低剂量CT扫描联合计算机辅助检测系统筛查肺结节的临床研究

目的 探讨低剂量胸部CT扫描联合计算机辅助检测肺结节(CAD)系统筛查肺癌高危人群肺内结节的临床价值和CAD系统对放射科医师的辅助作用.方法 选取219名具有肺癌高危因素体检者,行低剂量胸部CT平扫,由2名具有15年以上胸部诊断经验的放射科高年资医师独立阅读1.0 mm层厚重建图像,记录每例结节表现,两者意见一致后保留诊断结果作为金标准;应用CAD系统对上述图像进行结节识别处理并记录检出结果,另由2名具有5年影像诊断工作的放射科年轻医师阅读上述图像,记录诊断结果,然后应用CAD系统的输出结果再次阅读图像并记录诊断结果,根据金标准判断CAD系统检测肺结节的敏感性、假阳性率,应用X~2检验比较年轻医师应用CAD系统前后肺结节检测的能力.结果 219名体检者中最终确定有结节者104(47.5%)名,高年资医师共确定366个结节为真结节.在366个真结节中,CAD系统检测到271个(74.0%,CAD系统共检测到695个结节,假阳性结节424个);2名年轻医师未用CAD系统时分别检测到292(79.8%)和286个(78.1%)结节,应用CAD系统后分别检测到336(91.8%)和333个(91.0%)结节,年轻医师应用CAD系统前后肺结节检测的敏感性之间差异具有统计学意义(P<0.01).结论 CAD系统对肺门区或中心区的结节检测敏感性较年轻医师高,年轻医师对周围区、胸膜下结节、磨玻璃密度结节、≤4 mm结节的检测敏感性明显优于CAD系统,两者相互结合能够提高肺结节的检出率.     

计算机辅助诊断在肺结节中的应用进展

随着影像学肺癌筛查计划的研究进展，有关计算机辅助诊断（CAD）在肺结节中的应用受到越来越广泛的关注。目前计算机辅助分析系统的应用主要集中在2个方面：即在胸部X线片或CT模式上检测结节和鉴别结节的良恶性。笔者搜集CAD在肺结节中应用的报道，综述如下。     

计算机辅助检测肺结节在数字化X线胸片肺癌筛查中的应用价值

目的 评价计算机辅助检测(CAD)肺结节系统在数字化X线胸片上肺癌筛查中的应用价值.方法 由1名放射科医师和CAD肺结节检测系统独立阅读100例连续的数字摄影(DR)X线胸片,CAD系统可以检出最长直径在5～15 mm的肺结节.由2名放射科专家(有15年胸部影像诊断经验)进行回顾性阅读,参照相应的CT图像,两人意见达成一致后标记真结节的个数和位置并保存标记结果,将标记结果作为金标准来比较放射科医师和CAD系统的肺结节检测敏感性和假阳性率.结果 放射科医师共检测到95个结节,CAD系统共检测到304个结节.在回顾性检查中2名放射科专家共标记134个真结节,其中放射科医师检测到82个(61.2%),CAD检测到105个(78.4%),CAD系统检测到而被放射科医师漏诊的结节35个,放射科医师检测到而CAD系统漏诊的结节10个.放射科医师应用CAD系统后检测到112个真结节,检测率提高到83.6%.放射科专家意见一致后认为CAD系统检出199个假阳性结节,平均每张胸片约2.0个.结论 在肺癌筛查中放射科医师和CAD系统必须联合应用才可以识别X线胸片中所有的结节.     

经结节体积的分析对低剂量CT中肺结节的计算机辅助诊断性能与双人阅片法的比较

目的通过对结节体积的分析,评估低剂量CT中肺结节的计算机辅助诊断(CAD)性能对双人阅片法的优越性。方法从NELSON肺癌筛查试验中随机抽取400例低剂量胸部CT检查的影像。经2名独立的诊断医师和CAD分别对CT影像进行评估。根据目前胸部放射诊断标准,对经诊断医师和(或)CAD标记的1667个结节进行评价。通过计算肺结节检测的敏感性和假阳性的数量、结节的特点和数量对性能进行评估。结果根据筛查方法,90.9%的结节不需进一步的评估,49.2%为小结节(<50mm3)。排出小结节后,CAD将假阳性检测率从3.7%降低到1.9%。151个结节需要进一步评估,与双人阅片比较,仅被CAD发现的结节有33个(21.9%),其中1人第2年被确诊为肺癌。对结节检测的敏度:双人阅片为78.1%,CAD为96.7%。共有69.7%未被诊断医师发现的结节为连接性结节,其中78.3%与血管相连。结论当排出小结节后,CAD的假阳性率低于双人阅片,并且有助于提高在肺癌筛查中肺结节检测的敏感性。     

