基于深度学习人工智能骨龄测评系统临床应用

目的 观察基于深度学习的人工智能骨龄测评(BAA)系统临床应用及其对低年资儿科放射医师的辅助作用.方法 收集80名5?12岁儿童手腕骨X线正位片,对掌指骨进行骨龄测评,由高年资儿科放射医师借助BAA系统建立研究所用参考骨龄.根据中华-05法中的TW3-RUS标准,分别以BAA系统、低年资儿科放射医师及BAA系统辅助低年...     

深度学习模型在儿童TW3法骨龄评估的临床效能分析

目的 探讨深度学习模型在儿童应用TW3法进行骨龄评估的临床效能。方法 回顾性收集180例儿童左手X线片。评估基于Tanner-WhitehouseⅢ(TW3)法的掌指骨和腕骨骨龄。以3位高年资主任医师的评估均值为金标准组,计算并比较深度学习模型(模型组)及2位低年资医师(医师组,分别记作医师1、医师2)与金标准组评估时间差异,掌指骨骨龄、腕骨骨龄的均方误差(MSE)及平均绝对误差(MAE);采用组内相关系数(ICC)分析模型组和医师组与金标准组结果一致性。结果 骨龄评估所用时间模型组明显少于医师组(P<0.05)。掌指骨骨龄评估,模型组和医师1、医师2与金标准组相比MSE、MAE差异有统计学意义(P<0.05)。腕骨骨龄评估,模型组和医师1、医师2与金标准组相比MSE、MAE差异有统计学意义(P<0.05)。掌指骨骨龄评估,模型组与金标准组ICC为0.988,医师1、医师2与金标准组的ICC分别为0.986、0.977。腕骨骨龄评估,模型组与金标准组ICC为0.971,医师1、医师2与金标准组ICC分别为0.970、0.953。结论对于儿童,应用TW3法深度学习模型在...     

骨龄评估及其与运动的相关性

目的:对骨龄的评价方法,运动对骨龄的作用及影响进行综述。资料来源:应用计算机检索维普资讯、CNKI数据库及手工检索1989-01/2007-02期间的相关文献。中文检索词包括"骨龄","运动","体育锻炼","青少年";英文检索词有"skeletal age","movement","physical training","bone age"。资料选择:共收集到相关文献397篇,阅读全部文章的文题和大部分文章的摘要。选择文献所述内容与运动对骨龄的作用及影响相关的文献。排除重复性研究。资料提炼:共得到符合纳入条件的文献129篇,排除268篇。选择其中32篇进行分析,英文17篇,中文15篇。资料综合:目前,国际上普遍采用G-P图谱法和TW2计分法评价骨龄,但这两种方法都不完全适合中国儿童青少年。在20世纪90年代,国家体委在TW2法的基础上提出了一套中国人的骨发育等级标准——CHN计分法。2006年,张绍岩等参照TW3方法,以百分位数法分别制订了TW3-C RUS、TW3-C腕骨、RUS-CHN骨龄标准,称为《中国人手腕骨发育标准-中华05》,在这种评价法中,虽然考虑到一些因素的影响,但其调查对象均为城市汉族正常青少儿,然而,诸多因素如种族、遗传、性别、疾病、营养、体育锻炼、情绪波动、生活习惯等,均可影响全身发育和内分泌器官机能,从而影响骨骼发育。此外,地理环境不同,居民饮食结构、质量及生活习惯等亦不同,进而会引起各地区人群发育的差异。结论:由于骨的发育会受到多因素的影响,有些因素还互相影响、互相干扰,因此,在实际工作中,应充分考虑到诸多因素对骨龄评价的影响;同时,由于骨龄标准的时限性,一般认为骨龄标准最好每10～15年修正一次;并制定本地区、本民族人群的骨龄标准。     

