilage,meniscus,ligaments,muscles and effusion of knee can be automatically divided,and then volume of knee fluid and muscle content were measured. METHODS:100 normal knee joints and 100 knee osteoarthritis patients were selected and randomly divided into training dataset(n=160),validation dataset(n=20),and test dataset(n=20)according to the ratio of 8:1:1.The Coarse-to-Fine sequential training method was used to train the 3D-UNET network deep learning model.A Coarse MRI segmentation model of the knee sagittal plane was trained first,and the rough segmentation results were used as a mask,and then the fine segmentation model was trained.The T1WI and T2WI images of the sagittal surface of the knee joint and the marking files of each structure were input,and DeepLab v3 was used to segment bone,cartilage,ligament,meniscus,muscle,and effusion of knee,and 3D reconstruction was finally displayed and automatic measurement results(muscle content and volume of knee fluid)were displayed to complete the deep learning application program.The MRI data of 26 normal subjects and 38 patients with knee osteoarthritis were screened for validation. RESULTS AND CONCLUSION:(1)The 26 normal subjects were selected,including 13 females and 13 males,with a mean age of(34.88±11.75)years old.The mean muscle content of the knee joint was(1 051 322.94±2 007 249.00)mL,the mean median was 631 165.21 mL,and the mean volume of effusion was(291.85±559.59)mL.The mean median was 0 mL.(2)There were 38 patients with knee osteoarthritis,including 30 females and 8 males.The mean age was(68.53±9.87)years old.The mean muscle content was(782 409.18±331 392.56)mL,the mean median was 689 105.66 mL,and the mean volume of effusion was(1 625.23±5 014.03)mL.The mean median was 178.72 mL.(3)There was no significant difference in muscle content between normal people and knee osteoarthritis patients.The volume of effusion in patients with knee osteoarthritis was higher than that in normal subjects,and the difference was significant(P<0.05).(4)It is indicated that the intelligent segmentation of MRI images by deep learning can discard the defects of manual segmentation in the past.The more accuracy evaluation of knee osteoarthritis was necessary,and the image segmentation was processed more precisely in the future to improve the accuracy of the results.

Pulse recognition is an important part of the objectification and intelligence of TCM.This non-invasive and fast diagnostic method has great clinical value,however,data imbalance and cumbersome feature extraction are still challenging problems.The feature vectors were extracted from the one-dimensional pulse signal obtained after the Butterworth bandpass filter using the tsfresh library.And 9 columns of medical auxiliary features selected by exploratory data analysis were added.The feature filtering is performed jointly to derive 21 columns of feature vectors,which are used as input to the weighted soft voting fusion model.The data imbalance problem is solved by Borderline SMOTE algorithm.Construct a weighted soft-voting fusion model based on four types of machine learning:XGBoost,RF,LGBM,and GBDT.Eventually,the models will output specific pulse categories and demonstrate the performance by evaluating the metrics accuracy,precision,recall and F1 score.The experimental results show that the screened 21 feature vectors for a total of six types of pulse signal test sets achieve an accuracy of 90.04%in the five-fold cross-validation and take only 65.9466 seconds.It can provide a more accurate and intelligent auxiliary reference for pulse signal recognition,with lower operational complexity and higher accuracy compared to commonly used pulse recognition methods.The shorter training time also makes it more clinically useful in the recognition of multiple pulse signals.

Objective To evaluate the influence factors on surgical methods in DCIS (Ductal carcinoma in situ) patients,and the prognosis of different surgical methods in a 10-year single-center retrospective study.Methods We retrospectively included 1557 DCIS patients who received treatments in our center from Jan.2006 to Nov.2016.T tests,Chi-square analysis and logistic regression analysis were used to analyze influence factors on surgical methods.Kaplan-Meier and Log-rank analysis were used to evaluate recurrence-free survival(RFS) and loco-regional recurrence-free survival (LRRFS) in patients with different surgical methods.Results Of the enrolled 1557 DCIS patients,surgical methods included modified radical mastectomy,simple mastectomy (with or without axillary evaluation) and breast conservation surgery (with or without axillary evaluation).The number of DCIS cases in our center increased (P＜0.001),so did the percentage of DCIS in annual malignant surgery cases (P=-0.026).Significant decrease was found in modified radical mastectomy (P=0.012).More than half of the patients received simple mastectomy after 2010,and more than one fifth of the patients received breast conservation surgery after 2008.About 13.99％ patients who received mastectomy had breast reconstruction.The independent influence factors of refusing breast conservation surgery were age ≥ 50(P＜0.001),medium nuclear grade (P=0.044),tumor size ＞ 15mm (P＜0.001) and spontaneous discharge (P＜0.001).Patients with smaller tumor size (≤ 15mm) and no spontaneous discharge had 4.18-fold and 7.04-fold greater preference for breast conservation surgery,respectively(OR=0.232,P＜0.001;OR=0.144,P＜0.001).There were no significant differences in RFS and LRRFS in patients with different surgical methods.Conclusion The evaluation in trends and influence factors of different surgical methods provides basis on surgical precision medicine in DCIS patients.

