Image registration is of great clinical importance in computer aided diagnosis and surgical planning of liver diseases. Deep learning-based registration methods endow liver computed tomography (CT) image registration with characteristics of real-time and high accuracy. However, existing methods in registering images with large displacement and deformation are faced with the challenge of the texture information variation of the registered image, resulting in subsequent erroneous image processing and clinical diagnosis. To this end, a novel unsupervised registration method based on the texture filtering is proposed in this paper to realize liver CT image registration. Firstly, the texture filtering algorithm based on L0 gradient minimization eliminates the texture information of liver surface in CT images, so that the registration process can only refer to the spatial structure information of two images for registration, thus solving the problem of texture variation. Then, we adopt the cascaded network to register images with large displacement and large deformation, and progressively align the fixed image with the moving one in the spatial structure. In addition, a new registration metric, the histogram correlation coefficient, is proposed to measure the degree of texture variation after registration. Experimental results show that our proposed method achieves high registration accuracy, effectively solves the problem of texture variation in the cascaded network, and improves the registration performance in terms of spatial structure correspondence and anti-folding capability. Therefore, our method helps to improve the performance of medical image registration, and make the registration safely and reliably applied in the computer-aided diagnosis and surgical planning of liver diseases.
ObjectiveTo evaluate the clinical feasibility and safety of CT-guided percutaneous microwave ablation for peripheral solitary pulmonary nodules.MethodsThe imaging and clinical data of 33 patients with pulmonary nodule less than 3 cm in diameter treated by CT-guided microwave ablation treatment (PMAT) in our hospital from July 2018 to December 2019 were retrospectively analyzed. There were 21 males and 12 females aged 38-90 (67.6±13.4) years. Among them, 26 patients were confirmed with lung cancer by biopsy and 7 patients were clinically considered as partial malignant lesions. The average diameter of 33 nodules was 0.6-3.0 (1.8±0.6) cm. The 3- and 6-month follow-up CT was performed to evaluate the therapy method by comparing the diameter and enhancement degree of lesions with 1-month CT manifestation. Short-term treatment analysis including complete response (CR), partial response (PR), stable disease (SD) and progressive disease (PD) was calculated according to the WHO modified response evaluation criteria in solid tumor (mRECIST) for short-term efficacy evaluation. Eventually the result of response rate (RR) was calculated. Progression-free survival was obtained by Kaplan–Meier analysis.ResultsCT-guided percutaneous microwave ablation was successfully conducted in all patients. Three patients suffered slight pneumothorax. There were 18 (54.5%) patients who achieved CR, 9 (27.3%) patients PR, 4 (12.1%) patients SD and 2 (6.1%) patients PD. The short-term follow-up effective rate was 81.8%. Logistic analysis demonstrated that primary and metastatic pulmonary nodules had no difference in progression-free time (log-rank P=0.624).ConclusionPMAT is of high success rate for the treatment of solitary pulmonary nodules without severe complications, which can be used as an effective alternative treatment for nonsurgical candidates.
Abstract： Objective To explore the diagnosis and treatment of descending necrotizing mediastinitis (DNM). Methods We retrospectively analyzed the records of eight DNM patients treated at Tangdu Hospital between 2006 and 2009 year. There were 7 males and 1 female aged from 21-98 years with a median age of 49.5 years. The diagnostic criteria included clinical manifestations, neck and chest CT scans, and bacteriological culture. Six of the patients had odontogenic infections and six had diabetes. Antibiotic treatment, incision drainage, and other symptomatic treatments were applied. Two patients received cervical incision drainage, five received thoracotomy, and one received video-assisted thoracoscopic surgery (VATS). Results After treatment, six patients recovered and two died of heart failure and neck vessel rupture. According to the bacterial culture, six patients presented mixed infections, and four of these presented mixed aerobic and anaerobic infections. The mean operation time was 75.6 minutes, the average volume of pus removed during the operation was 318.7 ml, and the average inpatient stay was 18 days. At six months follow-up, all six surviving patients showed improvements in quality of life. Conclusion The valid diagnosed criteria of DNM include history, sign, symptom, neck and chest CT scanning, and secretion culture.DNM mortality can be reduced by employing broad spectrum antibiotics early in treatment, individual surgical managements, and effective treatments for complicating illnesses.
Corona virus disease 2019 (COVID-19) is an acute respiratory infectious disease with strong contagiousness, strong variability, and long incubation period. The probability of misdiagnosis and missed diagnosis can be significantly decreased with the use of automatic segmentation of COVID-19 lesions based on computed tomography images, which helps doctors in rapid diagnosis and precise treatment. This paper introduced the level set generalized Dice loss function (LGDL) in conjunction with the level set segmentation method based on COVID-19 lesion segmentation network and proposed a dual-path COVID-19 lesion segmentation network (Dual-SAUNet++) to address the pain points such as the complex symptoms of COVID-19 and the blurred boundaries that are challenging to segment. LGDL is an adaptive weight joint loss obtained by combining the generalized Dice loss of the mask path and the mean square error of the level set path. On the test set, the model achieved Dice similarity coefficient of (87.81 ± 10.86)%, intersection over union of (79.20 ± 14.58)%, sensitivity of (94.18 ± 13.56)%, specificity of (99.83 ± 0.43)% and Hausdorff distance of 18.29 ± 31.48 mm. Studies indicated that Dual-SAUNet++ has a great anti-noise capability and it can segment multi-scale lesions while simultaneously focusing on their area and border information. The method proposed in this paper assists doctors in judging the severity of COVID-19 infection by accurately segmenting the lesion, and provides a reliable basis for subsequent clinical treatment.
