Publications by authors named "Mao-Nian Wu"
Article Synopsis
- The study aimed to evaluate an intelligent diagnostic model for pterygium using a fusion of advanced attention mechanisms with a lightweight MobileNetV2 structure for tri-classification.
- It utilized a dataset of 1220 images from Nanjing Medical University and compared the performance of this model against conventional classification models, assessing factors like accuracy, Kappa value, and sensitivity.
- The results showed that the MobileNetV2+Self-Attention model achieved high accuracy (92.77%) and excellent sensitivity (up to 99.47%), demonstrating its potential for efficient detection and severity assessment of pterygium.
Artificial intelligence assisted pterygium diagnosis: current status and perspectives.
Int J Ophthalmol
September 2023
Article Synopsis
- Pterygium is a common eye condition that can lead to discomfort and impaired vision, highlighting the need for early and accurate diagnosis.
- The paper discusses how artificial intelligence (AI), including techniques like machine learning and computer vision, is being leveraged to improve pterygium diagnosis through enhanced detection and classification methods.
- It also evaluates the benefits and challenges of using AI in this context and explores future advancements that could lead to better diagnostic tools for pterygium.
Aim: To conduct a classification study of high myopic maculopathy (HMM) using limited datasets, including tessellated fundus, diffuse chorioretinal atrophy, patchy chorioretinal atrophy, and macular atrophy, and minimize annotation costs, and to optimize the ALFA-Mix active learning algorithm and apply it to HMM classification.
Methods: The optimized ALFA-Mix algorithm (ALFA-Mix+) was compared with five algorithms, including ALFA-Mix. Four models, including ResNet18, were established.
This study aims to implement and investigate the application of a special intelligent diagnostic system based on deep learning in the diagnosis of pterygium using anterior segment photographs. A total of 1,220 anterior segment photographs of normal eyes and pterygium patients were collected for training (using 750 images) and testing (using 470 images) to develop an intelligent pterygium diagnostic model. The images were classified into three categories by the experts and the intelligent pterygium diagnosis system: (i) the normal group, (ii) the observation group of pterygium, and (iii) the operation group of pterygium.
View Article and Find Full Text PDFBackground: In the development of artificial intelligence in ophthalmology, the ophthalmic AI-related recognition issues are prominent, but there is a lack of research into people's familiarity with and their attitudes toward ophthalmic AI. This survey aims to assess medical workers' and other professional technicians' familiarity with, attitudes toward, and concerns about AI in ophthalmology.
Methods: This is a cross-sectional study design study.
Five-Category Intelligent Auxiliary Diagnosis Model of Common Fundus Diseases Based on Fundus Images.
Transl Vis Sci Technol
June 2021
Article Synopsis
- This study addresses the shortage of ophthalmologists in China by proposing a five-category intelligent diagnosis model for common eye diseases like retinal vein occlusion and diabetic retinopathy.
- The research involved collecting and analyzing 2,000 fundus images, training three different models, and achieving over 90% accuracy in diagnosing these conditions.
- The findings will assist primary care doctors in delivering better diagnostic services to ophthalmologic patients, improving patient care overall.
Introduction: In April 2018, the US Food and Drug Administration (FDA) approved the world's first artificial intelligence (AI) medical device for detecting diabetic retinopathy (DR), the IDx-DR. However, there is a lack of evaluation systems for DR intelligent diagnostic technology.
Methods: Five hundred color fundus photographs of diabetic patients were selected.