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

Area of Science:

• Oncology
• Surgical Technology
• Medical Imaging

Background:

• Gastric cancer necessitates effective surgical interventions.
• Laparoscopic radical gastrectomy is a common treatment approach.
• Advancements in imaging and surgical techniques are crucial for improving patient outcomes.

Purpose of the Study:

• To evaluate the influence of intelligent algorithm-based magnetic resonance imaging (MRI) on the short-term curative effects of laparoscopic radical gastrectomy for gastric cancer.
• To compare the efficacy of 3D versus 2D laparoscopic surgery in terms of operative parameters and postoperative recovery.

Main Methods:

• A convolutional neural network (CNN) algorithm was employed for MRI image segmentation in gastric cancer patients.
• 158 patients were randomized into 3D laparoscopy and 2D laparoscopy groups (79 each).
• Key outcomes including operation time, blood loss, lymph node dissection, and postoperative recovery metrics were analyzed.

Main Results:

• The CNN algorithm demonstrated high accuracy in image segmentation (DSC: 0.89, sensitivity: 0.93).
• The 3D laparoscopic group exhibited significantly shorter operation times and reduced intraoperative blood loss compared to the 2D group (P < 0.05).
• No significant differences were observed in lymph node dissection, postoperative recovery times, or complication rates between the groups.

Conclusions:

• The developed CNN algorithm accurately segments target areas, supporting preoperative examination for gastric cancer.
• 3D laparoscopic surgery offers advantages in reducing operative time and blood loss for gastric cancer patients.
• Both 3D and 2D laparoscopic approaches provide comparable short-term curative effects for gastric cancer.