Objective:To evaluate the value of the proposed interpretable denoising deep learning model-grouped sharing convolutional attention-visual transformer（GSCAViT）for classifying normal fetal echocardiograms.Methods:A total of 2 501 images from 358 fetuses who underwent cardiac ultrasound examinations at Xiangya Second Hospital of Central South University from January to November 2024 were retrospectively analyzed. GSCAViT was constructed based on fetal echocardiograms from the three-vessel and trachea view，apical four-chamber view，long-axis view of the aortic arch，bicaval view，left ventricular outflow tract view，three-vessel view and right ventricular outflow tract view were compared with both baseline and improved models in the validation set to assess the performance of the classification echocardiography in terms of accuracy，precision，recall and F1-score. Its generalizability across test sets was assessed using the area under the ROC curve（AUC），sensitivity，specificity and F1-score. The impact of image features was interpreted using SHapley Additive exPlanations（SHAP）.The effectiveness of the GSCA module was compared through visual analysis，image parameter metrics and classification performance.Results:The GSCAViT model achieved classification performance for fetal echocardiograms second only to MaxViT，with an accuracy of 97.1%，precision of 97.1%，recall of 97.0%，and an F1-score of 97.0%. In the E10，E20 and E8 test sets，the AUCs of GSCAViT for the prediction of 7 types of fetal echocardiograms were 0.994，0.928 and 0.932，the sensitivities were 99.4%，81.3% and 72.9%，the specificities were 99.7%，96.8% and 94.8%，the F1-scores were 99.4%，81.3% and 67.6%，respectively. SHAP visualization indicated that the model could identify key structural features within the images. Images processed by the denoising-guided group-sharing convolutional attention module best captured and enhanced important regional features，achieving the highest contrast-to-noise ratio，peak signal-to-noise ratio and optimal classification performance，which demonstrated the module's effectiveness.Conclusions:The proposed GSCAViT model exhibits superior performance in classifying seven types of normal fetal echocardiograms compared to the baseline and some improved models. Furthermore，SHAP visualization enhances the interpretability of the classification results，and visual comparisons，image parameter analyses，as well as classification performance metrics confirming the effectiveness of the denoising-guided group-sharing convolutional attention module in the visual transformer model.

Objective:To focus on the comparison of protrusion and width in zygomatic bones between the patients with the maxillary retrusion and normal subjects, in order to explore the relationship between maxillary retrusion and protrusion and width of zygomatic bones.Methods:DICOM data of spiral CT in craniomaxillofacial region were collected from the database of Department of Radiology, the Affiliated Hospital of Stomatology, China Medical University from January 2020 to July 2023. The study group included patients with maxillary retrusion and mandibular protrusion. The control group included the normal people with Angle’s Class Ⅰ occlusion. The three-dimensional(3D) images of craniofacial skeletons were built with ProPlan CMF 2.0 Software. The 3D-McNamara cephalometric analysis based on the coronal plane (CP) containing midpoint of the nasofrontal suture (N) were carried out for the anterior-posterior linear distances to the coronal plan of the maxillary alveolar base point (A-CP), the anterior-posterior linear distances of the landmark points of zygomatic bones (zygomatic protrusion), and for the width of the same landmark points on the left and right sides. The normal distribution measurement data were expressed as Mean±SD. The independent sample t-test was carried out between the same measurements of the two groups. In order to prove the relationship between the protrusion of maxilla and zygoma, the test of Pearson’s correlation analysis was carried out between the A-CP and the zygomatic landmarks of the orbital point of frontal-malar suture (Fmo-CP), the lowest point on the margin of the orbital (Or-CP), the most protrusive and front point of zygomatic bone (Mp-CP), and the lowest point of zygomatic-maxillary suture (Zm-CP). Results:A Total of 37 patients with maxillary retrusion were collected for study group (male 21, female 16, mean age of 21.1±3.2) and 33 normal subjects for control group (male 14, female 19, mean age of 21.1±2.5). The Mp-CP and the Zm-CP in the study group were significantly smaller than those in the control group ( P<0.05). Pearson’s correlation test showed that Mp-CP and Zm-CP were positively correlated with A-CP in the two groups ( r=0.38-0.49, P<0.05). But the horizontal width of zygomatic bones between the two groups did not show significant differences ( P>0.05). The ratio between the width of the lowest point of the zygomatic-temporal suture (Ztl) and the width of temporal points of frontal-malar suture (Fmt) was 1.21. Conclusion:The lower parts of zygomatic bones below the frontal-malar suture in patients with maxillary retrusion are affected by development of maxillary bones in sagittal direction and keep a positive relationship with the protrusion of maxillary bones. The zygomatic bone width of patients with maxillary retrusion is not affected by the sagittal development state of maxillary bones.

