We propose an effective algorithm for accurate 3D segmentation of CT liver images based on statistical and specific information. We present a new intensity model which combines patient-specific intensity information of boundary with the statistical information for liver segmentation. Compared to the traditional methods, our approach not only produces excellent segmentation accuracy, but also increases the robustness.
Algorithms ; Humans ; Imaging, Three-Dimensional ; methods ; Liver ; diagnostic imaging ; Liver Diseases ; diagnostic imaging ; Liver Neoplasms ; diagnostic imaging ; Models, Statistical ; Radiographic Image Interpretation, Computer-Assisted ; methods ; Tomography, X-Ray Computed ; methods

Objective To observe the impact of readout-segmented echo-planar imaging(RS-EPI)based on small field of view(FOV)and saturation band on image quality of orbital diffusion weighted imaging(DWI).Methods Orbital MR scanning were prospectively performed in 33 healthy subjects.T1W,RS-RPI and optimized RS-EPI(based on small FOV and saturation band)images were acquired.Imaging quality of RS-EPI and optimized RS-EPI on displaying intraorbital structures(eyeballs,optic nerve and intraconal compartment)and periorbital structures(nasal cavity,orbital gyrus,optic chiasma,pituitary and temporal lobe)were evaluated subjectively using 5-point method.The geometric parameters of eyeball,signal-to-noise ratio(SNR)and apparent diffusion coefficient(ADC)were compared between images of RS-EPI and optimized RS-EPI.Results The display of eyeball,nasal cavity,orbital gyrus,optic chiasm,pituitary and temporal lobe on optimized RS-EPI were all better than those on RS-EPI(all P＜0.01),whereas no significant difference of optic nerve nor intraconal compartment was found between optimized RS-EPI and RS-EPI images(P＞0.05).Deformations of eyeball volume,sphericity,surface area,3D maximum diameter,axial maximum diameter and sagittal maximum diameter of bilateral eyes on optimized RS-EPI images were all slighter than those on RS-EPI(all P＜0.01),whereas no significant difference of deformations of coronal maximum diameters was found between optimized RS-EPI and RS-EPI images(P＞0.05).SNR of left temporal lobe white matter and ADC of vitreous body on optimized RS-EPI images were both lower than those on RS-EPI(both P＜0.01),whereas no significant difference of ADC of left temporal lobe white matter nor that of pons was found between optimized RS-EPI and RS-EPI images(P＞0.05).Conclusion Optimized RS-EPI with small FOV and saturation band could be used to improve imaging quality of orbital DWI.

Objective:To investigate the value of CT radiomic model based on analysis of primary gastric cancer and the adipose tissue outside the gastric wall beside cancer in differentiating stage T1-2 from stage T3-4 gastric cancer.Methods:This study was a case-control study. Totally 465 patients with gastric cancer treated in Affiliated People′s Hospital of Jiangsu University from December 2011 to December 2019 were retrospectively collected. According to postoperative pathology, they were divided into 2 groups, one with 150 cases of T1-2 tumors and another with 315 cases of T3-4 tumors. The cases were divided into a training set (326 cases) and a test set (139 cases) by stratified sampling method at 7∶3. There were 104 cases of T1-2 stage and 222 cases of T3-4 stage in the training set, 46 cases of T1-2 stage and 93 cases of T3-4 stage in the test set. The axial CT images in the venous phase during one week before surgery were selected to delineate the region of interest (ROI) at the primary lesion and the extramural gastric adipose tissue adjacent to the cancer areas. The radiomic features of the ROIs were extracted by Pyradiomics software. The least absolute shrinkage and selection operator was used to screen features related to T stage to establish the radiomic models of primary gastric cancer and the adipose tissue outside the gastric wall beside cancer. Independent sample t test or χ2 test were used to compare the differences in clinical features between T1-2 and T3-4 patients in the training set, and the features with statistical significance were combined to establish a clinical model. Two radiomic signatures and clinical features were combined to construct a clinical-radiomics model and generate a nomogram. The area under the receiver operating characteristic curve (AUC) was used to evaluate the efficacy of each model in differentiating stage T1-2 from stage T3-4 gastric cancer. The calibration curve was used to evaluate the consistency between the T stage predicted by the nomogram and the actual T stage of gastric cancer. And the decision curve analysis was used to evaluate the clinical net benefit of treatment guided by the nomogram and by the clinical model. Results:There were significant differences in CT-T stage and CT-N stage between T1-2 and T3-4 patients in the training set ( χ2=10.59, 15.92, P=0.014, 0.001) and the clinical model was established. After screening and dimensionality reduction, the 5 features from primary gastric cancer and the 6 features from the adipose tissue outside the gastric wall beside cancer established the radiomic models respectively. In the training set and the test set, the AUC values of the primary gastric cancer radiomic model were 0.864 (95% CI 0.820-0.908) and 0.836 (95% CI 0.762-0.910), and the adipose tissue outside the gastric wall beside cancer radiomic model were 0.782 (95% CI 0.731-0.833) and 0.784 (95% CI 0.702-0.866). The AUC values of the clinical model were 0.761 (95% CI 0.705-0.817) and 0.758 (95% CI 0.671-0.845), and the nomogram were 0.876 (95% CI 0.835-0.917) and 0.851 (95% CI 0.781-0.921). The calibration curve reflected that there was a high consistency between the T stage predicted by the nomogram and the actual T stage in the training set ( χ2=1.70, P=0.989). And the decision curve showed that at the risk threshold 0.01-0.74, a higher clinical net benefit could be obtained by using a nomogram to guide treatment. Conclusions:The CT radiomics features of primary gastric cancer lesions and the adipose tissue outside the gastric wall beside cancer can effectively distinguish T1-2 from T3-4 gastric cancer, and the combination of CT radiomic features and clinical features can further improve the prediction accuracy.