骨龄评价方法TW3-RUS、TW3-Ccarpal、RUS-CHN对比及可重复性分析

目的:探讨TW3-RUS、TW3-C carpal、RUS-CHN三种骨龄评价方法的差异性及可重复性。材料与方法:应用TW3-RUS、TW3-C carpal、RUS-CHN三种方法,由2名有骨龄评价培训经历的医师,阅读时间年龄为12岁的正常男性儿童的手腕部X线平片,独立盲法进行骨龄评价。结果:2名医师的骨龄评价结果差别无统计学差异(P>0.05);3种方法对骨龄评价结果的差别有统计学意义(P<0.05);2人组内3种方法两两比较,TW3-C carpal与TW3-RUS及RUS-CHN骨龄评价结果的差别有统计学意义(P<0.05),TW3-RUS与RUS-CHN骨龄评价结果的差别无统计学意义(P>0.05)。结论:2名医师应用3种方法对12岁男童骨龄评价结果的可重复性高。对12岁男童骨龄评价,TW3-RUS与RUS-CHN法无明显差别,TW3-C carpal与TW3-RUS及RUS-CHN差别较大,推测TW3-C carpal可能不适合12岁男童骨龄评价。     

特发性性早熟女孩骨龄评价的诊断性试验研究

目的探讨骨龄测定对诊断特发性性早熟(idiopathic precocious puberty)的诊断价值和实用性.方法参照"金标准"选择特发性性早熟患儿55例,正常对照83例.回顾性分析初诊时第一张左手腕部X线照片,由专人用TW2法盲法分期,骨龄结果分为RUS(Radius Ulna and Short bones)(13骨)骨龄、腕骨(7骨)骨龄和20骨骨龄3个系统,每个系统又分为＞P97、＞P90、＞P75、＞P50和≤P505个工作点,并对该诊断性试验进行评价,比较TW2法骨龄的3个系统对性早熟患儿的诊断价值,并帮助选择正常临界点.结果①敏感度和特异度都高的有13骨骨龄的＞P90点(敏感度0.836,特异度0.916),7骨骨龄的＞P90点(敏感度0.746,特异度0.916)以及20骨骨龄的＞P90点(敏感度0.746,特异度0.964)和＞P75点(敏感度0.982,特异度0.783)4个工作点;② 3条ROC曲线的曲线下面积(A)分别为:13骨骨龄A13 0.939±0.019[95%CI(0.902,0.977)],7骨骨龄A7 0.899±0.028[95%CI(0.845,0.954)],20骨骨龄A20 0.958±0.014[95%CI(0.930,0.986)].3条曲线下面积无统计学差异(F=2.03,P=0.13);③骨骺核分期重复性为89.28%,可比性为80.3%,骨龄测定Kappa值为0.68(u=6.87,P＜0.01).结论 13骨骨龄和20骨骨龄诊断性早熟有高度准确性;"13骨骨龄＞P90"工作点为综合考虑了敏感度和特异度之后的最佳工作点,故建议将此点作为骨龄诊断性早熟的正常值临界点.     

常规超声检测骨龄及鉴别性早熟与乳房过早发育

目的 观察常规超声检测骨龄的可行性及其鉴别特发性中枢性性早熟(ICPP)与乳房过早发育(PT)的价值。方法 前瞻性纳入139名儿童，于1周内完成超声骨龄评估和左手及腕部X线检查，分别针对后者以Greulich-Pyle(GP)图谱法和Tanner-Whitehouse 3(TW3)法评估骨龄，评价超声与GP结果的相关性；比较超声与TW3骨龄差、GP与TW3骨龄差之间的差异，观察以超声骨龄鉴别ICPP与PT的价值。结果 超声评估骨龄与TW3法结果呈高度正相关(全组：r=0.96;男性r=0.97;女性r=0.96)。超声骨龄与TW3骨龄之差为(-0.3±0.7)岁，GP骨龄与TW3骨龄之差为(-0.2±1.1)岁，其间差异无统计学意义(P>0.05)。ICPP患儿(n=9)超声骨龄与实际年龄差明显大于PT(n=10)患儿[(1.3±1.0)岁vs.(0.2±0.9)岁，P<0.05)]。结论 常规超声可用于测量骨龄，并对鉴别诊断ICPP与PT具有一定价值。     

