Pediatric Hematologic Malignancies CT Features for Differential Diagnosis

From August 2016 to November 2024, 133 children with acute pancytopenia were enrolled at the Children’s Hospital of Chongqing Medical University. The dataset, created by Junya Ma, compares thoracic and abdominal computed tomography features across three hematologic malignancies: malignancy-associated hemophagocytic lymphohistiocytosis, acute leukemia, and Epstein–Barr virus-associated HLH.

Use Cases

• Train a classifier to differentiate malignancy-associated HLH from acute leukemia based on mediastinal lymph node size.
• Build a model to predict Epstein–Barr virus-associated HLH using abdominal CT features like periportal space widening and splenomegaly.
• Develop a diagnostic support tool that uses CT-derived cutoff values for lymph node size as decision thresholds.
• Analyze correlations between specific thoracic CT findings, such as pulmonary lesions and pleural effusion, and disease subtypes.

Strengths

• Includes data from 133 pediatric patients across three distinct disease groups.
• Provides specific, statistically analyzed cutoff values for lymph node size differentiation.
• Covers a time range from August 2016 to November 2024.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Data is from a single hospital in Chongqing, China, which may limit geographic generalizability.

Provenance

Source

Children’s Hospital of Chongqing Medical University, Chongqing, China.

Collection Method

Retrospective cohort study analyzing thoracic and abdominal CT scans.

Time Range

August 2016 to November 2024

Freshness

Last updated 2026-05-28 04:50:40; freshness should be verified.

Geography

Chongqing, China