BACKGROUND: Neoadjuvant chemoradiotherapy followed by radical surgery has been a common practice for patients with locally advanced rectal cancer, but the response rate varies among patients. This study aimed to develop a ResNet-Vision Transformer based magnetic resonance imaging (MRI)-endoscopy fusion model to precisely predict treatment response and provide personalized treatment. METHODS: In this multicenter study, 366 eligible patients who had undergone neoadjuvant chemoradiotherapy followed by radical surgery at eight Chinese tertiary hospitals between January 2017 and June 2024 were recruited, with 2928 pretreatment colonic endoscopic images and 366 pelvic MRI images. An MRI-endoscopy fusion model was constructed based on the ResNet backbone and Transformer network using pretreatment MRI and endoscopic images. Treatment response was defined as good response or non-good response based on the tumor regression grade. The Delong test and the Hanley-McNeil test were utilized to compare prediction performance among different models and different subgroups, respectively. The predictive performance of the MRI-endoscopy fusion model was comprehensively validated in the test sets and was further compared to that of the single-modal MRI model and single-modal endoscopy model. RESULTS: The MRI-endoscopy fusion model demonstrated favorable prediction performance. In the internal validation set, the area under the curve (AUC) and accuracy were 0.852 (95% confidence interval [CI]: 0.744-0.940) and 0.737 (95% CI: 0.712-0.844), respectively. Moreover, the AUC and accuracy reached 0.769 (95% CI: 0.678-0.861) and 0.729 (95% CI: 0.628-0.821), respectively, in the external test set. In addition, the MRI-endoscopy fusion model outperformed the single-modal MRI model (AUC: 0.692 [95% CI: 0.609-0.783], accuracy: 0.659 [95% CI: 0.565-0.775]) and the single-modal endoscopy model (AUC: 0.720 [95% CI: 0.617-0.823], accuracy: 0.713 [95% CI: 0.612-0.809]) in the external test set. CONCLUSION The MRI-endoscopy fusion model based on ResNet-Vision Transformer achieved favorable performance in predicting treatment response to neoadjuvant chemoradiotherapy and holds tremendous potential for enabling personalized treatment regimens for locally advanced rectal cancer patients.
Humans ; Rectal Neoplasms/diagnostic imaging* ; Magnetic Resonance Imaging/methods* ; Male ; Female ; Middle Aged ; Neoadjuvant Therapy/methods* ; Aged ; Adult ; Chemoradiotherapy/methods* ; Endoscopy/methods* ; Treatment Outcome

