Search

Individual Tree Detection-and-Counting (ITDC) is among the important tasks in town areas, and numerous methods are proposed in this direction. Despite their many advantages, still, the proposed methods are inadequate to provide robust results because they mostly rely on the direct field investigations. This paper presents a novel approach involving high-resolution imagery and the Canopy-Height-Model (CHM) data to solve the ITDC problem. The new approach is studied in six urban scenes: farmland, woodland, park, industrial land, road and residential areas. First, it identifies tree canopy regions using a deep learning network from high-resolution imagery. It then deploys the CHM-data to detect treetops of the canopy regions using a local maximum algorithm and individual tree canopies using the region growing. Finally, it calculates and describes the number of individual trees and tree canopies. The proposed approach is experimented with the data from Shanghai, China. Our results show that the individual tree detection method had an average overall accuracy of 0.953, with a precision of 0.987 for woodland scene. Meanwhile, the R2 value for canopy segmentation in different urban scenes is greater than 0.780 and 0.779 for canopy area and diameter size, respectively. These results confirm that the proposed method is robust enough for urban tree planning and management.

Abstract The challenge of spatial resource allocation is pervasive across various domains such as transportation, industry, and daily life. As the scale of real-world issues continues to expand and demands for real-time solutions increase, traditional algorithms face significant computational pressures, struggling to achieve optimal efficiency and real-time capabilities. In recent years, with the escalating computational power of computers, the remarkable achievements of reinforcement learning in domains like Go and robotics have demonstrated its robust learning and sequential decision-making capabilities. Given these advancements, there has been a surge in novel methods employing reinforcement learning to tackle spatial resource allocation problems. These methods exhibit advantages such as rapid solution convergence and strong model generalization abilities, offering a new perspective on resolving spatial resource allocation problems. Despite the progress, reinforcement learning still faces hurdles when it comes to spatial resource allocation. There remains a gap in its ability to fully grasp the diversity and intricacy of real-world resources. The environmental models used in reinforcement learning may not always capture the spatial dynamics accurately. Moreover, in situations laden with strict and numerous constraints, reinforcement learning can sometimes fall short in offering feasible strategies. Consequently, this paper is dedicated to summarizing and reviewing current theoretical approaches and practical research that utilize reinforcement learning to address issues pertaining to spatial resource allocation. In addition, the paper accentuates several unresolved challenges that urgently necessitate future focus and exploration within this realm and proposes viable approaches for these challenges. This research furnishes valuable insights that may assist scholars in gaining a more nuanced understanding of the problems, opportunities, and potential directions concerning the application of reinforcement learning in spatial resource allocation.

Background The mechanism for hypoattenuating leaflet thickening (HALT) after transcatheter aortic valve replacement is still not well elucidated, and the role of Lp(a) (lipoprotein[a]) and hs‐CRP (high‐sensitivity C‐reactive protein) has rarely been studied. This study sought to test the hypothesis that the risk of HALT is associated with an elevated level of Lp(a) or hs‐CRP. Methods and Results A total of 307 consecutive individuals who underwent a transcatheter aortic valve replacement procedure were included. All patients received their first postoperative computed tomography scans within 12 months, and raw data were analyzed on 3mensio software. HALT was defined as visually identified increased leaflet thickness with typical meniscal appearance and at least 2 different multiplanar reformation projections. Associations of Lp(a) or hs‐CRP with the risk of HALT were evaluated using multivariable logistic regression analysis. The incidence of HALT within 12 months after transcatheter aortic valve replacement in this study was 36.2%, and the risk of HALT was associated with higher baseline Lp(a) (the multivariable adjusted odds ratio [OR] for every 10 mg/dL change was 1.18 [95% CI, 1.09–1.29]) and hs‐CRP level (the multivariable adjusted OR for every 1 mg/L change was 1.08 [95% CI, 1.00–1.27]). Compared with individuals out of the top 25th percentile for both Lp(a) and hs‐CRP, the multivariable adjusted OR for HALT was 4.74 (95% CI, 1.65–14.37) for the top 25th percentile. This result remained consistent after excluding patients receiving anticoagulant therapy. Conclusions The top 25th percentile of Lp(a) level (≥40 mg/dL) combined with the top 25th percentile of hs‐CRP level (≥3.5 mg/L) conferred a 4.74‐fold risk of HALT.

