目的 采用计算机深度神经网络技术,构建一款人工智能模型辅助99TcmO4?甲状腺图像诊断.资料与方法 回顾性纳入四川大学华西医院核医学科2013年1月—2020年6月临床已完成甲状腺全切手术、拟进行131I治疗的甲状腺癌患者3515例图像集,按甲状腺残留程度分类标注后,以8:2随机分成训练集2811例和测试集704例.利用3种深度神经网络模型Resnet34、InceptionV3和Densenet161分别对训练集样本进行特征提取和训练后,对测试集样本进行效能验证,并与3名初级医师独立阅片结果进行对比,记录3名医师和模型的阅片时间,采用Kappa检验分析医师阅片的一致性,采用受试者工作特征曲线分析不同模型的诊断效能.结果 在704例甲状腺图像分类测试时,3名医师的判断准确度分别为89.5％、86.5％、86.6％;Resnet34、InceptionV3和Densenet161神经网络模型的判断准确度分别为91.3％、90.4％和91.2％.3名医师两两比较诊断一致性较好(Kappa=0.773、0.746、0.711,P均<0.05),3名医师判断所需总时间分别为170 min、172 min和131 min;Resnet34、InceptionV3和Densenet161神经网络模型诊断总时间分别为4.5 s、2.9 s和17.3 s.结论 人工智能辅助诊断技术可快速、准确地完成甲状腺显像的阅片与甲状腺残留分类工作.

目的 基于头颈肩最大每秒计数率(CPSmax)及显像剂用量构建全身骨显像扫描速度(SS)回归方程,并验证其价值.方法 回顾性分析385例接受全身骨显像且图像总计数(TC)≥1.50 M的患者资料,采用Person相关性分析及多重线性回归分析基于患者性别、年龄、体质量指数(BMI)、显像剂用量、扫描前等候时间,以及头颈肩CPSmax筛选全身骨显像SS的独立影响因素,构建预测全身骨显像SS回归方程.另将172例患者分为方程拟合组(n=111)和对照组(n=61),采用2台不同SPECT设备行全身骨显像,记录方程拟合组CPSmax,以回归方程设定SS,对照组以固定SS(25 cm/min)进行扫描,比较组间TC合格率(TC≥1.50 M)的差异.结果 头颈肩CPSmax和显像剂用量是全身骨显像SS的独立影响因素(P均＜0.05),以之构建的回归方程为SS=18.98+0.13X显像剂用量+1.06×CPSmax(F=23.22,P＜0.01).方程拟合组TC合格率100％(111/111),高于对照组的88.52％(54/61,P=0.001).结论 基于头颈肩CPSmax及显像剂用量构建的全身骨显像SS回归方程具有一定临床实用性.

Myocardial perfusion imaging has been considered the reference standard for detection of myocardial ischemia in coronary heart disease. In clinical practice, doctors typically estimate the individual ischemic scores for 17 myocardial segments and then diagnose myocardial ischemia based on the scores for all segments considered together. However, prior works are generally limited to the diagnosis of myocardial ischemia and ignore the correlation between myocardial ischemia and the myocardial segment showing the defect. In this paper, we explore intra- and inter-granularity relationships between myocardial perfusion imaging tasks of different granularities and construct a multi-task learning framework to jointly learn these tasks. To this end, we propose a cross-granularity multi-task network, namely CGMT-Net. We present a task-specific module based on the attention mechanism to make the feature map task-specific. To explore the intra- and inter-granularity relationships among tasks, we propose a cross-granularity fusion module for the integration and transmission of task-specific information. We present a large dataset containing 1098 myocardial perfusion imaging sets paired with their diagnostic reports. Extensive experiments on the dataset demonstrate the superiority of our CGMT-Net over other methods. Furthermore, we performed ablation experiments that show the rationality and effectiveness of our network architecture.

态度、价值观和信念,这些具有人文属性的文化,在人类行为和社会进步过程中,无疑发挥着重要作用.社会主义核心价值观视域下,中共中央、国务院提出了"三全育人"的教育理念,为高校学生思想政治教育工作提供了基本遵循.新形势下,作为极具人文属性的医学,其初践者——高校医学生,构建正确的价值观对其自身成长以及整个医疗行业的发展都有着重要意义.

目的 探讨智能病灶标注系统在核医学科阅片教学中的应用效果.方法 选取2019年1月—12月在本科实习的本科生80名为研究对象,分为对照组(n=40,教师带教+单人阅片训练的教学模式)和实验组(n=40,教师带教+智能病灶标注系统阅片训练的教学模式).学生实习第1天、第15天、第30天,对学生进行全身骨显像阅片能力考核.实习结束后,比较学生对教学满意度的主观评价.结果 实习第1天,两组本科生阅片考核成绩差异无统计学意义(P>0.05).实习第15天、第30天,实验组本科生阅片考核成绩均高于对照组(P<0.05).实验组本科生教学满意度高于对照组(P<0.05).结论 智能病灶标注系统在核医学科阅片教学中应用效果较好.

