数字化x线胸片计算机辅助检测在肺结节诊断中的价值

目的探讨计算机辅助检测（CAD）系统对肺单发结节的检测价值。方法选取70例经病理证实的肺部单发结节（直径0．9—3cm）的数字化x线（DR）胸片病例。随机抽取50例年龄、性别与受检组相近者作为对照组。所有病例均行胸部CT扫描,并由多名高年制胸部放射医师共同诊断。高年制和低年制放射诊断医师各5名,分别独立对用和不用CADX线数字化胸片进行阅片。用受试者操作特性（ROC）曲线分析来衡量观察者所记录积分。结果平均ROC曲线下面积从不用CAD的0．755增加至用CAD的O．829（P〈0．05）。在使用CAD时,低年制放射医师比高年制放射医师的平均ROC曲线下面积增加更多。结论数字化x线胸片CAD系统有助于提高肺结节性病灶的检出率。     

数字化放射成像与普通X线诊断肺内单发结节的ROC曲线评价

目的比较数字化放射成像(DR)和普通X线对肺内单发结节的诊断价值。方法选取30例有肺部单发结节和30例无肺内结节的病例,所有肺结节病灶均经CT和病理学证实。分别摄取普通X线胸片和DR,4位高年资医生和4位低年资医生分别对两组影像资料进行评价,结果采用受试者工作特征(ROC)曲线进行统计分析。结果(1)在发现肺内单发结节方面:对高年资医生来说,DR组的ROC曲线下面积(Az=0.838)大于普通胸片组(Az=0.816)(P<0.05);对低年资医生来说,DR组的ROC曲线下面积(Az=0.842)大于普通胸片组(Az=0.712)(P<0.05);(2)在判断肺内单发结节的良恶性方面,两组无显著差异(P=0.272)。结论DR在发现肺内单发结节方面优于普通胸片,而在判断良恶性方面两者差别不大。     

基于ROC理论评价单色显示器对肺结节检出效能的影响

 目的评价不同分辨率的医用单色液晶显示器对胸部DR影像图上肺结节检出效能的影响。方法从图像存储与传输系统(PACS)中在线选取胸部直接数字化X线摄影(DR)影像图93幅,其中确诊图38幅、疑诊图32幅、正常图23幅(均由CT证实),将阳性病例按结节直径大小分为A、B两组,请3名高年资医师在3种不同分辨率的显示器上集中进行3次独立读图,对结节有无的评判采用5等分法:肯定有、可能有、不确定、可能无、肯定无,每名医师针对特定显示器上的每幅图像给出自己的信任等级。采用SPSS13.0绘制受试者操作特性(ROC)曲线,并对曲线下的面积(AUC)做Z检验。结果使用2MP、3MP、5MP显示器识读A组阳性病例的影像资料时ROC曲线AUC分别为0.643、0.686、0.739,识读B组阳性病例的影像资料时分别为0.813、0.832、0.846,Z检验表明不同放射系统诊断效能比较差异无统计学意义(P>0.05)。结论在不限制图像后处理工具的情况下,使用不同分辨率的医用单色液晶显示器识读不同尺寸肺结节时诊断效能相当。     

计算机辅助诊断在甲状腺TI-RADS分类中的临床价值

目的 探讨计算机辅助诊断(安克侦CAD)在甲状腺结节影像报告和数据系统(TI-RADS)分类中的临床应用价值.方法 收集四川成都3家综合医院2019年11月至2020年1月经超声检查的甲状腺结节患者资料,纳入经细针穿刺和手术病理证实的252个甲状腺结节,其中恶性109个(43.25％),良性143个(56.75％).比较低年资超声医师和安克侦CAD对甲状腺TI-RADS分类的诊断效能.结果 低年资超声医师对甲状腺TI-RADS分类的灵敏度(66.97％vs.93.58％)、特异度(65.03％vs.91.61％)及准确性(65.87％vs.92.46％)均低于安克侦CAD,差异有统计学意义(P<0.05).安克侦CAD诊断甲状腺结节受试者工作特征(ROC)曲线下面积(AUC)高于低年资超声医师(0.938 vs.0.718和0.938 vs.0.667),差异有统计学意义(P<0.05).结论 计算机辅助诊断可以帮助低年资超声医师提高甲状腺TI-RADS分类的准确性和一致性.     

