Dual-energy CT lung ventilation/perfusion imaging for diagnosing pulmonary embolism

Objectives

To evaluate the feasibility and findings of combined dual-energy computed tomography (DECT) lung ventilation/perfusion imaging in patients with suspected pulmonary embolism (PE).

Methods

This study was institutional review board-approved and written informed consent was obtained from each patient. Thirty-two subjects (aged 11–61 years) underwent combined xenon-enhanced ventilation and iodine-enhanced perfusion DECT. Ventilation, perfusion and morphological information were visually interpreted. Ventilation/perfusion information was classified as mismatch (differing patterns) or match (concordant patterns). Adverse reactions and radiation doses were recorded for each subject.

Results

Of 32 patients undergoing xenon-enhanced DECT, six patients reported adverse reactions (shortness of breath, n?=?2; mild dizziness, n?=?3; limb numbness, n?=?1). Twenty-eight of 32 patients could be included into the data analysis. PE was detected in 10/28 patients. PE-related ventilation/perfusion mismatch was found in 17 lung lobes in 8/10 patients and matched ventilation/perfusion was detected in 2 patients. Eighteen patients had no PE. In this group, there was no case of a ventilation/perfusion mismatch. Matched ventilation/perfusion impairment was seen in one patient. The overall radiation dose from two DECT acquisitions was 4.8?±?1.4 mSv (range 2.7-7.5 mSv).

Conclusions

DECT lung ventilation/perfusion imaging is feasible and can visualise ventilation/perfusion match or mismatch in patients with suspected PE.

Key Points

? Combined dual-energy CT lung ventilation/perfusion imaging is feasible. ? Combined dual-energy CT ventilation/perfusion imaging provides lung morphological and functional information. ? Dual-energy CT can demonstrate ventilation/perfusion mismatch in patients with pulmonary embolism.     

CT imaging of acute pulmonary embolism

CT pulmonary angiography (CTPA) has become the de facto clinical "gold standard" for the diagnosis of acute pulmonary embolism (PE) and has replaced catheter pulmonary angiography and ventilation-perfusion scintigraphy as the first-line imaging method. The factors underlying this algorithmic change are rooted in the high-sensitivity and specificity, cost-effectiveness, and 24-hour availability of CTPA. In addition, CTPA is superior to other imaging methods in its ability to diagnose and exclude, in a single examination, a variety of diseases that mimic the symptoms of PE. This article reviews the current role of CTPA in the diagnosis of acute PE as well as more recent developments, such as the use of CT parameters of right ventricular dysfunction for patient prognostication and the assessment of lung perfusion with CT.     

Multislice CT imaging of pulmonary embolism

In recent years CT has been established as the method of choice for the diagnosis of central pulmonary embolism (PE) to the level of the segmental arteries. The key advantage of CT over competing modalities is the reliable detection of relevant alternative or additional disease causing the patient's symptoms. Although the clinical relevance of isolated peripheral emboli remains unclear, the alleged poor sensitivity of CT for the detection of such small clots has to date prevented the acceptance of CT as the gold standard for diagnosing PE. With the advent of multislice CT we can now cover the entire chest of a patient with 1-mm slices within one breath-hold. In comparison with thicker sections, the detection rate of subsegmental emboli can be significantly increased with 1-mm slices. In addition, the interobserver correlation which can be achieved with 1-mm sections by far exceeds the reproducibility of competing modalities. Meanwhile use of multislice CT for a combined diagnosis of PE and deep venous thrombosis with the same modality appears to be clinically accepted. In the vast majority of patients who receive a combined thoracic and venous multislice CT examination the scan either confirms the suspected diagnosis or reveals relevant alternative or additional disease. The therapeutic regimen is usually chosen based on the functional effect of embolic vascular occlusion. With the advent of fast CT scanning techniques, also functional parameters of lung perfusion can be non-invasively assessed by CT imaging. These advantages let multislice CT appear as an attractive modality for a non-invasive, fast, accurate, and comprehensive diagnosis of PE, its causes, effects, and differential diagnoses.     

