A5083105832- Spectroscopy Techniques in Biomedical and Chemical Research
- AI in cancer detection
- Spectroscopy and Chemometric Analyses
- Gene expression and cancer classification
- Infrared Thermography in Medicine
- Radiomics and Machine Learning in Medical Imaging
- Bioinformatics and Genomic Networks
- Advanced Measurement and Detection Methods
- Industrial Vision Systems and Defect Detection
- Congenital gastrointestinal and neural anomalies
- Identification and Quantification in Food
- Face and Expression Recognition
- Thermography and Photoacoustic Techniques
- Neural Networks and Applications
- Cell Image Analysis Techniques
- Congenital Diaphragmatic Hernia Studies
- Machine Learning and Data Classification
- Advanced Graph Neural Networks
- Molecular Biology Techniques and Applications
- Gastrointestinal disorders and treatments
- Machine Learning in Bioinformatics
Hunan University
2023
Boston University
2015-2019
University of Massachusetts Chan Medical School
2018
City Of Hope National Medical Center
2018
City of Hope
2018
Northeastern University
2015-2018
Blackstone (United States)
2015-2018
Dalian Medical University
1999
Second Affiliated Hospital of Dalian Medical University
1999
Infrared thermography testing (IRT) has been widely used in the defect detection of composite materials. However, identification defects characteristics is unsatisfying due to interference factors such as uneven background and noise original thermal image sequence. A novel thermography-based method with semantic segmentation network proposed enhance contrast extract perfect features. To Figure out abnormal distribution temperature field images, AG-UNet was a spatial self-attention gate...
We report results on a statistical analysis of an infrared spectral dataset comprising total 388 lung biopsies from 374 patients.
This paper reports the results of a collaborative lung cancer study between City Hope Cancer Center (Duarte, California) and CIRECA, LLC (Cambridge, Massachusetts), comprising 328 samples from 249 patients, that used an optical technique known as spectral histopathology (SHP) for tissue classification. Because SHP is based on physical measurement, it renders diagnoses more objective reproducible basis than methods assessing cell morphology architecture. report demonstrates provides...
A machine learning (ML) feature network is a graph that connects ML features in tasks based on their similarity. This representation allows us to view vectors as functions the network. By leveraging function operations from Fourier analysis and functional analysis, one can easily generate new novel features, making use of structure imposed vectors. Such structures have previously been studied implicitly image processing computational biology. We thus describe networks vectors, provide...
This paper reviews methods to arrive at optimum decision tree or label structures analyze large SHP datasets. Supervised of analysis can utilize either sequential (flat) multi-classifiers depending on the variance in data, and number spectral classes be distinguished. For small classes, have been used past, but for datasets containing numbers (∼20) disease tissue types, mixed were found advantageous. In these structures, discrimination into subclasses is achieved via hierarchical...
This paper presents a new approach to the production of feature maps for improvement classification in machine learning. The idea is based on calculus differentiation and integration vectors, which can be viewed as functions metric space or network. Based this we propose novel network-based binary learning classifier. We illustrate our method using molecular networks alone distinguish phenotypes, including cancer types subtypes. include sets derived from disease-specific gene co-expression...