Combined CT venography and CT pulmonary angiography for the detection of deep venous thrombosis in injured patients

CT Venography (CTV) performed at the time of CT pulmonary angiography (CTPA) images the central, pelvic, and extremity venous circulation with minimal additional time, radiation, and no added contrast. CTV has been added to CTPA routinely at our Level I trauma center since 2000, and we sought to determine if this addition had increased the diagnostic yield of CTPA in trauma patients. The attending radiologist's interpretation of all CTPA-CTV studies performed over a 5-year period ending in August 2006 were retrospectively reviewed. CTPAs and CTVs were categorized as "positive", "negative", or "indeterminate" for pulmonary embolus (PE) and deep venous thrombosis (DVT). During the study period, 3798 patients underwent both a CTPA and CTV; 309 (8%) of these were trauma patients. Forty-four (14%) had a PE diagnosed on CTPA. Seventeen (6%) had a DVT diagnosed on CTV. In eight (3%), the CTV added clinically relevant data, diagnosing a DVT in a patient without PE. As the consequences of a missed pelvic DVT are high and the added time burden, radiation, and contrast required for a CTV are low, further investigation into optimizing the sensitivity of CTV performed at the time of CTPA is warranted.     

Automatic coronary artery calcium scoring from unenhanced-ECG-gated CT using deep learning

PurposeThe purpose of this study was to develop and evaluate an algorithm that can automatically estimate the amount of coronary artery calcium (CAC) from unenhanced electrocardiography (ECG)-gated computed tomography (CT) cardiac volume acquisitions by using convolutional neural networks (CNN).Materials and methodsThe method used a set of five CNN with three-dimensional (3D) U-Net architecture trained on a database of 783 CT examinations to detect and segment coronary artery calcifications in a 3D volume. The Agatston score, the conventional CAC scoring, was then computed slice by slice from the resulting segmentation mask and compared to the ground truth manually estimated by radiologists. The quality of the estimation was assessed with the concordance index (C-index) on CAC risk category on a separate testing set of 98 independent CT examinations.ResultsThe final model yielded a C-index of 0.951 on the testing set. The remaining errors of the method were mainly observed on small-size and/or low-density calcifications, or calcifications located near the mitral valve or ring.ConclusionThe deep learning-based method proposed here to compute automatically the CAC score from unenhanced-ECG-gated cardiac CT is fast, robust and yields accuracy similar to those of other artificial intelligence methods, which could improve workflow efficiency, eliminating the time spent on manually selecting coronary calcifications to compute the Agatston score.     

多排螺旋CT冠状动脉成像评价冠状动脉病变与Framingham评分的关系

目的探讨MDCT冠状动脉成像（MDCTCA）与传统Framingham危险评分（FRS）之间的关系。方法415例临床可疑或已知冠心病患者接受MDCTCA检查。冠状动脉按照狭窄程度分为狭窄≥50％、狭窄〈50％和正常。对患者进行FRS,根据FRS将患者分为低度危险组、中度危险组和高度危险组。比较3组间发生冠状动脉狭窄及斑块类型的差异。结果根据FRS,低度、中度、高度危险组患者分别占36．63％（152／415）、39．28％（163／415）、24．10％（100／415）。冠状动脉CTA正常患者在低度、中度、高度危险组中分别占72．37％（110／152）、46．63％（76／163）、36．00％（36／100）。低度、中度、高度危险组的患者中冠状动脉狭窄≥50％者分别占6．58％（10／152）、23．31％（38／163）、40．00％（40／1OO）,3支冠状动脉病变发病率分别为0．66％（1／152）、3．07％（5／163）、5．00％（5／100）,差异均有统计学意义（P〈0．05）。不同FRS之间冠状动脉斑块类型发生率差异无统计学意义。结论MDCTCA能够提供有关冠状动脉解剖学改变以外的信息。     

256层螺旋CT冠状动脉成像评价心肌桥相关冠心病危险因素

目的采用256层螺旋CT定量评价心肌桥相关冠心病(MB-CAD)危险因素。方法收集78例心肌桥(MB)患者的CT冠状动脉成像及临床资料,记录患者年龄、性别,分析MB长度、MB厚度、壁冠状动脉(MCA)近段血管动脉粥样硬化(AS)、MCA成角及MCA收缩期狭窄率;根据临床及影像学资料综合诊断MB-CAD,采用Logistic回归分析检验上述MB-CAD危险因素。结果共14例(14/78,17.95%)发生MB-CAD。MB厚度为发生MB-CAD的危险因素,其OR值为19.50,95%CI(1.86~20.47),MB厚度在MB-CAD(2.7~7.1mm,中位数3.70mm)与非MB-CAD患者(0~1.9mm,中位数0.65mm)间差异有统计学意义(χ2=35.91,P0.05)。结论 256层螺旋CT冠状动脉成像可定量检测MB特征,MB厚度是发生MB-CAD的危险因素。     