胸部低剂量直接数字化X线成像临床运用

本文应用低剂量直接数字化X线成像系统(LDRD)对12542例胸片进行特征分析。结果显示:数字化X线成像与传统X线摄影比较,除具有窗宽、窗位调节、边缘锐化处理、影像局部处理、低剂量高宽容度条件曝光、病例无片化管理等优点外,在以下胸部疾病检查中有明显优势:①肺内结节病灶。②心脏、大血管疾患的诊断。③肺纹影异常的诊断。     

不同分辨率影像诊断显示器对孤立性肺结节识读影响的ROC评价

目的 通过对胸部DR影像上孤立性肺结节检出准确率的比较来评价PACS影像诊断工作站所应用的不同分辨率的医用显示器的诊断效能.方法 选取经CT证实的具有非钙化孤立性肺结节(DR胸片上直径＜30 mm=100例,多发肺结节(直径＜30 mm,两肺数目不超过3个并散在分布24例和疑似病例15例.2位高年资医生(工作经验≥10年)和3位低年资医生(工作经验≤4年)在PACS系统的2种显示器(Barco MGD521 MKII(2560×2048,75Hz)21英寸医用单色RCT和EIZO RadiForce G20(1200×1600,60Hz)21英寸医用单色LCD)上分别使用或不使用放大后处理功能集中进行4次独立阅片,分别对胸片上是否有肺结节及结节个数进行判断,并记录结节的具体位置,评价的标准采用5分法:肯定有、可能有、不确定、可能没有、肯定没有;每次阅片时间间隔为1个月,每位医师每次均可根据需要使用窗宽、窗位调节功能,阅片时间不限.数据结果采用SPSS 13.0软件受试者工作特征(ROC)曲线法进行统计分析,计算和比较采用每种显示系统的诊断精确度(用曲线下面积-Az值来表示).结果 ①采用放大后处理功能后,各位医师的诊断准确率都能得到一定程度的改善,尤其在低年资医师更明显,在两种显示器上的Az值增加幅度都明显高于高年资医师(P＜0.05);而高年资医师采用2 k显示器阅片时,在使用放大后处理功能前后其Az值基本相同(Az=0.765～0.769,平均P=0.314＞0.05).在各种情况下阅片,高年资医师的诊断准确率都明显高于低年资医师(P＜0.05).②2位高年资医师在1 k显示器加用放大功能时所获得Az值(平均Az=0.742)都达不到2 k显示器不加用放大功能时的Az值(平均Az=0.771),之间存在小的但具有统计学显著性意义的差别(P=0.042＜0.05);而3位低年资医师使用1 k显示器加用放大功能,其平均Az值(Az=0.674)高于2 k显示器不加用放大功能时的平均Az值(Az=0.651),之间亦存在小的但具有统计学显著性意义的差别(P=0.044＜0.05).对所有医师而言,使用1 k显示器加用放大功能(Az=0.702)与2 k显示器不加用放大功能(Az=0.703)的诊断效能无明显差别(P=0.475＞0.05).结论 ①使用放大功能可以提高影像分辨率,进而提高诊断效能.相比于高年资医师而言,影像分辨率的增加更能改善低年资医师的诊断水平,并在一定程度上能减低诊断医师个体差别所造成的影响.②出于成本效益的考虑,科室可以安排低年资医师使用1 k医用显示器完成初步诊断,但是要求常规使用放大后处理功能,高年资医师应使用2 k医用显示器以保证最终诊断结果的可靠性;低年资医师在处理急诊报告时,仍然应当采用1k医用显示器.     

打印介质对肺孤立小结节诊断准确性影响的ROC分析:纸介打印与干式激光打印对比

目的 探讨纸质打印片及干式激光打印胶片对于数字化胸片上孤立性肺结节诊断准确性的影响.方法 分别采用LOCUS纸质打印机及KONICA DRYPRO 752干式激光打印机打印数字化正位胸片.由4位(具有3年工作经验和具有10年以上工作经验医师各2位)放射科医师分别对于50例正位胸片进行读片.读片分两次进行,两次读片间隔三周.每次读片分别采用其中的一种打印形式进行读片.读片结果 采用LABMR软件进行ROC分析,绘制ROC曲线.结果 采用两种方式读片时,结果 无显著性差异,干式激光打印胶片图像诊断结果 与纸质打印片之间无显著性差异.结论 对于孤立性肺结节的诊断,干式激光打印胶片诊断准确率与纸质打印片之闻无显著性差异.     