双源 CT 肺栓塞探测软件及能量灌注成像对外周型肺栓塞的诊断价值

目的：探索双源 CT 后处理软件在外周型肺栓塞诊断中的价值。方法对150例可疑肺栓塞患者进行扫描,20例患者符合标准。扫描数据采用肺栓塞分析软件(PED)、双能量肺灌注成像(DEPI)及肺动脉成像(CTPA)对图像重建,分别由2名高年资血管专业诊断医师对 PED 图、DEPI 图及 CTPA 图进行分析,根据诊断标准,分别记录由 PED 图、CTPA 图诊断的肺段及亚段动脉肺栓子位置、数目,计算显示率并评价其统计学差异;同时评价 PED 图与 DEPI 图对肺段动脉肺栓塞诊断一致性。结果 CTPA图共发现30处段动脉及40处亚段动脉内存在血栓,其检出率为7.50%及5.00%,PED 图共发现48处段动脉及62处亚段动脉内存在血栓,其检出率为12.00%及7.75%,CTPA 图与 PED 图存在显著的统计学差异(χ2=4.60、5.06,P <0.05)。以 PED 图诊断结果为参考标准,Kappa 系数=0.94,一致性极好。在 PED 图发现48处段动脉肺栓塞中,13处完全性栓塞,DEPI 图显示10例出现灌注缺损,3例出现灌注稀疏;35处不完全性肺栓塞,2例灌注缺损,29例出现灌注稀疏,4例无明显灌注改变。结论双源 CT肺栓塞探测软件联合能量灌注成像能够明显提高外周型肺栓塞的诊断率,具有较高的实用性及临床价值。     

64层CT血管成像与肺通气灌注显像诊断肺栓塞的对比研究

目的:通过比较两种无创影像检查为临床诊断肺栓塞提供有指导意义检查方法。方法:64层螺旋CT肺动脉成像和肺通气/灌注显像图像依据相同的诊断标准进行独立的分析。V/Q显像和多层螺旋CT肺动脉成像两种检查方法的判定结果进行相关分析,两者准确性、符合性及不确定性诊断比率的差异采用2检验进行比较。结果:180例患者中CTPA和V/Q显像诊断PE的敏感性、特异性、符合率分别为90.5%对83.8%,91.5%对85.0%,91.1%对84.4%。CTPA和V/Q显像诊断PE的κ值分别为0.680,0.648。结论:疑诊肺栓塞病例中两者皆可作为确诊及排除疑诊肺栓塞病例的检查方法。     

肺通气/灌注平面显像与肺灌注SPECT/CT对肺栓塞诊断价值的对比性研究

目的：探讨传统的肺通气/灌注（V/Q）平面显像、肺灌注断层显像与低剂量平扫CT相结合（肺Q SPECT/CT）对肺栓塞的诊断价值。方法收集69例临床可疑肺栓塞患者,在对其行肺V/Q平面显像的同时,进行了肺Q SPECT/CT显像。以临床最终确诊结果为金标准,对两种方法的诊断结果进行对比分析。结果69例临床可疑肺栓塞患者,最终确诊43例,排除26例。肺Q SPECT/CT对肺栓塞诊断的灵敏度、准确率、阴性预测值及与临床最终确诊结果的Kappa值均较肺V/Q平面显像高;肺Q SPECT/CT对合并有慢性阻塞性肺疾病（COPD）的病例诊断的特异度较肺V/Q平面显像低。排除COPD病例的影响后,肺Q SPECT/CT的特异度明显提高,且高于肺V/Q平面显像的特异度。两种方法检出肺栓塞的一致性为85%（34/40）,且两种方法检出率之间的差异有统计学意义（χ2=8.10,P<0.05）。结论肺Q SPECT/CT明显提高了对不伴有COPD的肺栓塞患者的诊断价值,用肺Q SPECT/CT取代肺V/Q平面显像值得商榷。     

