PET/CT Imaging Features for 289 Fever of Unknown Origin Patients

A retrospective cohort of 289 adult FUO patients with a mean age of 59 years, comprising 128 women and 161 men. The dataset, created by Sule Ceylan and last updated in May 2026, contains PET/CT imaging features extracted for unsupervised clustering analysis. It includes data on organ involvement patterns and SUVmax values to explore imaging phenotypes.

Use Cases

• Developing unsupervised clustering models based on PET/CT organ involvement patterns.
• Analyzing correlations between imaging phenotypes (e.g., reticuloendothelial vs. parenchymal involvement) and clinical outcomes.
• Benchmarking clustering algorithms (hierarchical, spectral, K-prototypes) on structured medical feature data.

Strengths

• Includes 289 patient records with detailed PET/CT feature extraction.
• Applies a consensus clustering approach using four different unsupervised algorithms for robust results.
• Provides specific statistical results comparing clusters to diagnoses, such as an Adjusted Rand Index of 0.006.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown for the underlying feature table, which may limit suitability assessment.
• The dataset is very small at 14.5 KB, indicating limited scope.

Provenance

Source

figshare, author Sule Ceylan.

Collection Method

Retrospective cohort study; data extracted from 18F-FDG PET/CT scans of adult FUO patients.

Freshness

Last updated 2026-05-29 04:50:48; freshness should be verified.