计算机辅助检测系统在低剂量肺癌筛查结节检出中的应用价值

目的 评价计算机辅助检测系统(CAD)在64层CT低剂量肺癌筛查肺结节检出中的应用价值及其对放射科医师的辅助作用.方法 从2007年6月至2008年6月肺癌低剂量筛查数据库共578例中运用纯随机抽样方法抽取100例.低剂量CT扫描参数管电压120 kV,管电流30及40 mA或管电流调制技术,层厚1.25或1.00 mm.由2名胸部影像医师首先阅读胸部CT图像,再应用CAD系统按结节所在位置分为肺外野、肺内野两部分,并将结节检出阈值分别设定为3.0、4.0、5.0 mm进行分析.所有结节以2人达成一致作为真结节.分别分析医师双阅片及CAD系统检出结节的能力,并进行McNemar-Bowker检验.结果 在100例胸部低剂量CT中,共检出真结节257枚,直径为1.7 ～18.5 mm;分布在双肺外野191枚,双肺内野66枚.CAD系统肺结节检出率为91.1％( 234/257),漏诊率为8.9％( 23/257),在漏诊的23枚结节中,10枚为实性结节,直径为2.4～6.0 mm;13枚为非实性结节,直径为2.1～8.6 mm;分布在肺外野17枚,肺内野6枚.放射科医师阅片结节检出率为59.1％(152/257),漏诊率为40.9％( 105/257),漏诊结节中94枚为实性结节,10枚为部分实性结节,1枚为非实性结节,结节大小2.4～11.8 mm;分布在肺外野69枚,肺内野36枚.结论 低剂量螺旋CT肺癌筛查中CAD检出肺结节的能力明显高于医师双阅片,尤其是对肺内野病灶的检出.使用CAD作为辅助诊断时,对非实性结节漏诊率高.     

CT三维体积测量技术在孤立性肺结节诊断中的初步应用

孤立性肺结节(solitary pulmonary nodule,SPN)的诊断一直是胸部CT最富挑战性的难题。确定孤立性肺结节的良恶性与病人的临床处理紧密相关。CT三维体积测量(three-dimensional volumetric measurement)作为一种计算机辅助诊断(computer-aided diagnosis,CAD)技术,有助于结节的定性诊断,现已初步应用于临床。本文介绍了孤立性肺结节的倍增时间、CT三维体积测量技术及该技术在孤立性肺结节诊断中的初步应用。     

计算机辅助检测系统在检测胸片肺结节中的应用

目的 探讨计算机辅助检测系统(CAD)在检测肺结节中的应用价值.方法 随机选取有胸部CT检查且在前后10 d内行胸部后前位片检查的200例患者,由3位不同临床经验的放射科医师分别记录应用CAD前和应用CAD后直径在3～20 mm的结节个数,并以CT检查为金标准,对其检出敏感性进行统计学分析.结果 CT发现45例80个结节符合直径在3～20 mm,CAD准确率51.25%,放射科医师甲、乙、丙在使用CAD前准确率分别为40%、37.5%及26.25%,使用CAD后准确率分别为46.25%、46.25%及30.0%.在直径3～10 mm的结节中,CAD发现30个,放射科医师甲、乙、丙在使用CAD前分别发现12、13、7个,各位医师的准确率与CAD间有显著差异(P<0.05);使用CAD后,放射科医师对3～20 mm结节的准确率无明显提高(P>0.05).结论放射科医师应重视CAD提示的小结节,尤其是低年资医师和对直径3～10 mm的结节.     

