Research on automatic segmentation of tumor target of lung cancer in CBCT images by multimodal style transfer technology based on deep learning / 中华放射肿瘤学杂志

Objective:Due to the low contrast between tumors and surrounding tissues in CBCT images, this study was designed to propose an automatic segmentation method for central lung cancer in CBCT images.Methods:There are 221 patients with central lung cancer were recruited. Among them, 176 patients underwent CT localization and 45 patients underwent enhanced CT localization. The enhanced CT images were set as the lung window and mediastinal window, and elastic registration was performed with the first CBCT validation images to obtain the paired data set. The CBCT images could be transformed into" enhanced CT" under the lung window and mediastinal window by loading the paired data sets into cycleGAN network for style transformation. Finally, the transformed images were loaded into the UNET-attention network for deep learning of GTV. The results of segmentation were evaluated by Dice similarity coefficient (DSC), Hausdorff distance (HD) and the area under the receiver operating characteristic curve (AUC).Results:The contrast between tumors and surrounding tissues was significantly improved after style transformation. The DSC value of cycleGAN+ UNET-attention network was 0.78±0.05, HD value was 9.22±3.42 and AUC value was 0.864, respectively.Conclusion:The cycleGAN+ UNET-attention network can effectively segment central lung cancer in CBCT images.

Observation on Microvascular Change of Bile Duct Ligation-induced Liver Fibrosis by X-ray Phase-contrast Computed Tomography / 中国医学影像学杂志

Purpose Liver fibrosis is the common pathological process of cirrhosis developed by chronic liver disease.This study aims to explore the application of microvascular change in assessing the liver fibrosis induced by bile duct ligation based on X-ray phasecontrast computed tomography (PCCT).Materials and Methods Ten rats were equally divided into the group of bile duct ligation-induced liver fibrosis and the control group at random.Then ten excised liver tissues were imaged at beamline BL13W1 of Shanghai Synchrotron Radiation Facility in China.After the imaging studies,the liver samples were stained with Sirius red and immunostained with antibodies against cytokeratin 19 (CK19).The microvasculature in livers was reconstructed via PCCT,and the correlation analysis on microvascular density and the proportion of fibrosis area was performed.Results The microvasculature including blood vessels,dilated bile ducts and ductular proliferation were clearly revealed by PCCT technology.Moreover,the 3D microvascular density and proportion of fibrosis area in the liver fibrosis group increased significantly compared with those in the control group (P＜0.01),and the correlation between them was obvious (r=0.812,P＜0.01).Conclusion Microvascular 3D characteristics of liver fibrosis are well demonstrated by PCCT,and 3D microvascular density is significantly correlated with the proportion of fibrosis area.Those findings indicate that microvascular change is closely related to the degree of liver fibrosis induced by bile duct ligation,and thus it provides a novel means to assess the severity of liver fibrosis through microvascular change.