MSCTA结合心肌首过灌注成像诊断冠状动脉狭窄

目的探讨MSCT血管造影(MSCTA)结合心肌首过灌注成像诊断冠状动脉狭窄的价值。方法对80例可疑冠心病患者行64排MSCTA检查,按MSCTA成像质量分为A组(n=41,血管显示清晰)和B组(n=39,血管显示不清);以CAG结果为金标准,计算并比较MSCTA和MSCTA结合心肌首过灌注成像诊断冠状动脉狭窄的准确率。结果A组中MSCTA诊断冠状动脉狭窄准确率[85.98%(141/164)]高于MSCTA结合首过灌注成像[80.49%(132/164)],B组中MSCTA诊断冠状动脉狭窄准确率[66.03%(103/156)]低于MSCTA结合首过灌注成像[79.49%(124/156)],差异均有统计学意义(P均0.05)。结论 MSCTA诊断冠状动脉狭窄时,对于血管显示不清者,结合心肌首过灌注成像能明显提高诊断准确率。     

CT angiography of the coronary arteries

There is insufficient knowledge about secondary prevention after coronary artery bypass grafting (CABG). Most of it is gathered from patients suffering from myocardial infarction and angina pectoris, only a minority of whom have undergone CABG. Whereas it seems clear that these patients should give up smoking and reduce low‐density lipoprotein (LDL) cholesterol, there is uncertainty about the optimal antiplatelet regimen and antithrombotic treatment. There are some data indicating the benefit of behaviour modification. There is room for improvement and more knowledge when it comes to secondary prevention after CABG.     

代谢综合征患者肾动脉狭窄的SCTA与DSA对比研究

目的探讨代谢综合征(MS)患者中肾动脉狭窄的发生率及无创性筛检的必要性与可靠性。方法45例MS患者预行肾动脉螺旋CT血管造影(SCTA),对所检出的14例肾动脉狭窄者行肾动脉数字减影血管造影(DSA)对照,并对SCTA及DSA结果进行对比分析。结果45例MS患者中SCTA显示肾动脉正常31例,其余14例患者存在单侧或双侧肾动脉狭窄,DSA对照显示肾动脉正常6条,肾动脉狭窄22条,与SCTA显示的情况基本符合。结论MS患者中肾动脉狭窄的发生率约31.1%,对可疑患者应常规予以肾动脉SCTA检查。     

16层CT与导管法造影在显示冠状动脉狭窄中的对照研究

目的探讨16层CT冠状动脉成像在显示冠状动脉狭窄中的应用价值和限度。方法回顾性分析52例临床诊断或可疑冠心病患者的16层CT冠状动脉成像检查结果,并将16层CT检查结果与导管法冠状动脉造影结果进行对照。结果在52例患者的冠状动脉直径≥2 mm的580节段中,CT图像能满足管腔评价为507节段(占87.41%)。在CT图像能满足管腔评价的冠状动脉节段中,16层CT显示中度或中度以上狭窄(≥50%)的敏感度、特异度和阳性、阴性预测值分别为87.88%、98.17%和76.32%、95.96%,若将CT图像不能满足管腔评价的中度或中度以上狭窄的5个节段包括在内,其敏感度为81.69%;16层CT显示高度狭窄(≥75%)的敏感度、特异度和阳性、阴性预测值分别为83.78%、99.35%和91.18%、98.7%,若将CT图像不能满足管腔评价的高度狭窄的2个节段包括在内,其敏感度为79.49%。结论16层CT在对冠状动脉中、高度狭窄的初步诊断及介入治疗的筛选方面,可部分取代导管法冠状动脉造影。     

护理干预对CT冠状动脉血管成像的影响

目的:探讨患者应用冠脉血管CT成像检查时,进行护理干预的临床意义.方法:对我院2009年10月～2011年5月冠脉血管CT成像检查的229例患者检查前进行相关的护理干预.结果:212例患者的心率控制＜每分钟70次,冠脉血管CT成像的影像质量与患者呼吸的幅度、心率以及心率的波动幅度密切相关.相关的护理干预可以帮助患者降低心率与心率的波动幅度,同时还能平缓患者呼吸的幅度.结论:患者应用冠脉血管CT成像检查时,进行护理干预能够改善影像质量,并对冠脉CTA的成功检查有着非常重的作用.     

