Objective To explore the clinical value of artificial intelligence (AI) quantitative parameters of pulmonary ground-glass nodules (GGN) in predicting the degree of infiltration. Methods A retrospective analysis of 168 consecutive patients with 178 GGNs in our hospital from October 2019 to May 2021 was performed, including 43 males and 125 females, aged 21-78 (55.76±10.88) years. Different lesions of the same patient were analyzed as independent samples. Totally, 178 GGNs were divided into two groups, a non-invasive group (24 adenocarcinoma in situ and 77 minimally invasive adenocarcinoma), and an invasive group (77 invasive adenocarcinoma). We compared the difference of AI quantitative parameters between the two groups, and evaluated predictive valve by receiver operating characteristic curve and binary logistic regression model. Results (1) Except for the gender (P=0.115), the other parameters, such as maximal diameter [15.10 (11.50, 21.60) mm vs. 8.90 (7.65, 11.15) mm], minimum diameter [10.80 (8.85, 15.20) mm vs. 7.40 (6.10, 8.95) mm], proportion of consolidation/tumor ratio [13.58% (1.61%, 63.76%) vs. 0.00% (0.00%, 0.67%)], mean CT value [–347.00 (–492.00, –101.50) Hu vs. –598.00 (–657.50, –510.00) Hu], CT maximum value [40.00 (–40.00, 94.50) Hu vs. –218.00 (–347.00, –66.50) Hu], CT minimum value [–584.00 (–690.50, –350.00) Hu vs. –753.00 (–786.00, –700.00) Hu], danger rating (proportion of high-risk nodules, 92.2% vs. 66.3%), malignant probability [91.66% (85.62%, 94.92%) vs. 81.81% (59.98%, 90.29%)] and age (59.93±8.53 years vs. 52.04±12.10 years) were statistically significant between the invasive group and the non-invasive group (all P<0.001). (2) The highest predictive value of a single quantitative parameter was the maximal diameter (area under the curve=0.843), the lowest one was the risk classification (area under the curve=0.627), the combination of two among the three parameters (maximal diameter, mean CT value, and consolidation/tumor ratio) improved the predictive value entirely. (3) Logistic regression analysis showed that maximal diameter and mean CT value both were the independent risk factor for predicting invasive adenocarcinoma. (4) When the threshold of v was 1.775%, the diagnostic sensitivity of invasive adenocarcinoma was 0.753 and the specificity was 0.851. Conclusion AI quantitative parameters can effectively predict the degree of infiltration of GGNs and provide a reliable reference basis for clinicians.
ObjectiveTo introduce the new nomenclature scheme of the International Working Group (1995) on hepatic nodules, and summarize the imaging features of various hepatic nodules in light of their pathological characteristics, and evaluate the diagnostic values of various imaging facilities.MethodsUltrasound, computed tomography(CT), magnetic resonance imaging(MRI), and angiographic CT were reviewed and introduced.ResultsMany of these types of hepatic nodules play a role in the de novo and stepwise carcinogenesis of hepatocellular carcinoma(HCC) in the following steps: regenerative nodule, lowgrade dysplastic nodule, highgrade dysplastic nodule, small HCC, and large HCC. Accompanying such transformations, there are significant alterations in the blood supply and perfusion of these hepatic nodules.ConclusionModern stateoftheart medical imaging facilities can not only delineate and depict these hepatic nodules, but also provide important clues for the characterization of focal hepatic lesions in most cases, thus facilitating the early detection, diagnosis and management of HCC in its early stage.
Lung four dimensional computed tomography (4D-CT) is of great value in tumor target localization and precise cancer radiotherapy. However, it is hard to segment tumors in 4D-CT data manually, since the data may contain a great number of slices with tumor. Meanwhile, auto-segmentation does not certainly guarantee the accuracy due to the complexity of images. Therefore, a new automatic segmentation technique based on Graph Cuts with star shape prior was proposed to increase automation and guarantee the accuracy of segmentation in our laboratory. Firstly, an object seed was selected in the image of initial phase and an initial target block was formed centering the selected seed. Then, the full search block-matching algorithm was adopted to obtain the most similar target block in the next phase and compute the motion field between them, and so on. Afterwards, the center seeds of each phase were obtained according to the motion fields, which would be set to the center point of star shape prior. Finally, tumors could be automatically segmented with Graph Cuts algorithm and star shape prior. Both qualitative and quantitative evaluation results showed that our approach could not only guarantee the accuracy of segmentation but also increase automation, compared with the traditional Graph Cuts algorithm.
