Automatic Grading Assessments for Knee MRI Cartilage Defects via Self-ensembling Semi-supervised Learning with Dual-Consistency

Knee cartilage defects caused by osteoarthritis are major musculoskeletal disorders, leading to joint necrosis or even disability if not intervened at early stage. Deep learning has demonstrated its effectiveness in computer-aided diagnosis, but it is time-consuming to prepare a large set of well-annotated data by experienced radiologists for model training. In this paper, we propose a semi-supervised framework to effectively use unlabeled data for better evaluation of knee cartilage defect grading. Our framework is developed based on the widely-used mean-teacher classification model, by designing a novel dual-consistency strategy to boost the consistency between the teacher and student models. The main contributions are three-fold: (1) We define an attention loss function to make the network focus on the cartilage regions, which can both achieve accurate attention masks and boost classification performance simultaneously; (2) Besides enforcing the consistency of classification results, we further design a novel attention consistency mechanism to ensure the focusing of the student and teacher networks on the same defect regions; (3) We introduce an aggregation approach to ensemble the slice-level classification outcomes for deriving the final subject-level diagnosis. Experimental results show that our proposed method can significantly improve both classification and localization performances of knee cartilage defects. Our code is available on https://github.com/King-HAW/DC-MT.     

多元化联合教学模式在超声引导下疼痛介入治疗中的应用

目的探讨多元化联合教学模式在超声引导下疼痛介入治疗教学中的应用效果。方法选择2018年1月至2020年12月在北京大学第三医院疼痛科进修的30名医师作为研究对象,将其分为对照组与观察组;对照组采用常规教学模式;观察组采用多元化联合教学模式,比较两组医师技能考核成绩、教学质量评分和满意度评分。结果观察组医师技能考核成绩优良率为93.3%,高于对照组的73.3%(P<0.05);观察组医师对基础理论知识掌握、临床思维能力的提高、学习兴趣的激发、疾病诊治能力的提高4个方面的评分均高于对照组(P<0.01)。结论多元化联合教学模式可促进超声引导下疼痛介入治疗技能的提高,有利于提高学员的综合临床能力。     

A comprehensive 3D CT based classification of intertrochanteric fracture

IntroductionDespite advancements in surgical techniques complications like implant failure is very common after the fixation of intertrochanteric fractures. Classifying these complex fractures based on plain radiographs underestimates the complexity of these fractures which in turn leads to complications. We propose a comprehensive classification of the intertrochanteric fractures based on 3D Non Contrast Computed Tomography (3D NCCT) scan.Material and methodsA total of 102 patients (51 males and 51 females) with intertrochanteric fractures were included in this study conducted over a time period of 22 months in a Tertiary care center in North India. NCCT proximal femur of the intertrochanteric fracture patients was done to formulate a new CT classification system and classify all fractures. Intra and inter-observer reliability was tested using kappa variance.ResultsNew classification system was proposed which included 3 main and a total of 6 groups. All the fractures were classifiable into the new system. Kappa variance of the study showed a good intra and interobserver reliability (0.95 and 0.90) proving clinical agreement of the classification.ConclusionThis new 3D-CT based classification has the advantages of being easy, comprehensible with high intra and inter-observer reliability. This 3DCT based classification can prove to be useful to detect occult intertrochanteric fractures undetectable in plain radiographs as well as choosing the optimum treatment plan.     

2022年北京冬奥会定点医院医疗卫生保障实践

2022年北京冬奥会是全球瞩目的盛事，如何有效提升延庆赛区定点医院医疗卫生保障能力是冬奥会筹办过程中需要解决的重大课题。文章系统总结延庆赛区冬奥定点医院医疗保障特点、主要做法和经验，旨在为今后大型赛事定点医院的医疗保障提供参考。     

Development and validation of an individualized nomogram to identify occult peritoneal metastasis in patients with advanced gastric cancer