Application of multiple deep learning models for automatic burn wound assessment

PurposeAccurate assessment of the percentage of total body surface area (%TBSA) burned is crucial in managing burn injuries. It is difficult to estimate the size of an irregular shape by inspection. Many articles reported the discrepancy of estimating %TBSA burned by different doctors. We set up a system with multiple deep learning (DL) models for %TBSA estimation, as well as the segmentation of possibly poor-perfused deep burn regions from the entire wound.MethodsWe proposed boundary-based labeling for datasets of total burn wound and palm, whereas region-based labeling for the dataset of deep burn wound. Several powerful DL models (U-Net, PSPNet, DeeplabV3+, Mask R-CNN) with encoders ResNet101 had been trained and tested from the above datasets. With the subject distances, the %TBSA burned could be calculated by the segmentation of total burn wound area with respect to the palm size. The percentage of deep burn area could be obtained from the segmentation of deep burn area from the entire wound.ResultsA total of 4991 images of early burn wounds and 1050 images of palms were boundary-based labeled. 1565 out of 4994 images with deep burn were preprocessed with superpixel segmentation into small regions before labeling. DeeplabV3+ had slightly better performance in three tasks with precision: 0.90767, recall: 0.90065 for total burn wound segmentation; precision: 0.98987, recall: 0.99036 for palm segmentation; and precision: 0.90152, recall: 0.90219 for deep burn segmentation.ConclusionCombining the segmentation results and clinical data, %TBSA burned, the volume of fluid for resuscitation, and the percentage of deep burn area can be automatically diagnosed by DL models with a pixel-to-pixel method. Artificial intelligence provides consistent, accurate and rapid assessments of burn wounds.     

基于第二代追踪冻结技术重建冠状动脉CT造影图像所测冠状动脉跨狭窄CT血流储备分数差值与冠状动脉狭窄风险及心肌损伤指标的相关性

目的 观察基于第二代追踪冻结(SSF2)技术重建冠状动脉CT造影(CCTA)图像所测冠状动脉跨狭窄CT血流储备分数(CT-FFR)差值(ΔCT-FFR)与冠状动脉狭窄风险及心肌损伤指标的相关性。方法 回顾性分析41例疑诊冠心病并接受CCTA患者,分别以标准算法及SSF2算法重建图像;比较不同方法重建CCTA显示左前降支(LAD)、左回旋支(LCX)及右冠状动脉(RCA)的图像质量,评估LAD、LCX及RCA狭窄程度,分析基于SSF2算法重建CCTA所测最窄CT-FFR及ΔCT-FFR与冠状动脉疾病报告和数据系统(CAD-RADS)分类、肌钙蛋白I(cTnI)及肌酸激酶同工酶MB(CK-MB)的相关性。结果 SSF2重建CCTA图像显示LAD、LCX及RCA质量评分均高于标准算法(P均＜0.05)。LAD、LCX及RCA的CAD-RADS分类分别为2(1,3)、1(1,3)及1(1,3),其最窄CT-FFR分别为0.77±0.13、0.79±0.16及0.78±0.14,ΔCT-FFR分别为0.16±0.10、0.13±0.07及0.14±0.09。冠状动脉上述3分支最窄CT-FFR与CAD-RADS分类、cTnI、CK-MB均呈负相关,ΔCT-FFR与CAD-RADS分类、cTnI、CK-MB均呈正相关(P均＜0.05)。结论 基于SSF2重建CCTA图像所测冠状动脉跨狭窄ΔCT-FFR与CAD-RADS评分和心肌损伤指标均呈正相关。     

