In this paper, a novel semi-supervised segmentation framework based on a spot-divergence supervoxelization of multi-sensor fusion data is proposed for autonomous forest machine (AFMs) applications in complex environments. Given the multi-sensor measuring system, our framework addresses three successive steps: firstly, the relationship of multi-sensor coordinates is jointly calibrated to form higher-dimensional fusion data. Then, spot-divergence supervoxels representing the size-change property are given to produce feature vectors covering comprehensive information of multi-sensors at a time. Finally, the Gaussian density peak clustering is proposed to segment supervoxels into sematic objects in the semi-supervised way, which non-requires parameters preset in manual. It is demonstrated that the proposed framework achieves a balancing act both for supervoxel generation and sematic segmentation. Comparative experiments show that the well performance of segmenting various objects in terms of segmentation accuracy (F-score up to 95.6%) and operation time, which would improve intelligent capability of AFMs.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6165460 | PMC |
| http://dx.doi.org/10.3390/s18093061 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Impact of Recent Translational and Therapeutic Developments on Clinical Course of BCR::ABL1-Positive and -Negative Myeloproliferative Neoplasms.
Hematol Oncol
January 2025
University of California Irvine, Irvine, California, USA.
Despite the study of BCR::ABL1-positive and -negative myeloproliferative neoplasms (MPNs) providing seminal insights into cancer biology, tumor evolution and precision oncology over the past half century, significant challenges remain. MPNs are clonal hematopoietic stem cell-derived neoplasms with heterogenous clinical phenotypes and a clonal architecture which impacts the often-complex underlying genetics and microenvironment. The major driving molecular abnormalities have been well characterized, but debate on their role as disease-initiating molecular lesions continues.
View Article and Find Full Text PDF[Clinical characteristics and prognosis of acute erythroleukemia in children].
Zhongguo Dang Dai Er Ke Za Zhi
January 2025
Department of Children's Hematology and Oncology, First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, China.
Objectives: To investigate the clinical characteristics and prognosis of acute erythroleukemia (AEL) in children.
Methods: A retrospective analysis was conducted on the clinical data, treatment, and prognosis of 8 children with AEL treated at the First Affiliated Hospital of Zhengzhou University from January 2013 to December 2023.
Results: Among the 7 patients with complete bone marrow morphological analysis, 4 exhibited trilineage dysplasia, with a 100% incidence of erythroid dysplasia (7/7), a 71% incidence of myeloid dysplasia (5/7), and a 57% incidence of megakaryocytic dysplasia (4/7).
MGATAF: multi-channel graph attention network with adaptive fusion for cancer-drug response prediction.
BMC Bioinformatics
January 2025
School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, 611756, Sichuan, China.
Background: Drug response prediction is critical in precision medicine to determine the most effective and safe treatments for individual patients. Traditional prediction methods relying on demographic and genetic data often fall short in accuracy and robustness. Recent graph-based models, while promising, frequently neglect the critical role of atomic interactions and fail to integrate drug fingerprints with SMILES for comprehensive molecular graph construction.
View Article and Find Full Text PDFThe role of MEGF10 in myoblast fusion and hypertrophic response to overload of skeletal muscle.
J Muscle Res Cell Motil
January 2025
School of Molecular and Cellular Biology, University of Leeds, Leeds, LS2 9JT, UK.
Biallelic mutations in multiple EGF domain protein 10 (MEGF10) gene cause EMARDD (early myopathy, areflexia, respiratory distress and dysphagia) in humans, a severe recessive myopathy, associated with reduced numbers of PAX7 positive satellite cells. To better understand the role of MEGF10 in satellite cells, we overexpressed human MEGF10 in mouse H-2k-tsA58 myoblasts and found that it inhibited fusion. Addition of purified extracellular domains of human MEGF10, with (ECD) or without (EGF) the N-terminal EMI domain to H-2k-tsA58 myoblasts, showed that the ECD was more effective at reducing myoblast adhesion and fusion by day 7 of differentiation, yet promoted adhesion of myoblasts to non-adhesive surfaces, highlighting the importance of the EMI domain in these behaviours.
View Article and Find Full Text PDFPerformance of MR fusion biopsy, systematic biopsy and combined biopsy on prostate cancer detection rate in 1229 patients stratified by PI-RADSv2 score on 3T multi-parametric MRI.
Abdom Radiol (NY)
January 2025
University of California, Los Angeles, Los Angeles, USA.
Purpose: We analyzed the additional value of systematic biopsy (SB) to MR-Ultrasound fusion biopsy (MRgFbx) for detection of clinically significant prostate cancer (csPCa), as increased sampling may cause increased morbidity.
Materials And Methods: This retrospective study cohort was comprised of 1229 biopsy sessions between July 2016 and May 2020 in men who had a Prostate Imaging-Reporting and Data System (PI-RADSv2) category ≥ 3 lesion on 3 Tesla multiparametric MRI (3TmpMRI) and subsequent combined biopsy (CB; MRgFbx and SB) for suspected prostate cancer (PCa). Cancer detection rates (CDR) were calculated for CB, MRgFbx and SB in the study cohort and sub-cohorts stratified by biopsy history and PI-RADSv2 category.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!