99Tcm-聚合白蛋白肺灌注显像对肺栓塞溶栓疗效的评价

目的 探讨99Tcm-聚合白蛋白(99Tcm-MAA)肺灌注显像评价肺栓塞溶栓治疗的价值.方法 对54例急性肺栓塞的患者进行回顾性分析,所有患者均由99Tcm-MAA肺灌注显像结合X线胸片检查确诊,并于溶栓治疗1周后复查肺灌注显像,部分病例于治疗3个月后再次复查.结果 54例急性肺栓塞患者溶拴治疗前99Tcm-MAA肺灌注显像共观察到347个受损肺段,X线胸片均无相应肺段或亚肺段异常.溶栓治疗后1周复查肺灌注显像,164个受损肺段(47.3%)恢复正常;3个月后再次复查,199个受损肺段(57.4%)恢复正常(χ2=10.68,P<0.05).结论 99Tcm-MAA肺灌注显像是一种无创的诊断方法,对肺栓塞溶栓治疗效果的评估有重要价值.     

肺通气血流灌注显像、螺旋CT肺动脉造影及D-二聚体测定对诊断肺栓塞的临床价值

目的探讨放射性核素肺通气血流灌注比值(V/Q)显像和螺旋CT肺动脉造影(SCTPA)以及血浆D-二聚体(dimer)检测对肺栓塞(PE)诊断的临床价值。方法对我院2010年2月—2013年2月可疑肺栓塞的患者,行V/Q显像、SCTPA检查和血浆D-二聚体测定以及相关检查,以最终临床诊断为依据,分别评价V/Q显像、SCTPA和血浆D-二聚体测定对PE的诊断价值。结果 278例高度怀疑PE患者经上述检查确诊PE患者151例,V/Q显像、SCTPA检查和血浆D-二聚体测定诊断PE的灵敏度、特异性、阳性预测值、阴性预测值分别为93.6%(132/141)、96.0%(120/125)、96.4%(132/137)、93.0%(120/129);95.8%(137/143)、96.9%(124/128)、97.2%(137/141)、95.4%(124/130);99.3%(140/141)、43.1%(59/137)、64.2%(140/218)、98.3%(59/60)。结论血浆D-二聚体测定的价值主要用于排除PE。对PE患者的检查应力求全面,V/Q显像、SCTPA检查均有其优点和不足,只有全面掌握各项检查的特点,才能对该项检查对疾病的诊断价值做出正确评价,从而正确运用这一诊断方法更好地服务于临床。     

肺栓塞MR增强肺灌注成像与核素肺灌注显像对比实验研究

目的:比较MR及SPECT核素肺灌注显像诊断肺栓塞的价值。方法:24只大白兔建立肺栓塞模型,栓塞后6h采用3D-FLASH序列,从耳缘静脉注入Gd-DTPA行肺灌注扫描,应用Evaluation自动生成肺灌注曲线,在冠状位原始图像上两侧对称性选取正常与病变区肺实质的ROI测量时间-信号强度曲线。从耳缘静脉注入99Tcm-MAA111-148MBq0·3ml8体位显像。病理学检查:分别于栓塞后分批处死实验动物,光学显微镜下观察栓塞肺组织及正常肺组织的表现。统计学采用t检验和χ2检验。结果:成功建立20只兔肺栓塞模型,栓塞后6hMR增强肺灌注成像正常和栓塞区肺实质增强率分别为317·5%和45·1%;正常肺组织灌注曲线峰值明显,栓塞区灌注曲线低平或峰值延迟(t=11·52,P<0·01)。MR增强肺灌注成像对肺栓塞模型检测的敏感性为95%,特异性为85%;SPECT肺灌注显像敏感性100%,特异性65%,统计学分析二者检查结果差异不具有统计学意义(χ2=2·06,P>0·05)。病理显示:梗死区可见大量的纤维素渗出,肺间质增厚,动脉腔内可见红细胞和血栓形成,其周围白细胞浸润伴肺淤血,部分可见点状出血及肺淤血。结论:Gd-DTPAMR增强肺灌注成像诊断肺栓塞是可行的;MR诊断肺栓塞与SPECT具有较好的一致性。     