The aim of this study is to analyze the concordance between EDV, ESV and LVEF values derived from 18F-FDG PET, GSPECT and ECHO in patients with myocardial infarction. Sixty-four patients with coronary artery disease (CAD) and myocardial infarction were enrolled in the study.. Each patient underwent at least two of the above mentioned studies within 2 weeks. LVEF、 EDV and ESV values were analyzed with dedicated software. Statistical evaluation of correlation and agreement was carried out EDV was overestimated by 18F-FDG PET compared with GSPECT [(137.98±61.71) mL and (125.35±59.34) mL]; ESV was overestimated by 18F-FDG PET (85.89±55.21) mL and GSPECT (82.39±55.56) mL compared with ECHO (68.22±41.37) mL; EF was overestimated by 18F-FDG PET (41.96%±15.08%) and ECHO (52.18%±13.87%) compared with GSPECT (39.75%±15.64%), and EF was also overestimated by 18F-FDG PET compared with GSPECT. The results of linear regression analysis showed good correlation between EDV, ESV and LVEF values derived from 18F-FDG PET, GSPECT and ECHO (r=0.643-0.873, P=0.000). Bland-Altman analysis indicated that 18F-FDG PET correlated well with ECHO in the Left ventricular function parameters. While GSPECT correlated well with 18F-FDG PET in ESV, GSPECT had good correlation with Echo in respect of EDV and EF; whereas GSPECT had poor correlation with PET/ECHO in the remaining left ventricular function parameters. Therefore, the clinical physicians should decide whether they would use the method according to the patients' situation and diagnostic requirements.
Objective To observe the value of serum soluble receptor of advanced glycation endproducts (sRAGE) combined with lung function and high resolution lung CT (HRCT) in predicting the risk of chronic obstructive pulmonary disease (COPD) developing non-small cell lung cancer (NSCLC). Methods From January 2019 to June 2021, 140 patients with COPD combined with NSCLC, 137 patients with COPD, and 133 patients with NSCLC were enrolled in the study from the People's Hospital of Ningxia Hui Autonomous Region. General data, clinical symptoms, pulmonary function indexes and HRCT emphysema indexes (EI) were collected. Serum sRAGE levels of these patients were measured by enzyme linked immunosorbent assay. Clinical characteristics of patients with COPD complicated with NSCLC were analyzed. Serum sRAGE, lung function and lung HRCT were combined to evaluate the correlation between the degree of emphysema and the occurrence of NSCLC in COPD, and receiver operator characteristic (ROC) curve analysis was performed for diagnostic efficiency. Results Compared with NSCLC group, COPD combined with NSCLC group had higher proportion of male patients, higher proportion of elderly patients, higher smoking index, and higher proportion of squamous cell carcinoma (P<0.05). FEV1 and FEV1%pred in COPD combined with NSCLC group were significantly lower than those in COPD group and NSCLC group. The Goddard score and EI values of emphysema were significantly increased (P<0.05). Serum sRAGE was significantly lower than that of COPD group and NSCLC group (P<0.05). Serum sRAGE level was positively correlated with FEV1%pred (r=0.366, P<0.001) and FEV1/FVC (r=0.419, P<0.001), and negatively correlated with Goddard score (r=–0.710, P=0.001) and EI value (r=–0.515, P<0.001). Binary multi-factor logistic regression analysis showed that age, smoking index, EI, Goddard score, RV/TLC were positively correlated with the risk of COPD developing NSCLC, while FEV1%pred, FVC, FEV1/FVC and serum sRAGE were negatively correlated with the risk of COPD developing NSCLC. ROC curve results showed that the area under the curve (AUC) of single diagnosis of sRAGE was 0.990, and the optimal cut-off value of 391.98 pg/mL with sensitivity of 93.3% and specificity of 89.7%. The AUC of sRAGE combined with age, smoking index, EI, Goddard score, FEV1%pred, FVC, FEV1/FVC, RV/TLC was 1.000 with sensitivity of 96.7%, specificity of 96.6%, and Yoden index of 0.933. Conclusion The combination of serum sRAGE, lung function and HRCT emphysema score can improve prediction of NSCLC occurrence in COPD.
ObjectiveTo summarize the manifestations of acute mesenteric ischemia (AMI) on multidetector computed tomography (MDCT) and the diagnostic value of MDCT in the prognosis of AMI. MethodRecent studies on pathophysiology, CT features, and prognosis of AMI were retrieved and reviewed. ResultsVascular insufficiency of AMI could occur as a result of mesenteric arterial embolism, arterial thrombosis, venous thrombosis, or nonocclusive. Two stages of AMI, early and late, were associated with distinct prognosis. In early ischemia, the lesions were reversible. The late AMI was characterized by the development of irreversible transmural necrosis. A delayed diagnosis leaded to considerable mortality. MDCT findings in AMI could be divided into imaging findings related to vascular insufficiency and ischemic intestinal injury. Pneumoperitoneum could be considered a sign of transmural necrosis in the AMI. While, other imaging features predicting transmural necrosis were controversial because of the heterogeneity of diagnostic tests. ConclusionsAMI is a life-threatening abdominal emergency. Early diagnosis can improve the prognosis of patient. It is important for radiologists to identify prognostic features for differentiating early from late forms of AMI.
