This paper presents a probability segmentation algorithm for lung nodules based on three-dimensional features. Firstly, we computed intensity and texture features in region of interest (ROI) pixel by pixel to get their feature vector, and then classified all the pixels based on their feature vector. At last, we carried region growing on the classified result, and got the final segmentation result. Using the public Lung Imaging Database Consortium (LIDC) lung nodule datasets, we verified the performance of proposed method by comparing the probability map within LIDC datasets, which was drawn by four radiology doctors separately. The experimental results showed that the segmentation algorithm using three-dimensional intensity and texture features would be effective.
Objective To determine feasibility of texture analysis of CT images for the discrimination of hepatic epithelioid hemangioendothelioma (HEHE) and liver metastases of colon cancer. Methods CT images of 9 patients with 19 pathologically proved HEHEs and 18 patients with 38 liver metastases of colon cancer who received treatment in West China Hospital of Sichuan University from July 2012 to August 2016 were retrospectively analyzed. Results Thirty best texture parameters were automatically selected by the combination of Fisher coefficient (Fisher)+classification error probability combined with average correlation coefficients (PA)+mutual information (MI). The 30 texture parameters of arterial phase (AP) CT images were distributed in co-occurrence matrix (22 parameters), run-length matrix (1 parameter), histogram (4 parameters), gradient (1 parameter), and autoregressive model (2 parameters). The distribution of parameters in portal venous phase (PVP) were co-occurrence matrix (18 parameters), run-length matrix (2 parameters), histogram (7 parameters), gradient (2 parameters), and autoregressive model (1 parameter). In AP, the misclassification rates of raw data analysis (RDA)/K nearest neighbor classification (KNN), principal component analysis (PCA)/KNN, linear discriminant analysis (LDA)/KNN, and nonlinear discriminant analysis, and nonlinear discriminant analysis (NDA)/artificial neural network (ANN) was 38.60% (22/57), 42.11% (24/57), 8.77% (5/57), and 7.02% (4/57), respectively. In PVP, the misclassification rates of RDA/KNN, PCA/KNN, LDA/KNN, and NDA/ANN was 26.32% (15/57), 28.07% (16/57), 15.79% (9/57), and 10.53% (6/57), respectively. The misclassification rates of AP and PVP images had no statistical significance on the misclassification rates of RDA/KNN, PCA/KNN, LDA/KNN, and NDA/ANN between AP and PVP (P>0.05). Conclusion The texture analysis of CT images is feasible to identify HEHE and liver metastases of colon cancer.
Objective To determine feasibility of texture analysis of CT images for the discrimination of nonhypervascular pancreatic neuroendocrine tumor (PNET) from pancreatic ductal adenocarcinoma (PDAC). Methods CT images of 15 pathologically proved as PNETs and 30 PDACs in West China Hospital of Sichuan University from January 2009 to January 2017 were retrospectively analyzed. Results Thirty best texture parameters were automatically selected by the combination of Fisher coefficient (Fisher)+classification error probability combined with average correlation coefficients (PA)+mutual information (MI). The 30 texture parameters of arterial phase (AP) CT images were distributed in co-occurrence matrix (18 parameters), run-length matrix (10 parameters), and autoregressive model (2 parameters). The distribution of parameters in portal venous phase (PVP) were co-occurrence matrix (15 parameters), run-length matrix (10 parameters), histogram (1 parameter), absolute gradient (1 parameter), and autoregressive model (3 parameters). In AP and PVP, the parameter with the highest diagnostic performance were both Teta2, and the area under curve (AUC) value was 0.829 and 0.740 (P<0.001,P=0.009), respectively. By the B11 of MaZda, the misclassification rate of raw data analysis (RDA)/K nearest neighbor classification (KNN), principal component analysis (PCA)/KNN, linear discriminant analysis (LDA)/KNN, and nonlinear discriminant analysis (NDA)/artificial neural network (ANN) was 28.89% (13/45), 28.89% (13/45), 0 (0/45), and 4.44% (2/45), respectively. In PVP, the misclassification rate of RDA/KNN, PCA/KNN, LDA/KNN, and NDA/ANN was 35.56% (16/45), 33.33% (15/45), 4.44% (2/45), and 11.11% (5/45), respectively. Conclusions CT texture analysis is feasible in the discrimination of nonhypervascular PNET and PDAC. Teta2 is the parameter with the highest diagnostic performance, and in AP, LDA/KNN modality has the lowest misclassification rate.
