A5091564313- Gastrointestinal Bleeding Diagnosis and Treatment
- AI in cancer detection
- Urological Disorders and Treatments
- Medical Imaging and Analysis
- Pelvic and Acetabular Injuries
- Video Analysis and Summarization
- Fetal and Pediatric Neurological Disorders
- Radiomics and Machine Learning in Medical Imaging
- Colorectal Cancer Screening and Detection
- Retinal Imaging and Analysis
- Music and Audio Processing
- Image Processing Techniques and Applications
- Medical Image Segmentation Techniques
- Advanced Radiotherapy Techniques
- Advanced Neural Network Applications
- Mycobacterium research and diagnosis
- Optical Systems and Laser Technology
- Advanced Algorithms and Applications
- Face and Expression Recognition
- Autopsy Techniques and Outcomes
- Image Retrieval and Classification Techniques
- Advanced Image Processing Techniques
- Advanced Data Compression Techniques
- Advanced Vision and Imaging
- Generative Adversarial Networks and Image Synthesis
Chongqing University of Technology
2023-2024
Chongqing University
2011-2021
Accurate medical image segmentation is essential for clinical quantification, disease diagnosis, treatment planning and many other applications. Both convolution-based transformer-based u-shaped architectures have made significant success in various tasks. The former can efficiently learn local information of images while requiring much more image-specific inductive biases inherent to convolution operation. latter effectively capture long-range dependency at different feature scales using...
Video summarization mainly aims to produce a compact, short, informative, and representative synopsis of raw videos, which is great importance for browsing, analyzing, understanding video content. Dominant approaches are generally based on recurrent or convolutional neural networks, even recent encoder-only transformers. We propose using full transformer as an alternative architecture perform summarization. The with encoder-decoder structure, specifically designed handling sequence...
Wireless capsule endoscopy (WCE) plays an important role in the diagnosis of gastrointestinal diseases. However, it is very time-consuming and fatiguing for a physician to review large number WCE images. Some methods address this problem have recently been presented. these generally employ classification algorithms discriminate abnormal from normal images, which do not localize, recognize, or detect patterns We sought identify better method pattern detection. In paper, convolutional neural...
Face recognition is an important research field of pattern recognition.Up to now,it caused researchers great concern from these fields,such as recognition,computer vision,and physiology,and so on.Various algorithms have been proposed. Generally,we can make sure that the performance face system determined by how extract feature vector exactly and classify them into a class accurately.Therefore,it necessary for us pay close attention extractor classifier.In this paper, in order raise...
Abstract Objectives Respiratory motion-induced displacement of internal organs poses a significant challenge in image-guided radiation therapy, particularly affecting liver landmark tracking accuracy. Methods Addressing this concern, we propose self-supervised method for robust long ultrasound sequences. Our approach leverages Siamese-based context-aware correlation filter network, trained by using the consistency loss between forward and back verification. By effectively utilizing both...
Pubic symphysis-fetal head segmentation in transperineal ultrasound images plays a critical role for the assessment of fetal descent and progression. Existing transformer methods based on sparse attention mechanism use handcrafted static patterns, which leads to great differences terms performance specific datasets. To address this issue, we introduce dynamic, query-aware image segmentation. Specifically, propose novel method, named BRAU-Net solve pubic task paper. The method adopts...
Segmentation of the fetal and maternal structures, particularly intrapartum ultrasound imaging as advocated by International Society Ultrasound in Obstetrics Gynecology (ISUOG) for monitoring labor progression, is a crucial first step quantitative diagnosis clinical decision-making. This requires specialized analysis obstetrics professionals, task that i) highly time- cost-consuming ii) often yields inconsistent results. The utility automatic segmentation algorithms biometry has been proven,...
In recent years, significant progress has been made in tumor segmentation within the field of digital pathology. However, variations organs, tissue preparation methods, and image acquisition processes can lead to domain discrepancies among pathology images. To address this problem, paper, we use Rein, a fine-tuning method, parametrically efficiently fine-tune various vision foundation models (VFMs) for MICCAI 2024 Cross-Organ Cross-Scanner Adenocarcinoma Segmentation (COSAS2024). The core...