X线数字摄影(DR)的临床应用研究

目的:探讨X线数字摄影的临床应用价值。方法:我院已是省内较早临床应用DR的医院之一,通过对近2a来我院日门诊量约150人次的DR图像,以及在实际操作工作中,对其产生图像的原理,图像的质量,以及DR摄影系统在现代化医院中的临床应用进行初步的研究总结。结果:DR是在专用的计算机控制下,直接读取感应介质,得到X线影像信息,并以数字化图像方式重放和记录,并且传送到影像阅读工作站,由医师通过显示屏调节窗宽、窗位、影像的放大、缩小、测量、影像的增强、黑白反转,区域裁剪等方法观察投照部位和病灶的内部情况,有利于更好的做出诊断。医师在观察DR影像时要比传统X胶片更加主动,更加直观。结论:1DR成像原理:直接数字化放射成像(DR)是指在专用的计算机控制下,直接读取感应介质,记录到的X线影响信息,并以数字化图像方式重放和记录。它是用X线探测器代替了传统的增感屏来接受X线管发射出的穿透人体的X线。检查者控制采集板及发生器,通过HIS/RIS的联网协议采集病人信息并输出图像到影像阅读工作站。由医师根据所调节出的图像做出相应的诊断。2DR的图像质量:DR摄影中,当X线照射量足够大时,X线探测器才能接受到足够的X线,并产生清晰度较高的数字化图像,同时通过图像的后处理功能,调节窗宽、窗位,亦可清晰的观察图像并     

螺旋CT在SARS鉴别诊断中的价值

目的：探讨肺CT在SARS或传染性非典型肺炎流行时鉴别肺部病变中的价值。方法：复习50例发热患者X线胸片及CT的影像特点。结果：X线胸片正常而CT检查有磨砂玻璃影最后临床诊断为传染性非典型肺炎者3例，胸片显示小片状影的在CT像上为结节灶2例；结论：肺CT比普通X线胸片显示肺内病灶准确，CT在SARS早期是发现和诊断的最佳影像检查手段。     

评价不同像素矩阵的单色液晶显示器对胸部DR影像识读影响的初步研究

目的评价不同分辨率的医用单色液晶显示器对胸部DR影像识读的影响,探讨放射线科影像诊断显示器的合理购置方案。方法从PACS系统中在线选取胸部DR影像图93幅,其中正常图23幅、疑诊图32幅、确诊图38幅。请低年资、中年资、高年资医师各3名在3种不同分辨率的显示器上集中进行三次独立读图,对结节的有无的评判采用5等分法：肯定有、可能有、不确定、可能无、肯定无,对纹理显示质量的优劣的评判采用3等分法：优、良、差,每名医师针对每台显示器上的每幅图像给出自己的信任等级。采用SPSS13.0对结果进行统计分析。结果对于结节检测而言,高年资医师使用2MP、3MP、5MP显示器的ROC曲线下面积AUC分别为0.774、0.784、0.816,中年资医师分别为0.754、0.764、0.768,低年资医师分别为为0.695、0.754、0.774;在相同分辨率显示器上不同年资的医师之间及同年资医师在不同分辨率的显示器上对肺结节的检出效能比较差异均无统计学意义（P＆gt;0.05）。对于纹理显示质量的评判,除在5MP显示器上高年资和中年资医师、高年资和低年资医师之间存在显著性差异（P＆lt;0.05）外,其他比较差异均无统计学意义。结论在检测肺结节时使用分辨率为2MP、3MP、5MP显示器的诊断效能相当;在观测肺纹理显示质量时在5MP显示器上高年资的医师会得到更多的信息;对于放射科完全可以采用高、中、低分辨率显示器相结合组成诊断工作站系统,不同年资的医师和不同分辨率的显示器之间合理配置可以提高性价比。     

IMPROVED MARKING AND CHARACTERIZING OF PULMONARY NODULES ON DIGITAL RADIOGRAPHS USING A COMPUTER-AIDED DIAGNOSIS SYSTEM

Objective To evaluate and reduce inter-observer variations in the detection and characterization of pulmonary nodules on digital radiograph (DR) chest images. Methods Two hundreds and thirty-two new posterior-anterior DR chest images were collected from out-patient screening patients. Consensus was reached by two experienced radiologists on the marking, rating, and segmentation of small actionable nodules ranged from 5 to 15 mm in diameter using a computer-aided diagnosis (CAD) system. Both their own nodule findings and the computer's automatic nodule detection results were analyzed to make the consensus. Nodules identified together with corresponding likelihood rating and segmentation results were referred as "Gold Standard". Two un-experienced radiologists were asked to first mark and characterize suspicious nodules independently, then were allowed to consult the computer nodule detection results and change their decisions. Results Large inter-observer variations in pulmonary nodule identification and characterization on DR chest images were observed between un-experienced radiologists. Un-experienced radiologists could greatly benefit from the CAD system, including substantial decrease of inter-observer variation and improvement of nodule detection rates. Moreover, radiologists with different levels of skillfulness could achieve similar high level performance after using the CAD system. Conclusion The CAD system shows a high potential for providing a valuable assistance to the examination of DR chest images.     