Abstract Background Stress hyperglycemia ratio (SHR) has recently been recognized as a novel biomarker that accurately reflects acute hyperglycemia status and is associated with poor prognosis of heart failure. We evaluated the relationship between SHR and clinical outcomes in patients with severe aortic stenosis receiving transcatheter aortic valve replacement (TAVR). Methods There were 582 patients with severe native aortic stenosis who underwent TAVR consecutively enrolled in the study. The formula used to determine SHR was as follows: admission blood glucose (mmol/L)/(1.59×HbA1c[%]–2.59). The primary endpoint was defined as all-cause mortality, while secondary endpoints included a composite of cardiovascular mortality or readmission for heart failure, and major adverse cardiovascular events (MACE) including cardiovascular mortality, non-fatal myocardial infarction, and non-fatal stroke. Multivariable Cox regression and restricted cubic spline analysis were employed to assess the relationship between SHR and endpoints, with hazard ratios (HRs) and 95% confidence intervals (CIs). Results During a median follow-up of 3.9 years, a total of 130 cases (22.3%) of all-cause mortality were recorded. Results from the restricted cubic spline analysis indicated a linear association between SHR and all endpoints (p for non-linearity > 0.05), even after adjustment for other confounding factors. Per 0.1 unit increase in SHR was associated with a 12% (adjusted HR: 1.12, 95% CI: 1.04–1.21) higher incidence of the primary endpoint, a 12% (adjusted HR: 1.12, 95% CI: 1.02–1.22) higher incidence of cardiovascular mortality or readmission for heart failure, and a 12% (adjusted HR: 1.12, 95% CI: 1.01–1.23) higher incidence of MACE. Subgroup analysis revealed that SHR had a significant interaction with diabetes mellitus with regard to the risk of all-cause mortality (p for interaction: 0.042). Kaplan-Meier survival analysis showed that there were significant differences in the incidence of all endpoints between the two groups with 0.944 as the optimal binary cutoff point of SHR (all log-rank test: p

Abstract. Background:. The study aimed to describe the aortic valve morphology in Chinese patients underwent transcatheter aortic valve replacement (TAVR) for symptomatic severe aortic stenosis (AS), and the impact of sizing strategies and related procedural outcomes. Methods:. Patients with severe AS who underwent TAVR were consecutively enrolled from 2012 to 2019. The anatomy and morphology of the aortic root were assessed. “Downsize” strategy was preformed when patients had complex morphology. The clinical outcomes of patients who performed downsize strategy were compared with those received annular sizing strategy. The primary outcome was device success rate, and secondary outcomes included Valve Academic Research Consortium-3 clinical outcomes variables based on 1-year follow-up. Results:. A total of 293 patients were enrolled. Among them, 95 patients (32.4%) had bicuspid aortic valve. The calcium volume (Hounsfield Unit-850) of aortic root was 449.90 (243.15–782.15) mm3. Calcium is distributed mostly on the leaflet level. Downsize strategy was performed in 204 patients (69.6%). Compared with the patients who performed annular sizing strategy, those received downsize strategy achieved a similar device success rate (82.0% [73] vs. 83.3% [170], P = 0.79). Aortic valve gradients (downsize strategy group vs. annular sizing group, 11.28 mmHg vs. 11.88 mmHg, P = 0.64) and percentages of patients with moderate or severe paravalvular regurgitation 2.0% (4/204) vs. 4.5% (4/89), P = 0.21) were similar in the two groups at 30 days after TAVR. These echocardiographic results were sustainable for one year. Conclusions:. Chinese TAVR patients have more prevalent bicuspid morphology and large calcium volume of aortic root. Calcium is distributed mostly on the leaflet level. Compare with annular sizing strategy, downsize strategy provided a non-inferior device success rate and transcatheter heart valve hemodynamic performance in self-expanding TAVR procedure.

BackgroundClinical evidence of transcatheter aortic valve replacement in patients with type-0 bicuspid aortic valve was relatively scarce.AimsOur goal was to explore determinants of device success after transcatheter aortic valve replacement in patients with type-0 bicuspid aortic valve morphology.MethodsIn this retrospective multicenter analysis, we included 59 patients with symptomatic severe aortic stenosis with type-0 bicuspid aortic valve morphology who underwent transcatheter aortic valve replacement. Type-0 bicuspid aortic valve was identified with multidetector computed tomography scans. The technical success rate was 89.8%, and the device success rate was 81.4%. Patients were divided into a device success group and a device failure group according to Valve Academic Research Consortium- 3 criteria.ResultsWhen we compared the two groups, we found that the ellipticity index of the aortic root and the presence of bulky calcifications at the commissure were statistically different (ellipticity index 35.7 ± 1.7 vs. 29.7 ± 1.1, p = 0.018; bulky calcification at the commissure, 54.5% vs. 4.5%, p