CT灌注成像在肺部肿瘤诊断中的应用进展

本文通过总结螺旋CT灌注成像的原理和技术要求,评价其在肺部肿瘤影像诊断中所提供的肿瘤微循环状况、血流动力学变化及其它参数,从而显示CT灌注成像不但能显示肿瘤形态学方面的改变,还能了解其功能、代谢变化的信息,因而在肺部肿瘤的影像诊断与鉴别诊断、生物学行为和严重度评价等方面具有重要作用,拥有较好的临床应用前景。     

双源CT双能量肺灌注成像对肺栓塞的初步研究

目的 探讨双源CT双能量扫描肺灌注成像的临床诊断价值.方法 选择临床怀疑肺动脉栓塞30例患者行双源CT双能量扫描,生成140、80 kV和融合系数为0.3的3组数据.根据融合数据的CT肺动脉造影(CTPA)图像将患者分为肺栓塞组和正常组.采用双能量评估软件将薄层重建数据进行灌注成像分析,将双肺野分为上、中、下3部分,正常组受试者肺组织灌注定量的双侧比较行配对t检验,2组间肺组织灌注量比较行独立样本t检验,并对融合图像行MinIP,评估肺组织通气情况.结果 正常组(16例)肺灌注均匀,无明显灌注缺损及减弱,灌注定量分析显示左、右全肺的灌注量分别为(27±7)、(28±8)HU,两侧比较差异无统计学意义(t=-1.73,P＞0.05);左肺上、中、下部的灌注量分别为(23±6)、(24±6)、(28±8)HU,右肺上、中、下部灌注量分别为(26±8)、(27±8)、(28±9)HU,两侧分别比较差异均无统计学意义(t值分别为-1.91、-1.96、-1.73,P值均＞0.05).肺栓塞组(14例)CTPA图像显示肺动脉干、段及亚段充盈缺损,肺灌注成像表现为栓塞血管所支配肺野区域的灌注缺损或缺失,灌注定量分析显示全肺及中、下肺的灌注量分别为(22±5)、(22±8)、(21±8)HU,与正常组分别比较差异均有统计学意义(t值分别为-2.10、-2.32、-2.63,P值均＜0.05＝.MinIP显示通气异常区与灌注异常区具有良好的一致性.结论 双源CT双能量扫描可用于肺栓塞的诊断,有利于肺栓塞的早期发现和精确解剖定位.

Abstract：

Objective To explore the diagnostic values of dual energy lung perfusion in the diagnosis of pulmonary embolism by using dual-source CT (DSCT). Methods Thirty patients with clinically suspected pulmonary embolism underwent dual-energy scanning with dual-source CT. The scanned data were integrated into three groups including 140, 80 kV and coefficient of 0.3. According to the CT pulmonary angiography (CTPA) of the fusion data, the patients were divided into pulmonary embolism group and normal group. The thin-slice reconstruction of data was analyzed using dual-energy perfusion imaging analysis software. The lung field was divided into upper, middle and lower part to make quantitative analysis of lung tissue perfusion. Paired t-tests were used in the normal patients to compare bilateral lungs, and independent samples t-tests were applied to compare the embolism group and normal group, while minimum intensity projection images (MinIP) were utilized in the assessment of lung ventilation. Results Dual energy CT showed symmetrical homogeneous perfusion in 16 normal cases, without significant perfusion defects. Quantitative analysis showed that left and right lung perfusion were (27 ± 7) and (28 ± 8 ) HU respectively, and no significant difference was found between the two sides ( t=-1.73, P ＞0.05 ).Perfusion of the left upper, middle and lower lung was ( 23 ± 6), (24 ± 6), and (28 ± 8) HU respectively, while the perfusion of right upper, middle and lower lung was (26 ±8), (27 ±8), and (28 ±9) HU respectively, showing no statistical significant difference between the two sides (t=-1.91, -1.96,-1.73 ,P＞0.05 ). Angiography of pulmonary embolism group(14 cases)showed filling defects in the pulmonary trunk, segments and sub-segments. Pulmonary perfusion imaging showed low perfusion or defectsin lung field that dominated by embolic vessels. Quantitative analysis showed that the perfusion of the whole lung and the middle and lower lung were (22 ±5), (22 ±8), and (21 ±8) HU in the embolism group,which were significantly different from the normal group (t=-2. 10, -2.32, -2.63, P＜0.05).Minimum intensity projection images showed a good consistency of abnormal ventilation zone area and perfusion abnormalities. Conclusions Pulmonary perfusion status, especially pulmonary embolism, can be analyzed by dual energy CT scanning. It helps to early discover and precisely locate the embolism.     