This study aims to explore the inferior adhesion of the renal fascia (RF), and the inferior connectivity of the perirenal spaces (PS) with multidetector computed tomography (MDCT), and to investigate the diagnostic value of CT for showing this anatomy. From May to July 2012, eighty-two patients with acute pancreatitis presented in our hospital were enrolled into this study and underwent contrast-enhanced CT scans. All the image data were used to perform three dimensional reconstruction to show the inferior attachment of RF and the inferior connectivity of PS. The fusion of anterior renal fascia (ARF) and posterior renal fascia (PRF) next to the plane of iliac fossa were found on the left in 71.95% (59/82) cases, and on the right in 75.61% (62/82). In these cases, bilateral perirenal spaces, and anterior and posterior pararenal spaces were not found to be connected with each other. No fusion of ARF and PRF below the level of bilateral kidneys occurred on the left side in 28.05% (23/82) cases and on the right side in 24.39% (20/82). In these patients, the PS extended to the extraperitoneal space of the pelvic cavity and further to the inguinal region, and bilateral anterior and posterior pararenal spaces were not found to be connected with each other. Three-dimensional reconstruction on contrast-enhanced MDCT could be a valuable procedure for depicting inferior attachment of RF, and the inferior connectivity of PS.
ObjectiveTo analyze and conclude CT and MRI imaging features of ectopic pancreas in gastrointestinal tract so as to improve the understanding of the features.MethodsThe clinical, imaging, and pathological data of 12 patients with ectopic pancreas in the gastrointestinal tract confirmed by the pathology in the Sichuan Provincial People’s Hospital from November 2016 to June 2019 were retrospectively analyzed. The characteristics of image presentation were summarized.Results① The anatomical distribution: all patients had a single lesion. Of the 12 cases, 6 cases located in the gastric body lesser curvature, 3 cases located in the gastric angle, 1 case located in the posterior wall of gastric antrum, 1 case occurred in the upper jejunum, and 1 case occurred in the terminal ileum; 8 cases located in the submucosa, 2 cases located in the submucosa and muscular layer simultaneously, 1 case located in the submucosa, muscular and serous layer simultaneously, and 1 case located in the muscular layer. ② Size of the lesions: the maxium dimensions of the lesions were all 3 cm or less, and the long axes of the lesions were parallel to the gastrointestinal tract wall in 10 cases. ③ The internal characteristics: the results of 9 of 11 cases showed the isodensity compared to main pancreas on the plain CT scan. The results of 8 patients with enhanced CT showed the moderate to obvious enhancement, with 2 cases showed the slightly enhanced flaky or tube-like foci. In the arterial phase and portal venous phase, 6 cases showed the isodensity compared to main pancreas respectively. The result of MRI in 1 patient showed the isointensity compared to main pancreas on the plain scan and obviously heterogeneous enhancement.ConclusionCT and MRI could provide some information about location, size, and internal density or intensity of ectopic pancreas, and could be helpful for diagnosis.
Objective To investigate differential points of clinical symptoms and pathology of solid-pseudopapillary tumor of the pancreas (SPTP) and islet cell tumor (ICT). Methods Fifteen cases of SPTP and twelve cases of ICT were studied in this retrospective research. Clinical symptom, pathologic feature and computed tomography (CT) image of patients with both tumors were analyzed, and the imaging features were compared with pathological results. Results The mean age of SPTP patients was 22.4 year-old. Twelve patients with SPTP presented a palpable abdominal mass as the initial symptom. It was observed that the tumor cells were located in a pseudopapillary pattern with a fibro-vascular core histologically. On the CT images, a mixture of solid and cystic structures could be seen in all the tumors. After taking enhanced CT scan, the solid portion was slightly enhanced in the arterial phase and the contrast intensity increased in the portal venous phase. On the other hand, the mean age of ICT patients was 39.3 year-old. The major symptom was due to the function of islet cell tumor, which was typical in 8 patients, presenting as Whipple triad. Histologically, cells demonstrated in trabecular, massive, acinar or solid patterns, and the blood supply of the tumor was abundant. On the CT images, most small tumors were difficulty to be detected. ICT could be markedly enhanced in the arterial phase and slightly enhanced in the portal venous phase on post-contrast CT scan. Conclusion Clinical symptom, pathologic feature and CT scanning are helpful to differentiate SPTP from ICT.
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.