基于皮肤图像年龄评估系统的设计

背景:普通的TW3骨龄检测年龄鉴定方法无法适用于成人年龄检测,而其他年龄检测方法一般需要大型医疗设备,操作流程复杂,检测成本高,或者需要提取组织器官等有损伤的解剖操作.目的:以"皮肤表面纹理中隐藏年龄信息"的事实比发,设计一种新的法医年龄检测方法-皮肤年龄检测方法.方法;采用医学图像处理技术,提取皮肤表面形态特征参数,从而分析这些特征参数与年龄之间的关系.结果与结论:采用该设计方法建立的基于皮肤图像的法医学年龄评估系统从理论上能检测成年人的年龄,摆脱了传统单一运用骨骼检测年龄的习惯,运用身体另一组织(皮肤)检测年龄,解决了常规手腕骨X射线TW3法测骨龄无法适用于成年人的问题,扩大了年龄检测范围.     

人工智能骨龄评测系统评估儿童腕骨骨龄

目的 探讨人工智能（AI）系统评测儿童腕骨骨龄的可行性。方法 回顾性分析130幅1~13岁儿童左手骨龄X线片。以3名中高年资放射科医师腕骨骨龄评测结果为参考标准,计算并对比AI系统（简称模型）及3名低年资放射科医师（医师1、2、3,简称医师）与参考标准之间腕骨骨龄和腕骨成熟度分值的均方根误差（RMSE）及平均绝对误差（MAE）;采用组内相关系数（ICC）评价模型、医师与参考标准之间评测骨龄结果的一致性;比较模型与医师间骨龄测评时间。结果 模型与参考标准之间腕骨骨龄的MAE、RMSE与医师1、2与参考标准之间MAE、RMSE差异均有统计学意义（P均<0.05）,与医师3的MAE、RMSE差异无统计学意义（P均>0.05）。模型与参考标准之间腕骨成熟度分值的MAE、RMSE与医师1、参考标准之间MAE、RMSE差异均有统计学意义（P均<0.05）,与医师2、3的MAE、RMSE差异均无统计学意义（P均>0.05）。模型与参考标准之间腕骨骨龄评测结果的ICC=0.997,医师1、2、3与参考标准之间ICC分别为0.994、0.996、0.997。模型对骨龄的测评时间均小于医师（P均<0.001）。结论 AI骨龄评测系统能够准确、快速评估儿童腕骨骨龄。     

CT三维最小类内散度多分类支持向量机在肺结节识别中的应用

目的分析CT三维最小类内散度多分类支持向量机(MC-SVM)对肺结节的识别能力及优点。方法选择2012年1月至2014年1月确诊的肺结节病患者50例,根据基于三维矩阵模式的感兴趣体(VOI)的构成,分为结节样和非结节样;采用自动提取算法提取感兴趣区(ROI),分为结节ROI和非结节ROI;采用受试者工作特征(ROC)曲线比较大规模训练人工神经网络(MTANN)、基于矩阵模式的模糊最小二乘SVM(matFLSSVM)、三维矩阵模式MC-SVM和三维最小类内散度MC-SVM的识别精度,同时比较各种方法在不同截断点时的真阳性率和假阳性率。结果三维最小类内散度MC-SVM的识别精度、真阳性率均高于其他算法,而假阳性率低于其他算法(P0.05)。结论三维最小类内散度MC-SVM对肺结节的识别精度较高,值得临床推广应用。     

以生境成像技术提取血肿内亚区域平扫CT影像组学特征预测自发性颅内出血患者血肿增大

目的 观察以生境成像技术提取血肿内亚区域平扫CT(NCCT)影像组学特征预测自发性颅内出血(sICH)患者血肿增大(HE)的价值。方法 回顾性分析228例传统影像学无明显异常的sICH患者,根据HE与否分为HE组(n=99)与非HE(NHE)组(n=129);同时按8∶2比例划分训练集(n=182)与测试集(n=46)。比较组间临床、NCCT资料及实验室检查结果,以logistic回归分析筛选HE的影响因素。以生境成像技术将血肿ROI聚类划分为3个亚区,提取血肿整体(ROI_整体)和3个亚区域ROI(ROI_亚区1、ROI_亚区2、ROI_亚区3)的影像组学特征(ROI_亚区3位于血肿与脑组织临界区)并进行筛选;分别基于4个ROI构建4种预测模型,评估其预测HE效能。结果 HE组空腹血糖高于NHE组(t=2.047,P=0.041),但此非sICH HE的独立预测因素(P=0.070)。ROI_亚区3影像组学模型预测训练集和测试集sICH HE的曲线下面积分别为0.9...     