实习医师以共同阅片和第二阅片者模式使用计算机辅助检测系统在低剂量CT中的应用研究

【摘要】目的:评估使用计算机辅助检测（CAD）系统辅助在低剂量胸部CT图像中,以第二阅片者模式和共同阅片模式对实习医生肺结节检出的敏感性和读片时间的影响。方法：前瞻性纳入60例胸外恶性肿瘤患者,接受2次连续低剂量胸部CT扫描。 3名实习生以盲法和随机顺序独立地对低剂量胸部CT图像进行三次阅片,一次使用共同阅片模式,第二次不使用CAD,第三次使用第二阅片模式。记录真阳性率（TP）,假阳性率（FP）和阅读时间。 以3名高年资胸部放射科医师（>20年）检出的肺结节（包括对CAD检出结节认可）的一致意见为真结节参照标准。结果：共同阅片模式（259s）的阅读时间明显短于不使用CAD的阅读时间（341s,P<0.01）和第二阅片模式（363s;P<0.01）。低剂量胸部CT,CAD作为共同阅片者(CR)的敏感性(67.36%)显著高于不使用CAD的敏感性(40.83%,P<0.001),而与CAD作为第二阅片者(SR)的敏感性(68.34%：P>0.05)无统计学差异。CAD作为CR的FP率(5.31/CT)高于无CAD的FP率(3.28/CT,P<0.0001),而与CAD作为SR的FP率(5.23/CT,P>0.05)无统计学差异。使用CAD在共同阅片模式下的FOM明显高于不使用CAD的FOM(分别为0.59和0.44,P<0.001),使用CAD在第二阅片模式的平均FOM值为0.60,与共同阅片模式无统计学意义(P=0.675)。结论:在低剂量CT图像,使用CAD显著提高实习医师对包括小结节在内的肺结节诊断敏感性;并且以共同读片模式使用CAD显著地缩短了实习医师的阅片时间。     

应用计算机辅助检测系统对观察者在数字化胸片肺结节检测中的训练

摘要目的评估短期反馈能否帮助观察者提高在数字化胸片中运用计算机辅助系统(CAD)检测肺结节的能力。方法140例胸部平片(56例CT证实存在孤立性肺结节,84例为阴性对照)分为4组,每组各35例;每组均有6名观察者按不同顺序阅片。在有和没有CAD(IQQA-Chest,EDDA Technology)辅助情况下分别对病变的存在、部位、诊断的可靠性进行计分。观察者在每组阅片后获得独立的反馈。     

2017 RSNA胸部影像学

【摘要】RSNA2017报道的胸部影像学的重点为机器深度学习、人工智能和影像组学,机器深度学习和人工智能除了在肺结节检测方面获得较大的进步之外,在肺结节良恶性鉴别方面也也显示了初步诊断价值。随着胸部疾病的诊疗需要,胸部放射介入诊疗技术的开展也逐渐增多,包括肺结节标记、肺结节诊断、肺结节基因检测和肺转移瘤消融治疗。磁共振功能成像在肺结节诊断中应用越来越多,尤其以DWI和DCE MRI技术为主。在肺结节筛查方面,机器辅助的人工智能系统开始崭露头角。一系列的技术进展为让胸部影像诊疗更加精准,符合了今年大会的主题“探索、发明、转化”。     

Automatic detection of pulmonary nodules at spiral CT: clinical application of a computer-aided diagnosis system

The aim of this study was to evaluate a computer-aided diagnosis (CAD) workstation with automatic detection of pulmonary nodules at low-dose spiral CT in a clinical setting for early detection of lung cancer. Eighty-eight consecutive spiral-CT examinations were reported by two radiologists in consensus. All examinations were reviewed using a CAD workstation with a self-developed algorithm for automatic detection of pulmonary nodules. The algorithm is designed to detect nodules with diameters of at least 5 mm. A total of 153 nodules were detected with at least one modality (radiologists in consensus, CAD, 85 nodules with diameter < 5 mm, 68 with diameter > or = 5 mm). The results of automatic nodule detection were compared to nodules detected with any modality as gold standard. Computer-aided diagnosis correctly identified 26 of 59 (38%) nodules with diameters > or = 5 mm detected by visual assessment by the radiologists; of these, CAD detected 44% (24 of 54) nodules without pleural contact. In addition, 12 nodules > or = 5 mm were detected which were not mentioned in the radiologist's report but represented real nodules. Sensitivity for detection of nodules > or = 5 mm was 85% (58 of 68) for radiologists and 38% (26 of 68) for CAD. There were 5.8+/-3.6 false-positive results of CAD per CT study. Computer-aided diagnosis improves detection of pulmonary nodules at spiral CT and is a valuable second opinion in a clinical setting for lung cancer screening despite of its still limited sensitivity.     