OBJECTIVE: To review clinical application and research progress of different types of intelligent responsive hydrogels in repairing articular cartilage injury. METHODS: The animal experiments and clinical studies of different types of intelligent responsive hydrogels for repairing articular cartilage injury were summarized by reviewing relevant literature at home and abroad. RESULTS: The intrinsic regenerative capacity of articular cartilage following injury is limited. Intelligent responsive hydrogels, including those that are temperature-sensitive, light-sensitive, enzyme-responsive, pH-sensitive, and other stimuli-responsive hydrogels, can undergo phase transitions in response to specific stimuli, thereby achieving optimal functionality. These hydrogels can fill the injured cartilage area, promote the proliferation and differentiation of chondrocytes, and expedite the repair of the damaged site. With advancements in cartilage tissue engineering materials research, intelligent responsive hydrogels offer a novel approach and promising potential for the treatment of cartilage injuries. CONCLUSION Intelligent responsive hydrogel is a kind of flexible, controllable, efficient, and stable polymer, which has similar structure and functional properties to articular cartilage, and has become one of the important biomaterials for cartilage repair. However, there is still a lack of unified treatment standards and simple and efficient preparation technology.
Hydrogels/therapeutic use* ; Cartilage, Articular/injuries* ; Tissue Engineering/methods* ; Humans ; Animals ; Chondrocytes/cytology* ; Biocompatible Materials/chemistry* ; Tissue Scaffolds/chemistry*

Objective:To evaluate the value of the proposed interpretable denoising deep learning model-grouped sharing convolutional attention-visual transformer（GSCAViT）for classifying normal fetal echocardiograms.Methods:A total of 2 501 images from 358 fetuses who underwent cardiac ultrasound examinations at Xiangya Second Hospital of Central South University from January to November 2024 were retrospectively analyzed. GSCAViT was constructed based on fetal echocardiograms from the three-vessel and trachea view，apical four-chamber view，long-axis view of the aortic arch，bicaval view，left ventricular outflow tract view，three-vessel view and right ventricular outflow tract view were compared with both baseline and improved models in the validation set to assess the performance of the classification echocardiography in terms of accuracy，precision，recall and F1-score. Its generalizability across test sets was assessed using the area under the ROC curve（AUC），sensitivity，specificity and F1-score. The impact of image features was interpreted using SHapley Additive exPlanations（SHAP）.The effectiveness of the GSCA module was compared through visual analysis，image parameter metrics and classification performance.Results:The GSCAViT model achieved classification performance for fetal echocardiograms second only to MaxViT，with an accuracy of 97.1%，precision of 97.1%，recall of 97.0%，and an F1-score of 97.0%. In the E10，E20 and E8 test sets，the AUCs of GSCAViT for the prediction of 7 types of fetal echocardiograms were 0.994，0.928 and 0.932，the sensitivities were 99.4%，81.3% and 72.9%，the specificities were 99.7%，96.8% and 94.8%，the F1-scores were 99.4%，81.3% and 67.6%，respectively. SHAP visualization indicated that the model could identify key structural features within the images. Images processed by the denoising-guided group-sharing convolutional attention module best captured and enhanced important regional features，achieving the highest contrast-to-noise ratio，peak signal-to-noise ratio and optimal classification performance，which demonstrated the module's effectiveness.Conclusions:The proposed GSCAViT model exhibits superior performance in classifying seven types of normal fetal echocardiograms compared to the baseline and some improved models. Furthermore，SHAP visualization enhances the interpretability of the classification results，and visual comparisons，image parameter analyses，as well as classification performance metrics confirming the effectiveness of the denoising-guided group-sharing convolutional attention module in the visual transformer model.

