Rapidly-developing remote sensing technology provides massive data for urban planning, mapping and disaster management. As a carrier of human productive activities, buildings are essential to both urban dynamic monitoring and suburban construction inspection. FCN-based methods have provided a paradigm for automatically extracting buildings from high-resolution imagery. However, high intra-class variance and complexity are two problems in building extraction. It is hard to identify different scales of buildings by using a single receptive field. For this purpose, in this paper we use the stable encoderdecoder architecture, combined with a grid-based attention gate (AG) and atrous spatial pyramid pooling (ASPP) module, to capture and restore features progressively and effectively. A modified ResNet50 encoder is also applied to extract features. The proposed method could learn gated features and distinguish buildings from complex surroundings such as trees. We evaluate our model on two building datasets, WHU aerial building dataset and our DB UAV rural building dataset. Experiments show that our model outperforms other five most recent models. The results also exhibit great potential for extracting buildings with different scales and validates the effectiveness of deep learning in practical scenarios.
We investigated the distribution of residual cancer cells (RCCs) within different layers of the bowel wall in surgical specimens and the value of biopsies of primary rectal lesion after preoperative volumetric modulated arc therapy (VMAT) with concurrent chemotherapy in patients with rectal cancer. Between April 2011 and April 2013, 178 patients with rectal cancer who received preoperative VMAT, concurrent chemotherapy, and surgery were evaluated; 79 of the patients received a biopsy of the primary lesion after chemoradiotherapy and prior to surgery. The distribution of RCCs in the surgical specimens and the sensitivity and specificity of the biopsy of primary rectal lesions for pathological response were evaluated. Fifty-two patients had a complete pathological response in the bowel wall. Of the 120 patients with ypT2-4, the rate of detection of RCCs in the mucosa, submucosa, and muscularis propria was 20%, 36.7%, 69.2%, respectively. The sensitivity and specificity of biopsies of primary rectal lesions was 12.9% and 94.1%, respectively. After chemoradiotherapy, the RCCs were primarily located in the deeper layers of the bowel wall, and the biopsy results for primary rectal lesions were unreliable due to poor sensitivity.
Adjuvant radiotherapy included external irradiation on pelvic area and brachytherapy to vaginal stump. Hormonal therapy and chemotherapy were administrated to some of the patients. Propensitymatched analysis (PSM) was used to eliminate group difference and Kaplan-Meier survival analysis was done to calculate survival. Results: 132 patients with resected Low-grade endometrial stromal sarcoma were included in the analysis. The median age was 43 years and 90.8% of patients was premenopausal. Stage I and II accounted for most (76.0% and 19.4%, respectively), followed by stage III-IVA. Among all patients, 103 patients underwent bilateral oophorectomy and 5 patients underwent unilateral oophorectomy while the others preserved ovaries. Hormonal therapy was prescribed to 60 (45.5%) patients. A total of 32 (24.2%) patients received postoperative radiotherapy (RT group), while 100 patients did not receive adjuvant radiotherapy (no RT group). The two groups were comparable in age, tumor diameter, stage, menopausal status et al. However, proportion of hormonal therapy (68.8% vs. 38.0%, P Z 0.002) and bilateral oophorectomy (90.6% vs. 74.0%, P Z 0.048) in the RT group were significantly higher than those in the no RT group. The median follow-up time was 40.5 months. 32 patients relapsed (24.2%, including 22 cases limited to pelvic area, 6 cases relapsed in pelvic and abdominal area, 2 cases relapsed in pelvic area and lungs, 1 case relapsed in pelvic, abdominal area and lungs, 1 case to lungs) and 1 patient (0.8%) died during follow-up. For all patients, 1-year disease-free survival (DFS) was 90.6%, 3 yrs DFS was 79.0%, 5 yrs DFS was 71.2%. Univariate analysis showed that radiotherapy, menopausal status and bilateral oophorectomy significantly prolonged DFS. Postoperative radiotherapy reduced recurrence rate (12.5% (4/32) vs. 27.0% (27/100)). We then did a propensity-matched analysis to eliminate unbalanced factors in RT group and no RT group. A total of 64 patients were matched according to menopausal status, bilateral oophorectomy and hormonal therapy. Kaplan-Meier analysis showed significant improved DFS in RT group compared to no RT group (median DFS: not reached vs. 81monthes, p Z 0.004). In terms of toxicity, there was no radiotherapy induced grade III-IV toxicity. Conclusion: In patients with Low-grade endometrial stromal sarcoma after radical resection, postoperative radiotherapy showed significant improvement on DFS which emphasized importance of radiotherapy in ESS.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.