64排冠状动脉CT成像延时时间的优化

目的探讨MSCT冠状动脉成像的扫描延时时间和对比剂注射的优化方案。方法将100例冠心病患者均分为两组。A组;预测冠状动脉成像延时时间一测试扫描中对比剂在升主动脉根部显像时间＋对比剂团注时间一扫描时间;B组：冠状动脉扫描延时时间一对比剂到达升主动脉根部的达峰时间＋4s。对两组数据均选择75％时相重建冠状动脉图像,分别测量降主动脉在不同心动周期及不同层面的CT值;根据降主动脉的时间一密度曲线（TDC）变化趋势,评价冠状动脉造影数据采集时相的准确性。结果A组34例冠状动脉成像采集时相与对比剂达峰时间相匹配,10例TDC呈持续上升型,6例呈持续下降型;B组10例冠状动脉成像采集时相与对比剂达峰时间相匹配,38例TDC呈持续上升型,2例呈持续下降型,A组扫描获得最佳时相明显多于B组（P〈0．01）。结论利用A组条件进行64排冠状动脉CT成像较易获得最佳扫描时相。     

Helical CT angiography in the preoperative evaluation of carotid artery stenosis

Purpose: To determine the utility and accuracy of helical CT angiography (CTA) in the evaluation of carotid artery stenosis. Methods: A comparison of CTA and conventional arteriogram was performed in 53 patients undergoing evaluation for carotid artery stenosis. Ninety-six carotid systems were evaluable. CTA stenosis was determined by the percent of area reduction seen on axial images through the level of greatest narrowing. MIP images were used to identify the point of maximal stenosis and to visualize overall vascular anatomy. The percent diameter stenosis was measured on conventional arteriograms using strict North American Symptomatic Carotid Endarterectomy Trial (NASCET) and European Carotid Surgery Trial (ECST) criteria. Results: Significant correlation was found between CTA and arteriography (NASCET method R = 0.87, ECST method R = 0.87, p < 0.001). Using NASCET >60% as an indicator for disease, CTA had a sensitivity of 87%, specificity of 90%, accuracy of 89%, negative predictive value of 88%, and positive predictive value of 89%. CTA identified plaque characteristics such as ulcerations (8), occlusion (10), fatty plaques (22), calcifications (48), and fibrosis (2). CTA underestimated 2 cases of short segment stenoses because of volume averaging, but this discrepancy was detected by duplex scan. No complications or renal dysfunction occurred with CTA; 1 patient became symptomatic during arteriography, necessitating termination of the procedure. Conclusion: CTA is a safe, non-invasive technique that precisely measures carotid artery area reduction and highly correlates to conventional arteriography. With this new technology, the current standards for carotid artery imaging may need to be reevaluated, and the precise role for helical CTA more clearly defined. (J Vasc Surg 1998;28:290-300.)     

Intraoperative detection of unsuspected distal coronary obstruction by thermal coronary angiography

Intraoperative assessment of graft patency and completeness of revascularization can increase the success of coronary artery bypass grafting. A 56-year-old man underwent a quadruple bypass operation. Flow in the graft to the anterior descending artery was verified after completion of the distal anastomosis using a Doppler flow detector. Visualization of the native artery by thermal coronary angiography demonstrated that the flow passed into the second diagonal branch and not into the distal anterior descending artery, which had an unsuspected obstruction just distal to the anastomosis. The obstruction was dilated. Patency was verified with cold solution, and flow of warm blood to the entire artery was accomplished. This case demonstrates how the early (intraoperative) recognition of an unsuspected coronary obstruction using an infrared imaging system can improve the results of myocardial revascularization and avoid potential postoperative complications.     

External validation of a commercially available deep learning algorithm for fracture detection in children

PurposeThe purpose of this study was to conduct an external validation of a fracture assessment deep learning algorithm (Rayvolve®) using digital radiographs from a real-life cohort of children presenting routinely to the emergency room.Materials and methodsThis retrospective study was conducted on 2634 radiography sets (5865 images) from 2549 children (1459 boys, 1090 girls; mean age, 8.5 ± 4.5 [SD] years; age range: 0–17 years) referred by the pediatric emergency room for trauma. For each set was recorded whether one or more fractures were found, the number of fractures, and their location found by the senior radiologists and the algorithm. Using the senior radiologist diagnosis as the standard of reference, the diagnostic performance of deep learning algorithm (Rayvolve®) was calculated via three different approaches: a detection approach (presence/absence of a fracture as a binary variable), an enumeration approach (exact number of fractures detected) and a localization approach (focusing on whether the detected fractures were correctly localized). Subgroup analyses were performed according to the presence of a cast or not, age category (0–4 vs. 5–18 years) and anatomical region.ResultsRegarding detection approach, the deep learning algorithm yielded 95.7% sensitivity (95% CI: 94.0–96.9), 91.2% specificity (95% CI: 89.8–92.5) and 92.6% accuracy (95% CI: 91.5–93.6). Regarding enumeration and localization approaches, the deep learning algorithm yielded 94.1% sensitivity (95% CI: 92.1–95.6), 88.8% specificity (95% CI: 87.3–90.2) and 90.4% accuracy (95% CI: 89.2–91.5) for both approaches. Regarding age-related subgroup analyses, the deep learning algorithm yielded greater sensitivity and negative predictive value in the 5–18-years age group than in the 0–4-years age group for the detection approach (P < 0.001 and P = 0.002) and for the enumeration and localization approaches (P = 0.012 and P = 0.028). The high negative predictive value was robust, persisting in all of the subgroup analyses, except for patients with casts (P = 0.001 for the detection approach and P < 0.001 for the enumeration and localization approaches).ConclusionThe Rayvolve® deep learning algorithm is very reliable for detecting fractures in children, especially in those older than 4 years and without cast.     

