A5100459390- AI in cancer detection
- Infrared Target Detection Methodologies
- Radiomics and Machine Learning in Medical Imaging
- Advanced Image Fusion Techniques
- Colorectal Cancer Screening and Detection
- Advanced Image and Video Retrieval Techniques
- Calibration and Measurement Techniques
- Satellite Image Processing and Photogrammetry
- Image Retrieval and Classification Techniques
- Optical measurement and interference techniques
- Genetic Associations and Epidemiology
- Advanced Measurement and Detection Methods
- Advanced Neural Network Applications
- Remote-Sensing Image Classification
- Optical Systems and Laser Technology
- Remote Sensing and Land Use
- Robotics and Sensor-Based Localization
- Image Enhancement Techniques
- Genetics and Neurodevelopmental Disorders
- Epigenetics and DNA Methylation
- Medical Image Segmentation Techniques
- Advanced Vision and Imaging
- CCD and CMOS Imaging Sensors
- Digital Imaging for Blood Diseases
- Antenna Design and Analysis
University of Chinese Academy of Sciences
2012-2025
Northeast Forestry University
2025
China Medical University
2020-2024
Chinese Academy of Sciences
2008-2024
Huainan Normal University
2024
Changchun University of Science and Technology
2023-2024
Guangdong University of Foreign Studies
2024
Beijing University of Technology
2023
Shanghai Institute of Technical Physics
2019-2023
Liaoning Cancer Hospital & Institute
2020-2023
Abstract Genome-wide association studies (GWASs) have identified over 180 independent schizophrenia risk loci. Nevertheless, how the variants in reported loci confer susceptibility remains largely unknown. Here we systematically investigate gene regulatory mechanisms underpinning through integrating data from functional genomics (including 30 ChIP-Seq experiments) and position weight matrix (PWM). We identify 132 single nucleotide polymorphisms (SNPs) that disrupt transcription factor...
Weakly supervised object detection aims at learning precise detectors, given image category labels. In recent prevailing works, this problem is generally formulated as a multiple instance module guided by an classification loss. The bounding box assumed to be the one contributing most among all proposals. However, region also likely crucial part or supporting context of object. To obtain more accurate detector, in work we propose novel end-to-end weakly approach, where newly introduced...
Background: Breast cancer has the highest prevalence among all cancers in women globally. The classification of histopathological images diagnosis breast is an area clinical concern. In computer-aided diagnosis, most traditional models use a single network to extract features, although this approach significant limitations. Moreover, many networks are trained and optimized on patient-level datasets, ignoring lower-level data labels. Method: This paper proposes deep ensemble model based...
Aerial moving target detection is an important technology to ensure the safety of civil flight and airspace. Different from ground-based active radar space-based visible imager, on-orbit thermal infrared sensor (TIS), which records temperature difference between background targets, proved be a stable means monitoring aircraft throughout day. Limited by low spatial resolution dataset scarcity, there are few existing research based on TIS. In this paper, new multi-model joint method detect...
Space probes are always obstructed by floating objects in the atmosphere (clouds, haze, rain, etc.) during imaging, resulting loss of a significant amount detailed information remote sensing images and severely reducing quality images. To address problem images, we propose an end-to-end detail enhancement network to directly remove haze restore image, improve image. In order enhance designed multi-scale unit stepped attention unit, respectively. The former extracts from integrates global...
Colorectal cancer is a common fatal malignancy, the fourth most in men, and third women worldwide. Timely detection of its early stages essential for treating disease. Currently, there lack datasets histopathological image segmentation colorectal cancer, which often hampers assessment accuracy when computer technology used to aid diagnosis.This present study provided new publicly available Enteroscope Biopsy Histopathological Hematoxylin Eosin Image Dataset Segmentation Tasks (EBHI-Seg). To...
High-accuracy sea surface temperature (SST) retrieval near nuclear power plants (NPPs) is one of the most significant indicators for evaluating marine ecological environment quality, monitoring real-time situation thermal discharge, and supporting planning decisions. However, complex computations, inaccessible vertical profile atmosphere, uncertainty atmospheric data increase error SST retrieval. Additionally, influenced by their low spatial resolution, widely used AVHRR/MODIS remote sensing...
Wide-swath and high-resolution Thermal infrared (TIR) data are limited by the mutual constraint between swath resolution. In this paper, we propose a whisk-broom imaging method with long-linear-array (LLA) 4-stage TDI detector (a total of 2048 pixels along splicing direction) high-precision one-dimensional scanning mirror to achieve 30 m resolution 300 km swath. And it is being implemented in first SDGs satellite (SATSAT-1) thermal spectrometer (TIS). Specially, integration time system speed...
The detection of new information in a document stream is an important component many potential applications. In this paper, novelty approach based on the identification sentence level patterns proposed. Given user's need, some sentences such as combinations query words, named entities and phrases, may contain more relevant than single words. Therefore, proposed focuses previously unseen query-related sentences. Specifically, preprocessed represented with that include both words required...
Because of the imaging mechanism complexity long-linear-array and wide-swath whisk-broom thermal infrared spectrometer (TIS) first Sustainable Development Goals Satellite (SDGSAT-1), how to achieve a high geometric positioning accuracy (GPA) becomes core factor in subsequent quantitative applications. Here, this article, three-step in-orbit calibration (GC) strategy comprising estimations exterior orientation parameters (EOPs), interior (IOPs), scanning compensation (SCPs) is proposed...
A multi-module staggered (MMS) long-linear-array (LLA) detector is presently recognized as an effective and widely adopted means of improving the field view (FOV) in-orbit optical line-array cameras. In particular, in terms low-orbit whisk-broom payloads, MMS LLA combined with one-dimensional scanning mirror capable achieving both large-swath high-resolution imaging. However, because complexity instantaneous relative motion model (IRMM) imaging mechanism, it really difficult to determine...