Objective:To investigate the value of MRI radiomics model in evaluating the pathological complete response (pCR) status of human epidermal growth factor receptor 2(HER-2) positive breast cancer after neoadjuvant therapy.Methods:The study was a cross-sectional study. The clinical, pathological, and MRI data of 243 HER-2 positive breast cancer patients who received neoadjuvant therapy in Shanxi Province Cancer Hospital from January 2021 to June 2023 were retrospectively analyzed. All patients were female, aged 26?75 years. All patients were randomly divided into training set (146 cases) and validation set (97 cases) at a ratio of 6∶4 according to the simple random sampling method. Univariate and multivariate logistic regression were used to screen independent predictors of pCR. Radiomics features were extracted from the early-phase (the 2nd phase) images of breast dynamic contrast-enhanced-MRI after neoadjuvant therapy.The four-step procedure was adopted for feature screening. The radiomics model was constructed by logistic regression. A combined model was constructed by integrating radiomics features and independent predictors. Two radiologists (Reader 1 with 10 years experience and Reader 2 with 13 years experience) who major in breast MRI visually evaluated the pCR status of breast cancer after neoadjuvant therapy. The receiver operating characteristic curve and area under the curve (AUC) were used to evaluate the efficacy of Reader 1, Reader 2, the radiomics model, and the combined model in predicting pCR status. The Hosmer-Lemeshow goodness-of-fit test was used to evaluate the calibration of the model.Results:Among 243 HER-2 positive breast cancer patients, totally 118 achieved pCR. In clinical and pathological features, HER-2 3+ was an independent predictor of pCR ( OR=2.71, 95% CI 1.03?7.12, P=0.043). In the training set and validation set, the AUCs of the radiomics model in predicting pCR status were 0.899 and 0.853, respectively.The AUCs of the combined model were 0.917 and 0.890, respectively. In the validation set, the AUC value of the radiomics model in predicting pCR status was higher than that of Reader 1 and Reader 2. Hosmer-Lemeshow goodness-of-fit test showed that there was no significant difference between the prediction of pCR status by the combined model and radiomics model and the actual results in the training set and validation set, and the fitting was good ( P>0.05). Conclusion:The MRI-based radiomics model can be used to predict pCR status in HER-2 positive breast cancer and outperforms the visual qualitative assessments of radiologists.

Objective:To develop an artificial intelligence (AI)-based automatic scoring model for magnetic resonance imaging-detected extramural vascular invasion (AI-mrEMVI) and evaluate its performance and prognostic value in patients with rectal cancer.Methods:In this multicenter retrospective cohort study, a total of 2 501 rectal cancer patients from seven centers between November 2012 and December 2020 were included and divided into completely independent training ( n=1 830) and validation ( n=671) cohorts. A nnUNet-based AI-mrEMVI scoring model was constructed. Manual mrEMVI scores assigned by two radiologists served as the reference standard for accessing the accuracy of the AI-mrEMVI scoring. Kaplan-Meier survival analysis and Cox regression were used to evaluate the prognostic stratification ability of the AI-mrEMVI scores. The concordance index (C-index) was calculated to evaluate prognostic performance. Results:In the validation cohort, the manual mrEMVI scores were 0-2 in 425 patients (63.3%), 3 in 89 (13.4%), and 4 in 157 (23.4%). The AI-mrEMVI model identified 0-2 in 375 patients (55.9%), 3 in 95 (14.2%), and 4 in 201 (30.0%), with an overall accuracy of 81.1% (544/671, 95% CI 77.9%-84.0%). The 3-year disease-free survival (DFS) rates for patients with AI-mrEMVI scores of 0-2, 3, and 4 were 85.2%, 70.0%, and 58.2%, respectively, and the 5-year overall survival (OS) rates were 87.2%, 81.6%, and 62.6%, respectively (DFS: χ2=48.74, P<0.001; OS: χ2=30.04, P<0.001). Multivariable Cox regression showed that for DFS, AI-mrEMVI scores of 3 and 4 were associated with hazard ratios ( HR) of 1.75 (95% CI 1.11-2.77, P=0.016) and 2.65 (95% CI 1.86-3.78, P<0.001), respectively. For OS, an AI-mrEMVI score of 4 was associated with an HR of 2.56 (95% CI 1.62-4.03, P<0.001). The C-index values of the AI-mrEMVI scoring model for predicting DFS and OS were 0.647 (95% CI 0.608-0.686) and 0.650 (95% CI 0.598-0.702), respectively. Conclusion:The proposed AI-mrEMVI automatic scoring model demonstrated high diagnostic accuracy and performed favorably in predicting DFS and OS prognostic risk in patients with rectal cancer.

