This study aims to develop a fully automated method for tooth segmentation and root canal measurement based on cone beam computed tomography (CBCT) images, providing objective, efficient, and accurate measurement results to guide and assist clinicians in root canal diagnosis grading, instrument selection, and preoperative planning. The method utilized Attention U-Net to recognize tooth descriptors, cropped regions of interest (ROIs) based on the center of mass of these descriptors, and applied an integrated deep learning method for segmentation. The segmentation results were mapped back to the original coordinates and position-corrected, followed by automatic measurement and visualization of root canal lengths and angles. The results indicated that the Dice coefficient for segmentation was 96.42%, the Jaccard coefficient was 93.11%, the Hausdorff Distance was 2.07 mm, and the average surface distance was 0.23 mm, all of which surpassed existing methods. The relative error of the root canal working length measurement was 3.15% (< 5%), the curvature angle error was 2.85 °, and the correct classification rate of the treatment difficulty coefficient was 90.48%. The proposed methods all achieved favorable results, which can provide an important reference for clinical application.
Cone-Beam Computed Tomography/methods* ; Deep Learning ; Humans ; Dental Pulp Cavity/diagnostic imaging* ; Image Processing, Computer-Assisted/methods*

A VLi-net based cell nucleus segmentation method integrating convolutional neural networks(CNN)and Vision Transformer(ViT)is proposed to address the limitation that the U-Net with CNN as its backbone is only proficient in capturing local features and has a restricted receptive field.Firstly,to mitigate challenges such as high cost of data annotation and insufficient annotated data,text annotations are introduced to enhance the network's understanding of image information.Secondly,to improve the segmentation performance of VLi-net,ViT and CNN are combined to fully extract global and local features,with multi-receptive field convolution features incorporating into the ViT structure for effectively mitigating the issues of limited local information interaction and single feature representation in ViT.Finally,an interactive fusion module(ViFusion)is used to efficiently fuse the multi-level features from the CNN and ViT branches.Experimental results show that VLi-net achieves a Dice coefficient of 80.85%and a mean intersection over union(MIoU)of 66.83%on the MoNuSeg dataset,obtains a Dice coefficient of 80.53%and a MIoU of 67.54%on the DSB-2018 dataset,and has a Dice coefficient of 86.87%and a MIoU of 77.44%on the TNBC dataset.These findings confirm that VLi-net outperforms other methods across multiple experimental metrics.

Objective To propose a classification model based on a pseudo-bag strategy and feature adjustment for whole slide imaging in pathology.Methods A pseudo-bag generator was constructed to divide a parent bag into 3 pseudo-bags for increasing the number of training bags.Then,a pseudo-bag learning method based on Nystr?m-based algorithm for approximating self-attention and a selective feature fusion method were employed to process the pseudo-bags.Specifically,the pseudo-bag learning method based on Nystr?m-based algorithm for approximating self-attention reduced computational complexity through an improved multi-head self-attention mechanism while deeply extracting instance features to obtain pseudo-bag classification predictions,thereby enhancing pseudo-bag classification accuracy;and the selective feature fusion method refined pseudo-bag features by filtering and extracting relevant instances.Finally,the model adjusted bag features by extracting confounding factors to avoid interference from irrelevant information and further improve classification accuracy.Results The proposed model was evaluated on two datasets(CAMELYON-16 and TCGA-NSCLC)and compared with 10 other methods,and the results demonstrated that the proposed model achieved the best performance.The proposed method reached an accuracy of 0.943 on the CAMELYON-16 dataset and 0.906 on the TCGA-NSCLC dataset.Conclusion The proposed model can significantly improve the accuracy of whole-slide pathological image classification by effectively mitigating the overfitting and avoiding interference from irrelevant information.

A VLi-net based cell nucleus segmentation method integrating convolutional neural networks(CNN)and Vision Transformer(ViT)is proposed to address the limitation that the U-Net with CNN as its backbone is only proficient in capturing local features and has a restricted receptive field.Firstly,to mitigate challenges such as high cost of data annotation and insufficient annotated data,text annotations are introduced to enhance the network's understanding of image information.Secondly,to improve the segmentation performance of VLi-net,ViT and CNN are combined to fully extract global and local features,with multi-receptive field convolution features incorporating into the ViT structure for effectively mitigating the issues of limited local information interaction and single feature representation in ViT.Finally,an interactive fusion module(ViFusion)is used to efficiently fuse the multi-level features from the CNN and ViT branches.Experimental results show that VLi-net achieves a Dice coefficient of 80.85%and a mean intersection over union(MIoU)of 66.83%on the MoNuSeg dataset,obtains a Dice coefficient of 80.53%and a MIoU of 67.54%on the DSB-2018 dataset,and has a Dice coefficient of 86.87%and a MIoU of 77.44%on the TNBC dataset.These findings confirm that VLi-net outperforms other methods across multiple experimental metrics.

