目的 探讨结核病在18氟-脱氧葡萄糖（18F-FDG）正电子发射断层扫描术（PET）中的影像学表现，提高对PET/CT在肺部包块诊断作用的认识，减少误诊。 方法 回顾分析2010年3月收治的1例肺结核合并纵隔淋巴结结核病患者的误诊及诊断治疗经过，分析误诊原因并总结诊治经验，结合文献复习肺部包块在PET/CT中的表现及临床特点。 结果 患者为肺部包块伴纵隔淋巴结包块，胸部CT提示肺癌伴纵隔淋巴结转移，PET/CT也考虑左肺下叶肺癌伴淋巴结转移。最后经纵隔镜淋巴结活检确诊结核，并抗结核治疗好转。 结论 结核等感染性疾病常可导致18F-FDG的摄取增加而造成PET/CT阳性结果，因此在18F-FDG PET/CT呈现阳性结果时须注意鉴别病变良恶性，其中高标准摄入值包块尤其需要注意与结核病相鉴别。
ObjectiveTo investigate the diagnostic value of 18F-FDG PET/CT scan for fever of unknown origin. MethodsThe 18F-FDG PET/CT scan results and clinical data were analyzed retrospectively in 32 patients with fever of unknown origin examined between January 2011 and October 2013. Final diagnoses were determined with recognized diagnostic standard. Results18F-FDG PET/CT scan was able to detect the cause of fever precisely in 53.1% (n=17) of the patients and was helpful in 25 patients (78.1%). The final cause of fever was determined in 20 patients, including infection (40%), malignancy (10%), non-infectious inflammatory disease (40%) and miscellaneous causes (10%). True positive, false positive, true negative and false negative rate of the modality were 17.0%, 4.0%, 8.0% and 3.0%; and the sensitivity and specificity were 85.0% and 66.7%. Conclusion18F-FDG PET/CT scan plays an important role in the diagnosis of fever of unknown origin.
There are various examination methods for cardiovascular diseases. Non-invasive diagnosis and prognostic information acquisition are the current research hotspots of related imaging examinations. Positron emission tomography (PET)/magnetic resonance imaging (MRI) is a new advanced fusion imaging technology that combines the molecular imaging of PET with the soft tissue contrast function of MRI to achieve their complementary advantages. This article briefly introduces several major aspects of cardiac PET/MRI in the diagnosis of cardiovascular disease, including atherosclerosis, ischemic cardiomyopathy, nodular heart disease, and myocardial amyloidosis, in order to promote cardiac PET/MRI to be more widely used in precision medicine in this field.
Epilepsy is a clinical syndrome characterized by recurrent epileptic seizures caused by various etiologies. Etiological diagnosis and localization of the epileptogenic focus are of great importance in the treatment of epilepsy. Positron emission tomography-computed tomography (PET-CT) technology plays a significant role in the etiological diagnosis and localization of the epileptogenic focus in epilepsy. It also guides the treatment of epilepsy, predicts the prognosis, and helps physicians intervene earlier and improve the quality of life of patients. With the continuous development of PET-CT technology, more hope and better treatment options will be provided for epilepsy patients. This article will review the guiding role of PET-CT technology in the diagnosis and treatment of epilepsy, providing insights into its application in etiological diagnosis, preoperative assessment of the condition, selection of treatment plans, and prognosis of epilepsy.
The PET/CT imaging technology combining positron emission tomography (PET) and computed tomography (CT) is the most advanced imaging examination method currently, and is mainly used for tumor screening, differential diagnosis of benign and malignant tumors, staging and grading. This paper proposes a method for breast cancer lesion segmentation based on PET/CT bimodal images, and designs a dual-path U-Net framework, which mainly includes three modules: encoder module, feature fusion module and decoder module. Among them, the encoder module uses traditional convolution for feature extraction of single mode image; The feature fusion module adopts collaborative learning feature fusion technology and uses Transformer to extract the global features of the fusion image; The decoder module mainly uses multi-layer perceptron to achieve lesion segmentation. This experiment uses actual clinical PET/CT data to evaluate the effectiveness of the algorithm. The experimental results show that the accuracy, recall and accuracy of breast cancer lesion segmentation are 95.67%, 97.58% and 96.16%, respectively, which are better than the baseline algorithm. Therefore, it proves the rationality of the single and bimodal feature extraction method combining convolution and Transformer in the experimental design of this article, and provides reference for feature extraction methods for tasks such as multimodal medical image segmentation or classification.