YWYi-Huei Wu

Yi-Huei Wu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yi-Huei Wu has a total of 5 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Classifying Dementia Severity Using MRI Radiomics Analysis of the Hippocampus and Machine Learning

    by Dong-Her Shih, Yi-Huei Wu, Ting-Wei Wu, Yi-Kai Wang, Ming-Hung Shih

    Dementia is a leading cause of global mortality, with limited treatment options available. Patients progress through three stages: cognitive normal (CN), mild cognitive impairment (MCI), and Alzheimer’s disease (AD). Accurate prediction of these stages can significantly slow deterioration. Recent research suggests analyzing MRI images, focusing on markers like whole brain, hippocampus, and entorhinal cortex atrophy, is diagnostically valuable. However, most methods analyze 2D MRI images, losing anatomical context. Our study processes 3D MRI data with AC-PC alignment correction and extracts radiomic features from the segmented hippocampus, followed by discretization and principal component analysis for optimization. Machine learning and deep learning methods are then used for classification with cross-validation, achieving the highest accuracy with support vector machine (SVM). Compared with other studies, our results show the highest accuracy among the three dementia severity classifications. Combining the radiomic features from segmented hippocampus in MRI with machine learning promises unprecedented accuracy in predicting dementia severity, potentially slowing progression and enhancing patients’ quality of life.


  • Open Access

    Stroke Prediction Using Deep Learning and Transfer Learning Approaches

    by Dong-Her Shih, Yi-Huei Wu, Ting-Wei Wu, Huei-Ying Chu, Ming-Hung Shih

    Stroke is one of the leading causes of death and disability worldwide. The ideal solution to the stroke problem is to prevent it in advance by controlling metabolic factors, atrial fibrillation, hypertension, smoking, Etc. However, unless the physiological indicators are abnormal, it is difficult for medical personnel to decide whether special precautions are necessary for a patient based solely on monitoring the potential patient. There was a great category imbalance between stroke and non-stroke patients, so this study tried to use various techniques to solve the problem of categorical unbalanced stroke prediction problem. Then, deep learning models were used to predict whether the patients would have a stroke. Finally, the classification experiment is carried out through transfer learning to observe whether the evaluation metrics are further improved. According to the experimental results, this study effectively reduced the false negative rate (FNR) and false positive rate (FPR) of stroke prediction and improved the overall accuracy of stroke prediction through the category imbalance treatment and deep learning method.