Objective:To develop an artificial intelligence（AI）-based sequential ultrasound-magnetic resonance imaging（US-MRI）diagnostic strategy to optimize the imaging workflow for ovarian masses.Methods:A total of 1 120 patients with pathologically confirmed ovarian masses who underwent both preoperative pelvic ultrasound and MRI between January 2021 and December 2023 at Women's Hospital，Zhejiang University School of Medicine were retrospectively included. Patients were randomly divided into the training（ n=672）and internal test set（ n=448）at a ratio of 6∶4. An external test set（ n=128）was established at the Forth Affiliated Hospital of School of Medicine. Deep learning was used for automated segmentation of MRI lesions，followed by radiomic feature extraction and machine learning classification to construct both a US-MRI multimodal model and sequential US-MRI strategy. Diagnostic performance and potential healthcare cost-saving effects were evaluated across strategies. Results:In the internal test set（ n=448），the AI-based sequential US-MRI strategy achieved a F1 score of 0.863 and a diagnostic accuracy of 82.14%，with no significant difference compared to the US-MRI multi-modal model（ P>0.05）. The sequential strategy identified 82 cases（18.30%，82/448）of patients as low-risk true negatives during initial ultrasound screening，suggesting a potential to reduce the need for MRI examinations in future clinical practice. In the external test set（ n=128），the strategy achieved an F1 score of 0.800 and a confirmed diagnosis rate of 85.94%，with a theoretical reduction of 26.56%（34 cases）in MRI utilization while maintaining a diagnostic accuracy rate higher than that of the multi-modal model（82.18%）. Conclusions:The AI-based US-MRI sequential diagnostic strategy demonstrates favorable diagnostic accuracy while offering the potential to optimize MRI utilization. This approach may enhance the efficiency of imaging resource allocation and reduce healthcare burden in the management of ovarian masses.

Objective To explore the value of clinical-MRI radiomics combined model for differentiating borderline ovarian tumor(BOT)from epithelial ovarian cancer(EOC).Methods Totally 139 patients with BOT(BOT group)and 307 patients with EOC(EOC group)confirmed by postoperative pathology and underwent preoperative pelvic MRI were retrospectively enrolled and randomly divided into training set(n=312)and test set(n=134)at a ratio of 7∶3.Multivariable logistic regression was used to identify independent clinical predictors for differentiating BOT and EOC,then a clinical model was constructed.Radiomics features were extracted from the volumes of interest(VOI)of lesions on T2WI,diffusion weighted imaging(DWI)and apparent diffusion coefficient(ADC)images,respectively,and single-sequence and multi-sequence MRI radiomics models were built using extreme gradient boosting(XGBoost)based on data in training set.The optimal MRI radiomics model was selected according to the highest area under the curve(AUC)in test set,and a clinical-MRI radiomics combined model was constructed combined the optimal radiomics model with independent clinical predictors.The performances of clinical model,the optimal MRI radiomics model and the combined model for differentiating BOT and EOC were compared in test set.SHapley Additive exPlanations(SHAP)analysis was applied to interpret key predictive features in the best model.Results Patients' age,carbohydrate antigen 153(CA153)and carbohydrate antigen 125(CA125)were all independent predictors for differentiating BOT and EOC(all P＜0.05).Multi-sequence MRI radiomics model was the optimal MRI radiomics model.The combined model showed superior performance(AUC=0.929)for discriminating BOT and EOC compared with clinical model(AUC=0.881)and multi-sequence MRI radiomics model(AUC=0.871)(both P＜0.05).SHAP beeswarm plot revealed that the top 10 important features of combined model included age,CA153 and CA125,as well as entropy,kurtosis and gray level non-uniformity from ADC and DWI sequences.Conclusion Clinical-MRI radiomics combined model based on multi-sequence MRI radiomics features and clinical features could be used to effectively differentiate BOT from EOC.

