A5101605415- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Colorectal Cancer Screening and Detection
- Neural Networks and Applications
- Advanced Memory and Neural Computing
- Systemic Sclerosis and Related Diseases
- COVID-19 diagnosis using AI
- Interstitial Lung Diseases and Idiopathic Pulmonary Fibrosis
- Image Retrieval and Classification Techniques
- Lung Cancer Diagnosis and Treatment
- Eosinophilic Disorders and Syndromes
- Digital Imaging for Blood Diseases
- EEG and Brain-Computer Interfaces
Taiyuan University of Technology
2023-2024
Ruhr University Bochum
2023
Cairns Hospital
2019
Abstract Novel methods are required to enhance lung cancer detection, which has overtaken other cancer-related causes of death as the major cause mortality. Radiologists have long-standing for locating nodules in patients with cancer, such computed tomography (CT) scans. must manually review a significant amount CT scan pictures, makes process time-consuming and prone human error. Computer-aided diagnosis (CAD) systems been created help radiologists their evaluations order overcome these...
The emergence of image-based systems to improve diagnostic pathology precision, involving the intent label sets or bags instances, greatly hinges on Multiple Instance Learning for Whole Slide Images(WSIs). Contemporary works have shown excellent performance a neural network in MIL settings. Here, we examine graph-based model facilitate end-to-end learning and sample suitable patches using tile-based approach. We propose MIL-GNN employ Variational Auto-encoder with Gaussian mixture discover...
Abstract Background Systemic sclerosis (SSc) refers to an autoimmune fibrosing disorder with high disease burden and mortality. The prevalence of 23/100 000 in South Australia (SA) is among the highest documented, but anecdotally it higher still Cairns. Aims To ascertain SSc Cairns surrounding regions, compare demographic clinical characteristics patients those SA. Methods Patients were ascertained through hospital records by referrals from specialist physicians region. These interviewed...
Abstract This paper presents a software-based Python framework for developing future AI-enhanced end-to-end Brain-Computer-Interfaces (BCI). contains modules from the emulated analogue front-end and neural signal pre-processing invasive applications. These can be assembled into several pipeline versions evaluation benchmarking. The aim of this is to accelerate development BCIs due system-wide optimizations in order set requirements hardware without prior knowledge on basis accuracy (recall...
Introduction Pathologists rely on whole slide images (WSIs) to diagnose cancer by identifying tumor cells and subtypes. Deep learning models, particularly weakly supervised ones, classify WSIs using image tiles but may overlook false positives negatives due the heterogeneous nature of tumors. Both cancerous healthy can proliferate in patterns that extend beyond individual tiles, leading errors at tile level result inaccurate tumor-level classifications. Methods To address this limitation, we...