Objectives: To examine the influence factors on axillary evaluation in ductal carcinoma in situ (DCIS) patients, and the prognosis of different choices of axillary evaluation in a single-center retrospective study. Methods: Totally 1 557 DCIS patients admitted in Department of Breast Surgery, Fudan University Shanghai Cancer Center from January 2006 to November 2016 were retrospectively enrolled. All patients were female. The median age was 49 years (range: 21 to 85 years). Surgical methods included modified radical mastectomy, simple mastectomy (with or without axillary evaluation) and breast conservation surgery (with or without axillary evaluation). Axillary evaluation included axillary lymph node dissection (ALND) and sentinel lymph node biopsy (SLNB). T tests, χ² test and Logistic regression analysis was used to analyze influence factors on axillary evaluation, respectively. Kaplan-Meier curve and Log-rank analysis were used to evaluate recurrence-free survival (RFS) and loco-regional recurrence-free survival (LRRFS) in patients with different surgical methods. Results: Among the 1 557 DCIS patients, there were 1 226 cases received axillary evaluation, while 331 cases not received axillary evaluation. Patients were separated into 3 groups by different axillary evaluation choices: SLNB group (957 cases, 61.46%), ALND group (197 cases, 12.65%) and no evaluation group (403 cases, 25.88%). The patients in SLNB group increased significantly (P=0.000), from 3.85% (60/1 557) in 2006 to 75.19% (1 170/1 557) in 2016. The independent influence factors of receiving axillary evaluation were high nuclear grade (OR=3.191, 95%CI: 1.722 to 5.912, P=0.001) and tumor size>15 mm (OR=1.698, 95%CI: 1.120 to 2.573, P=0.012). Also, patients received breast conservation surgery were more likely to refuse axillary evaluation (OR=0.155, 95%CI: 0.103 to 0.233, P=0.000). There were no significant differences in RFS and LRRFS in patients with different axillary evaluation choices. Conclusions The investigation in trends and influence factors of different axillary evaluation choices provided basis on surgical precision medicine in DCIS patients. Patients received SLNB increased significantly. The independent influence factors of axillary evaluation were nuclear grade, tumor size and surgical methods. There was no significant differences in prognosis among the groups receiving different axillary evaluations.

Objectives To examine the influence factors on axillary evaluation in ductal carcinoma in situ (DCIS) patients, and the prognosis of different choices of axillary evaluation in a single?center retrospective study. Methods Totally 1 557 DCIS patients admitted in Department of Breast Surgery, Fudan University Shanghai Cancer Center from January 2006 to November 2016 were retrospectively enrolled. All patients were female. The median age was 49 years (range: 21 to 85 years). Surgical methods included modified radical mastectomy, simple mastectomy (with or without axillary evaluation) and breast conservation surgery (with or without axillary evaluation). Axillary evaluation included axillary lymph node dissection (ALND) and sentinel lymph node biopsy (SLNB). T tests, χ2 test and Logistic regression analysis was used to analyze influence factors on axillary evaluation, respectively. Kaplan?Meier curve and Log?rank analysis were used to evaluate recurrence?free survival (RFS) and loco?regional recurrence?free survival (LRRFS) in patients with different surgical methods. Results Among the 1 557 DCIS patients, there were 1 226 cases received axillary evaluation, while 331 cases not received axillary evaluation. Patients were separated into 3 groups by different axillary evaluation choices: SLNB group (957 cases, 61.46%), ALND group (197 cases, 12.65%) and no evaluation group (403 cases, 25.88%). The patients in SLNB group increased significantly (P=0.000), from 3.85% (60/1 557) in 2006 to 75.19% (1 170/1 557) in 2016. The independent influence factors of receiving axillary evaluation were high nuclear grade ( OR=3.191, 95%CI : 1.722 to 5.912, P=0.001) and tumor size>15 mm ( OR=1.698, 95 %CI : 1.120 to 2.573, P=0.012). Also, patients received breast conservation surgery were more likely to refuse axillary evaluation ( OR=0.155, 95%CI : 0.103 to 0.233, P=0.000). There were no significant differences in RFS and LRRFS in patients with different axillary evaluation choices. Conclusions The investigation in trends and influence factors of different axillary evaluation choices provided basis on surgical precision medicine in DCIS patients. Patients received SLNB increased significantly. The independent influence factors of axillary evaluation were nuclear grade, tumor size and surgical methods. There was no significant differences in prognosis among the groups receiving different axillary evaluations.