Objective:Radiation doses to the general public and nuclear medicine technicians from patients undergoing 99Tc m-methylenediphosphonate(MDP) bone scintigraphy were estimated. Methods:A total of 64 patients (38 males and 26 females, aged 24-82 (55.1±12.8) years) undergoing bone scintigraphy with 99Tc m-MDP were retrospectively enrolled in this study. Approximately at 15 minutes after injection of 99Tc m-MDP, whole-body dose-equivalent rate (DR) was measured with a radiation-survey meter at 0.3 meter and 1.0 meter from the patients with nuclear radiation monitoring detector. On the basis of the human social contact model defined by the National Council on Radiation Protection and Measurements and human 99Tc m-MDP metabolic rate suggested by the International Commission of Radiological Protection, the radiation doses to the general public and the nuclear medicine technicians after exposure to patients undergoing 99Tc m-MDP bone scintigraphy were calculated. Results:The whole-body DR values of 64 patients at 15 minutes after injection of 99Tc m-MDP were 70.8-154.2 (105.5 ± 20.9) and 15.9-32.7 (22.6±3.6) μSv/h, respectively, at 0.3 meter and 1.0 meter. The following radiation doses were estimated: to a family member contacting with a patient at daytime 13.3-27.4 (18.9±3.0) μSv; to a family member sleeping with a patient at night 78.2-170.3 (116.5±23.4) μSv, to a colleague 17.6-36.2 (25.0±4.0) μSv and to a adjacent passenger 219.9-478.8 (327.5±65.7) μSv. The radiation dose to a technician per 99Tc m-MDP imaging patient was estimated to be 3.9-8.5 (5.8±1.2) μSv. Conclusion:The predicted radiation doses to the general public and technicians from exposure to patients undergoing 99Tc m-MDP bone scintigraphy are significantly lower than the regulatory dose limits.

The utility of integrated single-photon emission computed tomography/computed tomography (SPECT/CT) in children and young adults with differentiated thyroid carcinoma is incompletely studied. To determine the value of adding SPECT/CT to conventional whole-body scintigraphy in post-ablation iodine-131 (131I) scintigraphy for children and young adults with differentiated thyroid carcinoma. Planar scintigraphy and SPECT/CT were performed on 42 post-surgical children and young adults (32 female, 10 male; mean age 14.3±4.9 years, range 7–20 years) with differentiated thyroid carcinoma (39 papillary, 2 follicular, 1 mixed) 5 days after the therapeutic administration of 1.9–7.4 GBq of 131I. Planar and SPECT/CT images were interpreted independently, and sites of uptake were categorized as positive or equivocal with respect to thyroid bed, lymph node and distant metastasis uptake. An experienced thyroid endocrinologist used a combination of surgical histopathology and scintigraphic findings to determine whether the addition of SPECT/CT would change patient management. Planar scintigraphy evidenced 88 radioiodine-avid foci and SPECT/CT confirmed all foci. No additional foci were disclosed by SPECT/CT. SPECT/CT correctly classified 16/88 (18%) foci that were unclear or wrongly classified at planar scintigraphy. Globally, SPECT/CT showed an incremental value over planar scintigraphy in 9 (21.4%) patients and changed therapeutic management in 3 (7.1%; 95% confidence interval, 2–20%) patients. SPECT/CT improved localization and characterization of focal 131I uptake on post-ablation whole-body scintigraphy in children and young adults with differentiated thyroid carcinoma. Further prospective evaluation in a larger series is justified to prove the effect of post-ablation SPECT/CT-based management decisions.

