A5049444898- Medical Imaging Techniques and Applications
- Advanced Image Processing Techniques
- Gene expression and cancer classification
- Advanced MRI Techniques and Applications
- Privacy-Preserving Technologies in Data
- Multimodal Machine Learning Applications
- Bioinformatics and Genomic Networks
- Electric Motor Design and Analysis
- Domain Adaptation and Few-Shot Learning
- Brain Tumor Detection and Classification
- Sparse and Compressive Sensing Techniques
- Magnetic Bearings and Levitation Dynamics
- Medical Image Segmentation Techniques
- Radiomics and Machine Learning in Medical Imaging
- Machine Learning in Bioinformatics
- Image and Signal Denoising Methods
- COVID-19 diagnosis using AI
- Advanced Neural Network Applications
- AI in cancer detection
- Genomics and Chromatin Dynamics
- Image Retrieval and Classification Techniques
- Advanced Vision and Imaging
- Advanced Image and Video Retrieval Techniques
- Sensorless Control of Electric Motors
- Advanced Image Fusion Techniques
Ministry of Education of the People's Republic of China
2022-2024
Northwest University
2022-2024
Agency for Science, Technology and Research
2023-2024
Harbin Institute of Technology
2019-2024
Institute of High Performance Computing
2023-2024
Nanjing Normal University
2010-2024
Jiangsu Key Laboratory of 3D Printing Equipment and Manufacturing
2015-2022
Anhui Medical University
2022
Weifang University of Science and Technology
2022
Inception Institute of Artificial Intelligence
2021
ABSTRACT Automated and accurate classification of MR brain images is crucially importance for medical analysis interpretation. We proposed a novel automatic system based on particle swarm optimization (PSO) artificial bee colony (ABC), with the aim distinguishing abnormal brains from normal in MRI scanning. The method used stationary wavelet transform (SWT) to extract features images. SWT translation‐invariant performed well even image suffered slight translation. Next, principal component...
Accelerated multi-modal magnetic resonance (MR) imaging is a new and effective solution for fast MR imaging, providing superior performance in restoring the target modality from its undersampled counterpart with guidance an auxiliary modality. However, existing works simply combine as prior information, lacking in-depth investigations on potential mechanisms fusing different modalities. Further, they usually rely convolutional neural networks (CNNs), which limited by intrinsic locality...
Federated learning (FL) can be used to improve data privacy and efficiency in magnetic resonance (MR) image reconstruction by enabling multiple institutions collaborate without needing aggregate local data. However, the domain shift caused different MR imaging protocols substantially degrade performance of FL models. Recent techniques tend solve this enhancing generalization global model, but they ignore domain-specific features, which may contain important information about device...
Super-resolving the magnetic resonance (MR) image of a target contrast under guidance corresponding auxiliary contrast, which provides additional anatomical information, is new and effective solution for fast MR imaging. However, current multi-contrast super-resolution (SR) methods tend to concatenate different contrasts directly, ignoring their relationships in clues, e.g., high-and low-intensity regions. In this study, we propose separable attention network (comprising high-intensity...
Acquiring sufficient ground-truth supervision to train deep visual models has been a bottleneck over the years due data-hungry nature of learning. This is exacerbated in some structured prediction tasks, such as semantic segmentation, which require pixel-level annotations. work addresses weakly supervised segmentation (WSSS), with goal bridging gap between image-level annotations and segmentation. To achieve this, we propose, for first time, novel group-wise learning framework WSSS. The...
Principal component analysis (PCA) has been used to study the pathogenesis of diseases. To enhance interpretability classical PCA, various improved PCA methods have proposed date. Among these, a typical method is so-called sparse which focuses on seeking loadings. However, performance these still far from satisfactory due their limitation using unsupervised learning methods; moreover, class ambiguity within sample high. overcome this problem, paper developed new method, named supervised...
Federated Magnetic Resonance Imaging (MRI) reconstruction enables multiple hospitals to collaborate distributedly without aggregating local data, thereby protecting patient privacy. However, the data heterogeneity caused by different MRI protocols, insufficient training and limited communication bandwidth inevitably impair global model convergence updating. In this paper, we propose a new algorithm, FedPR, learn federated visual prompts in null space of prompt for reconstruction. FedPR is...