Objective To investigate the effects of hypoxia on the transcriptional phenotype and ultrastructure of tumor-associated macrophages(TAMs)in glioma.Methods CD14+monocytes were isolated from healthy human peripheral blood samples collected from the Blood Bank of the First Affiliated Hospital of Army Medical University,and the cells were induced to differentiate into TAMs through co-culture with glioma cell-conditioned medium.Hypoxic TAM models were established using varying concentrations of cobalt chloride hexahydrate(CoCl2,50～400 μmol/L)or hypoxic conditions(1%,5%,10%O2)for 48 h,while normoxic TAM models(21%O2)served as controls.RT-qPCR and transcriptome sequencing were employed to analyze transcriptional changes in TAMs under normoxic and hypoxic conditions.Gene set enrichment analysis(GSEA)was applied to compare the differences in angiogenesis,glycolysis and other hypoxia-responsive pathways between the 2 conditions.Transmission electron microscopy(TEM)or immunofluorescence staining was conducted to assess the ultrastructural alterations in cytoskeleton,endoplasmic reticulum(ER),and mitochondria in normoxic and hypoxic TAMs(1%O2).Results Hypoxic TAMs exhibited up-regulated transcription of hypoxia-responsive markers(oxygen transport,glycolysis,pro-angiogenesis),with the effects correlating with hypoxia severity(P<0.05).GSEA revealed significant up-regulation of hypoxia,angiogenesis regulation,glycolysis and gluconeogenesis,and starvation stress pathways,alongside down-regulation of innate immunity,macrophage activation,cytoskeleton,and protein maturation pathways in hypoxic TAMs(P<0.05).TEM and immunofluorescence staining demonstrated obvious ultrastructure changes,including disrupted cytoskeletal organization,shortened rough ER with reduced ribosomes,mitochondrial swelling with cristae damage,and diminished ER-mitochondria contacts in hypoxic TAMs.Conclusion CoCl2 and hypoxia induce a hypoxic transcriptional phenotype in TAMs,which may potentially associated with ultrastructural remodeling of the cytoskeleton,ER,and mitochondria.

Over the past 40 years,gynecological ultrasound in China has evolved from two-dimensional imaging to multi-modal imaging,quantitative analysis,artificial intelligence analysis and minimally invasive treatment,playing more and more important role in diagnosis and treatment of gynecological diseases.The development of diagnostic and therapeutic gynecological ultrasound techniques and relative clinical application advances in China were reviewed,and the future development prospects were looked forward to in this article.

Objective:To observe any therapeutic effect of kinesio taping the orbicularis oris and cervical swallowing muscle groups on drooling among children with cerebral palsy (CP).Methods:Fifty-two children with CP salivating excessively were divided at random into a control group and an experimental group, each of 26. Both groups received routine oral and facial exercise training and sensory stimulation, but the experimental group was additionally provided with kinesio taping of the orbicularis oris muscle and related neck muscle groups. The taping was applied twice a week for 12 hours each time, continuing for 6 months. Before and after the treatment, both groups′ drooling and language use were evaluated using the teacher drooling grading method (TDS) and a language developmental delay assessment (S-S), respectively. Kendall rank correlation coefficients were computed to compare the treatment efficacy for children with the same TDS grading, cerebral palsy classification, and S-S segmentation.Results:After the treatment the average TDS scores of both groups had decreased significantly. The average TDS score of the experimental group was then significantly lower than that of the control group. The total effectiveness rate for those in the experimental group with TDS grades II or V was significantly higher than those controls with the same TDS grades, the effectiveness rate for those with spastic and mixed type or language function in stage 4-2 and stage 5-2 in the experiment group was also significantly higher than for those of the control group. According to the correlation analysis, the language function of both groups was significantly correlated with the therapeutic effect.Conclusions:Supplementing routine rehabilitation training with kinesio taping of the orbicularis oris muscle and the cervical swallowing muscle group can significantly relieve CP children′s excessive salivation. Their language use is significantly positively correlated with the effectiveness of such combined treatment.

Objective:To observe any therapeutic effect of kinesio taping the orbicularis oris and cervical swallowing muscle groups on drooling among children with cerebral palsy (CP).Methods:Fifty-two children with CP salivating excessively were divided at random into a control group and an experimental group, each of 26. Both groups received routine oral and facial exercise training and sensory stimulation, but the experimental group was additionally provided with kinesio taping of the orbicularis oris muscle and related neck muscle groups. The taping was applied twice a week for 12 hours each time, continuing for 6 months. Before and after the treatment, both groups′ drooling and language use were evaluated using the teacher drooling grading method (TDS) and a language developmental delay assessment (S-S), respectively. Kendall rank correlation coefficients were computed to compare the treatment efficacy for children with the same TDS grading, cerebral palsy classification, and S-S segmentation.Results:After the treatment the average TDS scores of both groups had decreased significantly. The average TDS score of the experimental group was then significantly lower than that of the control group. The total effectiveness rate for those in the experimental group with TDS grades II or V was significantly higher than those controls with the same TDS grades, the effectiveness rate for those with spastic and mixed type or language function in stage 4-2 and stage 5-2 in the experiment group was also significantly higher than for those of the control group. According to the correlation analysis, the language function of both groups was significantly correlated with the therapeutic effect.Conclusions:Supplementing routine rehabilitation training with kinesio taping of the orbicularis oris muscle and the cervical swallowing muscle group can significantly relieve CP children′s excessive salivation. Their language use is significantly positively correlated with the effectiveness of such combined treatment.