Objectives To examine the influence factors on axillary evaluation in ductal carcinoma in situ (DCIS) patients, and the prognosis of different choices of axillary evaluation in a single?center retrospective study. Methods Totally 1 557 DCIS patients admitted in Department of Breast Surgery, Fudan University Shanghai Cancer Center from January 2006 to November 2016 were retrospectively enrolled. All patients were female. The median age was 49 years (range: 21 to 85 years). Surgical methods included modified radical mastectomy, simple mastectomy (with or without axillary evaluation) and breast conservation surgery (with or without axillary evaluation). Axillary evaluation included axillary lymph node dissection (ALND) and sentinel lymph node biopsy (SLNB). T tests, χ2 test and Logistic regression analysis was used to analyze influence factors on axillary evaluation, respectively. Kaplan?Meier curve and Log?rank analysis were used to evaluate recurrence?free survival (RFS) and loco?regional recurrence?free survival (LRRFS) in patients with different surgical methods. Results Among the 1 557 DCIS patients, there were 1 226 cases received axillary evaluation, while 331 cases not received axillary evaluation. Patients were separated into 3 groups by different axillary evaluation choices: SLNB group (957 cases, 61.46%), ALND group (197 cases, 12.65%) and no evaluation group (403 cases, 25.88%). The patients in SLNB group increased significantly (P=0.000), from 3.85% (60/1 557) in 2006 to 75.19% (1 170/1 557) in 2016. The independent influence factors of receiving axillary evaluation were high nuclear grade ( OR=3.191, 95%CI : 1.722 to 5.912, P=0.001) and tumor size>15 mm ( OR=1.698, 95 %CI : 1.120 to 2.573, P=0.012). Also, patients received breast conservation surgery were more likely to refuse axillary evaluation ( OR=0.155, 95%CI : 0.103 to 0.233, P=0.000). There were no significant differences in RFS and LRRFS in patients with different axillary evaluation choices. Conclusions The investigation in trends and influence factors of different axillary evaluation choices provided basis on surgical precision medicine in DCIS patients. Patients received SLNB increased significantly. The independent influence factors of axillary evaluation were nuclear grade, tumor size and surgical methods. There was no significant differences in prognosis among the groups receiving different axillary evaluations.

Objective To study effects of oxycodone post-operative early analgesia on stress re-sponse with in diabetics undergoing uvulopalatopharyngoplasty (UPPP).Methods Eighty patients undergoing UPPP,53 males,27 females,aged 28-65 years,ASA Ⅰ or Ⅱ were randomly divided in-to two groups(n =40).1 5 minutes before the end of the operation,group O was intravenously given oxycodone 0.07 mg/kg;Group F fentanyl 0.7 μg/kg.The patients of the two groups were sampled venous blood 3 ml in the morning of operation (T1 ),postoperative 1 hour (T2 ),postoperative 3 hours (T3 )for determination of serum cortisol (Cor),serum insulin(Ins),serum C-peptide(C-P)u-sing electrochemical luminescence method.Results Cor at T2 ,T3 was lower than that at T1 , C-P was higher than that at T1 (P <0.05)in group O,respectively;Cor at T2 ,T3 was higher than that at T1 , respectively,C-P was lower than that at T1 (P <0.05);Cor in group F was higher than that in group O,C-P in group F was lower than that in group O(P <0.05).Ins at T2 ,T3 was lower than that at T1 and was lower than that in group O(P <0.05).Conclusion Oxycodone 0.07 mg/kg early analgesia for UPPP significantly inhibits the occurrence of stress response.

Objective The aim of the current study is to determine the clinical value of incidental internal mammary lymph node biopsy in free abdominal flap breast reconstruction using internal mammary vessels as recipient vessels and to investigate the risk factors of internal mammary lymph nodes metastasis. Methods The clinical data of all patients who underwent free abdominal flap breast reconstruction using internal mammary vessels as recipient vessels from November 2006 to December 2015 in the Department of Breast Surgery, Fudan University Shanghai Cancer Center were reviewed in the study. The incidence of internal mammary lymph node biopsy and the rate of metastasis were analyzed. Statistical analysis was conducted to evaluate the risk factors of internal mammary lymph node metastasis. Results A total of 113 patients met the inclusion criteria, 53 (46.9%) of whom had internal mammary lymph nodes harvested. Four of these were positive for metastatic disease, all in immediate breast reconstructions. The incidence of metastasis was 7.5% in patients who had successful internal mammary lymph node biopsies.The multi?variate Logistic regression analysis showed that invasive tumor size, tumor location and axillary lymph node metastasis were not risk factors for internal mammary lymph node metastasis ( P>0. 05 ) . Conclusions Internal mammary lymph nodes found incidentally during recipient vessel exposure may provide important information about internal mammary lymph node metastasis in free flap breast reconstruction. This approach for internal mammary lymph node biopsy reveals an appreciable success rate and is convenient in clinical practice. The size of invasive tumor and the axillary lymph node metastasis are probably associated with internal mammary lymph node positivity.