^99Tcm-聚合白蛋白肺灌注显像对肺栓塞溶栓疗效的评价

目的 探讨^99Tcm-聚合白蛋白（^99Tcm-MAA）肺灌注显像评价肺栓塞溶栓治疗的价值。方法对54例急性肺栓塞的患者进行回顾性分析,所有患者均由^99Tcm-MAA肺灌注显像结合X线胸片检查确诊,并于溶栓治疗1周后复查肺灌注显像,部分病例于治疗3个月后再次复查。结果54例急性肺栓塞患者溶拴治疗前^99Tcm-MAA肺灌注显像共观察到347个受损肺段,X线胸片均无相应肺段或亚肺段异常。溶栓治疗后1周复查肺灌注显像,164个受损肺段（47．3％）恢复正常;3个月后再次复查,199个受损肺段（57．4％）恢复正常（χ^2=10．68,P〈0．05）。结论^99Tcm-MAA肺灌注显像是一种无创的诊断方法,对肺栓塞溶栓治疗效果的评估有重要价值。     

Low yield of ventilation and perfusion imaging for the evaluation of pulmonary embolism after indeterminate CT pulmonary angiography

Purpose

Ventilation and perfusion (VQ) imaging is common following suboptimal CT pulmonary angiogram (CTPA) for pulmonary embolism (PE) evaluation; however, the results of this diagnostic pathway are unclear. The purpose of our study is to determine the incidence of PE diagnosed on VQ scans performed in patients with suboptimal CTPAs.

Methods

One hundred twenty-two suboptimal CTPAs with subsequent VQ scans within 1 week were retrospectively identified. VQ reports utilizing modified ?prospective investigation of pulmonary embolism diagnosis (PIOPED) and prospective investigative study of acute pulmonary embolism diagnosis (PISAPED) criteria were evaluated for presence of PE; intermediate probability, high probability, and PE present were considered PE positive. Three hundred consecutive reports of each diagnostic CTPA and diagnostic VQ studies were reviewed to estimate baseline PE positive rates at our institution. These were compared to the positive VQ scan rate after suboptimal CTPA by Fisher’s exact test. Reported reason for suboptimal CTPA was noted. When contrast bolus timing was suboptimal, we measured main pulmonary artery (mPA) Hounsfield units (HU). Potential alternative diagnoses in CTPA reports were noted.

Results

97.5% (119/122) of VQ scans following suboptimal CTPA were negative for PE, and 2.5% (3/122) were positive for PE. This was significantly lower than baseline PE positive rate of 10.7% (32/300, p < 0.01) for VQ imaging, and 10.3% (31/300, p < 0.01) for CTPA at our institution. Most (79.5%) CTPAs were suboptimal due to contrast timing. Average mPA density in these cases was 164 ± 61 HU. Most of these studies ruled out central PE. Potential alternative diagnosis was reported in 34/122 (28%) of suboptimal CTPAs, for which pneumonia accounted 59%.

