Intelligent Algorithm-Based Magnetic Resonance Imaging in Radical Gastrectomy under Laparoscope

Abstract

The study focused on the influence of intelligent algorithm-based magnetic resonance imaging (MRI) on short-term curative effects of laparoscopic radical gastrectomy for gastric cancer. A convolutional neural network- (CNN-) based algorithm was used to segment MRI images of patients with gastric cancer, and 158 subjects admitted at hospital were selected as research subjects and randomly divided into the 3D laparoscopy group and 2D laparoscopy group, with 79 cases in each group. The two groups were compared for operation time, intraoperative blood loss, number of dissected lymph nodes, exhaust time, time to get out of bed, postoperative hospital stay, and postoperative complications. The results showed that the CNN-based algorithm had high accuracy with clear contours. The similarity coefficient (DSC) was 0.89, the sensitivity was 0.93, and the average time to process an image was 1.1 min. The 3D laparoscopic group had shorter operation time (86.3 ± 21.0 min vs. 98 ± 23.3 min) and less intraoperative blood loss (200 ± 27.6 mL vs. 209 ± 29.8 mL) than the 2D laparoscopic group, and the difference was statistically significant ( $P<0.05$ ). The number of dissected lymph nodes was 38.4 ± 8.5 in the 3D group and 36.1 ± 6.0 in the 2D group, showing no statistically significant difference ( $P>0.05$ ). At the same time, no statistically significant difference was noted in postoperative exhaust time, time to get out of bed, postoperative hospital stay, and the incidence of complications ( $P>0.05$ ). It was concluded that the algorithm in this study can accurately segment the target area, providing a basis for the preoperative examination of gastric cancer, and that 3D laparoscopic surgery can shorten the operation time and reduce intraoperative bleeding, while achieving similar short-term curative effects to 2D laparoscopy.