Determination of creatine kinase isoenzyme MB activity in serum using immunological inhibition of creatine kinase M subunit activity. Activity kinetics and diagnostic significance in myocardial infarction.

This is a new method for the determination of creatine kinase isoenzyme MB activity in serum. The method uses direct activity measurement of creatine kinase B subunit activity after blocking of CK-M subunit activity by inhibiting antibodies. The test takes no longer than 15 min. The method yields an intra-serial C.V. of 2.0-12.9%, and a C.V. from day to day of 5.5%. The detection limit is 3.4 U/l creatine kinase MB. In the 95 cases with proven myocardial infarction several types of creatine kinase MB activity kinetics could be determined. The percentage of creatine kinase MB of peak CK-total is 6-25%, with a mean of 11.1%. The amount of creatine kinase MB with respect to total CK activity after reinfarction is higher than the amount after initial infarction.     

俯卧位通气对高海拔地区肺复张治疗无效急性呼吸窘迫综合征患者氧合的影响

目的 探讨俯卧位通气对高海拔地区肺复张术(RM)治疗无效急性呼吸窘迫综合征(ARDS)患者的治疗作用.方法 从海拔2260m的地区医院筛选RM治疗无效的41例ARDS患者[平均氧合指数( PaO2/FiO2)较RM前升高＜20％视为RM无效],依不同病因分为肺内源性ARDS组(ARDSp组)和肺外源性ARDS组(ARDSexp组),每组再按信封法随机分为俯卧位组和仰卧位组,即ARDSp俯卧位组(11例)、ARDSp仰卧位组(9例)、ARDSexp俯卧位组(10例)、ARDSexp仰卧位组(11例).在通气前及通气1、2、3、4h监测动脉血氧分压( PaO2)、PaO2/FiO2、静态顺应性(Cst)、气道阻力(Raw)的变化.结果 通气lh时,ARDSexp俯卧位组PaO2/FiO2( mm Hg,l mm Hg=0.133 kPa)即较通气前显著升高(157.4±40.6比129.3±48.7,P＜0.05),并随通气时间延长呈持续增高趋势,4h达峰值(219.1 ±41.1);且ARDSexp俯卧位组通气3h内PaO2/FiO2较其他3组显著增高,另3组间则差异无统计学意义.ARDSp俯卧位组、ARDSexp俯卧位组通气4h时PaO2/FiO2均较相应仰卧位组显著增高(208.8±39.7比127.4±47.1,219.1±41.1比124.9±50.8,均P＜0.05).4组通气前后Cst无显著改变,各组间差异也无统计学意义.ARDSp俯卧位组通气4h时Raw(cmH2O·L-1·s-1)较通气前显著降低(6.8±1.7比10.7±1.8,P＜0.05),且明显低于其他3组;其他3组各时间点Raw组内及组间比较差异均无统计学意义.结论 俯卧位通气作为ARDS机械通气重要策略之一,可以改善RM无效高原ARDS患者的氧合,为抢救患者赢得宝贵的时间.     