Objective:To focus on the comparison of protrusion and width in zygomatic bones between the patients with the maxillary retrusion and normal subjects, in order to explore the relationship between maxillary retrusion and protrusion and width of zygomatic bones.Methods:DICOM data of spiral CT in craniomaxillofacial region were collected from the database of Department of Radiology, the Affiliated Hospital of Stomatology, China Medical University from January 2020 to July 2023. The study group included patients with maxillary retrusion and mandibular protrusion. The control group included the normal people with Angle’s Class Ⅰ occlusion. The three-dimensional(3D) images of craniofacial skeletons were built with ProPlan CMF 2.0 Software. The 3D-McNamara cephalometric analysis based on the coronal plane (CP) containing midpoint of the nasofrontal suture (N) were carried out for the anterior-posterior linear distances to the coronal plan of the maxillary alveolar base point (A-CP), the anterior-posterior linear distances of the landmark points of zygomatic bones (zygomatic protrusion), and for the width of the same landmark points on the left and right sides. The normal distribution measurement data were expressed as Mean±SD. The independent sample t-test was carried out between the same measurements of the two groups. In order to prove the relationship between the protrusion of maxilla and zygoma, the test of Pearson’s correlation analysis was carried out between the A-CP and the zygomatic landmarks of the orbital point of frontal-malar suture (Fmo-CP), the lowest point on the margin of the orbital (Or-CP), the most protrusive and front point of zygomatic bone (Mp-CP), and the lowest point of zygomatic-maxillary suture (Zm-CP). Results:A Total of 37 patients with maxillary retrusion were collected for study group (male 21, female 16, mean age of 21.1±3.2) and 33 normal subjects for control group (male 14, female 19, mean age of 21.1±2.5). The Mp-CP and the Zm-CP in the study group were significantly smaller than those in the control group ( P<0.05). Pearson’s correlation test showed that Mp-CP and Zm-CP were positively correlated with A-CP in the two groups ( r=0.38-0.49, P<0.05). But the horizontal width of zygomatic bones between the two groups did not show significant differences ( P>0.05). The ratio between the width of the lowest point of the zygomatic-temporal suture (Ztl) and the width of temporal points of frontal-malar suture (Fmt) was 1.21. Conclusion:The lower parts of zygomatic bones below the frontal-malar suture in patients with maxillary retrusion are affected by development of maxillary bones in sagittal direction and keep a positive relationship with the protrusion of maxillary bones. The zygomatic bone width of patients with maxillary retrusion is not affected by the sagittal development state of maxillary bones.

TCM believes that spleen deficiency is the root cause of emotional abnormalities in chronic fatigue syndrome (CFS), and clinical treatment often involves the heart, liver and kidney. TCM therapy has a significant efficacy in CFS emotional abnormalities. It is mostly treated with oral administration of TCM, acupuncture, moxibustion and massage therapy. It may play a therapeutic role by improving oxidative stress and immune inflammation, regulating nerve-endocrine, controlling energy metabolism and other ways. It is suggested to establish the syndrome differentiation standard of CFS emotional abnormality in the future, so as to improve the accuracy of syndrome differentiation and treatment; form a perfect treatment guide or expert consensus to guide the standardized application of various internal and external treatment methods; explore objective indicators based on the pathogenesis, and focus on the morphological and functional changes of disease target brain regions with the help of neuroimaging techniques, so as to improve the diagnosis and prognosis evaluation of CFS; based on the guidance of TCM theory, improve the CFS emotional abnormal animal modeling method.

Objective:To explore the relationship between social exclusion, rumination, executive function and mobile phone addiction among college students.Methods:From November to December 2023, a total of 516 college students were investigated by social exclusion questionnaire for undergraduate, ruminative responses scale, the Geurten-questionnaire of executive functioning in Chinese college students and mobile phone addiction tendency scale. SPSS 26.0 statistical software was used for common method bias test, descriptive statistics, correlation analysis, and PROCESS 3.5 macro program was used to test the mediation effect.Results:Social exclusion (31.21±12.69), rumination (42.85±12.38), executive function (71.46±9.41), and college students' mobile phone addiction tendency (43.53±11.74) were all significantly and positively correlated with each other ( r=0.299-0.500, all P<0.01). The direct effect of social exclusion on mobile phone addiction was significant (effect size=0.138, 95% CI=0.048-0.228), accounting for 37.91%(0.138/0.364) of the total effect. Rumination had a mediating effect between social exclusion and mobile phone addiction (effect size=0.053, 95% CI=0.001-0.112), accounting for 14.56%(0.053/0.364) of the total effect. Executive function mediates the relationship between social exclusion and mobile phone addiction (effect size=0.137, 95% CI=0.091-0.188), accounting for 37.64%(0.137/0.364) of the total effect.Rumination and executive function has a chain mediating effect between social exclusion and mobile phone addiction (effect size=0.036, 95% CI=0.016-0.061), accounting for 9.89%(0.036/0.364) of the total effect. Conclusion:Social exclusion can directly affect mobile phone addiction in college students and can also influence mobile phone addiction in college students through the independent mediating effects of rumination and executive function, as well as the chain mediating effect of rumination and executive function.