Objective:To investigate the value of tumor volume to uterine volume ratio (N/U) combined with the expression of alpha-fetoprotein (AFP), sugar antigen 199 (CA199) and human epididymal secretory protein 4 (HE4) in evaluating the pathologic grade and prognosis of endometrial carcinoma (EC) .Methods:A total of 160 EC patients admitted to Linyi Central Hospital from Jan. 2021 to Dec. 2023 were divided into low-grade group and high-grade group according to FIGO grading method, and were divided into poor prognosis group and good prognosis group according to cancer death, recrudescence. The levels of N/U, AFP, CA199 and HE4 in patients with different pathologic grades and prognosis were compared. COX regression was used to analyze the influencing factors of EC adverse prognosis, ROC curve was used to analyze the value of N/U combined with serum AFP, CA199 and HE4 in predicting EC adverse prognosis, and a nomogram model was constructed.Results:Pathological examination of 160 EC patients showed that 12 cases were non-endometrioid adenocarcinoma, 148 cases were endometrioid adenocarcinoma, 41 cases were high-grade and 119 cases were low-grade.According to the follow-up, 94 of the 160 EC patients had good prognosis and 66 had poor prognosis. The levels of N/U, AFP, CA199 and HE4 in the poor prognosis group were higher than those in the good prognosis group ( P<0.05). COX regression analysis showed that high levels of N/U, AFP, CA199 and HE4 were all factors affecting the poor prognosis of EC patients ( P<0.05). The AUC value of combined detection of N/U, AFP, CA199 and HE4 in predicting adverse prognosis of EC patients was higher than that of single detection ( Z=3.140, 3.658, 4.277, 4.378, P<0.05) .The ROC curve AUC (95% CI) of the training set and the validation set were 0.84 (0.77-0.92) and 0.90 (0.81-0.98) respectively for the training set and the validation set to predict the adverse prognosis of EC patients. Calibration curve results showed that the calibration curve for EC patients predicted by the nomogram model was close to the ideal curve ( P=0.521, 0.743). The DCA curve shows that the probability threshold of the nomogram model has a higher positive net return at 20%~100%. Conclusion:The levels of N/U, AFP, CA199 and HE4 in EC patients are related to the pathologic grade, and the combined detection of these indicators can predict the poor prognosis of EC patients, and the nomogram model constructed based on these indicators has high predictive value.

Objective:To investigate the value of tumor volume to uterine volume ratio (N/U) combined with the expression of alpha-fetoprotein (AFP), sugar antigen 199 (CA199) and human epididymal secretory protein 4 (HE4) in evaluating the pathologic grade and prognosis of endometrial carcinoma (EC) .Methods:A total of 160 EC patients admitted to Linyi Central Hospital from Jan. 2021 to Dec. 2023 were divided into low-grade group and high-grade group according to FIGO grading method, and were divided into poor prognosis group and good prognosis group according to cancer death, recrudescence. The levels of N/U, AFP, CA199 and HE4 in patients with different pathologic grades and prognosis were compared. COX regression was used to analyze the influencing factors of EC adverse prognosis, ROC curve was used to analyze the value of N/U combined with serum AFP, CA199 and HE4 in predicting EC adverse prognosis, and a nomogram model was constructed.Results:Pathological examination of 160 EC patients showed that 12 cases were non-endometrioid adenocarcinoma, 148 cases were endometrioid adenocarcinoma, 41 cases were high-grade and 119 cases were low-grade.According to the follow-up, 94 of the 160 EC patients had good prognosis and 66 had poor prognosis. The levels of N/U, AFP, CA199 and HE4 in the poor prognosis group were higher than those in the good prognosis group ( P<0.05). COX regression analysis showed that high levels of N/U, AFP, CA199 and HE4 were all factors affecting the poor prognosis of EC patients ( P<0.05). The AUC value of combined detection of N/U, AFP, CA199 and HE4 in predicting adverse prognosis of EC patients was higher than that of single detection ( Z=3.140, 3.658, 4.277, 4.378, P<0.05) .The ROC curve AUC (95% CI) of the training set and the validation set were 0.84 (0.77-0.92) and 0.90 (0.81-0.98) respectively for the training set and the validation set to predict the adverse prognosis of EC patients. Calibration curve results showed that the calibration curve for EC patients predicted by the nomogram model was close to the ideal curve ( P=0.521, 0.743). The DCA curve shows that the probability threshold of the nomogram model has a higher positive net return at 20%~100%. Conclusion:The levels of N/U, AFP, CA199 and HE4 in EC patients are related to the pathologic grade, and the combined detection of these indicators can predict the poor prognosis of EC patients, and the nomogram model constructed based on these indicators has high predictive value.

