A5028267453- AI in cancer detection
- Cutaneous Melanoma Detection and Management
- Asian Culture and Media Studies
- Photoacoustic and Ultrasonic Imaging
- Bone and Joint Diseases
- Non-Invasive Vital Sign Monitoring
- Optical Coherence Tomography Applications
- Hip disorders and treatments
- Cardiac, Anesthesia and Surgical Outcomes
- Advanced Neural Network Applications
- Cell Image Analysis Techniques
- Cerebrovascular and Carotid Artery Diseases
- Robotics and Sensor-Based Localization
- EEG and Brain-Computer Interfaces
- Hemodynamic Monitoring and Therapy
- Advanced Image and Video Retrieval Techniques
- Atomic and Subatomic Physics Research
- Advanced MRI Techniques and Applications
- Food Allergy and Anaphylaxis Research
- Nonmelanoma Skin Cancer Studies
- Infrared Thermography in Medicine
- Dental Radiography and Imaging
- NMR spectroscopy and applications
- Natural Language Processing Techniques
- Spondyloarthritis Studies and Treatments
Huazhong University of Science and Technology
2024-2025
Tongji Hospital
2024-2025
Yonsei University
2015-2025
Beijing Information Science & Technology University
2024
North Carolina State University
2024
Fudan University
2013
Huashan Hospital
2013
Abstract Background Several studies have achieved high‐level performance of melanoma detection using convolutional neural networks ( CNN s). However, few described the extent to which implementation s improves diagnostic physicians. Objective This study is aimed at developing a for detecting acral lentiginous ALM ) and investigating whether its can improve initial decision made by Methods A was trained 1072 dermoscopic images benign nevi, intermediate tumours. To investigate detection, 60...
The rising incidence of thyroid cancer globally is increasing the number thyroidectomies, causing visible scars that can greatly affect quality life due to cosmetic, psychological, and social impacts. In this study, we explored application deep learning algorithms objectively assess post‐thyroidectomy scar morphology using computer‐aided diagnosis. This study was approved by Institutional Review Board Yonsei University College Medicine (approval no. 3‐2021‐051). A dataset comprising 7524...
Skin lesion images are relatively easy to obtain, but variations in imaging conditions, particularly positioning, can cause inconsistencies deep learning model activations, impacting diagnostic reliability. In this study, a robust deep-learning for melanoma prediction was developed using class-agnostic activation maps (CAAMs) enhanced accuracy and reliability by addressing issues related image variability transformation robustness. The international skin collaboration (ISIC) 2017 2019...
Quantitative assessment of cortical bone microstructure is crucial for the evaluation osteoporosis, yet current clinical methods such as dual-energy X-ray absorptiometry (DXA) have many limitations. The
Background: Ultrasound-induced thermal strain imaging (US-TSI) is a promising ultrasound modality that has been demonstrated in preclinical studies to identify lipid-rich necrotic core of an atherosclerotic plaque.However, human physiological motion, e.g., cardiac pulsation, poses challenges implementing US-TSI applications, where achieving millisecond-level temperature rise by delivering acoustic energy from compact probe key requirement.This study aims develop transient heating and...
Arrhythmia is the heartbeat losing its regularity or deviating from average number. Among types of arrhythmia atrial fibrillation (AF) and flutter (AFL), which are considered risk factors for development due to high morbidity mortality. The early detection AF/AFL essential because their effects on heart complications appear after a considerable time. Electrocardiography (ECG) widely used screening method in primary care low cost convenience. ECG records heart's electrical activity period...