Lung Disease Dataset
Main product
Data Quantity
Optional product
Total Price
USD 0 VAT included
- Main productPremium
- Data QuantityBasic
- Optional productNot selected
- DownloadNo data
- All products are priced including VAT.
- Premium datasets are custom-made and take approximately two weeks from the date of application to improve quality.
- Common datasets can be checked on My Page after purchase.
Basic Price
USD 9,100 VAT included
X-ray images categorized into three balanced classes: Normal, Lung Opacity, and Viral Pneumonia.
- Labeling type: disease
- Data Format: Image
Related Tags:
Categories:
About Dataset
1) Data Introduction
• The Lung Disease Dataset is a medical imaging dataset designed for binary and multi-class classification tasks in computer vision. It consists of X-ray images categorized into three balanced classes: Normal, Lung Opacity, and Viral Pneumonia.2) Data Utilization
(1) Characteristics of the Lung Disease Dataset: • The dataset is well-balanced across classes, making it suitable for multi-class classification model training, and it is based on real clinical data that closely resembles actual diagnostic environments.. • It consists of X-ray images collected from various medical institutions such as hospitals and clinics, making it highly useful for early detection of lung diseases and AI-based medical model development. (2) Applications of the Lung Disease Dataset: • Development of AI-based lung disease classification models: The dataset can be used to train deep learning models that automatically classify the presence and type of lung disease from chest X-ray images (Normal / Lung Opacity / Viral Pneumonia). • Differentiation of similar disease patterns and fine-grained classification experiments: It is useful for experiments that involve distinguishing between visually similar findings such as pneumonia and opacity, and is also applicable in Explainable AI (XAI) research through tools like Class Activation Maps (CAM) and Attention Maps.Meta Data
Normal
Outstanding
Data Samples 5
Utility
| Downstream Classification (▲) | KID (▼) | One Class Classification (▼) | |
|---|---|---|---|
| Total | 0 | 0 | 0 |
| Suitability | OK | OK | OK |
The higher the value, the better (▲)
Model Performance
Downstream classification accuracy is an indicator used to evaluate the usefulness of synthetic data. It measures whether synthetic data performs similarly to real data. The method involves training the same model separately on real data and synthetic data, and then comparing the accuracies of the two models. Interpretation: A high accuracy rate means that the model trained on synthetic data performs similarly to the one trained on real data, indicating that the synthetic data is of high quality and well represents the real data.
The closer to zero or the lower the value, the better (▼)
Quality
KID (Kernel Inception Distance) is a metric used to evaluate the similarity between generated images and real images. It compares the differences between the two sample distributions using Kernel Mean Embedding, without assuming a normal distribution. Interpretation: A lower KID score suggests that generated images are more similar to real images, with a score close to 0 being ideal. Specifically, a score below 0.01 indicates very high similarity.
Privacy
| LPIPS (▲) | SSIM (▼) | |
|---|---|---|
| Total | 0 | 0 |
| Suitability | OK | OK |
The higher the value, the better (▲)
Perceptual Similarity
Learned Perceptual Image Patch Similarity (LPIPS) is a metric used to measure the visual similarity between two images by utilizing neural networks to extract key features and calculate the distance between them. High LPIPS value: Indicates high similarity between images, raising the risk of information leakage. Low LPIPS value: Suggests that synthetic images are perceptually different from real images, indicating a lower risk of sensitive information leakage.
The closer to zero or the lower the value, the better (▼)
Structural Similarity
The Structural Similarity Index Measure (SSIM) is a metric used to assess the similarity between two images. It is primarily used to compare the quality of a restored or compressed image with the original image. SSIM measures visual similarity by considering brightness, contrast, and structure.
High SSIM value (0.9 or above): Indicates that the synthetic image is very similar to the real image, which may increase the risk of information leakage.
Low SSIM value (0.6 or below): Indicates low similarity and reduced risk of leakage.
Premium Report Information
Premium dataset sample
