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.
ObjectiveTo investigate the radiological and clinicopathological factors affecting the postoperative recurrence of early lung adenocarcinoma with micropapillary/solid structure.MethodsA total of 198 patients undergoing surgical resection for early stage lung adenocarcinoma in the First Affiliated Hospital of Nanjing Medical University from January 2016 to August 2019 were enrolled, including 100 males and 98 females, aged 28-82 (53.5±9.5) years. All patients were allocated to a recurrence group (n=21) and a non-recurrence group (n=177) according to postoperative recurrence status. Correlations of imaging and clinical features and clinical outcomes were analyzed to determine prognostic significance.ResultsThe mean follow-up time was 27.0±11.2 months. There was no statistical difference in the imaging features of tumor maximum diameter in mediastinal window (P=0.014), C/T ratio (P=0.001), bronchial positive sign (P=0.015), pathological features of vascular invasion (P=0.024) and postoperative chemotherapy (P<0.001) between the two groups. In multivariate analysis, vascular invasion was the only independent prognostic factor (OR=0.146, P=0.047).ConclusionVascular invasion is an independent risk factor for postoperative recurrence of early-stage lung adenocarcinoma with micropapillary/solid structure.
Objective To summarize the imaging manifestation and identification of ectopic pancreas (EP), so as to improve clinicians and radiologists’ knowledge of EP and aid in accurate preoperative diagnosis, thereby reducing the misdiagnosis rate and avoiding unnecessary surgery. Methods Combined with clinical experience and relevant literatures in recent years, the histopathology, common imaging manifestations and main differential diagnosis of ectopic pancreas were summarized. Results EP is a rare congenital developmental anomaly of pancreas, the most common location is the upper digestive system. At present, the commonly used imaging technology is computed tomography. The imaging findings of ectopic pancreas were similar to those of normal pancreas, and its density and enhancement characteristics were related to its histopathological composition. The specific signs of ectopic pancreas include “central umbilical sign” “ductal structure” and “flat/adherent sign”. Heterotopic pancreas should be differentiated from submucosal tumor of gastrointestinal tract. Conclusions The imaging findings of EP have certain characteristics. For some cases with atypical imaging findings, imaging diagnosis is difficult.
More and more relevant research results show that anatomical segmentectomy has the same effect as traditional lobectomy in the surgical treatment of early-stage non-small cell lung cancer (diameter<2.0 cm). Segmentectomy is more difficult than lobotomy. Nowadays, with the promotion of personalization medicine and precision medicine, three-dimensional technique has been widely applied in the medical field. It has advantages such as preoperative simulation, intraoperative positioning, intraoperative navigation, clinical teaching and so on. It plays a key role in the discovery of local anatomical variation of pulmonary segment. This paper reviewed the clinical application of three-dimensional technique and briefly described the clinical application value of this technique in segmentectomy.
Objective To explore the early diagnostic value of single photon emission computed tomography(SPECT), thoracic computed tomography(CT),and chest X-ray for closed chest trauma. Methods To establish the animal model of unilateral chest impact trauma,to adopt SPECT, thoracic CT, and chest X-ray for early diagnosis of closed chest trauma,and to compare these findings with postmortem examination. Results Thirty minutes after blunt chest trauma, the region of interesting (ROI) between traumatized lung and the heart (ROI2/ROI1) immediately increased to the peak six hours after trauma; on the contralateral lung, the ratio (ROI3/ROI1) increased slowly and reached the peak after six hours, these ratio was still smaller than that of the traumatized lung. These differences were significant (Plt;0.01). Conclusions Chest X-ray is still the most fundamental diagnostic method of chest trauma,but it was thought that the patients of severe chest trauma and multiple injuries should be examined early by thoracic CT. Radionuclide imaging have more diagnostic value than chest X-ray on pulmonary contusion. The diagnostic sensibility to pulmonary contusion of thoracic CT is superior to conventional radiograph,but thoracic CT is inferior to SPECT on exploring exudation and edema of pulmonary contusion. Thoracic CT is superior to conventional radiograph on diagnosis of chest trauma,therefore patients of severe chest trauma and multiple injuries should be adopted to thoracic CT examination at emergency room in order to be diagnosed as soon as possible.