ObjectiveTo investigate CT image features of ground glass opacity (GGO)-like 2019 novel coronavirus (2019-nCoV, SARS-CoV-2) pneumonia (COVID-19) and early-stage lung carcinoma for control and therapy of this acute severe respiratory disease.MethodsWe retrospectively analyzed the clinical data of 71 GGO-like COVID-19 patients who received therapy in Tongji Hospital of Huazhong University of Science and Technology between January 17th and February 13th, 2020. These 71 GGO-like COVID-19 patients were as a COVID-19 group. And 80 GGO-like early-stage lung carcinoma patients who underwent resection were as a lung carcinoma group. Clinical features such as sex, age, symptoms including fever, cough, fatigue, myalgia and dyspnea, detailed exposure history, confirmatory test (SARS-CoV-2 quantitative RT-PCR) and pathologic diagnosis were analyzed.ResultsSignificantly different symptoms and exposure history between the two groups were detected (P<0.001). More lesions (61 patients at percentage of 85.92%, P<0.001), relative peripheral locations (69 patients at percentage of 97.18%, P<0.001) and larger opacities (65 patients at percentage of 91.55%, P<0.001) were found in chest radiographs of GGO-like COVID-19 compared with GGO-like early-stage lung carcinoma. Similar features appeared in early-stage of COVID-19 and lung carcinoma, while pneumonia developed into more extensive and basal predominant lung consolidation. Coexistence of GGO-like COVID-19 and early-stage lung carcinoma might occur.ConclusionConsidering these similar and unique features of GGO-like COVID-19 and early-stage lung carcinoma, it is necessary to understand short time re-examination of chest radiographs and other diagnostic methods of these two diseases. We believe that the findings reported here are important for diagnosis and control of COVID-19 in China.
ObjectiveTo evaluate the diagnostic value of artificial intelligence (AI)-assisted diagnostic system for pulmonary cancer based on CT images.MethodsDatabases including PubMed, The Cochrane Library, EMbase, CNKI, WanFang Data and Chinese BioMedical Literature Database (CBM) were electronically searched to collect relevant studies on AI-assisted diagnostic system in the diagnosis of pulmonary cancer from 2010 to 2019. The eligible studies were selected according to inclusion and exclusion criteria, and the quality of included studies was assessed and the special information was identified. Then, meta-analysis was performed using RevMan 5.3, Stata 12.0 and SAS 9.4 softwares. The sensitivity, specificity, positive likelihood ratio, negative likelihood ratio and diagnostic odds ratio were pooled and the summary receiver operating characteristic (SROC) curve was drawn. Meta-regression analysis was used to explore the sources of heterogeneity.ResultsTotally 18 studies were included with 4 771 patients. Random effect model was used for the analysis due to the heterogeneity among studies. The results of meta-analysis showed that the pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, diagnosis odds ratio and area under the SROC curve were 0.87 [95%CI (0.84, 0.90)], 0.89 [95%CI (0.84, 0.92)], 7.70 [95%CI (5.32, 11.15)], 0.14 [95%CI (0.11, 0.19)], 53.54 [95%CI (30.68, 93.42)] and 0.94 [95%CI (0.91, 0.95)], respectively.ConclusionAI-assisted diagnostic system based on CT images has high diagnostic value for pulmonary cancer, and thus it is worthy of clinical application. However, due to the limited quality and quantity of included studies, above results should be validated by more studies.