Conclusion

There is very low incidence of PE diagnosed on VQ imaging performed after suboptimal CTPA. This may be attributed to the ability of most suboptimal CTPAs to rule out central PE.

     

CT imaging in acute pulmonary embolism: diagnostic strategies

Computed tomography pulmonary angiography (CTA) has increasingly become accepted as a widely available, safe, cost-effective, and accurate method for a quick and comprehensive diagnosis of acute pulmonary embolism (PE). Pulmonary catheter angiography is still considered the gold standard and final imaging method in many diagnostic algorithms. However, spiral CTA has become established as the first imaging test in clinical routine due to its high negative predictive value for clinically relevant PE. Despite the direct visualization of clot material, depiction of cardiac and pulmonary function in combination with the quantification of pulmonary obstruction helps to grade the severity of PE for further risk stratification and to monitor the effect of thrombolytic therapy. Because PE and deep venous thrombosis are two different aspects of the same disease, additional indirect CT venography may be a valuable addition to the initial diagnostic algorithm—if this was positive for PE—and demonstration of the extent and localization of deep venous thrombosis has an impact on clinical management. Additional and alternate diagnoses add to the usefulness of this method. Using advanced multislice spiral CT technology, some practitioners have advocated CTA as the sole imaging tool for routine clinical assessment in suspected acute PE. This will simplify standards of practice in the near future.     

肺通气/灌注显像诊断不典型亚肺段肺栓塞

目的评价核索肺通气／灌注（V／Q）显像对不典型亚肺段肺栓塞（PE）的诊断价值。方法患者141例，男58例，女83例，年龄（65．67±11．29）岁，其中下肢静脉病变史者14例，糖尿病、高脂血症史者45例，63例近期内行有创性诊断和治疗，另19例均无上述病史或诊疗史。所有患者行常规盼^99Tc^m-MAA和^99Tc^m气体显像后进行1—24个月的抗凝治疗，于治疗后再行肺灌注显像。将抗凝治疗前后肺灌注显像进行对比分析，根据肺内放射性分布的变化判断治疗效果，再结合临床资料及其他影像检查综合判断不典型PE的诊断。结果141例患者肺灌注显像均显示某个肺野内不呈肺段或亚肺段分布的片状或小斑片状放射性分布稀疏区。肺通气显像示肺野内放射性分布基本均匀，未见放射性分布稀疏区。治疗后118例肺灌注显像显示双肺内放射性分布不同程度的增多或均匀。按肺野内放射性分布改善情况标准评价：抗凝治疗后恢复正常35例，显效49例，有效34例。总有效率为83．69％（118／141）。另23例肺内放射性分布无明显变化，视为无效。结论V／Q显像是诊断不典型亚肺段PE的首选方法。     

增强MR肺灌注扫描诊断肺动脉栓塞的初步研究

目的应用增强MR肺灌注扫描技术（MRPP）与增强MR肺动脉造影（MRPA）、核素肺灌注扫描相对照，初步探讨此项成像技术诊断肺动脉栓塞的敏感性及特异性。方法14例最终明确诊断为肺动脉栓塞患者，均行增强MRPA及MRPP。5例患者同时拥有核素肺通气一灌注扫描结果。3例经溶栓治疗后复查MRPA及MRPP。通过在上、中下肺野和异常区域内设置感兴趣区（ROI），测量信号强度（SI）、时间一信号曲线，获取灌注高峰期信号强度变化率。结果14例肺动脉栓塞患者，MRPA发现共62支肺动脉闭塞，MRPP共发现55个肺灌注异常区与之相吻合。符合率为88．71％，14例中MRPP显示有25个肺段合并有段及段以远的肺动脉栓塞。5例同时拥有核素扫描结果的患者，核素显示37个段灌注缺损，MRPP显示33个段，敏感度为89．19％，3例经溶栓治疗后复查MRPA和MRPP，均见受累肺动脉明显改善，肺灌注缺损区明显减少。正常灌注与灌注缺损区及低灌注区的信号强度变化率（TROS）差异有统计学意义（t=22．882，P〈0．01）。结论MRPP能够显示肺动脉栓塞的灌注缺损区和低灌注区。时间一信号曲线显示肺动脉栓塞区对比剂无灌注高峰期，信号曲线波动幅度小，信号强度变化率减低。MRPP对段及段以远的肺动脉栓塞的显示有较高的研究价值。MRPP联合MRPA可进一步提高MR诊断肺动脉栓塞的敏感度。     