Recent progress in computer-aided diagnosis of lung nodules on thin-section CT.

Computer-aided diagnosis (CAD) provides a computer output as a "second opinion" in order to assist radiologists in the diagnosis of various diseases on medical images. Currently, a significant research effort is being devoted to the detection and characterization of lung nodules in thin-section computed tomography (CT) images, which represents one of the newest directions of CAD development in thoracic imaging. We describe in this article the current status of the development and evaluation of CAD schemes for the detection and characterization of lung nodules in thin-section CT. We also review a number of observer performance studies in which it was attempted to assess the potential clinical usefulness of CAD schemes for nodule detection and characterization in thin-section CT. Whereas current CAD schemes for nodule characterization have achieved high performance levels and would be able to improve radiologists' performance in the characterization of nodules in thin-section CT, current schemes for nodule detection appear to report many false positives, and, therefore, significant efforts are needed in order further to improve the performance levels of current CAD schemes for nodule detection in thin-section CT.     

多层螺旋CT灌注成像在肺结节鉴别诊断中的应用

目的 探讨多层螺旋CT灌注成像在肺结节的良恶性鉴别诊断中的价值.方法 采用多层螺旋CT机对96例肺结节患者行灌注扫描,其中良性结节18例、炎性结节28例、恶性结节50例.以perfusion 3软件测定结节的血流量(BF),血容量(BV),平均通过时间(MTT),渗透表面积乘积(PS)以及拟合时间-密度曲线(TDC),采用灌注参数及曲线形态来评价结节的良恶性.结果 BF、BV在炎性结节与良性结节之间具有显著性差异(P＜0.05),炎性结节均大于良性结节.MTT在三组结节之间没有显著性差异(P＞0.05),PS在恶性结节与良性结节之间、以及良性与炎性结节之间具有显著性差异(P＜0.05),恶性结节与炎性结节均高于良性结节,三组不同性质结节之间的TDC曲线形态也不同.结论 CT灌注成像能够较准确的判断肺结节的性质,在良恶性鉴别诊断中具有重要意义.     

Computer-aided diagnosis for lung cancer

CAD methods may provide radiologists with tools to obtain more accurate diagnoses for lung cancer. Considerable effort has been devoted to developing CAD tools for CXR; however, these are limited by the fundamental constraints of the projective CXR modality. CT provides far more detailed information that can be exploited better by CAD systems. There has been very little work done in this area to date, although the basic technology has already been developed through the more extensive research in the computer vision areas supported by industry and the military. Initial prototype CT CAD systems have been described that are highly effective in detecting small pulmonary nodules and in predicting malignancy of nodules. CT is now achieving momentum in the study of lung cancer. It has taken time for this modality to gain acceptance because of several factors: higher radiation dose, higher cost, and the novelty of use in this application. It is important to note that the technology for CT scanners is still rapidly evolving. As the speed, resolution, and cost of CT scanners continue to improve, computer techniques for the measurement and analysis of nodules will also achieve corresponding improvements in accuracy and diagnostic utility. Future knowledge-based CT CAD systems will provide detailed analysis of the related conditions of the lungs, such as emphysema, and diagnostic analysis of nodules. The issue is not whether CAD will improve the performance and capabilities of the radiologist, but at what rate their development and the corresponding improvement will occur. Current prototype CAD systems may be considered as tools. As such they will improve the performance of the user/radiologist if they are well engineered and if the user understands their capabilities and limitations. These systems need to be improved by knowledge-based engineering, which is notoriously difficult to implement robustly and requires model refinement and optimization based on a large database of cases. Research should be directed at developing these methods rather than comparing prototype systems with current practices. Future performance should be expected to exceed that of today's grand masters.     

