U-Net神经网络分割锥形束CT影像中下颌磨牙牙体与牙髓腔及其准确性验证

目的: 使用U-net卷积神经网络实现锥形束CT（cone-beam CT, CBCT）影像中下颌磨牙的牙体和牙髓腔的自动分割,采用基于显微CT（Micro-CT）扫描结果构建的三维模型作为金标准,评估分割准确性。方法: 从同济大学附属口腔医院放射科收集20组包含完整单侧下颌磨牙的口腔小视野CBCT数据,预处理后,由牙体牙髓病学专家使用MITK Workbench软件手动标注牙体与牙髓腔,作为U-net神经网络分割算法的训练集。另收集5颗下颌磨牙和相应的小视野CBCT数据,5组数据经相同预处理后作为测试集。随后由完成训练的神经网络和同一专家对测试集数据进行牙体和牙髓腔分割和三维重建。离体牙预处理后行Micro-CT扫描,将三维重建后获得的模型作为金标准。分别比较测试集数据中,专家的手动标注、神经网络分割结果与金标准两两之间的差异。采用Dice相似性系数（Dice similarity coefficient, DSC）、平均对称表面距离（average symmetric surface distance, ASSD）、Hausdorff距离（Hausdorff distance, HD）和形态差异分析对结果进行评估。采用SPSS 20.0软件包对数据进行统计学分析。结果: 神经网络分割结果与金标准相比,其牙体组的DSC为(95.30±1.01)%、ASSD为(0.11±0.02) mm、HD为(1.05±0.31) mm,牙髓腔组的DSC为(81.21±2.27)%、ASSD为(0.15±0.05) mm、HD为(3.29±1.85) mm,结合形态差异分析结果显示,神经网络的分割结果与金标准的牙体与髓室部分基本相似,但在根管部分,能分割出较粗的根管,对于根管下段和侧支根管等较细的根管分割能力有限。结论: 在现有实验条件下,以专家手动标注作为训练样本的U-net神经网络,实现了在CBCT影像上对下颌磨牙牙体与髓室的自动化精准分割。但对根管部分,其分割结果有待进一步提升。     

Diagnosing pulmonary thromboembolism: Concerns and controversies

Pulmonary thromboembolism (PTE) is an important cause of mortality/morbidity even today despite advancement in clinical understanding as well as diagnostic facilities. Clinical diagnosis of PTE is often challenging because of nonspecific sign/symptoms. Adherence to clinical decision-making protocols and appropriate use of diagnostic modalities like computed tomography pulmonary angiography can resolve the diagnostic dilemma in most cases and help in the overall management of PTE. This article deals with various concerns as well as controversies surrounding accurate diagnosis of PTE as on date.     

造影剂碘普罗胺在妇科盆腔CT检查中的效果及其安全性

目的 探究与分析造影剂碘普罗胺在妇科盆腔CT检查中的效果及其安全性。方法 运用回顾性研究方法，选取我院2018年2月—2021年1月收治的78例接受妇科盆腔CT增强检查者作为研究对象，观测全部患者的影像质量、全身及局部耐受性和相关不良反应。结果 在78例检查中，影像质量优良率为97.44%，患者耐受度为97.44%。患者出现恶心呕吐、头晕头痛、局部痛感、面部潮红的轻度不良反应占8.98%；有2例患者分别出现剧烈呕吐和胸闷气促，并伴有全身性皮疹的中度不良反应，给予相应处置后，患者均恢复正常。结论 非离子型造影剂碘普罗胺在妇科盆腔CT增强检查中能获得良好的影像质量，碘普罗胺的不良反应发生率低于离子型碘造影剂，但高于其他非离子型造影剂。     

Segmentation of CT Lung Images Using FCM with Active Contour and CNN Classifier

Objective: Lung cancer is one of the unsafe diseases for human which reduces the patient life time. Generally, most of the lung cancers are identified after it has been spread into the lung parts and moreover it is difficult to find the lung cancer at the early stage. It requires radiologist and special doctors to find the tumoral tissue of the lung cancer. For this reason, the recommended work helps to segment the tumoral tissue of CT lung image in an effective way. Methods:  The research work uses hybrid segmentation technique to separate the lung cancer cells to diagnose the lung tumour. It is a technique which combines active contour along with Fuzzy c means to diagnose the tumoral tissue. Further the segmented portion was trained by Convolutional Neural Network (CNN) in order to classify the segmented region as normal or abnormal. Results: The evaluation of the proposed method was done by analyzing the results of test image with the ground truth image. Finally, the results of the implemented technique provided good accuracy, Peak signal to noise ratio (PSNR), Mean Square Error (MSE) value. In future the other techniques can be utilized to improve the details before segmentation. The proposed work provides 96.67 % accuracy. Conclusion: Hybrid segmentation technique involves several steps like preprocessing, binarization, thresholding, segmentation and feature extraction using GLCM.     

Feasibility of a method for low contrast CT image quality assessment using difference detail curves for abdominal scans

This work describes a measurement method for assessing dose-related image-quality of CT scans based on the difference detail curve (DDC) method, and showcases its use in a low contrast setting. The method is based on a phantom consisting of elliptical slices of different sizes into which contrast object modules can be inserted. These modules contain contrast objects based on (synthetic) resin mixtures with sucrose (native) or sodium iodine (contrast medium). Mixing ratios are provided to achieve a range of clinically relevant CT-numbers with these materials. The phantom is characterized in terms of contrast accuracy, energy dependency and long-term drift with satisfying results. Contrast accuracy and energy dependency are similar to that of water or soft tissue. Image quality of 655 scans of the phantom acquired at 30 different clinical institutions and with 16 different CT scanner models from 4 manufacturers was assessed by calculating a difference detail curve (DDC) from evaluation of up to 5 human observers using a custom-made software (RadiVates) described in this work. Based on these measurements, inter-observer variability was quantified using a bootstrap method and was shown to be a large contributor to the overall variability. This work demonstrates that assessment of CT image quality is feasible with the aforementioned phantom and DDC method.     