Introduction The strategy for initiating antithrombotic therapy to prevent bioprosthetic valve thrombosis (BPVT) after transcatheter aortic valve replacement (TAVR) remains uncertain. There is still lacking evidence on the efficacy and safety of early 6 months usage of single-antiplatelet therapy (SAPT) or oral anticoagulant (OAC) after TAVR in patients without anticoagulant indications.Methods and analysis This is a multicentre, randomised controlled, open-label trial, and 650 patients undergoing TAVR from 13 top TAVR centres in China will be recruited. Each eligible participant will be randomly assigned to two groups (1:1 ratio) as (1) SAPT (aspirin 75–100 mg for 6 months) group or (2) OAC group (warfarin, therapeutic international normalised ratio at 1.8–2.5 for 6 months), both followed by sequential aspirin 75–100 mg for 6 months. Participants in both groups will be invited for three follow-up visits of 1, 6 and 12 months after discharge. We will use both the net clinical benefit endpoint (composite of all-cause mortality, myocardial infarction, stroke/transient ischaemic attacks, peripheral artery thrombosis, intracardiac thrombosis and major bleeding and disabling or life-threatening bleeding) and the BPVT endpoint evaluated by four-dimensional CT as our primary endpoints. P value of

Summary: Background: Pre-procedural computed tomography (CT) imaging assessment of the aortic valvular complex (AVC) is essential for the success of transcatheter aortic valve replacement (TAVR). However, pre-TAVR assessment is a time-intensive process, and the visual assessment of anatomical structures at the AVC shows interobserver variability. This study aimed to develop and validate a deep learning-based algorithm for pre-TAVR CT assessment and anatomical risk factor detection. Methods: This retrospective, multicentre study used AVC CT scans to develop a deep learning-based, fully automated algorithm, which was then internally and externally validated. After loading CT scans into the algorithm, it automatically assessed the essential anatomical structure data required for TAVR planning. CT scans of 1252 TAVR candidates continuously enrolled from Fuwai Hospital were used to establish training and internal validation datasets, while CT scans of 100 patients with aortic valve disease across 19 Chinese hospitals served as an external validation dataset. The validation focused on segmentation performance, localisation and measurement accuracy of key anatomical structures, detection ability of specific anatomical risk factors, and improvement in assessment efficiency. Findings: Relative to senior observers, our algorithm achieved significant consistent performance with remarkable accuracy, efficiency and ease in segmentation, localisation, and the assessment of the aortic annulus perimeter-derived diameter, and other basic planes, coronary ostia height, calcification volume, and aortic angle. The intraclass correlation coefficient values for the algorithm in the internal and external validation datasets were up to 0.998 (95% confidence interval 0.998–0.998), respectively. Furthermore, the algorithm demonstrated high alignment in detecting specific anatomical risk factors, with accuracy, sensitivity, and specificity up to 0.989 (95% CI 0.973–0.996), 0.979 (95% CI 0.936–0.995), 0.986 (95% CI 0.945–0.998), respectively. Interpretation: Our algorithm efficiently performs pre-TAVR assessments by using AVC CT imaging with accuracy comparable to senior observers, potentially improving TAVR planning in clinical practice. Funding: National Key R&D Program of China (2020YFC2008100), CAMS Innovation Fund for Medical Sciences (2022-I2M-C&T-B-044).

The integration of artificial intelligence (AI) into clinical management of aortic stenosis (AS) has redefined our approach to the assessment and management of this heterogenous valvular heart disease (VHD). While the large-scale early detection of valvular conditions is limited by socioeconomic constraints, AI offers a cost-effective alternative solution for screening by utilizing conventional tools, including electrocardiograms and community-level auscultations, thereby facilitating early detection, prevention, and treatment of AS. Furthermore, AI sheds light on the varied nature of AS, once considered a uniform condition, allowing for more nuanced, data-driven risk assessments and treatment plans. This presents an opportunity to re-evaluate the complexity of AS and to refine treatment using data-driven risk stratification beyond traditional guidelines. AI can be used to support treatment decisions including device selection, procedural techniques, and follow-up surveillance of transcatheter aortic valve replacement (TAVR) in a reproducible manner. While recognizing notable AI achievements, it is important to remember that AI applications in AS still require collaboration with human expertise due to potential limitations such as its susceptibility to bias, and the critical nature of healthcare. This synergy underpins our optimistic view of AI’s promising role in the AS clinical pathway.

