Development and validation of the ISGPP model marks a significant advancement in automating residual pancreatic cancer (RPC) quantification. The model demonstrated robust performance across diverse scanners, achieving mean F1 scores of 0.81-0.71 upon validation. A comprehensive dataset of 528 unique H&E slides from 528 patients facilitated training the model, which is now publicly available. This […]
Category: Digital Surgery and Telemedicine
New neural network enhances drug discovery for surgical treatments
A novel attention-based convolution transpositional interfusion network (ACTIN) has shown promising results for drug discovery with limited data. Utilizing just 393 training instances, ACTIN achieved state-of-the-art performance by leveraging graph convolution and transformer mechanisms to analyze drug and transcriptome data. It identifies pharmacophores that may benefit surgical patients, aiming to reduce complications and expedite recovery. […]
AI-driven gaming enhances laparoscopic cholecystectomy training effectiveness
An AI-powered mobile game, LapBot, was validated for teaching safe laparoscopic cholecystectomy skills. Among 903 global participants, increased game difficulty led to lower scores (p
AI Model Successfully Evaluates Surgical Skill in Robotic Distal Gastrectomy
An AI model effectively evaluates surgical skill in robotic distal gastrectomy (RDG) by accurately recognizing and analyzing instrument usage. Experienced surgeons demonstrated shorter durations using specific instruments during infrapyloric lymphadenectomy compared to non-experienced surgeons. This study showcases the feasibility of using AI for objective skill assessment in RDG, enhancing training and potentially improving patient outcomes […]
Augmented Reality System Enhances 3D Visualization in Liver Surgeries
An augmented reality (AR) system for laparoscopic liver surgery shows promise in improving visualization of internal anatomy. The system achieved a mean registration time of 2.4 minutes and a high accuracy rate of 93.8% in aligning preoperative 3D models with real-time laparoscopic images. Evaluations by surgeons demonstrate that this AR technology could significantly enhance tumor […]
Positive reaction to immersive robotic surgical training
Researchers found that using 3D visors for immersive robotic surgery training garnered positive feedback from medical students and residents. Nearly 90% of participants expressed high engagement and intention to use the technology. The median System Usability Scale score was 80, and the median Simulator Sickness Questionnaire score was 44.88. These results suggest that immersive reality […]
AI Platform Outperforms CT in Diagnosing Acute Appendicitis
Researchers validated an artificial intelligence platform for diagnosing acute appendicitis. The platform demonstrated high sensitivity (92.2%), specificity (97.2%), and negative predictive value (98.7%), outperforming CT scanning in accuracy metrics. Decision curve analysis showed a substantial net benefit, indicating the platform’s clinical utility in decision-making. The AI platform may assist clinicians in cases where access to […]
Improved Grasper Enhances Detection of Arterial Pulsations in Laparoscopy
Study validates optigrip® haptic grasper for arterial pulsation detection in laparoscopy. Results show 96% pulsation detection rate with haptic grasper compared to 6% with conventional grasper. Optigrip® identifies pulsations in 100% of 4-5mm arteries and 92% of smallest arteries, while conventional grasper only detects 8% of smallest arteries. Findings highlight significant tactile perception improvement for […]
AI’s pivotal role in gastric cancer management
Explores AI’s significant impact on early detection and surgical intervention for gastric cancer, crucial for improving patient outcomes. AI enhances early detection precision through image analysis and aids surgical decision-making with predictive modeling. The review discusses the historical shift in gastric cancer treatment towards surgical resection and the challenges posed by deploying AI in healthcare. […]
Deep Learning Model for Predicting Gastric Cancer Recurrence
Using CT imaging data, a deep learning model accurately predicts postoperative recurrence in gastric cancer patients. Developed and validated on 2,813 patients, the model showed excellent performance in identifying high-risk cases of recurrence. The deep learning fusion signature outperformed clinical models and baseline deep learning signatures, demonstrating its potential as a prognostic factor for patients […]