BACKGROUND Hepatocellular carcinoma (HCC) is one of the most common cancers in the world,and the identification of biomarkers for the early detection is a relevant target. The purpose of the study is to discover specific low molecular weight (LMW) serum peptidome biomarkers and establish a diagnostic pattern for HCC. METHODS We undertook this pilot study using a combined application of magnetic beads with Matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) technique and ClinPro Tools v2.2 to detect 32 patients with HCC, 16 patients with chronic hepatitis (CH), 16 patients with liver cirrhosis (LC) and 16 healthy volunteers. RESULTS The results showed 49, 33 and 37 differential peptide peaks respectively appeared in HCC, LC and CH groups. A Supervised Neural Network (SNN) algorithm was used to set up the classification model. Eleven of the identified peaks at m/z 5247.62, 7637.05, 1450.87, 4054.21, 1073.37, 3883.64, 5064.37, 4644.96, 5805.51, 1866.47 and 6579.6 were used to construct the peptides patterns. According to the model, we could clearly distinguish between HCC patients and healthy controls as well as between LC or CH patients and healthy controls. CONCLUSIONS The study demonstrated that a combined application of magnetic beads with MALDI-TOF MB technique was suitable for identification of potential serum biomarkers for HCC and it is a promising way to establish a diagnostic pattern. The virtual slide(s) for this article can be found here: http://www.diagnosticpathology.diagnomx.eu/vs/1503629821958720.