A5033195512- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Sensorless Control of Electric Motors
- Multilevel Inverters and Converters
- Brain Tumor Detection and Classification
- Dental Radiography and Imaging
- Induction Heating and Inverter Technology
- Diabetic Foot Ulcer Assessment and Management
- Medical Imaging and Analysis
- Non-Invasive Vital Sign Monitoring
- ZnO doping and properties
- ECG Monitoring and Analysis
- Sinusitis and nasal conditions
- Image Processing Techniques and Applications
- Hepatocellular Carcinoma Treatment and Prognosis
- Dental Research and COVID-19
- Cerebral Palsy and Movement Disorders
- Foot and Ankle Surgery
- Transition Metal Oxide Nanomaterials
- Retinal Imaging and Analysis
- Liver Disease Diagnosis and Treatment
- Hand Gesture Recognition Systems
- Gait Recognition and Analysis
- Liver Disease and Transplantation
- Retinal and Optic Conditions
I-Shou University
2013-2024
Zuoying Armed Forces General Hospital
2013-2021
Kaohsiung Armed Forces General Hospital
2017-2021
National Dong Hwa University
2018
Uniform hexagonal single phase Ni1–xFexO (x = 0, 0.01, 0.05, and 0.1) nanoparticles synthesized by a standard hydrothermal method are characterized with an enhanced lattice expansion along decrease in the microstrain, crystal size, Ni occupancy as function of Fe concentration. The observed anomalous temperature field dependent magnetic properties content were explained using core–shell type structure nanoparticle such that effect Fe-doping has led to disordered surface spins increase...
Anesthesia assessment is most important during surgery. Anesthesiologists use electrocardiogram (ECG) signals to assess the patient’s condition and give appropriate medications. However, it not easy interpret ECG signals. Even physicians with more than 10 years of clinical experience may still misjudge. Therefore, this study uses convolutional neural networks classify image types assist in anesthesia assessment. The research Internet Things (IoT) technology develop signal measurement...
This study focuses on overcoming challenges in classifying eye diseases using color fundus photographs by leveraging deep learning techniques, aiming to enhance early detection and diagnosis accuracy. We utilized a dataset of 6392 across eight disease categories, which was later augmented 17,766 images. Five well-known convolutional neural networks (CNNs)-efficientnetb0, mobilenetv2, shufflenet, resnet50, resnet101-and custom-built CNN were integrated trained this dataset. Image sizes...
Postural control decreases with aging. Thus, an efficient and accurate method of detecting postural is needed. We enrolled 35 elderly adults (aged 82.06 ± 8.74 years) 20 healthy young 21.60 0.60 who performed standing tasks for 40 s, six times. The coordinates 15 joint nodes were captured using a Kinect device (30 Hz). plotted positions into single 2D figure (named joint–node plot, JNP) once per second up to s. A total methods combining deep machine learning classification investigated....
Dental panoramic imaging plays a pivotal role in dentistry for diagnosis and treatment planning. However, correctly positioning patients can be challenging technicians due to the complexity of equipment variations patient anatomy, leading errors. These errors compromise image quality potentially result misdiagnoses.This research aims develop validate deep learning model capable accurately efficiently identifying multiple dental imaging.This retrospective study used 552 images selected from...
Many neurological and musculoskeletal disorders are associated with problems related to postural movement. Noninvasive tracking devices used record, analyze, measure, detect the control of body, which may indicate health in real time. A total 35 young adults without any were recruited for this study participate a walking experiment. An iso-block identity method was quantitatively analyze posture behavior. The participants who exhibited straightforward skewed defined as experimental groups,...
According to the Health Promotion Administration in Ministry of and Welfare statistics Taiwan, over ten thousand women have breast cancer every year. Mammography is widely used detect cancer. However, it limited by operator's technique, cooperation subjects, subjective interpretation physician. It results inconsistent identification. Therefore, this study explores use a deep neural network algorithm for classification mammography images. In experimental design, retrospective was collect...
Background/Objectives: Breast cancer is a leading cause of mortality among women in Taiwan and globally. Non-invasive imaging methods, such as mammography ultrasound, are critical for early detection, yet standalone modalities have limitations regard to their diagnostic accuracy. This study aims enhance breast detection through cross-modality fusion approach combining ultrasound imaging, using advanced convolutional neural network (CNN) architectures. Materials Methods: images were sourced...
The ultrasonography is widely used to diagnose nonalcoholic fatty liver disease (NAFLD). However, the diagnostic reports were affected by operating bias of interobserver and intraobserver. main aim build a feasible classified model for NAFLD with images. significant features image are inner-quartile range (IQR), standard deviation (STD), hepatorenal index (HI) specific region interest (ROI). A logistic regression classifier was predictors IQR, STD HI. accuracy, sensitivity, specificity, area...
Positron emission tomography (PET) can provide functional images and identify abnormal metabolic regions of the whole-body to effectively detect tumor presence distribution. The filtered back-projection (FBP) algorithm is one most common reconstruction methods. However, it will generate strike artifacts on reconstructed image affect clinical diagnosis lesions. Past studies have shown reduction in improvement quality by two-dimensional morphological structure operators (2D-MSO). method merely...