Digital imaging among medical facilities

The Department of Veterans Affairs (VA) in the USA operates a network of 172 medical centres which all utilize a hospital information system (HIS) which has been developed and is currently maintained by the VA. During the past several years, an image management and communication module has been developed, installed and clinically utilized at the Washington DC and Maryland VA Medical Centres. This image management and communication system, referred to as the decentralized hospital computer program (DHCP) imaging system, is fully integrated with a commercial picture archiving and communication system (PACS). The system is utilized to capture, archive, and display all images generated within the hospital including radiology, nuclear medicine, pathology, endoscopy, bronchoscopy, and dermatology, intraoperative photographs, ECG data, and a limited number of paper documents. The ultimate goal of the project is to have all patient text and image data available at any clinical workstation to any authorized user anywhere within the network of medical centres. Clinical requirements for an imaging workstation include ease of use, rapid and reliable access to the complete set of patient information, and images which are of acceptable quality to meet the requirements of the user and the subspecialty. Patient confidentiality and data security must be safeguarded at all times. Integration of the images with the remainder of the patient's database was found to be critical to the success of the project. The experience at the Washington and Maryland facilities suggests that an imaging system that is successfully integrated with a hospital information system can provide substantial clinical and economic benefits both within and among medical centres. Clinical acceptance and utilization of the system has been excellent, particularly in diagnostic radiology where DHCP Imaging has been interfaced to a commercial PAC system. Based upon this initial experience, the VA has begun to deploy the system throughout its large network of medical centres.     

Myocardial elastography at both high temporal and spatial resolution for the detection of infarcts

Myocardial elastography is a novel method for noninvasively assessing regional myocardial function, with the advantages of high spatial and temporal resolution and high signal-to-noise ratio (SNR). In this paper, in-vivo experiments were performed in anesthetized normal and infarcted mice (one day after left anterior descending coronary artery [LAD] ligation) using a high-resolution (30 MHz) ultrasound system (Vevo 770, VisualSonics Inc., Toronto, ON, Canada). Radiofrequency (RF) signals of the left ventricle (LV) in longitudinal (long-axis) view and the associated electrocardiogram (ECG) were simultaneously acquired. Using a retrospective ECG gating technique, 2-D full field-of-view RF frames were acquired at an extremely high frame rate (8 kHz) that resulted in high-quality incremental displacement and strain estimation of the myocardium. The incremental results were further accumulated to obtain the cumulative displacements and strains. Two-dimensional and M-mode displacement images and strain images (elastograms), as well as displacement and strain profiles as a function of time, were compared between normal and infarcted mice. Incremental results clearly depicted cardiac events including LV contraction, LV relaxation and isovolumetric phases in both normal and infarcted mice, and also evidently indicated reduced motion and deformation in the infarcted myocardium. The elastograms indicated that the infarcted regions underwent thinning during systole rather than thickening, as in the normal case. The cumulative elastograms were found to have higher elastographic SNR (SNR(e)) than the incremental elastograms (e.g., 10.6 vs. 4.7 in a normal myocardium, and 6.0 vs. 2.4 in an infarcted myocardium). Finally, preliminary statistical results from nine normal (m = 9) and seven infarcted (n = 7) mice indicated the capability of the cumulative strain in differentiating infracted from normal myocardia. In conclusion, myocardial elastography could provide regional strain information at simultaneously high temporal (>/=0.125 ms) and spatial ( approximately 55 microm) resolution as well as high precision ( approximately 0.05 microm displacement). This technique was thus capable of accurately characterizing normal myocardial function throughout an entire cardiac cycle, at the same high resolution, and detecting and localizing myocardial infarction in vivo.     

Clinical Pharmacokinetics of Morphine

Morphine, the most widely used mu-opioid analgesic for acute and chronic pain, is the standard against which new analgesics are measured. A thorough understanding of the pharmacokinetics of morphine is required in order to safely and effectively use this analgesic in a wide variety of patients with different levels of organ function. A MEDLINE search was conducted to identify literature published between 1966 and January 2002 relevant to the pharmacokinetics of morphine. These publications were reviewed and the literature summarized regarding unique and clinically important elements of morphine disposition relative to its parenteral administration (including intravenous, intramuscular, subcutaneous, epidural and intrathecal administration), absorption profile (immediate release, controlled release, and sublingual/buccal, and rectal administration), distribution, and its metabolism/ excretion. Special populations, including infants, elderly, and those with renal/liver failure, have a unique morphine pharmacokinetic profile that must be taken into account in order to maximize analgesic efficacy and reduce the risk of adverse events.     

