SZH Dataset
收藏资源简介:
SZH Dataset是由广州医科大学的第二附属医院和佛山市三水区人民医院共同创建的大型耳内镜图像数据集,包含8种耳病和正常样本,共计24,233张图像。该数据集通过专家分类,确保了图像的质量和准确性。数据集的创建旨在解决深度学习模型在耳病诊断中的实际应用问题,特别是在模型推理速度和参数大小之间的平衡。该数据集的应用领域包括实时耳病诊断,帮助公众和医疗提供者在实时视频中进行全面的耳道扫描和诊断,及时发现耳部病变。
The SZH Dataset is a large-scale otoscopic image dataset jointly developed by the Second Affiliated Hospital of Guangzhou Medical University and Sanshui District People's Hospital of Foshan. It contains 24,233 images covering 8 types of ear diseases and normal samples. All images are classified by medical experts to ensure their quality and labeling accuracy. The dataset was created to address the practical application challenges of deep learning models in ear disease diagnosis, particularly the trade-off between model inference speed and parameter size. Its application scenarios include real-time ear disease diagnosis, assisting the public and medical providers to perform comprehensive ear canal scanning and diagnosis via real-time videos, so as to detect ear lesions in a timely manner.

- 1Ear-Keeper: Real-time Diagnosis of Ear Lesions Utilizing Ultralight-Ultrafast ConvNet and Large-scale Ear Endoscopic Dataset广州医科大学 · 2024年



