Comparison Results of CR and CNR Values for Liver Ultrasound Image Enhancement

A study by Jaeyoung Huh, uploaded to figshare in April 2026, presents quantitative results from a deep learning-based image enhancement algorithm for liver ultrasound. The 5.5 KB XLS file likely contains comparison metrics, such as Contrast Ratio (CR) and Contrast-to-Noise Ratio (CNR), evaluating the algorithm's performance on images from older and newer ultrasound devices. The algorithm aimed to improve brightness, contrast, and overall quality of low-quality liver ultrasound images for clinical assessment.

Use Cases

• Benchmarking deep learning models for medical image quality enhancement based on reported CR and CNR metrics.
• Analyzing the impact of ultrasound device age on image quality based on the comparison between 12-year-old and 4-year-old devices.
• Evaluating inter-reader agreement in medical imaging studies based on the reported weighted kappa values ranging from 0.225 to 0.838.

Strengths

• Data is openly licensed under CC-BY-4.0, permitting reuse with attribution.
• Results are derived from a study with inter-reader agreement metrics, indicating a measure of validation.
• The dataset is small (5.5 KB), facilitating quick download and inspection.

Limitations

• Row count is unknown, which may limit suitability assessment for statistical analysis.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small (5.5 KB), suggesting it contains summary statistics rather than raw image data.

Provenance

Source

figshare, author Jaeyoung Huh.

Collection Method

Likely derived from a study comparing ultrasound image quality before and after a deep learning enhancement algorithm.

Time Range

null

Freshness

Last updated 2026-04-28 17:44:28; freshness should be verified.

Geography

null