A5100328001- Radiomics and Machine Learning in Medical Imaging
- Advanced Neural Network Applications
- COVID-19 diagnosis using AI
- Medical Image Segmentation Techniques
- Domain Adaptation and Few-Shot Learning
- Advanced Image and Video Retrieval Techniques
- Generative Adversarial Networks and Image Synthesis
- AI in cancer detection
- Image Retrieval and Classification Techniques
- Medical Imaging Techniques and Applications
- Advanced X-ray and CT Imaging
- Digital Media Forensic Detection
- Advanced Radiotherapy Techniques
- Topic Modeling
- Phonocardiography and Auscultation Techniques
- Machine Learning in Healthcare
- Brain Tumor Detection and Classification
- Machine Learning and Data Classification
- Advanced Neuroimaging Techniques and Applications
- Image and Signal Denoising Methods
- Multimodal Machine Learning Applications
- Cell Image Analysis Techniques
- Optical Systems and Laser Technology
- COVID-19 Clinical Research Studies
- Adversarial Robustness in Machine Learning
Albany State University
2016-2024
University at Albany, State University of New York
2016-2024
The University of Texas MD Anderson Cancer Center
2017-2024
The University of Texas Health Science Center at Houston
2023-2024
Affiliated Hospital of Qingdao University
2017-2024
State Grid Corporation of China (China)
2024
Qingdao University
2017-2024
Sichuan University
2023
West China Hospital of Sichuan University
2023
University at Buffalo, State University of New York
2004-2023
Background Coronavirus disease 2019 (COVID-19) has widely spread all over the world since beginning of 2020. It is desirable to develop automatic and accurate detection COVID-19 using chest CT. Purpose To a fully framework detect CT evaluate its performance. Materials Methods In this retrospective multicenter study, deep learning model, neural network (COVNet), was developed extract visual features from volumetric scans for COVID-19. community-acquired pneumonia (CAP) other non-pneumonia...
To evaluate the performance of a novel three-dimensional (3D) joint convolutional and recurrent neural network (CNN-RNN) for detection intracranial hemorrhage (ICH) its five subtypes (cerebral parenchymal, intraventricular, subdural, epidural, subarachnoid) in non-contrast head CT.A total 2836 subjects (ICH/normal, 1836/1000) from three institutions were included this ethically approved retrospective study, with 76,621 slices CT scans. ICH annotated by independent experienced radiologists,...
Intelligent network is crucial in the building of telecom networks because it utilizes artificial intelligent technologies to improve performance. Salient object detection has increasingly attracted interest from research since estimating human attention objects a step various surveillance applications. However, computational-consuming and memory-consuming model still less effective when deployed only either on cloud or edge. In this article, we propose specially-designed cloud-edge...
Recent works have revealed an essential paradigm in designing loss functions that differentiate individual losses versus aggregate losses. The measures the quality of model on a sample, while combines losses/scores over each training sample. Both common procedure aggregates set values to single numerical value. ranking order reflects most fundamental relation among In addition, decomposability, which can be decomposed into ensemble terms, becomes significant property organizing...
To develop a machine learning model to classify the severity grades of pulmonary edema on chest radiographs.In this retrospective study, 369 071 radiographs and associated radiology reports from 64 581 patients (mean age, 51.71 years; 54.51% women) MIMIC-CXR radiograph dataset were included. This was split into with without congestive heart failure (CHF). Pulmonary labels extracted CHF as four different ordinal levels: 0, no edema; 1, vascular congestion; 2, interstitial 3, alveolar edema....
Generative Adversarial Network (GAN) based techniques can generate and synthesize realistic faces that cause profound social concerns security problems. Existing methods for detecting GAN-generated perform well on limited public datasets. However, images from existing datasets do not represent real-world scenarios enough in terms of view variations data distributions, where real largely outnumber synthetic ones. The state-of-the-art generalize problems lack the interpretability detection...
MR scans used in radiotherapy can be partially truncated due to the limited field of view (FOV), affecting dose calculation accuracy MR-based radiation treatment planning.
Recent advancements in Artificial Intelligence (AI) have significantly influenced the field of Cardiovascular Disease (CVD) analysis, particularly image-based diagnostics. Our paper presents an extensive review AI applications CVD offering insights into its current state and future potential. We systematically categorize literature based on primary anatomical structures related to CVD, dividing them non-vessel (such as ventricles atria) vessel (including aorta coronary arteries). This...
Energy conservation is important for ad hoc networks. However, little effort has been made to carefully study the energy cost metrics upon which design of various efficient algorithms based. More specifically, most existing consumption models only considered exchanging data packets, although common wireless protocols also need control packets (e.g., ACK) reliable transmissions. Without considering these tend underestimate actual consumption, and thus leading suboptimal designs. In this...
Current minimum energy routing schemes in wireless networks only consider consumption for transmitting data packets. However most devices also transmit some control packets (such as RTS and CTS 802.11) besides Without considering the packets, existing tend to use more intermediate nodes, which results less throughput. We first propose comprehensive models that well Based on these models, we our scheme. The simulation verify scheme performs better than terms of