A5100430478- AI in cancer detection
- Advanced Neural Network Applications
- Radiomics and Machine Learning in Medical Imaging
- Domain Adaptation and Few-Shot Learning
- Medical Image Segmentation Techniques
- COVID-19 diagnosis using AI
- Topic Modeling
- Advanced oxidation water treatment
- Multimodal Machine Learning Applications
- Brain Tumor Detection and Classification
- Text and Document Classification Technologies
- Adversarial Robustness in Machine Learning
- Retinal Imaging and Analysis
- Handwritten Text Recognition Techniques
- Image Retrieval and Classification Techniques
- Reliability and Maintenance Optimization
- Advanced Image Processing Techniques
- Advanced Computational Techniques and Applications
- Medical Imaging and Analysis
- Fault Detection and Control Systems
- Advanced Battery Technologies Research
- Digital Imaging for Blood Diseases
- Advanced Image and Video Retrieval Techniques
- Natural Language Processing Techniques
- Prosthetics and Rehabilitation Robotics
Harbin Institute of Technology
2011-2025
Northeastern University
2024-2025
Ningxia Medical University
2024
Guangxi University
2024
Anhui University of Science and Technology
2024
Zhejiang Institute of Communications
2024
Polytechnic University
2024
Tsinghua University
2022-2024
Huashan Hospital
2024
Fudan University
2024
Abstract The study of artificial intelligence (AI) has been a continuous endeavor scientists and engineers for over 65 years. simple contention is that human-created machines can do more than just labor-intensive work; they develop human-like intelligence. Being aware or not, AI penetrated into our daily lives, playing novel roles in industry, healthcare, transportation, education, many areas are close to the general public. believed be one major drives change socio-economical lives. In...
Retinal vessel image is an important biological information that can be used for personal identification in the social security domain, and disease diagnosis medical domain. While automatic segmentation essential, it also a challenging task because retinal vessels have complex topological structures, vary size shape. In recent years, based on deep learning technique has become mainstream method. Unfortunately, existing methods cannot make best use of global information, model complexity...
Abstract The global Coronavirus disease 2019 (COVID-19) pandemic caused by SARS-CoV-2 has affected more than eight million people. There is an urgent need to investigate how the adaptive immunity established in COVID-19 patients. In this study, we profiled immune cells of PBMCs from recovered patients with varying severity using single-cell RNA and TCR/BCR V(D)J sequencing. sequencing data revealed SARS-CoV-2-specific shuffling repertories COVID-19-induced remodeling peripheral lymphocytes....
Survey/review study Deep Learning Attention Mechanism in Medical Image Analysis: Basics and Beyonds Xiang Li 1, Minglei Pengfei Yan Guanyi Yuchen Jiang Hao Luo 1,*, Shen Yin 2 1 Department of Control Science Engineering, Harbin Institute Technology, 150001, China Mechanical Industrial Faculty Norwegian University Trondheim 7034, Norway * Correspondence: hao.luo@hit.edu.cn Received: 16 October 2022 Accepted: 25 November Published: 27 March 2023 Abstract: With the improvement hardware...
As an indispensable energy device, 18650 lithium-ion battery has widespread applications in electric vehicles. Remaining useful life (RUL) prediction of is critical for the normal operation In conventional approaches, adaptive estimation model parameters and detection capacity regeneration await further research. To adaptively estimate noise variables degradation to accurately detect regeneration, this article proposes a novel expectation maximization-unscented particle filter-Wilcoxon rank...
Accurate remaining useful life (RUL) prediction of lithium-ion batteries is critical for energy supply systems. In conventional data-driven RUL approaches, the battery's degradation mechanism difficult into incorporate in prediction. Furthermore, there are notable limitations reflecting significance different time instances, and uncertainty process. Consequently, a novel data-model interactive approach based on particle filter-temporal attention mechanism-bidirectional gated recurrent unit...
Convolutional neural networks (CNN) have successfully been employed to tackle several remote sensing tasks such as image classification and show better performance than previous techniques. For the radar imaging community, a natural question is: Can CNN be introduced enhance its performance? This letter gives an affirmative answer this question. We first propose processing framework by which complex-valued (CV-CNN) is used imaging. Then we introduce two modifications CV-CNN adapt it tasks....
Sarcasm is a peculiar form and sophisticated linguistic act to express the incongruity of someone's implied sentiment expression, which pervasive phenomenon in social media platforms. Compared with sarcasm detection purely on texts, multi-modal more adapted rapidly growing platforms, where people are interested creating messages. When focusing for tweets consisting texts images Twitter, significant clue improving performance evolves into how determine relations between images. In this paper,...
Abstract Deep learning techniques have promoted the rise of artificial intelligence (AI) and performed well in computer vision. Medical image analysis is an important application deep learning, which expected to greatly reduce workload doctors, contributing more sustainable health systems. However, most current AI methods for medical are based on supervised requires a lot annotated data. The number images available usually small acquisition annotations expensive process. Generative...
Zero-shot stance detection (ZSSD) aims to detect the for an unseen target during inference stage. In this paper, we propose a joint contrastive learning (JointCL) framework, which consists of and target-aware prototypical graph learning. Specifically, strategy is employed better generalize features targets. Further, build each instance learn target-based representation, in prototypes are deployed as bridge share structures between known targets ones. Then novel devised reasoning ability...
Knee segmentation and landmark localization from 3D MRI are two significant tasks for diagnosis treatment of knee diseases. With the development deep learning, Convolutional Neural Network (CNN) based methods have become mainstream. However, existing CNN mostly single-task methods. Due to complex structure bone, cartilage ligament in knee, it is challenging complete or alone. And establishing independent models all will bring difficulties surgeon's clinical using. In this paper, a Spatial...
In this paper, we present a computer‐aided detection (CAD) method to extract and use internal features reduce false positive (FP) rate generated by surface‐based measures on the inner colon wall in computed tomographic (CT) colonography. Firstly, new shape description global curvature , which can provide an overall of wall, is introduced improve suspicious patches whose geometrical are similar that colonic polyps. By ray‐driven edge finder, volume each detected patch extracted as fitted...