Objective:To investigate the value of MRI radiomics model in evaluating the pathological complete response (pCR) status of human epidermal growth factor receptor 2(HER-2) positive breast cancer after neoadjuvant therapy.Methods:The study was a cross-sectional study. The clinical, pathological, and MRI data of 243 HER-2 positive breast cancer patients who received neoadjuvant therapy in Shanxi Province Cancer Hospital from January 2021 to June 2023 were retrospectively analyzed. All patients were female, aged 26?75 years. All patients were randomly divided into training set (146 cases) and validation set (97 cases) at a ratio of 6∶4 according to the simple random sampling method. Univariate and multivariate logistic regression were used to screen independent predictors of pCR. Radiomics features were extracted from the early-phase (the 2nd phase) images of breast dynamic contrast-enhanced-MRI after neoadjuvant therapy.The four-step procedure was adopted for feature screening. The radiomics model was constructed by logistic regression. A combined model was constructed by integrating radiomics features and independent predictors. Two radiologists (Reader 1 with 10 years experience and Reader 2 with 13 years experience) who major in breast MRI visually evaluated the pCR status of breast cancer after neoadjuvant therapy. The receiver operating characteristic curve and area under the curve (AUC) were used to evaluate the efficacy of Reader 1, Reader 2, the radiomics model, and the combined model in predicting pCR status. The Hosmer-Lemeshow goodness-of-fit test was used to evaluate the calibration of the model.Results:Among 243 HER-2 positive breast cancer patients, totally 118 achieved pCR. In clinical and pathological features, HER-2 3+ was an independent predictor of pCR ( OR=2.71, 95% CI 1.03?7.12, P=0.043). In the training set and validation set, the AUCs of the radiomics model in predicting pCR status were 0.899 and 0.853, respectively.The AUCs of the combined model were 0.917 and 0.890, respectively. In the validation set, the AUC value of the radiomics model in predicting pCR status was higher than that of Reader 1 and Reader 2. Hosmer-Lemeshow goodness-of-fit test showed that there was no significant difference between the prediction of pCR status by the combined model and radiomics model and the actual results in the training set and validation set, and the fitting was good ( P>0.05). Conclusion:The MRI-based radiomics model can be used to predict pCR status in HER-2 positive breast cancer and outperforms the visual qualitative assessments of radiologists.

Objective:To develop an artificial intelligence (AI)-based automatic scoring model for magnetic resonance imaging-detected extramural vascular invasion (AI-mrEMVI) and evaluate its performance and prognostic value in patients with rectal cancer.Methods:In this multicenter retrospective cohort study, a total of 2 501 rectal cancer patients from seven centers between November 2012 and December 2020 were included and divided into completely independent training ( n=1 830) and validation ( n=671) cohorts. A nnUNet-based AI-mrEMVI scoring model was constructed. Manual mrEMVI scores assigned by two radiologists served as the reference standard for accessing the accuracy of the AI-mrEMVI scoring. Kaplan-Meier survival analysis and Cox regression were used to evaluate the prognostic stratification ability of the AI-mrEMVI scores. The concordance index (C-index) was calculated to evaluate prognostic performance. Results:In the validation cohort, the manual mrEMVI scores were 0-2 in 425 patients (63.3%), 3 in 89 (13.4%), and 4 in 157 (23.4%). The AI-mrEMVI model identified 0-2 in 375 patients (55.9%), 3 in 95 (14.2%), and 4 in 201 (30.0%), with an overall accuracy of 81.1% (544/671, 95% CI 77.9%-84.0%). The 3-year disease-free survival (DFS) rates for patients with AI-mrEMVI scores of 0-2, 3, and 4 were 85.2%, 70.0%, and 58.2%, respectively, and the 5-year overall survival (OS) rates were 87.2%, 81.6%, and 62.6%, respectively (DFS: χ2=48.74, P<0.001; OS: χ2=30.04, P<0.001). Multivariable Cox regression showed that for DFS, AI-mrEMVI scores of 3 and 4 were associated with hazard ratios ( HR) of 1.75 (95% CI 1.11-2.77, P=0.016) and 2.65 (95% CI 1.86-3.78, P<0.001), respectively. For OS, an AI-mrEMVI score of 4 was associated with an HR of 2.56 (95% CI 1.62-4.03, P<0.001). The C-index values of the AI-mrEMVI scoring model for predicting DFS and OS were 0.647 (95% CI 0.608-0.686) and 0.650 (95% CI 0.598-0.702), respectively. Conclusion:The proposed AI-mrEMVI automatic scoring model demonstrated high diagnostic accuracy and performed favorably in predicting DFS and OS prognostic risk in patients with rectal cancer.

