PET/CT Feature Clusters for 289 Fever of Unknown Origin Patients

A dataset of 289 adult patients with fever or inflammation of unknown origin (FUO/IUO) who underwent 18F-FDG PET/CT imaging. The data includes extracted features on organ and vessel involvement, SUVmax values, and uptake patterns, which were used in a consensus clustering analysis to identify four distinct imaging phenotypes. The dataset was created by Sule Ceylan and last updated in May 2026.

Use Cases

• Benchmark unsupervised clustering algorithms based on multi-feature medical imaging data.
• Study the relationship between PET/CT imaging phenotypes and clinical etiologies like infections or rheumatologic diseases.
• Develop feature extraction methods for reticuloendothelial, parenchymal, and large vessel involvement from PET/CT scans.

Strengths

• Includes data from 289 patients with a mean age of 59 ± 17 years.
• Features were analyzed using four unsupervised algorithms and a consensus clustering approach.
• Results include statistical comparisons with final diagnoses using Adjusted Rand Index and Mutual Information.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count for the underlying feature table is unknown, which may limit suitability assessment.
• The 14.5 KB file size suggests the dataset is a summary or document, not the raw feature matrix.

Provenance

Source

figshare, author Sule Ceylan.

Collection Method

Retrospective cohort study where data were extracted from patient PET/CT scans.

Freshness

Last updated 2026-05-29 04:50:49; freshness should be verified.