计算机辅助检测系统在CT筛查肺结节中的应用研究

目的通比较CAD、医生双阅片、医生结合CAD阅片三种CT筛查肺结节方式,评价计算机辅助检测系统(CAD)在CT筛查肺结节中的应用价值。方法从CT扫描的无症状体检者中,应用随机抽样方法抽取60例肺结节患者。分别使用3种方式阅读图像,方法A:应用CAD软件对图像进行自动诊断;方法B:由2名放射科医生共同阅读图像并以一致意见作为诊断;方法C:由另外1名同等年资的放射科医生结合CAD软件阅读图像并做出诊断。结节参照标准由3位主任医生共同拟定。应用χ2检验分析三种阅读方式灵敏度是否存在差异,P0.05为差异有统计学差异。结果 CAD、医生双阅片、医生结合CAD三种方式肺结节检出灵敏度分别为75.1%、73.8%、87.3%。医生结合CAD方式肺结节检出灵敏度显著高于CAD、医生双阅片方式(P=0.001,P=0.0003)。CAD与医生双阅片方式之间肺结节检出灵敏度没有显著差异(P=0.74)。结论 CAD系统可以提高放射科医生肺结节检出能力,且医生结合CAD诊断方式优于同年资医生双阅片方式。     

数字化放射成像与普通X线诊断肺内单发结节的ROC曲线评价

OBJECTIVE: To compare digital radiographs with conventional radiographs in the detection of solitary pulmonary nodules. METHODS: Thirty patients with solitary pulmonary nodule and 30 cases without pulmonary nodules were enrolled in the study. The existence of solitary pulmonary nodule was confirmed by chest computed tomography (CT) as well as biopsy. All patients examined by both digital radiography (group A) and conventional radiographs (group B) were reviewed by four experienced chest radiologists and four residents. Assessment was performed with receiver operating characteristic (ROC) analysis of the images in both groups. RESULTS: (1) Observer performance of the experienced radiologists in group B (Az=0.838) was superior to that in group A (Az=0.816) (P<0.05) in detection of solitary pulmonary nodule. For the residents, observer performance in group B (Az=0.842) was superior to that in group A (Az=0.712) (P<0.05). (2) There was no difference between the two groups (P=0.272), for the judgement of benign or malignant solitary pulmonary nodule. CONCLUSIONS: Digital radiographs is superior to conventional radiographs in detection of solitary pulmonary nodule. However, there was no significant differences in discrimination between benign and malignant solitary pulmonary nodules in the two groups.     

LDCT检查与DR胸片检查在社区高危人群肺癌筛查中的应用价值比较

目的:比较低剂量CT(LDCT)检查与直接数字化X射线摄影系统(DR)胸片检查在社区高危人群肺癌筛查中的应用价值。方法:选取544例社区肺癌高危人群为研究对象,均行LDCT检查和DR胸片检查,统计LDCT检查、DR胸片检查及病理检查结果,以病理检查结果为"金标准",比较LDCT检查与DR胸片检查的肺癌检出率、不同直径结节数检出率,以及毛刺征、空泡征、分叶征、胸膜凹陷征等肺癌征象检出率。结果:544例社区肺癌高危人群中,经LDCT检查、DR胸片检查检出阳性156例,阴性388例,其中LDCT检查检出阳性127例,DR胸片检查检出阳性91例;156例检查呈阳性者均自愿于医院进行检查,经手术病理检查确诊肺癌93例,占59.62%。LDCT检查肺癌检出率为97.85%,高于DR胸片检查的72.04%,差异有统计学意义(P<0.05);LDCT检查不同直径结节数检出率为73.24%,高于DR胸片检查的51.41%,差异有统计学意义(P<0.05);LDCT检查毛刺征、空泡征、分叶征、胸膜凹陷征等肺癌征象检出率均高于DR胸片检查,差异有统计学意义(P<0.05)。结论:LDCT检查应用于社区高危人群肺癌筛查,可提高肺癌检出率、不同直径结节数检出率和肺癌征象检出率,效果优于DR胸片检查。     

Neural network-based computer-aided diagnosis in distinguishing malignant from benign solitary pulmonary nodules by computed tomography