Objective: To investigate the potential association among preoperative breast MRI features, axillary nodal burden (ANB), and disease-free survival (DFS) in patients with early-stage breast cancer. Materials and Methods: We retrospectively reviewed 297 patients with early-stage breast cancer (cT1-2N0M0) who underwent preoperative MRI between December 2016 and December 2018. Based on the number of positive axillary lymph nodes (LNs) determined by postoperative pathology, the patients were divided into high nodal burden (HNB; ≥3 positive LNs) and non-HNB (<3 positive LNs) groups. Univariable and multivariable logistic regression analyses were performed to identify independent risk factors associated with ANB. Predictive efficacy was evaluated using the receiver operating characteristic (ROC) curve and area under the curve (AUC). Univariable and multivariable Cox proportional hazards regression analyses were performed to determine preoperative features associated with DFS. Results: We included 47 and 250 patients in the HNB and non-HNB groups, respectively. Multivariable logistic regression analysis revealed that multifocality/multicentricity (adjusted odds ratio [OR] = 3.905, 95% confidence interval [CI]: 1.685– 9.051, P= 0.001) and peritumoral edema (adjusted OR = 3.734, 95% CI: 1.644–8.479, P = 0.002) were independent risk factors for HNB. Combined peritumoral edema and multifocality/multicentricity achieved an AUC of 0.760 (95% CI: 0.707– 0.807) for predicting HNB, with a sensitivity and specificity of 83.0% and 63.2%, respectively. During the median follow-up period of 45 months (range, 5–61 months), 26 cases (8.75%) of breast cancer recurrence were observed. Multivariable Cox proportional hazards regression analysis indicated that younger age (adjusted hazard ratio [HR] = 3.166, 95% CI: 1.200–8.352, P= 0.021), larger tumor size (adjusted HR = 4.370, 95% CI: 1.671–11.428, P= 0.002), and multifocality/multicentricity (adjusted HR = 5.059, 95% CI: 2.166–11.818, P< 0.001) were independently associated with DFS. Conclusion Preoperative breast MRI features may be associated with ANB and DFS in patients with early-stage breast cancer.

Objective:To investigate the value of preoperative breast MRI combined with axillary ultrasound in predicting lymphovascular invasion (LVI) of breast invasive ductal carcinoma.Methods:The clinical, pathological and imaging features of 160 female patients [age 25-74(49±10)years] with breast invasive ductal carcinoma from March 2014 to December 2017 in Shanxi Cancer Hospital were retrospectively analyzed. According to the LVI status determined by postoperative pathology, 160 patients were divided into LVI positive group (56 cases) and LVI negative group (104 cases). The clinical characteristics, pathological characteristics and imaging features of LVI positive group and LVI negative group were compared by the independent t test, Mann-Whitney U test or χ 2 test. Multivariate logistic regression analysis was performed to identify independent predictors for predicting LVI and construct a predictive model. The receiver operating characteristic (ROC) curve and area under the curve (AUC) was used to evaluate the discrimination of the prediction model, and the Hosmer-Lemeshow test was used to evaluate its calibration. Results:There was no significant difference in age, menopausal status, estrogen receptor, progesterone receptor, human epidermal growth factor 2, Ki67 index and molecular subtype between LVI positive group and negative group ( P>0.05). Tumor size, peritumoral edema, adjacent vessel sign, multifocality or multicentricity, peritumoral maximum-apparent diffusion coefficient (ADC), peritumour-tumour ADC ratio, MRI axillary lymph node status and ultrasound axillary lymph node status between LVI positive group and LVI negative group showed significantly statistical difference ( P<0.05). Variables with significant difference in the univariate analysis were entered into multivariate logistic regression analysis to explore predictors for LVI. Peritumoral edema (OR=3.367, 95%CI 1.382-8.201, P=0.008), multifocality or multicentricity (OR=4.026, 95%CI 1.268-12.776, P=0.018), high peritumoral-tumor ADC ratio (OR=7.321, 95%CI 2.226-24.079, P=0.001) and positive ultrasound axillary lymph node (OR=6.779, 95%CI 2.819-16.303, P<0.001) were independent predictors for predicting LVI. A logistic regression model was constructed using the above four indicators, and ROC showed AUC of this model for predicting LVI was 0.882, superior to any of the single indicator ( P<0.05); its sensitivity was 80.36% and specificity was 84.62%. Hosmer-lemeshow test showed that the prediction model had good calibration ( P=0.503). Conclusion:The combined prediction model constructed by preoperative breast MRI and axillary ultrasound could help to predict the LVI status of breast invasive ductal carcinoma.

