A5101855968- Radiomics and Machine Learning in Medical Imaging
- Digital Radiography and Breast Imaging
- COVID-19 diagnosis using AI
- Medical Imaging Techniques and Applications
- Lung Cancer Diagnosis and Treatment
- Blind Source Separation Techniques
- EEG and Brain-Computer Interfaces
- Neuroscience and Neuropharmacology Research
- Advanced X-ray and CT Imaging
- Advanced Radiotherapy Techniques
- Pain Mechanisms and Treatments
- Nerve injury and regeneration
- Medical Imaging and Analysis
- Advanced Image Fusion Techniques
- AI in cancer detection
- ECG Monitoring and Analysis
Stony Brook School
2019-2025
Stony Brook University
2025
Southern University of Science and Technology
2023
Kunming General Hospital of Chengdu Military Command
2018
Yamaguchi University
2013-2015
PurposeWe aim to develop accurate volumetric quantitative imaging of iodinated contrast agent (ICA) in contrast-enhanced digital breast tomosynthesis (DBT).ApproachThe two main components the approach are use a dual-energy DBT (DE-DBT) scan and development an optimization-based algorithm that can yield images with isotropic resolution. The image reconstruction exploits sparsity subject's directional derivative magnitudes, it also performs direct regularization help confine true support...
Digital Breast Tomosynthesis (DBT) provides a quasi-3D impression of the breast volume resulting in better visualization mass. However, one serious drawback is that compared to Mammography, each projection gets lower x-ray dose into higher quantum noise which seriously hampers visibility calcifications. To solve this problem we propose Convolutional Neural Network model based on Adversarial loss. We train deep network using synthetic data obtained from Virtual Clinical Trials. Unlike earlier...
We applied and optimized the sparse representation (SR) approaches in computer-aided diagnosis (CAD) to classify normal tissues five kinds of diffuse lung disease (DLD) patterns: consolidation, ground-glass opacity, honeycombing, emphysema, nodule. By using K-SVD which is based on singular value decomposition (SVD) orthogonal matching pursuit (OMP), it can achieve a satisfied recognition rate, but too much time was spent experiment. To reduce runtime method, K-Means algorithm substituted for...
Abstract Neuropathic pain is a complex, chronic condition and the treatment major clinical challenge. Recent studies have shown that two FDA approved drugs dexmedetomidine (DEX) midazolam (MZL), may be useful in treating neuropathic pain, but mechanism not fully dementated. Here, we investigated effects mechanisms of DEX MZL peripheral nerve injury model. Intramuscular injection with attenuated development mechanical allodynia thermal hyperalgesia rats constriction (CCI). Concurrently,...
Ultrasound is widely used for image-guided therapy (IGT) in many surgical fields, thanks to its various advantages, such as portability, lack of radiation and real-time imaging. This article presents the first attempt utilize multiple deep learning algorithms distal humeral cartilage segmentation dynamic, volumetric ultrasound images employed minimally invasive surgery.The dataset, consisting 5,321 were collected from 12 healthy volunteers. These randomly split into training validation sets...
Electrocardiogram (ECG) delineation is a process to detect multiple characteristic points, which contain critical diagnostic information about cardiac diseases. We treat the ECG task as an one-dimensional segmentation problem, and propose novel end-to-end deep learning method segment sections of signal. Our neural network consists two parts: composed 1D Convolutional Neural Networks (CNN) postprocessing sequential Conditional Random Field (CRF). trained validated on QT database. The...
This paper describes a computer-aided diagnosis (CAD) method to classify pneumoconiosis on HRCT images. In Japan, the is divided into 4 types according density of nodules: Type 1 (no nodules), 2 (few small 3-a (numerous nodules) and 3-b nodules presence large nodules). Because most pneumoconiotic are small-sized irregular-shape, only few can be detected by conventional nodule extraction methods, which would affect classification pneumoconiosis. To improve performance extraction, we proposed...