Objective To summarize the CT, MRI, and positron emission computed tomography (PET) imaging findings of hematologic malignancies of the pancreas, so as to improve the capacity of its diagnosis. Methods After searching articles concerning radiological research about hematologic malignancies of the pancreas, summarizing its imaging characteristics. Results Hematologic malignancies of the pancreas include pancreatic lymphoma, pancreatic multiple myeloma, myeloid sarcoma, posttransplantation lymphoproliferative disorder, and giant lymph node hyperplasia. ① Pancreatic lymphoma: imaging features of pancreatic lymphoma are segmental or diffuse homogeneous enlargement of the pancreas, diameter of mass >5 cm, adenopathy below the level of renal veins, and lack of pancreatic duct dilation. Blurred margins of pancreas by lymphadenopathy is highly suggestive of lymphoma. ② Pancreatic multiple myeloma: pancreatic multiple myeloma are hyperintense on both T1- and T2-weighted images. ③ Pancreatic granulocytic sarcoma: pancreatic granulocytic sarcoma present as homogeneous hypoenhancing mass on CT, usually without pancreatic duct dilation. On MRI, the lesions are isointense and mildly hyperintense on T1- and T2-weighted images respectively. ④ Posttransplantation lymphoproliferative disorder: diameter of leison of posttransplantation lymphoproliferative disorder usually is >5 cm with poor enhancement. Lesions are mildly hyperintense on T2-weighted images and extremely hypermetabolic on PET images. ⑤ Giant lymph node hyperplasia: it mainly appear as solitary noninvasive masses. Punctate calcification and surrounding supply vessels are observed in hyaline vascular type. Plasma cell type demonstrate unapparent enhancement and less calcification. Conclusions Hematologic malignancies of the pancreas manifest different imaging features on CT, MRI, and PET. Familiarity with such characteristics helps to early recognize diseases and determine next-step measures.
ObjectiveTo study the clinical and pathological characteristics and imaging manifestations of pulmonary mucosa associated lymphoid tissue (MALT) lymphoma.MethodsThe clinical and multidetector computed tomography (MDCT) imaging data of 17 patients with pathological proven pulmonary MALT lymphoma were reviewed retrospectively.ResultsThe MDCT manifestations were divided into 4 types: ① pneumonia/consolidation, ② mass/nodule type, ③ bronchovascular lymphatic type, ④ mixed type. The imaging features included air bronchiectasis in 13 cases and bronchiectasis in 9 cases. Multiple small pulmonary nodules were found in 11 cases, ground glass opacity in 9 cases, 4 cases of pleural effusion, pulmonary hilar and mediastinal lymph node enlargement in 3 cases. Among these 17 cases, 4 had extra-pulmonary involvement and 2 without obvious symptoms. The main clinical symptoms including cough, expectoration, dyspnea, fever, chest pain, hemoptysis, night sweats. The pathological manifestation is the infiltration of a large number of B lymphocytes and nuclear heterocells.ConclusionsThe clinical manifestations of pulmonary MALT lymphoma are not specific, but the progress is slow, and may be associated with autoimmune diseases. The main MDCT findings of pulmonary MALT lymphoma include consolidation, nodules or masses with air bronchogram. Lymph node enlargement is rare. Clinical diagnosis should also be based on pathological results.