Abstract Background We aimed to construct an artificial intelligence (AI) guided identification of suspicious bone metastatic lesions from the whole-body bone scintigraphy (WBS) images by convolutional neural networks (CNNs). Methods We retrospectively collected the 99mTc-MDP WBS images with confirmed bone lesions from 3352 patients with malignancy. 14,972 bone lesions were delineated manually by physicians and annotated as benign and malignant. The lesion-based differentiating performance of the proposed network was evaluated by fivefold cross validation, and compared with the other three popular CNN architectures for medical imaging. The average sensitivity, specificity, accuracy and the area under receiver operating characteristic curve (AUC) were calculated. To delve the outcomes of this study, we conducted subgroup analyses, including lesion burden number and tumor type for the classifying ability of the CNN. Results In the fivefold cross validation, our proposed network reached the best average accuracy (81.23%) in identifying suspicious bone lesions compared with InceptionV3 (80.61%), VGG16 (81.13%) and DenseNet169 (76.71%). Additionally, the CNN model's lesion-based average sensitivity and specificity were 81.30% and 81.14%, respectively. Based on the lesion burden numbers of each image, the area under the receiver operating characteristic curve (AUC) was 0.847 in the few group (lesion number n ≤ 3), 0.838 in the medium group (n = 4–6), and 0.862 in the extensive group (n > 6). For the three major primary tumor types, the CNN-based lesion identifying AUC value was 0.870 for lung cancer, 0.900 for prostate cancer, and 0.899 for breast cancer. Conclusion The CNN model suggests potential in identifying suspicious benign and malignant bone lesions from whole-body bone scintigraphic images.

目的 探讨影像采集传输系统(PACS)结合以病例为基础教学法(CBL)在核医学肾动态显像临床教学中的应用效果.方法 选取2018年10月—2019年10月在四川大学华西医院核医学科实习的医学本科生100名为研究对象,按随机数字表法分为对照组和实验组,各50例,对照组采用"PACS+LBL"的教学模式,实验组采用"PACS+CBL"教学模式,实习30天.实习结束后,分别考核学生的理论成绩和阅片成绩以评定教学效果,并比较学生对教学满意度的主观评价.结果 对学生进行理论知识和阅片能力考核后,实验组学生所得成绩及教学满意度均高于对照组,差异有统计学意义(P<0.05).结论 PACS结合CBL教学模式在核医学肾动态显像临床教学中应用效果较好,可提升临床思维能力.

Background 99m Tc-pertechnetate thyroid scintigraphy is a valid complementary avenue for evaluating thyroid disease in the clinic, the image feature of thyroid scintigram is relatively simple but the interpretation still has a moderate consistency among physicians. Thus, we aimed to develop an artificial intelligence (AI) system to automatically classify the four patterns of thyroid scintigram. Methods We collected 3087 thyroid scintigrams from center 1 to construct the training dataset (n = 2468) and internal validating dataset (n = 619), and another 302 cases from center 2 as external validating datasets. Four pre-trained neural networks that included ResNet50, DenseNet169, InceptionV3, and InceptionResNetV2 were implemented to construct AI models. The models were trained separately with transfer learning. We evaluated each model’s performance with metrics as following: accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), recall, precision, and F1-score. Results The overall accuracy of four pre-trained neural networks in classifying four common uptake patterns of thyroid scintigrams all exceeded 90%, and the InceptionV3 stands out from others. It reached the highest performance with an overall accuracy of 92.73% for internal validation and 87.75% for external validation, respectively. As for each category of thyroid scintigrams, the area under the receiver operator characteristic curve (AUC) was 0.986 for ‘diffusely increased,’ 0.997 for ‘diffusely decreased,’ 0.998 for ‘focal increased,’ and 0.945 for ‘heterogeneous uptake’ in internal validation, respectively. Accordingly, the corresponding performances also obtained an ideal result of 0.939, 1.000, 0.974, and 0.915 in external validation, respectively. Conclusions Deep convolutional neural network-based AI model represented considerable performance in the classification of thyroid scintigrams, which may help physicians improve the interpretation of thyroid scintigrams more consistently and efficiently.

Background: 99mTc-pertechnetate thyroid scintigraphy is a valid avenue for distinguishing causes of thyrotoxicosis in the clinic, but the interpretation of thyroid scintigraphic images is subjected with significant variation among different inter-observers. We aim to develop an artificial intelligence (AI) system to improve the diagnosis of thyrotoxicosis.Materials and methods: We constructed an AI model based on a deep neural network with 2468 thyroid scintigraphic images collected from West China Hospital, and evaluated the diagnostic accuracy for classifying four patterns of thyrotoxicosis: ‘diffusely increased,’ ‘diffusely decreased,’ ‘focal increased,’ and ‘heterogeneous uptake.’ Then, we compared the diagnostic performance of the AI model and five physicians with 200 testing cohorts from two centers.Results: We constructed the AI model, which has the best performance in internal database validation based on four kinds of standout pre-trained networks. This AI model achieves satisfactory performance in classifying four patterns of thyrotoxicosis with an overall accuracy of 91.92% for internal and 86.75% for external data validation. In the following contrastive study, the AI model represented improved diagnostic accuracy and consistency than 5 physicians for interpreting data from West China Hospital (88% vs. 66~73%) and Panzhihua Central Hospital (83% vs. 53%~79%), respectively.Conclusion: Deep convolution neural network based AI model represented considerable performance in classifying four patterns of thyroid scintigraphic images; this may help physicians diagnose causes of thyrotoxicosis and reduced the physicians’ error rate.

