Objective To construct a mammography image classification assistant system suitable for Chinese population,and explore the potential of artificial intelligence technology to assist early screening of breast cancer in China.Methods Curated breast imaging subset of digital database for screening mammography(CBIS-DDSM),Mammographic image analysis society database(MIAS)and other international open datasets were used to conduct model training respectively in order to reproduce the mainstream in-depth learning methods in the current literature.The model was also tested on the Chinese breast mammography database(CBMD)provided by Huajiao Technology Co.,Ltd,and the performance was compared.Aiming at the problem that the Chinese population data are not ideal in the performance test of the open dataset training model,an optimization strategy based on the sliding window adjustment mechanism was implemented in combination with the characteristics of Chinese population data.Then a two-stage migration learning method was designed to improve the overall performance of the model,and then development of our system was carried out.Results With the sliding window adjustment mechanism and the CBMD training model after two-stage transfer learning,the accuracy of our developed system was improved from 0.50 of the open datasets to 0.80,precision from 0.54 to 0.82,sensitivity from 0.52 to 0.80,F1 value from 0.52 to 0.80,and AUC value from 0.51 to 0.89 based on the Chinese population dataset as the test set.Conclusion Through the introduction of sliding window adjustment mechanism and two-stage migration learning strategy,the performance of the breast molybdenum target image classification model has been significantly improved in the Chinese population dataset,and our system primarily achieves the purpose of assisting the classification of breast molybdenum target images for the Chinese population.

Purpose: Several predictive models have been developed to predict the pathological complete response (pCR) after neoadjuvant chemotherapy (NAC); however, few are broadly applicable owing to radiologic complexity and institution-specific clinical variables, and none have been externally validated. This study aimed to develop and externally validate a machine learning model that predicts pCR after NAC in patients with breast cancer using routinely collected clinical and demographic variables. Methods: The electronic medical records of patients with advanced breast cancer who underwent NAC before surgical resection between January 2017 and December 2020 were reviewed. Patient data from Seoul National University Bundang Hospital were divided into training and internal validation cohorts. Five machine learning techniques, including gradient boosting machine (GBM), support vector machine, random forest, decision tree, and neural network, were used to build predictive models, and the area under the receiver operating characteristic curve (AUC) was compared to select the best model. Finally, the model was validated using an independent cohort from Seoul National University Hospital. Results: A total of 1,003 patients were included in the study: 287, 71, and 645 in the training, internal validation, and external validation cohorts, respectively. Overall, 36.3% of the patients achieved pCR. Among the five machine learning models, the GBM showed the highest AUC for pCR prediction (AUC, 0.903; 95% confidence interval [CI], 0.833–0.972).External validation confirmed an AUC of 0.833 (95% CI, 0.800–0.865). Conclusion Commonly available clinical and demographic variables were used to develop a machine learning model for predicting pCR following NAC. External validation of the model demonstrated good discrimination power, indicating that routinely collected variables were sufficient to build a good prediction model.

Objective: To investigate the effect of different mechanical loading on the expression of Notch-1, Notch-3, Jagged-1 and Delta-like-1 in growing rabbits' condylar cartilage. Methods: Sixty-four ten-days-old rabbits were randomly divided into experimental and control groups. The rabbits in the experimental groups were fed on a powder diet, while the control groups were fed on a solid diet. The animals were sacrificed after 2, 4, 6 and 8 weeks. Notch-1, Notch-3, Jagged-1 and Delta-like-1 gene and protein expressions were examined by HE, immunohistochemistry, Western blotting and quantitative real-time PCR. Results: At 2, 4, 6, 8 weeks, the anterior part of condylar cartilage in solid diet groups ([318.1±4.3], [342.4±2.6], [364.2±3.2], [380.7±6.0] mm, respectively) were thicker than those in powder diet groups ([275.4±2.6], [301.1±2.0], [322.3±3.3], [366.5±8.4] mm, respectively) (P<0.05). There was no significant difference between the two groups in the middle part (P>0.05). From 2 to 6 weeks, the posterior part of cartilage in solid diet groups ([444.1±1.5], [451.1±0.3], [476.4±5.7] mm, respectively) was thinner than those in power diet groups ([470.4±2.7], [494.3±2.9], [512.3±5.7] mm, respectively) (P<0.05). At 6 weeks, there were more mRNA expressions of Notch-3, Jagged-1 and Delta-like-1 in solid diet group than in power diet group (P<0.05). The Notch-1 protein could be found in all layers of condylar cartilage, especially in the surface of hypertrophic zone. The expressions of Notch-1, Notch-3, and Delta-like-1 protein were increased from 2 to 6 weeks, and decreased at 8 weeks. In solid diet groups, the protein expressions of Notch-1 (at 2, 4, 6, 8 weeks), Notch-3 (at 2, 4, 6 weeks), Jagged-1 (at 2, 4, 6 weeks) and Delta-like-1 (at 4, 6, 8 weeks) were greater than in power diet groups (P<0.05). Conclusions Low masticatory loading may delay or inhibit the development of condylar cartilage and its growing factors such as Notch-1, Notch-3, Jagged-1 and Delta-like-1. Appropriate masticatory loading plays an important role in normal development of the condyle.

