Objective To detect the serum protein fingerprint in gastric cancer patients by using the surface-enhanced laser desorption-ionization time-of-flight mass spectrometry (SELDI-TOF-MS) and protein chip array technology, screen biomarker candites, build diagnostic models and evaluate its clinical significance. Methods The serum proteomic patterns were detected in 40 patients with gastric cancer, 20 patients with gastric ulcer and 20 healthy blood donors. The diagnostic models were developed and valited by discriminant analysis. Results The peak intensity of differential expression proteins was not found in healthy blood donors, and 1 case was found in patient with gastric ulcer (m/z: 5 910,4 095). The peak intensity of 5 329, 4 095, 5 910, 8 691 and 3 300 (m/z) proteins were significantly higher in 40 gastric cancer patients than those in 20 gastric ulcer patients and 20 healthy blood donors ( P ＜0.05）. Three differential expression proteins were set up a diagnostic model together to diagnose gastric cancer. The diagnostic model made up of the differential expression proteins of 4 095, 5 910 and 8 691 had a sensitivity of 92.5% and a specificity of 97.5% . Conclusion Using SELDI-TOF-MS shows great potential to detect, and screen novel and better biomarkers for gastric cancer.
Automatic detection of pulmonary nodule based on computer tomography (CT) images can significantly improve the diagnosis and treatment of lung cancer. However, there is a lack of effective interactive tools to record the marked results of radiologists in real time and feed them back to the algorithm model for iterative optimization. This paper designed and developed an online interactive review system supporting the assisted diagnosis of lung nodules in CT images. Lung nodules were detected by the preset model and presented to doctors, who marked or corrected the lung nodules detected by the system with their professional knowledge, and then iteratively optimized the AI model with active learning strategy according to the marked results of radiologists to continuously improve the accuracy of the model. The subset 5−9 dataset of the lung nodule analysis 2016(LUNA16) was used for iteration experiments. The precision, F1-score and MioU indexes were steadily improved with the increase of the number of iterations, and the precision increased from 0.213 9 to 0.565 6. The results in this paper show that the system not only uses deep segmentation model to assist radiologists, but also optimizes the model by using radiologists' feedback information to the maximum extent, iteratively improving the accuracy of the model and better assisting radiologists.