Objective:To explore the mediating roles of rumination and avoidance coping between information anxiety and suicidal ideation.Methods:In March 2022, a total of 896 college students were surveyed by the information anxiety scale(IAS), ruminative responses scale(RRS), coping style questionnaire(CSQ)and self-rating idea of suicidal ideation scale(SIOSS). The ANOVA analysis, Pearson correlation analysis and mediating effect analysis were performed by the SPSS 22.0 software.Results:The detection rate of suicidal ideation among college students was 9.15%(82/896). The information anxiety score was(73.84±17.29), the rumination score was(47.73±12.16), the avoidance coping score was(3.76±2.52), and the suicidal ideation score was(5.41±4.09). Information anxiety was significantly positively correlated with rumination, avoidance coping and suicidal ideation( r=0.49, 0.36, 0.37, all P<0.05). Rumination was significantly positively correlated with avoidance coping and suicidal ideation( r=0.42, 0.59, both P<0.05). There was a significantly positive correlation between avoidance coping and suicidal ideation( r=0.45, P<0.05). Information anxiety affected suicidal ideation of college students through four paths.The direct effect value of information anxiety on suicidal ideation was 0.06, accounting for 16.67% of the total effect. The effect values of the separate mediating effect of rumination and avoid coping were 0.22 and 0.04, and accounting for 61.11% and 11.11% of the total effect respectively. The chain mediating effect value of rumination and avoid coping was 0.04, accounting for 11.11% of the total effect. Conclusion:Information anxiety can directly affect suicidal ideation of college students and indirectly affect suicidal ideation through rumination and avoidance coping.

Objective:To explore the mediating effect of experiential avoidance and emotional eating between intolerable uncertainty and life satisfaction of college students.Methods:From October to December 2021, a total of 890 college students in the Beijing-Tianjin-Hebei region were tested by the intolerable uncertainty scale (simplified version), the acceptance action scale second edition, the Dutch eating behavior questionnaire and the life satisfaction scale. All data processing and analysis were preformed by SPSS 22.0 software, and the mediating effect was tested by Pearson correlation analysis and Bootstrap analysis.Results:The intolerable uncertainty score was (26.43±7.64), the experiential avoidance score was (22.63±9.67), the emotional eating score was (26.43 ±11.83), and the life satisfaction score was (16.74±6.03). Intolerable uncertainty was significantly and negatively correlated with life satisfaction( r=-0.76, P<0.01), and was significantly and positively correlated with experience avoidance and emotional eating( r=0.66, 0.78, both P<0.01). Experience avoidance was significantly and positively correlated with emotional eating( r=0.70, P<0.01), and was significantly and negatively correlated with life satisfaction( r=-0.62, P<0.01). Emotional eating was significantly and negatively correlated with life satisfaction( r=-0.68, P<0.01). Intolerable uncertainty affects life satisfaction through four paths.The direct effect value of intolerable uncertainty on life satisfaction was -0.53, accounting for 70.23% of the total effect. The separate mediating effect value of experience avoidance was -0.11, accounting for 50.00% of the total indirect effect.The separate mediating effect value of emotional eating was -0.08, accounting for 36.36% of the total indirect effect, and the chain mediating effect value of experience avoidance and emotional eating was -0.03, accounting for 13.64% of the total indirect effect. Conclusion:Intolerable uncertainty can directly affect life satisfaction of college students and indirectly through experiencing avoidance and emotional eating.