A5089400844- Coconut Research and Applications
- Medical Image Segmentation Techniques
- Advanced Neural Network Applications
- Digital Games and Media
- Image and Signal Denoising Methods
- Prostate Cancer Diagnosis and Treatment
- Image Processing Techniques and Applications
- Date Palm Research Studies
- Urologic and reproductive health conditions
- Infrared Thermography in Medicine
- Advanced Image Processing Techniques
- Radiomics and Machine Learning in Medical Imaging
- Medical Imaging and Analysis
- Advanced Optical Imaging Technologies
- Brain Tumor Detection and Classification
- Oil Palm Production and Sustainability
- Cardiovascular Disease and Adiposity
- Prostate Cancer Treatment and Research
- Educational Technology and Pedagogy
- Advanced Battery Technologies Research
- Identification and Quantification in Food
Central South University
2022-2025
Hainan Medical University
2024
Chongqing Vocational Institute of Engineering
2024
Hainan University
2024
Haikou City People's Hospital
2023
The primary objective of interactive medical image segmentation systems is to achieve more precise outcomes with reduced human intervention. This endeavor holds significant clinical importance for both pre-diagnostic pathological assessments and prognostic recovery. Among the various interaction methods available, click-based interactions stand out as an intuitive straightforward approach compared alternatives such graffiti, bounding boxes, extreme points. To improve model's ability...
In prostate 3D MRI image segmentation methods, it is usually necessary to annotate each slice, and these annotations are generally time-consuming specialized. this study, we generate pseudo-labels using an annotation method with one foreground seed point six edge relaxation points. We design a weakly supervised semantic learning framework, ACEA-Net. This framework solves the under-expansion problem due lack of affinity pixels in pseudo-labeling generation process. Seed Cluster Geodesic...
This study trains a U-shaped fully convolutional neural network (U-Net) model based on peripheral contour measures to achieve rapid, accurate, automated identification and segmentation of periprostatic adipose tissue (PPAT).
Due to the unique structure of coconuts, their cultivation heavily relies on manual experience, making it difficult accurately and timely observe internal characteristics. This limitation severely hinders optimization coconut breeding. To address this issue, we propose a new model based improved architecture Deeplab V3+. We replace original ASPP(Atrous Spatial Pyramid Pooling) with dense atrous spatial pyramid pooling module introduce CBAM(Convolutional Block Attention Module). approach...
Computed tomography (CT) is a non-invasive examination tool that widely used in medicine. In this study, we explored its value visualizing and quantifying coconut.Twelve coconuts were scanned using CT for three months. Axial images of the obtained dual-source scanner. postprocessing process, various three-dimensional models created by volume rendering (VR), plane sections different angles through multiplanar reformation (MPR). The morphological parameters values exocarp, mesocarp, endocarp,...
<title>Abstract</title> Video stands as the paramount medium for humans to perceive world, and within this realm, video defocus deblurring (VDD) emerges a distinct blurring phenomenon, from both single image (SIDD) motion-induced blurring. Despite its significance, VDD remains an underexplored territory in academic research. In study, we introduce novel neural network architecture, grounded multi-scale recurrent framework, tailored VDD. This architecture meticulously propagates information...
Background The study aimed to observe the internal structure of coconuts from two locations (coastal and non-coastal) using computed tomography (CT). Methods Seventy-six mature were collected Wenchang Ding’an cities in Hainan Province. These scanned four times CT, with a two-week interval between each scan. CT data post-processed reconstruct two-dimensional slices three-dimensional models. density morphological parameters coconut structures measured, differences these characteristics groups...
Coconut is one of the largest seeded fruits in world. While its hard shell provides some protection for growth and development coconuts, it also hinders observation internal structural changes quality inspection during early seedling selection. The cultivation coconut seedlings takes about a year, several years them to grow into mature trees. Therefore, selection coconuts crucial. To address issue difficult features, we utilized CT scans non-destructive scanning obtain images at different...
Because of the special structure coconut, it is difficult to observe development its internal accurately, so research on coconut organs blank at present, which leads quality and can not be guaranteed. To solve this problem, we use CT carry out non-destructive scanning, obtain different kinds, stages image images. In paper, a novel YOLO V5 model was designed detect Coconut haustorium plumule, are key structures Coconut. order improve detection accuracy haustoriums buds, an ASFF mechanism GAM...