Objective To study the clinical and CT findings of bronchiolar adenoma. Methods Patients diagnosed with bronchiolar adenoma confirmed by surgical pathology at Linyi People's Hospital and Yantai Yuhuangding Hospital from 2016 to 2021 were collected. Their clinical and CT imaging features were retrospectively analyzed. ResultsFinally, 25 patients were collected, including 6 males and 19 females, aged 32-73 (58.6±10.1) years. The immunohistochemical Ki-67 (MIB1) of all lesions was <5%. The lesions were located in the upper and middle lobe of both lungs in 9 patients, lower lobes in 16 patients, extrapulmonary zone in 22 patients, intrapulmonary middle zone in 3 patients, round in 11 patients, irregular in 14 patients, well-defined in 22 patients, pure ground-glass/mixed ground-glass nodules in 6 patients, solid nodules in 19 patients. There were 11 patients with central small cavity, 18 patients with single bronchioles sign, 19 patients without adhesion with adjacent pleura, and 24 patients without mediastinal lymph node enlargement. ConclusionBronchiolar adenomas usually occur in the middle-aged and elderly, mostly in the lower lobe of both lungs and the distribution of the peripheral lung field, most of the patients do not have any clinical symptoms, and the postoperative prognosis is good. CT may show large nodules or masses, pure ground-glass/mixed ground-glass nodules, irregular solid nodules and central small cavities. Irregular stellate nodules, central small cavity shadow, and single bronchiolar vascular bundle connected with the lesions are relatively specific imaging findings of bronchiolar adenoma.
A method was proposed to detect pulmonary nodules in low-dose computed tomography (CT) images by two-dimensional convolutional neural network under the condition of fine image preprocessing. Firstly, CT image preprocessing was carried out by image clipping, normalization and other algorithms. Then the positive samples were expanded to balance the number of positive and negative samples in convolutional neural network. Finally, the model with the best performance was obtained by training two-dimensional convolutional neural network and constantly optimizing network parameters. The model was evaluated in Lung Nodule Analysis 2016(LUNA16) dataset by means of five-fold cross validation, and each group's average model experiment results were obtained with the final accuracy of 92.3%, sensitivity of 92.1% and specificity of 92.6%.Compared with other existing automatic detection and classification methods for pulmonary nodules, all indexes were improved. Subsequently, the model perturbation experiment was carried out on this basis. The experimental results showed that the model is stable and has certain anti-interference ability, which could effectively identify pulmonary nodules and provide auxiliary diagnostic advice for early screening of lung cancer.
Objective To investigate the CT and MR imaging manifestation of rare pancreatic tumors in order to deepen the understanding of their imaging characteristics and improve the diagnostic accuracy. Methods Clinical and image date of 34 cases with rare pancreatic tumors proved by surgery and histopathologically were analyzed retrospectively. Including neuroendocrine tumors of the pancreas (NETP,n=13), solid-pseudopapillary tumors of pancreas (SPTP,n=10), intraductal papillary mucinous neoplasms (IPMN,n=2), serous cystadenoma (SCA,n=7), and mucinous cystadenoma (MCA,n=2). Examined by CT in 19 cases, by MRI in 11 cases, examined by CT and MRI at the same time in 4 cases. The characterized imaging features of each kind of tumors were analyzed emphatically. Results Of the 13 cases of NETP, solid lesions in 6 cases, predominantly soild in 4 cases, predominantly cystic in 3 cases. Homogenous enhancement in 6 cases, heterogeneous enhancement in 7cases, the soild constituent of all cases were showed moderate to marked enhancement. Of the 10 cases of SPTP, predominantly soild in 2 cases, soild and cystic in 5 cases, predominantly cystic in 3 cases. The solid part of 10 cases presented as gradually enhancement, 2 cases appeared hemorrhage, 1 case appeared stippled calcification. Of the 2 cases of IPMN, both of them were combined type, showed multilocular cystic tumors due to the dilated of the pancreatic duct. Of the 7 cases of SCA, microcystic partten in 3 cases and single cyst partten in 4 cases, showed unilocular or multilocular cystic with clear boundary. The 2 cases of MCA, showed unilocular cystic with clear boundary. Conclusion Different histological types of pancreatic rare tumor appeared different kinds of imaging characteristic, we may improve the diagnostic accuracy by analyzing their features.