Objective To evaluate the application of high-resolution magnetic resonance vessel wall imaging(HRMR-VWI)in identifying high-risk features of intracranial atherosclerotic plaques,and to analyze the correlation between plaque characteristics and stroke recurrence under varying degrees of stenosis.Methods The data from 368 patients with intracranial atherosclerotic stenosis(ICAS)across two centers were retrospectively analyzed.Based on the degree of stenosis,all patients were categorized into mild-to-moderate stenosis group(luminal stenosis<70%,n=155)and severe stenosis group(luminal stenosis≥70%,n=213).HRMR-VWI images and clinical information of the patients were collected and analyzed,and the culprit plaques were quantitatively analyzed.Univariate and multivariate logistic regression analyses were employed to identify the risk factors for stroke recurrence,and the predictive performance was evaluated using the area under the curve(AUC)of the receiver operating characteristic(ROC)curve.Results Higher normalized wall index(NWI)[odds ratio(OR)=1.082,95%confidence interval(CI)1.050-1.118,P<0.05]and the presence of intraplaque hemorrhage(IPH)(OR=1.843,95%CI 1.120-3.036,P<0.05)were risk factors for stroke recurrence in all patients.And these two factors were also significant in the mild-to-moderate stenosis group(NWI:OR=1.088,95%CI 1.009-1.186,P<0.05;IPH:OR=4.049,95%CI 1.227-16.065,P<0.05).A predictive model for stroke recurrence was constructed using the combination of IPH and NWI,with the best performance in the mild-to-moderate stenosis group(AUC=0.813,95%CI 0.723-0.906).Conclusion In patients with luminal stenosis<70%,the increase of NWI and the presence of IPH have been validated as significant and effective indicators for predicting stroke recurrence,demonstrating notable predictive performance.In contrast,among patients with luminal stenosis≥70%,the utility of plaque characteristics in predicting stroke recurrence is relatively lower,indicating that the correlation between plaque characteristics and stroke recurrence varies across different degrees of stenosis.

Objective To propose a classification model based on a pseudo-bag strategy and feature adjustment for whole slide imaging in pathology.Methods A pseudo-bag generator was constructed to divide a parent bag into 3 pseudo-bags for increasing the number of training bags.Then,a pseudo-bag learning method based on Nystr?m-based algorithm for approximating self-attention and a selective feature fusion method were employed to process the pseudo-bags.Specifically,the pseudo-bag learning method based on Nystr?m-based algorithm for approximating self-attention reduced computational complexity through an improved multi-head self-attention mechanism while deeply extracting instance features to obtain pseudo-bag classification predictions,thereby enhancing pseudo-bag classification accuracy;and the selective feature fusion method refined pseudo-bag features by filtering and extracting relevant instances.Finally,the model adjusted bag features by extracting confounding factors to avoid interference from irrelevant information and further improve classification accuracy.Results The proposed model was evaluated on two datasets(CAMELYON-16 and TCGA-NSCLC)and compared with 10 other methods,and the results demonstrated that the proposed model achieved the best performance.The proposed method reached an accuracy of 0.943 on the CAMELYON-16 dataset and 0.906 on the TCGA-NSCLC dataset.Conclusion The proposed model can significantly improve the accuracy of whole-slide pathological image classification by effectively mitigating the overfitting and avoiding interference from irrelevant information.

Objective To evaluate the application of high-resolution magnetic resonance vessel wall imaging(HRMR-VWI)in identifying high-risk features of intracranial atherosclerotic plaques,and to analyze the correlation between plaque characteristics and stroke recurrence under varying degrees of stenosis.Methods The data from 368 patients with intracranial atherosclerotic stenosis(ICAS)across two centers were retrospectively analyzed.Based on the degree of stenosis,all patients were categorized into mild-to-moderate stenosis group(luminal stenosis<70%,n=155)and severe stenosis group(luminal stenosis≥70%,n=213).HRMR-VWI images and clinical information of the patients were collected and analyzed,and the culprit plaques were quantitatively analyzed.Univariate and multivariate logistic regression analyses were employed to identify the risk factors for stroke recurrence,and the predictive performance was evaluated using the area under the curve(AUC)of the receiver operating characteristic(ROC)curve.Results Higher normalized wall index(NWI)[odds ratio(OR)=1.082,95%confidence interval(CI)1.050-1.118,P<0.05]and the presence of intraplaque hemorrhage(IPH)(OR=1.843,95%CI 1.120-3.036,P<0.05)were risk factors for stroke recurrence in all patients.And these two factors were also significant in the mild-to-moderate stenosis group(NWI:OR=1.088,95%CI 1.009-1.186,P<0.05;IPH:OR=4.049,95%CI 1.227-16.065,P<0.05).A predictive model for stroke recurrence was constructed using the combination of IPH and NWI,with the best performance in the mild-to-moderate stenosis group(AUC=0.813,95%CI 0.723-0.906).Conclusion In patients with luminal stenosis<70%,the increase of NWI and the presence of IPH have been validated as significant and effective indicators for predicting stroke recurrence,demonstrating notable predictive performance.In contrast,among patients with luminal stenosis≥70%,the utility of plaque characteristics in predicting stroke recurrence is relatively lower,indicating that the correlation between plaque characteristics and stroke recurrence varies across different degrees of stenosis.

