Hepatocellular carcinoma (HCC) has relatively sensitive and specific serum tumor antigen markers (AFP), which is also the most common serological marker for cancer screening. However, there are unignorable limitations, including possible false-negatives/positives owing to confounding conditions. Reliable non-invasive diagnostics is still in urgent need. This work proposes a novel LDI-TOF-MS technique for HCC screening and diagnosis. By taking advantage of 3D nanostructures and machine learning, our technique enables high fidelity and reproducibility.
An LDI-TOF-MS platform was established for HCC screening and was applied to 139 patients with liver cancer, as well as 203 healthy controls (Table). All mass spectrum was collected within a mass range of 100 to 1,100 Da for metabolites. Based on the data acquired by LDI-TOF-MS, SVM algorithm was developed and applied for automated cancer classification across six cancer types, which was further validated by single blinded samples with randomly selected cancer patients and controls. Summary of patient and healthy control characteristicsPatient Type N Gender Gender Age AJCC Stage AJCC Stage AJCC Stage AJCC Stage M(%) F(%) I II III IV HCC 139 120 (86.33%) 19 (13.67%) 55.63± 11.22(25-80) 51 48 40 - HC 203 117 (57.64%) 86 (42.36%) 47.68± 10.78(23-76) - - - -
This assay demonstrated an average sensitivity of 96% and a specificity over 98% in detecting HCC. In our cohort, 47 of 137 HCC patients (35.77%) were AFP negative (AFP<20ng/ml, stage I n = 18, stage II n = 17 and stage III n = 12). Here, we showed that the LDI-TOF-MS recognized almost all AFP-negative HCC. The sensitivity and specificity were obviously superior to AFP in HCC: only 2 of 137 HCCs (1.46%) were misclassified as healthy controls. In contrast, AFP positive and AFP negative HCCs were not readily distinguished by this method. Therefore, this method was independent of tumor markers.
This work established a low-cost, high-throughput procedure based on trace amount of serum to identify HCC as well as healthy controls with superior precision, making it a promising technique for clinical cancer research and translation.
Zhongshan Hospital, Fudan University.
Has not received any funding.
All authors have declared no conflicts of interest.