Retroperitoneal liposarcoma is usually large and can press on other organs. We report a case of a 66-year-old woman with a history of retroperitoneal liposarcoma resection who presented to the emergency department with abdominal pain. Ultrasonography revealed a large abdominal mass with renal displacement. Dynamic renal scintigraphy with Tc-99m-DTPA was conducted to evaluate renal function. However, severe impairment of the right kidney function and abnormal tracer accumulation were observed during the examination. SPECT/CT was performed; 2 kidneys were successfully localized, and the recurrence of tumor was correctly detected.

Bone scintigraphy is accepted as an effective diagnostic tool for whole-body examination of bone metastasis. However, the manual analysis of bone scintigraphy images requires extensive experience and is exhausting and time-consuming. An automated diagnosis system for such images is therefore much desired. Although automatic or semi-automatic methods for the diagnosis of bone scintigraphy images have been widely studied, they employ various steps to classify the images, including segmentation of the entire skeleton, detection of hot spots, and feature extraction, which are complex and inadequately validated on small datasets, thereby resulting in low accuracy and reliability. In this paper, we describe the development of a deep convolutional neural network to determine the absence or presence of bone metastasis. This model consisting of three sub-networks that aim to extract, aggregate, and classify high-level features in a data-driven manner. There are two main innovations behind this method; First, the diagnosis is performed by jointly analyzing both anterior and posterior views, which leads to high accuracy. Second, a spatial attention feature aggregation operator is proposed to enhance the spatial location information. A large annotated bone scintigraphy image dataset containing 15,474 examinations from 13,811 patients was constructed to train and evaluate the model. The proposed method is compared with three human experts. The high classification accuracy achieved demonstrates the effectiveness of the proposed architecture for the diagnosis of bone scintigraphy images, and that it can be applied as a clinical decision support tool.

Bone scintigraphy (BS) is one of the most frequently utilized diagnostic techniques in detecting cancer bone metastasis, and it occupies an enormous workload for nuclear medicine physicians. So, we aimed to architecture an automatic image interpreting system to assist physicians for diagnosis. We developed an artificial intelligence (AI) model based on a deep neural network with 12,222 cases of 99m Tc-MDP bone scintigraphy and evaluated its diagnostic performance of bone metastasis. This AI model demonstrated considerable diagnostic performance, the areas under the curve (AUC) of receiver operating characteristic (ROC) was 0.988 for breast cancer, 0.955 for prostate cancer, 0.957 for lung cancer, and 0.971 for other cancers. Applying this AI model to a new dataset of 400 BS cases, it represented comparable performance to that of human physicians individually classifying bone metastasis. Further AI-consulted interpretation also improved human diagnostic sensitivity and accuracy. In total, this AI model performed a valuable benefit for nuclear medicine physicians in timely and accurate evaluation of cancer bone metastasis.

The aim was to estimate the effective doses associated with different types of scanning protocols and how much the diagnostic computed tomography (DCT) scan contributed to the total dose of the dual-modality positron emission tomography/computed tomography (PET/CT) examinations. The results showed that an average radiation dose of 8.19 ± 0.83 mSv and 13.44 ± 5.14 mSv for the PET and CT components, respectively, resulting in a total dose of 21.64 ± 5.20 mSv. Approximately 92.7% (980 of 1057) of the patients underwent additional DCT protocols. The DCT protocols contributed 42% of the overall effective radiation doses, which was larger than the percentage contributed by the PET component (38%) and LCT protocols (20%). Reducing the diagnostic area of the DCT scans that patients undergo and decreasing the use of chest-abdomen-pelvis (CAP), abdomen-pelvis (AP) and chest DCT protocols, especially the CAP protocol, will be helpful in decreasing the effective radiation doses of PET/CT scan.

A 66-year-old man with follicular thyroid cancer after total thyroidectomy was referred for I therapy. Thyroid function tests before I administration exhibited severe thyrotoxicosis although the patient did not take levothyroxine after thyroidectomy. A 185 MBq I whole-body scintigraphy and SPECT/CT revealed multiple iodine-avid pulmonary metastases with the largest tumor diameter of 1.4 cm and remnant thyroid. A diagnosis of thyrotoxicosis caused by hyperfunctioning pulmonary metastases was then made. The patient was administered 7.4 GBq of I. Six months after I therapy, a significant reduction of the pulmonary metastatic disease and thyroglobulin level was observed. However, the remnant thyroid was still visualized.