基于深度学习T2WI及弥散加权成像双模态影像一体化模型自动识别及分割宫颈癌

目的 基于深度学习(DL)结合Transformer网络及卷积神经网络(CNN)构建T2WI及弥散加权成像(DWI)双模态宫颈癌影像自动识别及分割一体化模型,并观察其应用价值。方法 回顾性收集116例经病理确诊的宫颈癌患者,对其中58例基于盆腔轴位T2WI、80例基于盆腔轴位DWI手动勾画肿瘤ROI,之后行2D切片,标注为“肿瘤”或“非肿瘤”,共获得1 166幅T2WI和1 066幅DWI 2D切片。随机选取200幅T2WI(46幅肿瘤切片及154幅非肿瘤切片)和174幅DWI 2D切片(62幅肿瘤及112幅非肿瘤)为测试集,按4∶1比例将其余966幅T2WI和892幅DWI 2D切片分为训练集和验证集。以Swin Transformer网络构建宫颈癌四分类自动识别模型,结合迁移学习方法,对训练集和验证集的2个模态切片进行分类。基于nnU-Net框架开发2个通道深度分别为7层与8层的U-Net网络,构建不同模态影像宫颈癌自动分割模型;根据准确率(ACC)、精确度(Precision)、召回率(Recall)和平衡F分数(F1-score)评估模型自动识别测试集宫颈癌的效能,以戴斯相似性...     

Imaging of acute mesenteric ischemia using multidetector CT and CT angiography in a porcine model

Acute mesenteric ischemia, a frequently lethal disease, requires prompt diagnosis and intervention for favorable clinical outcomes. This goal remains elusive due, in part, to lack of a noninvasive and accurate imaging study. Traditional angiography is the diagnostic gold standard but is invasive and costly. Computed tomography (CT) is readily available and noninvasive but has shown variable success in diagnosing this disease. The faster scanning time of multidetector row CT (M.D.CT) greatly facilitates the use of CT angiography (CTA) in the clinical setting. We sought to determine whether M.D.CT-CTA could accurately demonstrate vascular anatomy and capture the earliest stages of mesenteric ischemia in a porcine model. Pigs underwent embolization of branches of the superior mesenteric artery, then imaging by M.D.CT-CTA with three-dimensional reconstruction protocols. After scanning, diseased bowel segments were surgically resected and pathologically examined. Multidetector row CT and CT angiography reliably defined normal and occluded mesenteric vessels in the pig. It detected early changes of ischemia including poor arterial enhancement and venous dilatation, which were seen in all ischemic animals. The radiographic findingsd—compared with pathologic diagnosesd—predicted ischemia, with a positive predictive value of 92%. These results indicate that M.D.CT-CTA holds great promise for the early detection necessary for successful treatment of acute mesenteric ischemia. Presented at the Forty-Sixth Annual Meeting of The Society for Surgery of the Alimentary Tract, Chicago, Illinois, May 14–18, 2005 (oral presentation). Supported by the Karin Grunebaum Research Fellowship, Harvard Medical School (D.E.R.), the German Research Fellowship, German Research Foundation STR 690/1-1 (O.S.), and the Phillip H. Meyers Grant from the Society of Gastrointestinal Radiologists (S.P.T.).     

冠状动脉CT成像在心房颤动患者中的应用

随着多层螺旋CT在心脏成像中的应用日益完善及其时间分辨率和空间分辨率的提高,冠状动脉CT成像(CTCA)用于AF患者已成为可能。目前已有多种成像技术可有效消除运动伪影,改善AF患者的CTCA质量。本文针对相关扫描及重建技术手段进展进行综述。