Objective The aim of the current study is to determine the clinical value of incidental internal mammary lymph node biopsy in free abdominal flap breast reconstruction using internal mammary vessels as recipient vessels and to investigate the risk factors of internal mammary lymph nodes metastasis. Methods The clinical data of all patients who underwent free abdominal flap breast reconstruction using internal mammary vessels as recipient vessels from November 2006 to December 2015 in the Department of Breast Surgery, Fudan University Shanghai Cancer Center were reviewed in the study. The incidence of internal mammary lymph node biopsy and the rate of metastasis were analyzed. Statistical analysis was conducted to evaluate the risk factors of internal mammary lymph node metastasis. Results A total of 113 patients met the inclusion criteria, 53 (46.9%) of whom had internal mammary lymph nodes harvested. Four of these were positive for metastatic disease, all in immediate breast reconstructions. The incidence of metastasis was 7.5% in patients who had successful internal mammary lymph node biopsies.The multi?variate Logistic regression analysis showed that invasive tumor size, tumor location and axillary lymph node metastasis were not risk factors for internal mammary lymph node metastasis ( P>0. 05 ) . Conclusions Internal mammary lymph nodes found incidentally during recipient vessel exposure may provide important information about internal mammary lymph node metastasis in free flap breast reconstruction. This approach for internal mammary lymph node biopsy reveals an appreciable success rate and is convenient in clinical practice. The size of invasive tumor and the axillary lymph node metastasis are probably associated with internal mammary lymph node positivity.

OBJECTIVETo explore the current trends of breast reconstruction (BR) for breast cancer patients in China.

METHODSA questionnaire was designed for this study, and it included questions on surgeon demographics, number of mastectomy and BR, type and timing of BR, reconstructive choices in the setting of preoperative or postoperative radiotherapy or chemotherapy, etc. All data were collected until December 2012. Questionnaires were sent to 52 members of the Committee of Breast Cancer Society by e-mail or mail.

RESULTSBy July 2013, 41 questionnaires had been returned. Among all, 5 were excluded for not performing BR. These 36 hospitals covered 22 provinces and municipalities in China. A total of 538 surgeons working in the general surgery or oncological surgery department, but only 123 (22.9%) were qualified to perform BR. In 2012, except for 4 missing data, 24, 763 mastectomies were performed in 32 hospitals; among them, 1120 (4.5%) received BR. According to these 36 respondents, 32 (88.9%) performed prosthetic (1, 843 cases in all) while 4 (11.1%) performed prosthetic BR with acellular dermal matrix (17 cases in all) from the time of their first BR operation to the end of 2012. During the same period, 965 latissimus dorsi myocutaneous flaps with implant were performed in 23 (63.9%) hospitals while 738 latissimus dorsi myocutaneous flaps without implant were performed in 32 (88.9%) hospitals. At the same time, 366 pedicled transverse rectus abdominis myocutaneous flap BRs were performed in 28 (77.8%) hospitals, while 155 abdominal free flap BRs were carried out in 9 (25.0%) hospitals. The overall complication rate was 18.2%. Postoperative radiotherapy had some effect on influencing the esthetic outcomes of BR, so the autologous BR was recommended, but the timing remained controversial. Regarding chemotherapy, most respondents concluded that it had no effect or only a mild effect. The overall cosmetic outcomes of the reconstructed breasts satisfied the majority of physicians and patients.

CONCLUSIONSWith more attention paid to the quality of life after mastectomy, more and more BRs are needed, but the ratio is still low in China. To improve this situation, more efforts are needed, including the improvement of the intrahospital framework of multi-disciplinary service, the training for doctors and the educational program for patients, etc.

Breast Neoplasms ; epidemiology ; surgery ; China ; epidemiology ; Humans ; Mammaplasty ; Mastectomy ; trends ; Postoperative Complications ; Postoperative Period ; Quality of Life ; Reconstructive Surgical Procedures ; Surgical Flaps ; Surveys and Questionnaires