Pengju Lyu

ORCID: 0009-0004-0863-8110
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Radiomics and Machine Learning in Medical Imaging
  • AI in cancer detection
  • Advanced Neural Network Applications
  • Medical Imaging and Analysis
  • Blockchain Technology Applications and Security
  • Advanced Radiotherapy Techniques
  • Coronary Interventions and Diagnostics
  • Computational and Text Analysis Methods
  • Retinal Imaging and Analysis
  • Dental Radiography and Imaging
  • COVID-19 diagnosis using AI
  • Medical Image Segmentation Techniques
  • Image Retrieval and Classification Techniques
  • Hemodynamic Monitoring and Therapy
  • Cerebrovascular and Carotid Artery Diseases
  • Software-Defined Networks and 5G
  • Surgical Simulation and Training
  • Cloud Computing and Resource Management

University of Macau
2024

City University of Macau
2023

Abstract Precise liver tumors and associated organ segmentation hold immense value for surgical radiological intervention, enabling anatomical localization pre-operative planning intra-operative guidance. Modern deep learning models medical image have evolved from convolution neural networks to transformer architectures, significantly boosting global context understanding. However, accurate delineation especially of hepatic lesions remains an enduring challenge due models’ predominant focus...

10.1088/2632-2153/ad4c38 article EN cc-by Machine Learning Science and Technology 2024-05-15

Non-contrast CT (NCCT) imaging may reduce image contrast and anatomical visibility, potentially increasing diagnostic uncertainty. In contrast, contrast-enhanced (CECT) facilitates the observation of regions interest (ROI). Leading generative models, especially conditional diffusion model, demonstrate remarkable capabilities in medical modality transformation. Typical models commonly generate images with guidance segmentation labels for modal Limited access to authentic its low cardinality...

10.48550/arxiv.2406.13977 preprint EN arXiv (Cornell University) 2024-06-19

ABSTRACT Background Percutaneous puncture procedures, guided by image‐guided robotic‐assisted intervention (IGRI) systems, are susceptible to disruptions in patients' respiratory rhythm due factors such as pain and psychological distress. Methods We developed an IGRI system with a coded structured light camera binocular camera. Our incorporates dual‐pathway deep learning networks, combining convolutional long short‐term memory (ConvLSTM) point (PointLSTM) modules for real‐time signal...

10.1002/rcs.70017 article EN International Journal of Medical Robotics and Computer Assisted Surgery 2024-12-01

Recently, the extensive applications of blockchain technology in fields like financial exchanges, insurance, Logistics and healthcare has proven to be pragmatic revolutionary. In order enable have a more complete development space, Blockchain-based Service Network (BSN) was proposed. It integrates developers, portal, cloud resources framework provide basic environment for applications. Researches on its security kept place with advent technology, while potential issues BSN remain largely...

10.54254/2755-2721/6/20230463 article EN cc-by Applied and Computational Engineering 2023-06-14

Coronary artery segmentation in digital substraction angiography, as one of the most critical steps percutaneous coronary intervention (PCI) procedures, has strict accuracy requirements for clinical diagnosis. However, previous studies have seldom considered topological structure and connectivity their inherent tubular structures, resulting limited improvement at distal ends arteries. To address this issue, we propose a novel multi-scale aggregation block consisting channel- wise dynamic...

10.1145/3622896.3622913 article EN 2023-08-25
Coming Soon ...