A5100689910- Advanced Neural Network Applications
- Medical Image Segmentation Techniques
- Domain Adaptation and Few-Shot Learning
- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Phonocardiography and Auscultation Techniques
- ECG Monitoring and Analysis
- Generative Adversarial Networks and Image Synthesis
- Brain Tumor Detection and Classification
- COVID-19 diagnosis using AI
- Advanced Image and Video Retrieval Techniques
- Digital Imaging for Blood Diseases
- EEG and Brain-Computer Interfaces
- Multimodal Machine Learning Applications
Zhejiang University of Science and Technology
2022-2023
Lenovo (China)
2021-2022
Institute of Computing Technology
2020
Chinese Academy of Sciences
2020
Convolutional neural networks (CNNs) have been successfully applied to various fields. However, CNNs' overparameterization requires more memory and training time, making it unsuitable for some resource-constrained devices. To address this issue, filter pruning as one of the most efficient ways was proposed. In article, we propose a feature-discrimination-based importance criterion, uniform response criterion (URC), key component pruning. It converts maximum activation responses into...
Intestinal parasitic infections, as a leading causes of morbidity worldwide, still lacks time-saving, high-sensitivity and user-friendly examination method. The development deep learning technique reveals its broad application potential in biological image. In this paper, we apply several object detectors such YOLOv5 variant cascadeRCNNs to automatically discriminate eggs microscope images. Through specially-designed optimization including raw data augmentation, model ensemble, transfer test...
Automatic brain tumor segmentation from multi-modality Magnetic Resonance Images (MRI) using deep learning methods plays an important role in assisting the diagnosis and treatment of tumor. However, previous mostly ignore latent relationship among different modalities. In this work, we propose a novel end-to-end Modality-Pairing method for segmentation. Paralleled branches are designed to exploit modality features series layer connections utilized capture complex relationships abundant...
Automated liver tumor segmentation from computed tomography (CT) images is a necessary prerequisite in the interventions of hepatic abnormalities and surgery planning. However, accurate remains challenging due to large variability sizes inhomogeneous texture. Recent advances based on fully convolutional network (FCN) for medical image drew success learning discriminative pyramid features. In this paper, we propose decoupled correlation (DPC-Net) that exploits attention mechanisms leverage...
Recently, the dominant DETR-based approaches apply central-concept spatial prior to accelerate Transformer detector convergency. These methods gradually refine reference points center of target objects and imbue object queries with updated central information for spatially conditional attention. However, centralizing may severely deteriorate queries' saliency confuse detectors due indiscriminative prior. To bridge gap between salient detectors, we propose SAlient Point-based DETR (SAP-DETR)...
Deep learning models are notoriously data-hungry. Thus, there is an urging need for data-efficient techniques in medical image analysis, where well-annotated data costly and time consuming to collect. Motivated by the recently revived "Copy-Paste" augmentation, we propose TumorCP, a simple but effective object-level augmentation method tailored tumor segmentation. TumorCP online stochastic, providing unlimited possibilities tumors' subjects, locations, appearances, as well morphologies....