ML Fitted PS Data: Optical Properties of Phantoms from Inverse Modeling

Extracted optical properties of phantoms with fixed absorption coefficient using a neural network-based inverse model. The dataset includes fitted diffuse reflectance, extracted absorption coefficient, extracted scattering coefficient, and extracted anisotropy factor. It was created by Qing Lan of the National Institutes of Health.

Use Cases

• Validate inverse models for optical property extraction based on fitted diffuse reflectance.
• Train neural networks for scattering property estimation based on extracted scattering coefficient data.
• Benchmark optical property recovery algorithms using the extracted absorption coefficient.
• Study the relationship between phantom reference and target data based on the suffix numbering scheme.

Strengths

• Data originates from the National Institutes of Health, a recognized research institution.
• Includes multiple derived optical properties: diffuse reflectance, absorption coefficient, scattering coefficient, and anisotropy factor.
• The suffix numbering provides a traceable link between reference and target phantom data.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Last update date is unknown; freshness unverified.

Provenance

Source

National Institutes of Health

Collection Method

Extracted using a neural network-based inverse model from phantom data.