BackgroundOccult peritoneal metastasis (PM) in advanced gastric cancer (AGC) patients is highly possible to be missed on computed tomography (CT) images. Patients with occult PMs are subject to late detection or even improper surgical treatment. We therefore aimed to develop a radiomic nomogram to preoperatively identify occult PMs in AGC patients.Patients and methodsA total of 554 AGC patients from 4 centers were divided into 1 training, 1 internal validation, and 2 external validation cohorts. All patients’ PM status was firstly diagnosed as negative by CT, but later confirmed by laparoscopy (PM-positive n = 122, PM-negative n = 432). Radiomic signatures reflecting phenotypes of the primary tumor (RS1) and peritoneum region (RS2) were built as predictors of PM from 266 quantitative image features. Individualized nomograms of PM status incorporating RS1, RS2, or clinical factors were developed and evaluated regarding prediction ability.ResultsRS1, RS2, and Lauren type were significant predictors of occult PM (all P < 0.05). A nomogram of these three factors demonstrated better diagnostic accuracy than the model with RS1, RS2, or clinical factors alone (all net reclassification improvement P < 0.05). The area under curve yielded was 0.958 [95% confidence interval (CI) 0.923–0.993], 0.941 (95% CI 0.904–0.977), 0.928 (95% CI 0.886–0.971), and 0.920 (95% CI 0.862–0.978) for the training, internal, and two external validation cohorts, respectively. Stratification analysis showed that this nomogram had potential generalization ability.ConclusionCT phenotypes of both primary tumor and nearby peritoneum are significantly associated with occult PM status. A nomogram of these CT phenotypes and Lauren type has an excellent prediction ability of occult PM, and may have significant clinical implications on early detection of occult PM for AGC.     

加拿大问题赌博指数中文版的效度和信度

目的:评估加拿大问题赌博指数中文版(CPGI-C)的效度和信度。方法:选取43例匿名戒赌会成员和202例正常成人为研究对象,将其随机分为两半,分别进行探索性因子分析和验证性因子分析;以赌博相关认知量表(GRCS-C)、Barratt冲动性人格问卷(BIS-11)、抑郁自评量表(SDS)、网络成瘾量表修订版(CIAS-R)和DSM-IV多重反应问卷(DSM-IV-MR)作为效标工具;以受试者工作特征曲线(ROC)评估量表区分问题赌博者的特异度与灵敏度。2周后有5例匿名戒赌会成员和31例正常成人完成重测。结果:CPGI-C的问题赌博指数(PGSI)分量表共9个条目,探索性因子分析得出1个主成分因子,可解释总方差的74.3%;验证性因子分析显示,单因子结构模型的拟合指标良好(χ~2=2.087,CFI=0.926,TLI=0.963,GFI=0.926,IFI=0.978,NFI=0.958, RMSEA=0.094,SRMR=0.032);CPGI总分与各效标量表的总分均呈正相关(r=0.48～0.82,均P<0.001);ROC曲线下面积为0.962,划界分为9.5。CPGI-C的...     

Registration methods for surgical navigation of the mandible: a systematic review

Image-to-patient registration in navigated mandibular surgery is complex due to the mobile nature of the mandible compared with other craniofacial bones. As a result, surgical navigation is rarely employed in the mandibular region. This systematic review provides an overview of the different registration methods that are used for surgical navigation of the mandible. A systematic search was performed in the MEDLINE Ovid, Scopus, and Embase databases on March 25, 2021. Search terms included synonyms for mandibular surgery, surgical navigation, and registration methods. Articles about navigated mandibular surgery, where the registration method was explicitly mentioned, were included. The database search yielded a total of 2952 articles, from which 81 articles remained for analysis. Four main registration methods were identified: point registration, surface registration, hybrid registration, and computer vision-based registration. The mobility of the mandible is accounted for by either keeping the mandible in a fixed position during preoperative imaging and surgery, or by tracking the mandibular movements. Although different registration methods are available for navigated mandibular surgery, there is always a trade-off between accuracy, registration time, usability, and invasiveness. Future studies should focus on testing the different methods in larger patient studies and should report the registration accuracy.