手转胎头术失败的原因与分娩结局临床分析

目的 探讨手转胎头术失败的原因与分娩结局.方法 选择2008年1月至2010年12月于我院住院分娩的持续性枕横位、枕后位产妇198例,根据行手转胎头术后结果分为成功组126例、失败组72例.比较两组分娩结局,对比分析失败原因.结果 失败组胎儿体质量≥3500 g的发生率[76.4％(55/72)]明显高于成功组[31.7％(40/126)],差异有统计学意义(x2=30.177,P=0.001)、失败组宫缩乏力发生率[58.3％(42/72)]高于成功组[38.1％ (48/126)],差异有统计学意义(x2=7.569,P=0.006)、失败组骨盆临界或轻度狭窄发生率[38.9％ (28/72)]高于成功组[23.8％(30/126)],差异有统计学意义(x2 =5.030,P=0.002)、失败组手转胎头时机不当(宫口开大＜6 cm、胎头位于坐骨棘上及宫口开大8～10 cm、胎头位于坐骨棘下≥2 cm)发生率[61.1％(44/72)]高于成功组[38.9％(49/126)],差异有统计学意义(x2=9.084,P=0.003).失败组母儿并发症(产后出血、产褥病率、胎儿窘迫、新生儿窒息)发生率高于成功组(x2 =9.586,P=0.002、x2=9.334,P=0.002、x2=5.910,P=0.015、x2=5.240,P=0.022)、失败组剖宫产发生率[72.2％(52/72)]明显高于成功组[34.1 ％(43/126),x2=26.641,P=0.001)].结论 手转胎头术能使难产变顺产,降低剖宫产率,减少母儿并发症,但须积极预防、处理导致手转胎头术失败的原因,对矫正失败后继续矫正及试产应慎重.     

Evidence-Based Pain Management and Palliative Care in Issue Four for 2009 of The Cochrane Library

ABSTRACT

The Cochrane Library of Systematic Reviews is published quarterly. Issue 4 for 2009 contains 4027 complete reviews, 1906 protocols for reviews in production, and 11447 one-page summaries of systematic reviews published in the general medical literature. In addition, there are citations of 600,000 randomized controlled trials, and 12,200 cited papers in the Cochrane methodology register. The health technology assessment database contains over 7500 citations. This edition of the Library contains 90 new reviews, of which 19 have potential relevance for practitioners in pain and palliative medicine.     

Wie zuverlässig sind Angaben zu nichtentzündlichen ausgedehnten Schmerzen?

ZusammenfassungFragestellung Es wurde geprüft, wie sich der Differenziertheitsgrad zweier Schmerzmessmethoden auf Angaben zur Ausgedehntheit klinischer Schmerzen auswirkt. Zugleich wurde der Referenzzeitraum variiert, über den die Patienten berichten sollten.Methode Erfasst wurde der Einfluss zu Lasten der Befragungsdifferenziertheit durch den Vergleich zweier Körperschema-Bildvorlagen. Drei Referenzzeiträume (Schmerz aktuell, letzte Woche, letztes halbes Jahr) wurden vorgegeben.Ergebnisse Patienten mit ausgedehnten Schmerzen gaben bei differenzierter Befragung um so mehr Schmerzen an, je weiter die Schmerzen zurück lagen und je größer der Berichtszeitraum war. Patienten mit gelenknahen Schmerzen gaben bei hoch differenzierter Befragung weniger ausgedehnte Schmerzen in der Vergangenheit an als bei globaler Einschätzung. Patienten mit Rückenschmerzen berichteten bei differenzierter Befragung zum aktuellen Schmerz über weniger ausgedehnte Schmerzen als bei globaler Befragung.Schlussfolgerung Die Angaben zur Schmerzausdehnung variieren vor allem bei Patienten mit ausgedehnten Schmerzen in Abhängigkeit von der Differenziertheit der Befragung. In diesen Fällen ist die Wahrscheinlichkeit erhöht, dass sich die Beschwerdesymptomatik zumindest teilweise erst in der Reaktion auf die situativen Befragungsbedingungen konstituiert und daher nicht auf andere Befragungsbedingungen generalisiert werden kann.