As China's manned space missions gradually develop towards long-term residence and deep space exploration,astronauts will face increasingly severe psychological challenges.As a psychological adjustment method involving multiple disciplines such as music,psychology,and medicine,music therapy has the advantages of being convenient to implement,cost-effective,and highly personalized.This paper integrates the concept of music therapy and explores the research progress of music therapy in regulating psychological states in aspects such as physiology,emotional regulation,cognitive ability,and interpersonal relationships.Combined with the mechanism of action of music therapy and the practical situation in the field of manned spaceflight,it aims at the future development trends and problems to be solved,to construct a music therapy system for astronauts during on-orbit flight and ground daily training.This will help astronauts achieve healthy physical and mental development and promote the completion of missions.

Objective:This study explores the relationship between emotional dysregulation, attention-deficit/hyperactivity disorder (ADHD) and oppositional defiant disorder (ODD) symptoms using network models.Method:A total of 967 children with ADHD comorbid ODD were recruited from the outpatient department of Peking University Sixth Hospital from September 2002 to June 2022. All subjects were rated for the ADHD symptom severity using the ADHD symptom rating scale. ODD symptoms and emotional dysregulation symptoms were assessed by the Children′s Clinical Diagnostic Interview Scale, and the Conners′ Parent Symptom Questionnaire. R (version 4.2.1) packages mgm, qgraph, bnlearn, etc. were used for network analysis, and centrality indices were calculated to define central symptoms and bridge symptoms. Results:The relationship between emotional dysregulation and ODD symptoms was closer. ODD symptoms had higher strength indices, especially the items "gets annoyed or irritated by the behavior of adults"(strength=3.57) and "loses temper or gets angry with adults when does not get his or her own way"(strength=2.32). Emotional dysregulation symptoms had a higher bridge strength indices, with "temper outbursts, explosive and unpredictable behavior" (bridge strength=2.64) as the most prominent item. Bayesian network analysis showed that ADHD symptoms were at the upper of DAG, directly linked with emotional dysregulation symptoms and indirectly linked with ODD symptoms through emotional dysregulation symptoms.Conclusion:Emotional dysregulation symptoms were more closely associated with ODD symptoms than ADHD symptoms, and might potentially acted as bridge symptoms between ADHD and ODD. ADHD symptoms might drive ODD symptoms indirectly through emotional dysregulation symptoms.

Objective:This study explores the relationship between emotional dysregulation, attention-deficit/hyperactivity disorder (ADHD) and oppositional defiant disorder (ODD) symptoms using network models.Method:A total of 967 children with ADHD comorbid ODD were recruited from the outpatient department of Peking University Sixth Hospital from September 2002 to June 2022. All subjects were rated for the ADHD symptom severity using the ADHD symptom rating scale. ODD symptoms and emotional dysregulation symptoms were assessed by the Children′s Clinical Diagnostic Interview Scale, and the Conners′ Parent Symptom Questionnaire. R (version 4.2.1) packages mgm, qgraph, bnlearn, etc. were used for network analysis, and centrality indices were calculated to define central symptoms and bridge symptoms. Results:The relationship between emotional dysregulation and ODD symptoms was closer. ODD symptoms had higher strength indices, especially the items "gets annoyed or irritated by the behavior of adults"(strength=3.57) and "loses temper or gets angry with adults when does not get his or her own way"(strength=2.32). Emotional dysregulation symptoms had a higher bridge strength indices, with "temper outbursts, explosive and unpredictable behavior" (bridge strength=2.64) as the most prominent item. Bayesian network analysis showed that ADHD symptoms were at the upper of DAG, directly linked with emotional dysregulation symptoms and indirectly linked with ODD symptoms through emotional dysregulation symptoms.Conclusion:Emotional dysregulation symptoms were more closely associated with ODD symptoms than ADHD symptoms, and might potentially acted as bridge symptoms between ADHD and ODD. ADHD symptoms might drive ODD symptoms indirectly through emotional dysregulation symptoms.