Objective:To investigate the efficacy prediction and evaluation value of neoadjuvant chemotherapy for breast cancer by using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) texture analysis.Methods:The clinical data of 63 patients with pathologically confirmed breast cancer in the Shanxi Provincial Cancer Hospital from September 2014 to October 2018 were retrospectively analyzed. All the patients underwent DCE-MRI before and after neoadjuvant chemotherapy and they were divided into the treatment-effective group (40 cases) and the treatment-ineffective group (23 cases) according to the postoperative pathological results. Texture parameters from volume transfer (Ktrans) maps of DCE-MRI before neoadjuvant chemotherapy and after 4-8 cycles of neoadjuvant chemotherapy were measured by using Omni-Kinetics software. The comparison of texture parameters between the two groups was performed by using independent sample t test or Mann-Whitney U test. The receiver operating characteristic curve was drawn and the prediction efficiency of these texture parameters in the therapeutic efficacy of neoadjuvant chemotherapy for breast cancer according to the corresponding area under the curve (AUC) was evaluated.Results:A total of 33 texture parameters were enrolled, and finally 29 texture parameters were retained. Before and after neoadjuvant chemotherapy 22 texture parameters had statistically significant difference in 63 patients (all P < 0.05). There was a statistically significant difference in 9 texture parameters between the two groups before neoadjuvant chemotherapy (all P < 0.05), including uniformity [0.17 (-0.06, 0.34), 0.39 (0.22, 0.48), Z = -2.955, P < 0.01], histogram energy [169.88 (129.36, 288.77), 116.22 (93.77, 151.95), Z = 3.241, P < 0.01] and histogram entropy [6.33 (5.71, 6.69), 6.68 (6.52, 6.97), Z = -2.991, P < 0.01]. After neoadjuvant chemotherapy, 8 of the 29 texture parameters between the two groups had statistically significant differences (all P < 0.05), including histogram entropy (6.00±0.71, 6.46±0.49, t = -2.720, P < 0.01), entropy (6.81±1.40, 8.02±1.48, t = -3.238, P < 0.01), Haralick entropy [0.49±0.10, 0.55±0.10, Z = -2.613, P < 0.01], grey level non-uniformity (GLN) [1.68 (1.42, 3.37), 4.92 (3.58, 8.50), Z = -3.897, P < 0.01], run length non-uniformity (RLN) [100.38 (65.31, 305.75), 359.75 (176.75, 655.00), Z = -4.033, P < 0.01]. There were statistical differences in 8 parameters change rate before and after neoadjuvant chemotherapy between the two groups (all P < 0.05), mainly including ΔGLN [-0.72 (-0.78, -0.60), -0.23 (-0.55, 0.36), Z = -4.554, P < 0.01], ΔRLN [-0.71 (-0.85, -0.52), -0.33 (-0.48, -0.10), Z = -4.454, P < 0.01], Δhigh grey level run emphasis (HGLRE) [1.28 (0.39, 3.46), 0.11 (-0.24, 0.86), Z = 3.184, P < 0.01]. According to the ROC curve, AUC of GLN, RLN, ΔGLN and ΔRLN after neoadjuvant chemotherapy was 0.80, 0.81, 0.85 and 0.84, respectively. Conclusion:Some texture parameters obtained from DCE-MRI Ktrans map can predict and evaluate the efficacy of neoadjuvant chemotherapy in breast cancer.

Objective: To observe the related factors of premature infants with different gestational age. Methods: In the premature infants who were followed up after discharge, 114 cases with complete data were selected, and grouped at birth by gestational age.The possible impact variables were collected, single factor analysis was used to screen possible factors, then multiple linear regression analysis was conducted. Results: Of 114 premature infants, the incidence rate of pregnancy induced hypertension in pregnancy complications was 38.60%.Secondly, the incidence rate of premature rupture of membranes was 30.70%.The incidence of preterm birth in pregnancy complications was 2.111 times greater than that in non pregnancy complications, its confidence interval was (0.846, 5.269). The level of education of parents above college was preterm, and the severity was 0.627 times higher than that in non universities, its confidence interval was (0.311, 1.266). Multiple linear regression analysis showed that preconception complications and parents' degree of culture were the related factors of premature infants. Conclusion Reducing pregnancy complications and raising the level of parent culture can reduce preterm birth.