Serum samples from endometrial cancer (EC) patients and healthy females were analyzed using surface-enhanced laser desorption-ionization time-of-flight mass spectrometry (SELDI-TOF-MS) to discover the potential diagnostic biomarker for detection of EC. A preliminary training set of spectra derived from 40 EC patients and 30 healthy women were used to develop a proteomic model that effectively discriminated cancer patients from healthy women. The training set had a specificity of 100% and sensitivity of 92.5% in the EC detection. A blind test set, including 20 new cancer cases and 10 healthy women, was used to validate the sensitivity and specificity of this multivariate model, which had a corresponding results of 60% in specificity and 75% in sensitivity, respectively. The combination of SELDI-TOF-MS with bioinformatics tools could help find new biomarkers and establish the detection of EC with high sensitivity and specificity.