Background Computer-aided diagnosis (CAD) of lung cancer is the subject of many current researches. Statistical methods and artificial neural networks have been applied to more quantitatively characterize solitary pulmonary nodules (SPNs). In this study, we developed a CAD scheme based on an artificial neural network to distinguish malignant from benign SPNs on thin-section computed tomography (CT) images, and investigated how the CAD scheme can help radiologists with different levels of experience make diagnostic decisions.Methods Two hundred thin-section CT images of SPNs with proven diagnoses (135 small peripheral lung cancers and 65 benign nodules) were analyzed. Three clinical features and nine CT signs of each case were studied by radiologists, and the indices of qualitative diagnosis were quantified. One hundred and forty nodules were selected randomly to form training samples, on which the neural network model was built. The remaining 60 nodules, forming test samples, were presented to 9 radiologists with 3–20 years of clinical experience, accompanied by standard reference images. The radiologists were asked to determine whether a nodule was malignant or benign first without and then with CAD output. Diagnostic performance was evaluated by receiver operating characteristic (ROC) analysis.Results CAD outputs on test samples had higher agreement with pathological diagnoses (Kappa=0.841, P&lt;0.001). Compared with diagnostic results without CAD output, the average area under the ROC curve with CAD output was 0.96 (P&lt;0.001) for junior radiologists, 0.94 (P=0.014) for secondary radiologists and 0.96 (P=0.221) for senior radiologists, respectively. The differences in diagnostic performance with CAD output among the three levels of radiologists were not statistically significant (P=0.584, 0.920 and 0.707, respectively). Conclusions This CAD scheme based on an artificial neural network could improve diagnostic performance and assist radiologists in distinguishing malignant from benign SPNs on thin-section CT images.     

数字化乳腺X线计算机辅助诊断系统临床应用价值的初步探讨

目的 评价数字化乳腺X线摄影的计算机辅助诊断(CAD)系统的临床应用价值。方法 随机抽取120例乳腺癌患者数字化乳腺X线平片,比较放射科医师应用CAD前后诊断乳腺癌敏感度的差异。详细记录患者乳腺密度、肿块直径、钙化直径、是否为毛刺样肿块、病理类型等特点,探讨其对CAD辅助放射科医师诊断乳腺癌敏感度的影响。结果 放射科医师应用CAD前后诊断乳腺癌的敏感度分别为74．2％和89．2％(χ^2=37．628,P=0．000)。乳腺密度(χ2=7．352,P=0．007)、钙化直径(χ^2=10．549,P=0．014)和病理类型(χ^2=13．751,P=0．003)对CAD提高放射科医师诊断敏感度的影响具有重要意义。CAD可以显著降低致密型乳腺内病变、直径小的钙化灶、导管内癌及浸润性导管癌的漏诊率;但对其余各种病变的辅助诊断价值有限。放射科医师漏诊的原因主要有：大量阅片过程中,视觉疲劳、注意力降低而忽略了一些微小的病灶(Ⅰ型漏诊);无典型的恶性肿块或钙化(Ⅱ型漏诊)。应用CAD可以有效地避免Ⅰ型漏诊,但对Ⅱ型漏诊的帮助意义较小。结论 基于数字化乳腺X摄影的CAD系统对提高放射科医师诊断乳腺癌的敏感度有较大帮助,但它仅能作为放射科医生的诊断助手,而不能对乳腺疾病的良恶性作出判断。     

An Assisted Diagnosis System for Detection of Early Pulmonary Nodule in Computed Tomography Images

Lung cancer is still the most concerned disease around the world. Lung nodule generates in the pulmonary parenchyma which indicates the latent risk of lung cancer. Computer-aided pulmonary nodules detection system is necessary, which can reduce diagnosis time and decrease mortality of patients. In this study, we have proposed a new computer aided diagnosis (CAD) system for detection of early pulmonary nodule, which can help radiologists quickly locate suspected nodules and make judgments. This system consists of four main sections: pulmonary parenchyma segmentation, nodule candidate detection, features extraction (total 22 features) and nodule classification. The publicly available data set created by the Lung Image Database Consortium (LIDC) is used for training and testing. This study selects 6400 slices from 80 CT scans containing totally 978 nodules, which is labeled by four radiologists. Through a fast segmentation method proposed in this paper, pulmonary nodules including 888 true nodules and 11,379 false positive nodules are segmented. By means of an ensemble classifier, Random Forest (RF), this study acquires 93.2, 92.4, 94.8, 97.6% of accuracy, sensitivity, specificity, area under the curve (AUC), respectively. Compared with support vector machine (SVM) classifier, RF can reduce more false positive nodules and acquire larger AUC. With the help of this CAD system, radiologist can be provided with a great reference for pulmonary nodule diagnosis timely.