CT肺结节分析软件在肺部筛查中的应用价值

目的:对比分析肺结节分析软件在肺部筛查中的应用价值。方法:80例肺部结节患者随机均分为A、B、C、D 4组。3位放射科医师(D1、D2、D3)分别采用常规阅片法和计算机辅助检测(computer aided detection,CAD)联合阅片法,分别在无限时和限时模式下,对这4组患者行CT阅片,记录肺部结节数量。其中A组采用无限时常规阅片法,B组采用无限时CAD联合阅片法,C组采用限时常规阅片法,D组采用限时CAD联合阅片法。将所有记录的肺结节结果与金标准进行对比,绘制受试者工作特性曲线(ROC曲线),记录曲线下面积(Az值)。通过Az值的比较,判断肺结节分析软件对于诊断者的辅助价值。结果:D1、D2、D3的Az值A组分别为0.777、0.693、0.506,B组分别为0.816、0.759、0.599,C组分别为0.666、0.559、0.295,D组分别为0.779、0.744、0.542。各诊断者于无限时模式下的Az值均高于限时模式下的Az值,差异具有统计学意义。在2种模式下,CAD联合阅片法的Az值均较常规阅片法升高,但是在无限时模式下差异无统计学意义,在限时模式下差异有统计学意义;Az值的升高有随着诊断经验的增加而下降的趋势。结论:肺结节分析软件能够帮助提高诊断者在肺结节检测中的诊断价值,尤其对快速诊断及低年资诊断者的帮助意义更大。     

动态增强CT扫描在孤立性肺结节临床诊断中的应用现状和进展

对孤立性肺结节的诊断仍是当前临床工作中的难点之一。借助于动态增强CT扫描，可以了解结节增强形态、增强幅度以及结节的密度随时间变化情况，进而判断结节的性质。就动态增强CT扫描技术具体操作环节及其对结节的诊断价值进行综述。     

计算机辅助诊断在CT诊断孤立性肺结节的应用进展

孤立性肺结节（Solitary pulmonary nodules,SPN）是肺内较常见的病变,及时的检测与诊断SPN的良恶性有利于早期肺癌的发现。CT有良好的密度分辨率,可以很好地显示肺结节特征。本文叙述了计算机辅助诊断在CT诊断肺内孤立结节的研究进展。     

Recent technological and application developments in computed tomography and magnetic resonance imaging for improved pulmonary nodule detection and lung cancer staging

This review compares the emerging technologies and approaches in the application of magnetic resonance (MR) and computed tomography (CT) imaging for the assessment of pulmonary nodules and staging of malignant findings. Included in this review is a brief definition of pulmonary nodules and an introduction to the challenges faced. We have highlighted the current status of both MR and CT for the early detection of lung nodules. Developments are detailed in this review for the management of pulmonary nodules using advanced imaging, including: dynamic imaging studies, dual energy CT, computer aided detection and diagnosis, and imaging assisted nodule biopsy approaches which have improved lung nodule detection and diagnosis rates. Recent advancements linking in vivo imaging to corresponding histological pathology are also highlighted. In vivo imaging plays a pivotal role in the clinical staging of pulmonary nodules through TNM assessment. While CT and positron emission tomography (PET)/CT are currently the most commonly clinically employed modalities for pulmonary nodule staging, studies are presented that highlight the augmentative potential of MR.     

CT灌注成像在肺部良恶性结节鉴别诊断中的潜能

目的确定CT灌注成像在肺部良恶性结节鉴别诊断中的潜能。方法 32例经临床和病理证实为孤立性肺结节患者,其中,24例恶性和8例良性均经CT灌注成像,随后,对两组的灌注参数、强化峰值及达峰时间进行了测量与统计学比较。结果恶性组血流量(BF)为33.35±10.23mL/(100 g·min),良性组BF为23.58±8.65mL/(100 g·min),两组间有显著性差异(P<0.05);恶性组血容量(BV)为11.36±3.89mL/100 g,良性组BV为6.32±3.21 mL/100 g,两组间有显著性差异(P<0.01);恶性组达峰时间(TTP)为32.8±2.9 s,良性组为24.6±2.3 s,两组间有显著性差异(P<0.05);良性与恶性两组间强化峰值无统计学差异(P>0.05)。结论 CT灌注成像不仅是评价全部结节灌注情况的一种可行方法,而且有助于肺部良恶性结节的鉴别。