双源CT双能量肺灌注成像对肺栓塞的诊断和临床应用价值

目的:探讨双源CT双能量肺灌注成像对肺动脉栓塞的诊断和临床应用价值。方法:对疑诊肺动脉栓塞的78名患者行双源CT肺动脉成像双能量扫描,数据经后处理得到肺动脉血管图像(CTA)和肺灌注图像(PBV)。两位医师对PBV图像进行质量评价和分型,同时观察CTA图像有无栓塞以及栓塞的部位、程度。分析PBV图像的表现与CTA图像、肺部异常改变的关系。用Kappa系数检验两位观察者对PBV图像质量评价和分型的一致性,计算PBV图像诊断肺栓塞的敏感度、特异度、阳性预测值和阴性预测值。结果:两位医师对肺灌注图像质量的分级以及肺灌注图像的分型一致性极强,K值分别为0.87、0.80,P值均<0.01。PBV图像诊断肺栓塞的敏感度为95.30%,特异度为56.40%,阳性预测值为70.70%,阴性预测值为91.20%。对于完全栓塞的患者,其敏感度和特异度均为100%。结论:双源CT双能量肺灌注成像能够显示肺动脉栓塞导致肺血流改变的肺灌注异常。     

Quantitative lobar pulmonary perfusion assessment on dual-energy CT pulmonary angiography: applications in pulmonary embolism

To assess quantitative lobar pulmonary perfusion on DECT-PA in patients with and without pulmonary embolism (PE). Our retrospective study included 88 adult patients (mean age 56 ± 19 years; 38 men, 50 women) who underwent DECT-PA (40 PE present; 48 PE absent) on a 384-slice, third-generation, dual-source CT. All DECT-PA examinations were reviewed to record the presence and location of occlusive and non-occlusive PE. Transverse thin (1 mm) DECT images (80/150 kV) were de-identified and exported offline for processing on a stand-alone deep learning–based prototype for automatic lung lobe segmentation and to obtain the mean attenuation numbers (in HU), contrast amount (in mg), and normalized iodine concentration per lung and lobe. The zonal volumes and mean enhancement were obtained from the Lung Analysis™ application. Data were analyzed with receiver operating characteristics (ROC) and analysis of variance (ANOVA). The automatic lung lobe segmentation was accurate in all DECT-PA (88; 100%). Both lobar and zonal perfusions were significantly lower in patients with PE compared with those without PE (p < 0.0001). The mean attenuation numbers, contrast amounts, and normalized iodine concentrations in different lobes were significantly lower in the patients with PE compared with those in the patients without PE (AUC 0.70–0.78; p < 0.0001). Patients with occlusive PE had significantly lower quantitative perfusion compared with those without occlusive PE (p < 0.0001). The deep learning–based prototype enables accurate lung lobe segmentation and assessment of quantitative lobar perfusion from DECT-PA. • Deep learning–based prototype enables accurate lung lobe segmentation and assessment of quantitative lobar perfusion from DECT-PA. • Quantitative lobar perfusion parameters (AUC up to 0.78) have a higher predicting presence of PE on DECT-PA examinations compared with the zonal perfusion parameters (AUC up to 0.72). • The lobar-normalized iodine concentration has the highest AUC for both presence of PE and for differentiating occlusive and non-occlusive PE.