Lung diseases such as lung cancer and COVID-19 seriously endanger human health and life safety, so early screening and diagnosis are particularly important. computed tomography (CT) technology is one of the important ways to screen lung diseases, among which lung parenchyma segmentation based on CT images is the key step in screening lung diseases, and high-quality lung parenchyma segmentation can effectively improve the level of early diagnosis and treatment of lung diseases. Automatic, fast and accurate segmentation of lung parenchyma based on CT images can effectively compensate for the shortcomings of low efficiency and strong subjectivity of manual segmentation, and has become one of the research hotspots in this field. In this paper, the research progress in lung parenchyma segmentation is reviewed based on the related literatures published at domestic and abroad in recent years. The traditional machine learning methods and deep learning methods are compared and analyzed, and the research progress of improving the network structure of deep learning model is emphatically introduced. Some unsolved problems in lung parenchyma segmentation were discussed, and the development prospect was prospected, providing reference for researchers in related fields.
肺栓塞( PE) 的确诊依赖于肺动脉的影像学检查。电子计算机断层扫描肺动脉造影( CTPA) 诊断PE 的敏感性和特异性高[ 1] , 而且该项检查是无创技术, 患者痛苦小, 并发症少, 已成为诊断PE 的一线技术[ 2,3] 。随着CT 仪器的不断升级和改进以及检查技术的不断研究, CT 在PE 中的应用不再仅限于PE 的定性诊断, 还用于肺动脉栓塞程度的量化、右心室改变的诊断、患者预后判断以及下肢深静脉血栓形成( DVT) 的诊断等。
ObjectiveTo investigate the CT presenting rate and features of gastric bare area (GBA, including the area posterior to GBA and the adipose tissue in the gastrophrenic ligament) without pathologic changes.MethodsThirty cases with superior peritoneal ascites, but without pathological involvement of GBA were included into the study to show the normal condition of GBA, including the presenting rate and CT features. We selected some cases with GBA invasion by inflammation or neoplasm to observe their CT features. ResultsAll cases with superior peritoneal ascites showed the GBA against the contrast of ascites with the presenting rate of 100%. The GBA appeared at the level of gastricesophageal conjunction and completely disappeared at the level of hepatoduodenal ligament and Winslow’s foramen. The maximum scope of GBA presented at the level of the sagital part of the left portal vein with mean right to left distance of （4.39±0.08）cm (3.8~5.7 cm) (distance between the left and right layer of the gastrophrenic ligament). In acute pancreatitis, the width of GBA increased, in which local hypodensity area could be seen. In gastric leiomyosarcoma invading GBA, the mass could not separate from the crus of the diaphragm. In lymphoma and metastasis invading GBA, the thickness of GBA increased and the density was heterogeneous, in which lymph nodes presenting as small nodes or fused mass. ConclusionThe results of this study show that it is helpful to use contrast enhanced spiral CT scanning to observe the change of GBA and to diagnose retroperitoneal abnormalities that involving GBA comprehensively and accurately.
Liver cancer is a common type of malignant tumor in digestive system. At present, computed tomography (CT) plays an important role in the diagnosis and treatment of liver cancer. Segmentation of tumor lesions based on CT is thus critical in clinical diagnosis and treatment. Due to the limitations of manual segmentation, such as inefficiency and subjectivity, the automatic and accurate segmentation based on advanced computational techniques is becoming more and more popular. In this review, we summarize the research progress of automatic segmentation of liver cancer lesions based on CT scans. By comparing and analyzing the results of experiments, this review evaluate various methods objectively, so that researchers in related fields can better understand the current research progress of liver cancer segmentation based on CT scans.
The convolutional neural network (CNN) could be used on computer-aided diagnosis of lung tumor with positron emission tomography (PET)/computed tomography (CT), which can provide accurate quantitative analysis to compensate for visual inertia and defects in gray-scale sensitivity, and help doctors diagnose accurately. Firstly, parameter migration method is used to build three CNNs (CT-CNN, PET-CNN, and PET/CT-CNN) for lung tumor recognition in CT, PET, and PET/CT image, respectively. Then, we aimed at CT-CNN to obtain the appropriate model parameters for CNN training through analysis the influence of model parameters such as epochs, batchsize and image scale on recognition rate and training time. Finally, three single CNNs are used to construct ensemble CNN, and then lung tumor PET/CT recognition was completed through relative majority vote method and the performance between ensemble CNN and single CNN was compared. The experiment results show that the ensemble CNN is better than single CNN on computer-aided diagnosis of lung tumor.