The small round blue cell tumors (SRBCTs) are 4 different childhood tumors named so because of their similar appearance on routine histology, which makes correct clinical diagnosis extremely challenging. However, accurate diagnosis is essential because the treatment options, responses to therapy and prognoses vary widely depending on the diagnosis. They include Ewing's family of tumors (EWS), neuroblastoma (NB), non-Hodgkin lymphoma (in our case Burkitt's lymphoma, BL) and rhabdomyosarcoma (RMS). Our classification model was built to distinguish between these four tumors based on gene expression values.
Platform: cDNA microarrays
Diagnostic classes:
- Ewing's sarcoma (EWS): 29 examples (34.9%)
- Burkitt's lymphoma (BL): 11 examples (13.3%)
- neuroblastoma (NB): 18 examples (21.7%)
- rhabdomyosarcoma (RMS): 25 examples (30.1%)
Number of genes: 2308 Number of samples: 83
Predictive accuracy with 10-fold cross validation (classifying using the best projection with eight attributes):
Following are the three best-ranked visualization with eight, six and four attributes in respect to the visualization score, that is, visualizations where examples from different diagnostic classes are best separated: