Peizhong Liu

ORCID: 0000-0001-8785-0195
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • AI in cancer detection
  • Video Surveillance and Tracking Methods
  • Image Enhancement Techniques
  • Radiomics and Machine Learning in Medical Imaging
  • Cervical Cancer and HPV Research
  • Advanced Multi-Objective Optimization Algorithms
  • Metaheuristic Optimization Algorithms Research
  • Advanced Vision and Imaging
  • Infrared Thermography in Medicine
  • Human Pose and Action Recognition
  • Impact of Light on Environment and Health
  • Advanced Image and Video Retrieval Techniques
  • Fetal and Pediatric Neurological Disorders
  • COVID-19 diagnosis using AI
  • Medical Imaging and Analysis
  • Infrared Target Detection Methodologies
  • Neural Networks Stability and Synchronization
  • Evolutionary Algorithms and Applications
  • Coastal wetland ecosystem dynamics
  • Advanced Image Fusion Techniques
  • Congenital Heart Disease Studies
  • Image Retrieval and Classification Techniques
  • Brain Tumor Detection and Classification
  • Tracheal and airway disorders
  • Vehicle Routing Optimization Methods

Huaqiao University
2016-2025

Jiangsu Normal University
2025

Xiamen University
2014-2024

Quanzhou Normal University
2020-2024

Chinese Medical Center
2022

Beijing Institute of Big Data Research
2019

Xiamen University of Technology
2006

Abstract Accurate glioma subtype classification is critical for the treatment management of patients with brain tumors. Developing an automatically computer-aided algorithm challenging due to many factors. One difficulties label constraint. Specifically, each case simply labeled without precise annotations lesion regions information. In this paper, we propose a novel hybrid fully convolutional neural network (CNN)-based method using both whole slide imaging (WSI) and multiparametric magnetic...

10.1038/s41598-022-09985-1 article EN cc-by Scientific Reports 2022-04-12

Underwater images suffer from serious color distortion and detail loss because of the wavelength-dependent light absorption scattering, which seriously influences subsequent underwater object detection recognition. The latest methods for image enhancement are based on deep models, focus finding a mapping function subspace to ground-truth subspace. They neglect diversity conditions leads different background colors images. In this paper, we propose Class-condition Attention Generative...

10.1109/access.2020.3003351 article EN cc-by IEEE Access 2020-01-01

Congenital heart defects (CHDs) are the most common birth defects. Recently, artificial intelligence (AI) was used to assist in CHD diagnosis. No comparison has been made among various types of algorithms that can prenatal diagnosis.Normal and abnormal fetal ultrasound images, including five standard views, were collected according International Society Ultrasound Obstetrics Gynecology (ISUOG) Practice guidelines. You Only Look Once version 5 (YOLOv5) models trained tested. An excellent...

10.1515/jpm-2023-0041 article EN Journal of Perinatal Medicine 2023-05-10

10.1007/s13246-018-0678-z article EN Australasian Physical & Engineering Sciences in Medicine 2018-09-13

Colposcopy is an essential medical examination that mainly through visual inspection for cervical epithelial tissue to preventing cancer. However, screening by artificial vision has the problems of missed diagnosis, low efficiency, and diversity. This paper proposes a deep learning-based method using multi-CNN decision feature integration classification diagnosis lesions. The proposed first uses k-means algorithm aggregate training data into specific classes in preprocessing then trained...

10.1109/access.2020.2972610 article EN cc-by IEEE Access 2020-01-01

Deep learning in ultrasound(US) imaging aims to construct foundational models that accurately reflect the modality's unique characteristics. Nevertheless, limited datasets and narrow task types have restricted this field recent years. To address these challenges, we introduce US-MTD120K, a multi-task ultrasound dataset with 120,354 real-world two-dimensional images. This covers three standard plane recognition two diagnostic tasks imaging, providing rich basis for model training evaluation....

10.1109/jbhi.2024.3382604 article EN IEEE Journal of Biomedical and Health Informatics 2024-01-01

10.1109/icassp49660.2025.10888928 article EN ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2025-03-12

Abstract Because of not needing training samples and performing the classification just according to inherent similarity data in multidimensional space, unsupervised method now gets more attention by remote sensing analyst. Duo special growth environment mangroves, field measurements is difficult be done obtain samples. Therefore provides a good adjunct way for mangroves image. This paper presents an immune network based method, which necessary define complex objective function. By...

10.21307/ijssis-2017-648 article EN International Journal on Smart Sensing and Intelligent Systems 2014-01-01
Coming Soon ...