Objective To compare the accuracy of blood volume perfusion imaging (perfusion CT)with contrast enhanced 64-slice spiral computed tomography (CECT) in the evaluation of gross tumor volume (GTV) and clinical target volume (CTV) using rabbits with VX2 brain tumor. Methods Perfusion CT and CECT were performed in 20 rabbits with VX2 brain tumor. The GTV and CTV calculated with the maximal and minimal diameter of each tumor in the blood volume (BV) maps and CECT were measured and compared to those in pathological specimens. Results The mean value of the maximal and minimal diameter of GTV was (8.19 ± 2. 29) mm and (4.83 ± 1.31) mm in pathological specimens, (11.98 ±3.29) mmand (7.03±1.82) mm in BV maps, while (6.36±3.85) mm and (3.17±1.93) mm in CECT images, which were significantly different (pathological specimen vs. BV map, t = 7. 17,P =0. 000;pathological specimen vs. CECT, t = 8.37, P = 0. 000, respectively). The mean value of the maximal and minimal diameter of CTV in pathologic specimens was (12.87 ± 3.74) mm and (7.71 ± 2. 15) mm, which was significantly different from that of GTV and CTV in CECT (t = - 3. 18, P = 0. 005 and t = - 4. 24, P =0. 000;t= -11.59,P=0.000 and t= -9.39,P=0.000), while similar with that of GTV in BV maps (t = - 1.95,P = 0. 067; t = - 2. 06, P = 0. 054). For CECT, the margin from GTV to CTV was 81.83% ±40.33% for the maximal diameter and 276.73% ± 131.46% for the minimal. While for BV maps, the margin was 7.93% ± 17. 84% and 12.52% ± 27. 83%, which was significant different from that for CECT images (t=7.36,P=0. 000 and t= -8.78,P=0.000). Conclusions Compared with CECT, the BV map from 64-slice spiral CT peffusion imaging might have higher accuracy in target volume delineation for brain tumor.

OBJECTIVETo investigate the effect of Zilongjin (ZLJ) on human androgen-dependent type of prostate cancer cell line LNCaP.

METHODSMTT assay, flow cytometry and fluorescence microscopy were used to observe the effect of ZLJ in anti-proliferation, cell cycle arresting and apoptosis induction. RT-PCR was used to examine the effect of ZLJ on expressions of prostate marker gene (PSA), androgen receptor (AR), apoptosis related genes (bcl-2 and bax), and Western blot assay was used to detect the effect on protein expression of bcl-2 and bax.

RESULTSZLJ could cause apparent inhibition on proliferation, induce G0/G1 phase arresting and apoptosis in time- and dose-dependent manner on LNCaP cells. The concentration for inhibiting cell growth by 50% (IC50) in 72 hrs was 0.79 mg/ml. ZLJ could down-regulate the expression of PSA, AR, bcl-2 genes and lower bcl-2 protein expression, but showed ineffective on bax protein expression.

CONCLUSIONZLJ displays its anti-tumor effects by way of inhibiting the cell proliferation, arresting the G0/G1 phase, inducing apoptosis, down-regulating PSA, AR, bcl-2 gene expression and lowering bcl-2 protein expressions.

Antineoplastic Agents, Phytogenic ; pharmacology ; Cell Line, Tumor ; Cell Proliferation ; drug effects ; Drugs, Chinese Herbal ; pharmacology ; Humans ; Male ; Neoplasms, Hormone-Dependent ; metabolism ; pathology ; Prostate-Specific Antigen ; biosynthesis ; genetics ; Prostatic Neoplasms ; metabolism ; pathology ; Proto-Oncogene Proteins c-bcl-2 ; biosynthesis ; genetics ; Receptors, Androgen ; biosynthesis ; genetics

Objective To assess the value of MRI,US and CT in the differential diagnosis of benign and malignant biliary obstruction.Methods The diagnostic efficiency of MRI and US in 86 cases (including 34 cases with CT) of benign and malignant biliary obstruction were compared using ROC curves . Results The differential diagnostic efficiency with MRI were significantly better than those with US and CT ( P