The goal of Camouflaged object detection (COD) is to detect objects that are visually embedded in their surroundings. Existing COD methods only focus on detecting camouflaged from seen classes, while they suffer performance degradation unseen classes. However, a real-world scenario, collecting sufficient data for classes extremely difficult and labeling them requires high professional skills, thereby making these not applicable. In this paper, we propose new zero-shot framework (termed as...
Magnetic resonance (MR) image acquisition is an inherently prolonged process, whose acceleration has long been the subject of research. This commonly achieved by obtaining multiple undersampled images, simultaneously, through parallel imaging. In this article, we propose dual-octave network (DONet), which capable learning multiscale spatial-frequency features from both real and imaginary components MR data, for fast reconstruction. More specifically, our DONet consists a series convolutions...
Benefiting from prompt tuning, recent years have witnessed the promising performance of pre-trained vision-language models, e.g., CLIP, on versatile downstream tasks. In this paper, we focus a particular setting learning adaptive prompts fly for each test sample an unseen new domain, which is known as test-time tuning (TPT). Existing TPT methods typically rely data augmentation and confidence selection. However, conventional techniques, random resized crops, suffers lack diversity, while...
Abstract Surgical video workflow analysis has made intensive development in computer-assisted surgery by combining deep learning models, aiming to enhance surgical scene and decision-making. However, previous research primarily focused on coarse-grained of videos, e.g., phase recognition, instrument triplet recognition that only considers relationships within triplets. In order provide a more comprehensive fine-grained this work focuses accurately identifying triplets < , verb target >...
The rapid adoption of Artificial Intelligence (AI) in medical imaging raises fairness and privacy concerns across demographic groups, especially diagnosis treatment decisions. While federated learning (FL) offers decentralized preservation, current frameworks often prioritize collaboration over group fairness, risking healthcare disparities. Here we present FlexFair, an innovative FL framework designed to address both challenges. FlexFair incorporates a flexible regularization term...
In modern molecular biology, the hotspots and difficulties of this field are identifying characteristic genes from gene expression data. Traditional reconstruction-error-minimization model principal component analysis (PCA) as a matrix decomposition method uses quadratic error function, which is known sensitive to outliers noise. Hence, it necessary learn good PCA when noise exist. paper, we develop novel enforcing P-norm on function graph-Laplacian regularization term for problem, called...
Magnetic resonance (MR) image acquisition is an inherently prolonged process, whose acceleration by obtaining multiple undersampled images simultaneously through parallel imaging has always been the subject of research. In this paper, we propose Dual-Octave Convolution (Dual-OctConv), which capable learning multi-scale spatial-frequency features from both real and imaginary components, for fast MR reconstruction. By reformulating complex operations using octave convolutions, our model shows...
MET exon 14 skipping mutation (METex14m) is rare and occurs in approximately 1-4% of all non-small cell lung cancer (NSCLC) patients 2.8% resected stage I-III NSCLC patients. Savolitinib an oral, potent highly selective type Ib inhibitor, which has been shown to be promising activity acceptable safety profile with advanced harboring METex14m. Most recently, many studies have probing into the feasibility efficacy target therapy for perioperative application NSCLC. Interestingly, there are...
Video super-resolution (VSR) aiming to reconstruct a high-resolution (HR) video from its low-resolution (LR) counterpart has made tremendous progress in recent years. However, it remains challenging deploy existing VSR methods real-world data with complex degradations. On the one hand, there are few well-aligned datasets, especially large scale factors, which limits development of tasks. other alignment algorithms perform poorly for videos, leading unsatisfactory results. As an attempt...
Thanks to its powerful ability depict high-resolution anatomical information, magnetic resonance imaging (MRI) has become an essential non-invasive scanning technique in clinical practice. However, excessive acquisition time often leads the degradation of image quality and psychological discomfort among subjects, hindering further popularization. Besides reconstructing images from undersampled protocol itself, multi-contrast MRI protocols bring promising solutions by leveraging additional...
It is of great importance to early detect abnormal brains, in order save social resources.However, potential wavelet decomposition not fully explored and widely used.The wavelet-energy was a successful feature descriptor that achieved excellent performance various applications; hence, we propose based new approach for automated classification MR human brain images.The consisted three-stage system, including decomposition, energy extraction, support vector machines.The results proposed showed...