Background: Aortic stenosis (AS) increases left ventricular afterload, leading to cardiac damage and heart failure (HF). Transcatheter aortic valve replacement (TAVR) is an effective therapy for AS. No inotropic agents including levosimendan have been evaluated in patients undergoing TAVR.Methods: A total of 285 patients underwent TAVR between 2014 and 2019; 210 were included in the matched analysis and 105 received 0.1 μg/kg body weight/min levosimendan immediately after the prosthesis had been successfully implanted. Medical history, laboratory tests, and echocardiography results were analyzed. Endpoints including 2-year all-cause mortality, stroke, or HF-related hospitalization, and a combination of the above were analyzed by Cox proportional hazard models.Results: The levosimendan group had no difference in 2-year mortality compared with the control group (hazard ratio [HR]: 0.603, 95% confidence interval [CI]: 0.197–1.844; p = 0.375). However, levosimendan reduced stroke or HF-related hospitalization (HR: 0.346; 95% CI: 0.135–0.884; p = 0.027) and the combined endpoint (HR: 0.459, 95% CI: 0.215–0.980; p = 0.044). After adjusting for multiple variants, levosimendan still reduced stroke or HF-related hospitalization (HR: 0.346, 95% CI: 0.134–0.944; p = 0.038).Conclusion: Prophylactic levosimendan administration immediately after valve implantation in patients undergoing TAVR can reduce stroke or HF-related hospitalization but does not lower all-cause mortality.

Background: The association between prior percutaneous coronary intervention (PCI) and prognosis after coronary artery bypass grafting (CABG) remains uncertain. We aimed to evaluate the aforementioned association in a meta-analysis. Methods: PubMed, Cochrane’s Library, and Embase databases were searched for potential studies. A random-effects model was used for the meta-analysis. Meta-regression was performed to evaluate the influence of study characteristics on the outcomes. Results: Thirty-six follow-up studies with 308,284 patients were included, and 40,892 (13.3%) patients had prior PCI. Pooled results showed that prior PCI was associated with higher risks of early (in-hospital or within 1 month) all-cause mortality [odds ratio (OR): 1.26, 95% confidence interval (CI): 1.11–1.44, p = 0.003; I 2 = 64%] and major adverse cardiovascular events (MACEs; OR: 1.36, 95% CI: 1.12–1.66, p = 0.002, I 2 = 79%), but not with late (follow-up durations from 1 to 13 years) mortality (OR: 1.03, 95% CI: 0.95–1.13, p = 0.44, I 2 = 46%) or MACEs (OR: 1.03, 95% CI: 0.97–1.09, p = 0.38, I 2 = 0%). Meta-regression showed that the study characteristics of patient number, age, sex, diabetic status, and proportion of patients with prior PCI did not affect the outcomes. Sensitivity analyses limited to multivariate studies excluding patients with acute PCI failure showed similar results (early mortality, OR: 1.25, p = 0.003; early MACE, OR: 1.50, p = 0.001; late mortality, OR: 1.03, p = 0.70). Conclusion: The current evidence, mostly from retrospective observational studies, suggests that prior PCI is related to poor early clinical outcomes, but not to late clinical outcomes, after CABG.

Street space quality assessment refers to the extraction and appropriate evaluation of the space quality information of urban streets, which is usually employed to improve the quality of urban planning and management. Compared to traditional approaches relying on expert knowledge, the advances of big data collection and analysis technologies provide an alternative for assessing street space more precisely. With street view imagery (SVI), points of interest (POI) and comment data from social media, this study evaluates street space quality from the perspective of exploring and discussing the relationship among street vitality, service facilities and built environment. Firstly, a transfer-learning-based framework is employed for SVI semantic segmentation to quantify the street built environment. Then, we use POI data to identify different urban functions that streets serve, and comment data are utilized to investigate urban vitality composition and integrate it with different urban functions associated with streets. Finally, a function-driven street space quality assessment approach is established. To examine its applicability and performance, the proposed method is experimented with data from part area in Xiamen, China. The output is compared to results based on expert opinion using the correlation analysis method. Results show that the proposed assessment approach designed in this study is in accordance with the validation data, with the overall R2 value being greater than 0.6. In particular, the proposed method shows better performance in scenic land and mixed functional streets with R2 value being greater than 0.8. This method is expected to be an efficient tool for discovering problems and optimizing urban planning and management.

Information extraction from multi-sensor remote sensing images has increasingly attracted attention with the development of remote sensing sensors. In this study, a supervised change detection method, based on the deep Siamese convolutional network with hybrid convolutional feature extraction module (OB-DSCNH), has been proposed using multi-sensor images. The proposed architecture, which is based on dilated convolution, can extract the deep change features effectively, and the character of “network in network” increases the depth and width of the network while keeping the computational budget constant. The change decision model is utilized to detect changes through the difference of extracted features. Finally, a change detection map is obtained via an uncertainty analysis, which combines the multi-resolution segmentation, with the output from the Siamese network. To validate the effectiveness of the proposed approach, we conducted experiments on multispectral images collected by the ZY-3 and GF-2 satellites. Experimental results demonstrate that our proposed method achieves comparable and better performance than mainstream methods in multi-sensor images change detection.