NEMA NU 2-2018标准在PET/CT系统性能测试中的作用评价

目的 评价美国国家电器制造协会(National Electrical Manufactures Association, NEMA)最新标准(NU 2-2018)在正电子发射型计算机断层显像/电子计算机断层显像(positron emission tomography/computed tomography, PET/CT)设备性能检测中的作用。 方法 依据最新的NEMA NU 2-2018标准,检测西门子Biograph Vision PET/CT的空间分辨率、灵敏度、散射分数、计数丢失、随机符合、飞行时间分辨率、计数丢失率和随机符合校正精度、图像质量、衰减和散射校正精度及PET与CT配准精度指标。 结果 距视野中心1 cm处横向和轴向空间分辨率分别为3.75 mm和3.76 mm;在视野中心和轴向10 cm处的灵敏度分别为16.83 kcps/MBq和16.67 kcps/MBq;放射性浓度为27.37 kBq/mL时,最大等效噪声计数率为258.26 kcps,散射分数为38.58%;系统时间分辨率为209.82 ps;图像质量模型的对比度恢复系数范围为88.9%~96.2%,背景变异系数范围为2.05%~6.80%,平均肺插件残余误差为2.43%;计数丢失和随机符合校正最大误差为3.9%;距离床板末端 5 cm 和 100 cm处,在距视野中心Y轴1 cm处,PET和CT的配准精度分别为0.46 mm和1.07 mm,在距视野中心X轴20 cm处,PET和CT的配准精度分别为1.06 mm和1.45 mm,在距视野中心Y轴20 cm处PET和CT的配准精度分别为0.85 mm和1.15 mm。 结论 NEMA NU 2-2018标准检测条件更加接近临床,能更好地反映PET/CT设备的系统性能。     

脾脏血管性病变与淋巴瘤CT鉴别诊断

目的 运用CT区分脾脏血管性病变与淋巴瘤。方法 回顾性分析20例经手术、穿刺病理学检查证实的脾脏病变的发病年龄、性别、脾脏指数、病变大小、数目、有无液化、钙化、强化幅度、强化方式等特征,并进行统计学分析。结果 20例脾脏病变中,11例血管性病变(6例海绵状血管瘤,3例窦岸细胞血管瘤,2例硬化性血管瘤样结节性转化),9例淋巴瘤;两组间发病年龄、病变大小、数目、有无液化、钙化等差异无统计学意义;两组间脾脏指数、动脉期强化幅度差异具有统计学意义(P＜0.05)。5例海绵状血管瘤呈不均匀性强化,1例呈渐进性填充式强化,2例窦岸细胞血管瘤呈“雀斑征”,1例硬化性血管瘤样结节性转化呈“辐轮征”;9例淋巴瘤实质部分均呈均匀、轻中度强化。结论 脾脏血管性病变与淋巴瘤CT表现不同,CT有助于明确诊断。     

多排螺旋CT诊断腹内疝的临床价值

目的研究分析腹内疝患者采用多排螺旋CT进行诊断的临床价值。方法将本院接收的32例腹内疝患者作为此次研究之中的观察主体,均通过手术证实,临床资料完整,均进行多排螺旋CT检查,对其诊断结果进行分析,对比CT与手术证实的符合率。结果多排螺旋CT确诊率高达90.63%,与手术证实结果无差异(P> 0.05);同时,通过多排螺旋CT检查,可清晰的观察到腹内疝相关征象,与手术证实结果高度一致,无显著差异(P> 0.05)。结论多排螺旋CT诊断技术能够较好的诊断腹内疝,且CT征象清晰,为临床有效诊治腹内疝提供了可靠指导,值得在临床中普及。     

肾透明细胞癌不同CT影像学征象对患者术后康复情况的影响

目的探究肾透明细胞癌不同CT影像学征象对患者术后康复情况的影响。方法选取2010年1月到2014年4月我院收治的50例肾透明细胞癌患者的CT征象,进行T分期,并分析不同CT征象与患者预后关系。结果利用CT征象进行T分期区别主要在T3a期,T3a期分为T3a-CT(10例)和T3a-仅病理(6例),T3a-仅病理CT分期可分为T1期2例,T2期4例;单因素分析显示,肿瘤大小、肿瘤是否侵及肾被膜外、是否侵及肾窦集合系统、是否侵及肾静脉及分支、是否侵及下腔静脉、有无广泛性坏死、是否存在囊性改变、瘤周是否受侵、瘤周是否存在新生血管与5年生存率具有一定相关性(P<0.05);多因素回归分析显示,肿瘤≥7cm、肿瘤穿透肾被膜、肾静脉及分支受侵、下腔静脉受侵、肿瘤无囊变、瘤周受侵及瘤周新生血管是影响肾透明细胞癌预后的独立危险因素(P<0.05)。结论肾透明细胞瘤患者肿瘤大于7cm、肿瘤穿透肾被膜、肾静脉及分支受侵、下腔静脉受侵、肿瘤无囊变、瘤周受侵及瘤周新生血管是影响肾透明细胞癌预后的独立危险因素,肿瘤周围受侵及瘤周新生血管形成可降低患者5年生存率,而肿瘤囊变可作为预测术后康复情况较好的标志之一。