Performance Metrics for CNN-Based AI Models Counting TH-Positive Neurons

A 5.5 KB spreadsheet compiled by Ken Kunugitani, last updated in March 2026, aggregates reported performance metrics for convolutional neural networks designed to count tyrosine hydroxylase-positive cells. The dataset likely contains quantitative measures comparing AI-based counting to expert manual counting, a method described as having limited reproducibility. This collection appears focused on applications in Parkinson's disease research using mouse and human substantia nigra samples.

Use Cases

• Benchmarking CNN model accuracy for automated cell counting based on reported performance metrics.
• Comparing AI-based quantification to conventional manual counting methods described in the literature.
• Analyzing reproducibility improvements in cell counting for Parkinson's disease research models.
• Reviewing the state of AI applications in dopaminergic neuron analysis from published studies.

Strengths

• Explicitly licensed under CC-BY-4.0 for open reuse.
• Last updated date is precisely recorded (2026-03-17 17:26:22).
• Focus on a specific, niche application in biomedical AI.

Limitations

• Dataset is very small at 5.5 KB, indicating limited scope.
• Row count and column definitions are unknown, requiring inspection after download.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

figshare, author Ken Kunugitani

Collection Method

Likely a literature review and compilation of published metrics.

Time Range

Covers studies 'reported to date' as of the update.

Freshness

Last updated 2026-03-17 17:26:22; freshness should be verified.

Geography

null