Objective To explore the value of clinical-MRI radiomics combined model for differentiating borderline ovarian tumor(BOT)from epithelial ovarian cancer(EOC).Methods Totally 139 patients with BOT(BOT group)and 307 patients with EOC(EOC group)confirmed by postoperative pathology and underwent preoperative pelvic MRI were retrospectively enrolled and randomly divided into training set(n=312)and test set(n=134)at a ratio of 7∶3.Multivariable logistic regression was used to identify independent clinical predictors for differentiating BOT and EOC,then a clinical model was constructed.Radiomics features were extracted from the volumes of interest(VOI)of lesions on T2WI,diffusion weighted imaging(DWI)and apparent diffusion coefficient(ADC)images,respectively,and single-sequence and multi-sequence MRI radiomics models were built using extreme gradient boosting(XGBoost)based on data in training set.The optimal MRI radiomics model was selected according to the highest area under the curve(AUC)in test set,and a clinical-MRI radiomics combined model was constructed combined the optimal radiomics model with independent clinical predictors.The performances of clinical model,the optimal MRI radiomics model and the combined model for differentiating BOT and EOC were compared in test set.SHapley Additive exPlanations(SHAP)analysis was applied to interpret key predictive features in the best model.Results Patients' age,carbohydrate antigen 153(CA153)and carbohydrate antigen 125(CA125)were all independent predictors for differentiating BOT and EOC(all P＜0.05).Multi-sequence MRI radiomics model was the optimal MRI radiomics model.The combined model showed superior performance(AUC=0.929)for discriminating BOT and EOC compared with clinical model(AUC=0.881)and multi-sequence MRI radiomics model(AUC=0.871)(both P＜0.05).SHAP beeswarm plot revealed that the top 10 important features of combined model included age,CA153 and CA125,as well as entropy,kurtosis and gray level non-uniformity from ADC and DWI sequences.Conclusion Clinical-MRI radiomics combined model based on multi-sequence MRI radiomics features and clinical features could be used to effectively differentiate BOT from EOC.

Over the past 40 years,gynecological ultrasound in China has evolved from two-dimensional imaging to multi-modal imaging,quantitative analysis,artificial intelligence analysis and minimally invasive treatment,playing more and more important role in diagnosis and treatment of gynecological diseases.The development of diagnostic and therapeutic gynecological ultrasound techniques and relative clinical application advances in China were reviewed,and the future development prospects were looked forward to in this article.

Objective:To develop an artificial intelligence（AI）-based sequential ultrasound-magnetic resonance imaging（US-MRI）diagnostic strategy to optimize the imaging workflow for ovarian masses.Methods:A total of 1 120 patients with pathologically confirmed ovarian masses who underwent both preoperative pelvic ultrasound and MRI between January 2021 and December 2023 at Women's Hospital，Zhejiang University School of Medicine were retrospectively included. Patients were randomly divided into the training（ n=672）and internal test set（ n=448）at a ratio of 6∶4. An external test set（ n=128）was established at the Forth Affiliated Hospital of School of Medicine. Deep learning was used for automated segmentation of MRI lesions，followed by radiomic feature extraction and machine learning classification to construct both a US-MRI multimodal model and sequential US-MRI strategy. Diagnostic performance and potential healthcare cost-saving effects were evaluated across strategies. Results:In the internal test set（ n=448），the AI-based sequential US-MRI strategy achieved a F1 score of 0.863 and a diagnostic accuracy of 82.14%，with no significant difference compared to the US-MRI multi-modal model（ P>0.05）. The sequential strategy identified 82 cases（18.30%，82/448）of patients as low-risk true negatives during initial ultrasound screening，suggesting a potential to reduce the need for MRI examinations in future clinical practice. In the external test set（ n=128），the strategy achieved an F1 score of 0.800 and a confirmed diagnosis rate of 85.94%，with a theoretical reduction of 26.56%（34 cases）in MRI utilization while maintaining a diagnostic accuracy rate higher than that of the multi-modal model（82.18%）. Conclusions:The AI-based US-MRI sequential diagnostic strategy demonstrates favorable diagnostic accuracy while offering the potential to optimize MRI utilization. This approach may enhance the efficiency of imaging resource allocation and reduce healthcare burden in the management of ovarian masses.

The application of artificial intelligence(AI)in medical diagnosis and treatment is becoming increasingly widespread,providing doctors and patients with more high-quality,efficient and personalized medical services.However,it also raised a series of ethical issues such as data security,algorithm transparency,responsibility definition,fairness and justice,doctor-patient relationships,and other aspects.Based on the combing of existing research results,this paper analyzed the research status of medical ethics in the application of AI in diagnosis and treatment,as well as expected that future medical ethics research can further explore the ethical issues of AI technology in medical treatment in greater depth,thus ensuring the rational application of AI in the medical field and maximizing the protection of patients'rights and interests.