| 1 | Incorporating DeepLabv3+and object-based image analysis for semantic segmentation of very high resolution remote sensing images显示文摘Semantic segmentation of remote sensing images is an important but unsolved problem in the remote sensing society.Advanced image semantic segmentation models,such as DeepLabv3+,have achieved astonishing performance for semantically labeling very high resolution(VHR)remote sensing images.However,it is difficult for these models to capture the precise outlines of ground objects and explore the context information that revealing relationships among image objects for optimizing segmentation results.Consequently,this study proposes a semantic segmentation method for VHR images by incorporating deep learning semantic segmentation model(DeepLabv3+)and objectbased image analysis(OBIA),wherein DSM is employed to provide geometric information to enhance the interpretation of VHR images.The proposed method first obtains two initial probabilistic labeling predictions using a DeepLabv3+network on spectral image and a random forest(RF)classifier on hand-crafted features,respectively.These two predictions are then integrated by Dempster-Shafer(D-S)evidence theory to be fed into an object-constrained higher-order conditional random field(CRF)framework to estimate the final semantic labeling results with the consideration of the spatial contextual information.The proposed method is applied to the ISPRS 2D semantic labeling benchmark,and competitive overall accuracies of 90.6%and 85.0%are achieved for Vaihingen and Potsdam datasets,respectively. | Shouji Du Shihong Du Bo Liu Xiuyuan Zhang | 2021 | International Journal of Digital Earth2021，14，3： | 9 |
| 2 | Evaluating Tislelizumab, Lenvatinib, and FOLFOX4-HAIC as a Conversion Therapy for Unresectable Hepatocellular Carcinoma显示文摘Background and aims:Conversion therapy downstages tumors and renders patients with unresectable hepatocel-lular carcinoma(HCC)eligible for radical resection.This study aimed to evaluate the efficacy and safety of tislelizumab plus lenvatinib and hepatic artery infusion chemotherapy with oxaliplatin,fluorouracil,and leuco-vorin(FOLFOX4-HAIC)as a first-line conversion therapy.Methods:Clinical data from HCC patients who were treated with the triple therapy between April 2021 and April 2022 were retrospectively analyzed.The primary outcome included objective response rate(ORR),disease control rate(DCR),conversion resection rate(CRR),and treatment-related adverse events(TRAEs).Results:A total of 18 patients completed conversion therapy assessment,which ended on March 27,2023.The patients had a median age of 55.5(37–72)years,and 94.4%were male.According to mRECIST,tumor shrinkage was observed in all patients,with an ORR of 94.4%(17/18),a DCR of 94.4%(17/18),and a median time to response of 1.4(0.7–3.0)months.Successful conversion was observed in 61.1%(11/18)of patients(mRECIST).The CRR and pathological complete response were 38.9%(7/18)and 57.1%(4/7),respectively.The median progression-free survival(PFS)was 17.8 months,while median overall survival was not reached.The 6-and 9-month PFS rates were 83.3%and 66.7%,respectively.The most common TRAE(16/18 patients,88.9%)was an increase in aspartate aminotransferase levels.Conclusion:Tislelizumab combined with lenvatinib and FOLFOX4-HAIC achieved a high conversion rate and acceptable toxicity in patients with unresectable HCC,suggesting that this combination may represent a new conversion strategy for this population. | Kai Tan Xiaojun He Haoran Yuan Shoujie Zhao Chenyu Gong Yaoyao Zhao Haiyan Nan Li Zang Zhonghua Luo Xilin Du | 2023 | iLIVER2023，2，3： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员