AI applications in laparoscopic surgery simulation demonstrate significant promise, achieving concordance rates of 42%-100% with human assessments. The study tested AI trained on multiple procedures, revealing 100% accuracy for the appendectomy in the five-class scoring system and also high accuracy in the two-class system across three different procedures. These results suggest that AI can reliably […]
Category: Digital Surgery and Telemedicine
AI system enhances polyp detection in colonoscopy
The developed AI-assisted system significantly improves the detection and localization of colorectal polyps during colonoscopy. Out of five CNN models tested, EfficientNetV2 excelled, achieving an accuracy of 93.3% and a specificity of 94.6% on the test set. The system’s performance metrics, including a high AUC of 0.983, suggest its potential for clinical applications, as illustrated […]
A novel MRI-based model predicts perineural invasion in cholangiocarcinoma
An innovative MRI-based fusion model effectively predicts perineural invasion (PNI) status in intrahepatic cholangiocarcinoma (ICC) patients. The model, incorporating deep learning, radiomics, and clinical features, was developed from a study involving 192 patients. In the training phase, it achieved an AUC of 0.905 and 82.3% accuracy, while the external test set yielded an AUC of […]
AI model predicts in-hospital mortality for elderly surgical patients
An AI-driven Geriatric Emergency Perioperative Risk Index (GEPR) effectively predicts postoperative in-hospital mortality for elderly patients undergoing emergency general surgery. Utilizing data from 1,500 patients, the Random Forest Classifier algorithm excelled in accuracy, achieving a c-statistic of 0.872. The probability of in-hospital mortality varied significantly, increasing from 0% to 100% as GEPR scores ranged from […]
Interactive model enhances pancreas segmentation accuracy in CT images
A novel deep-learning network, RRM-TransUNet, significantly improves pancreas segmentation accuracy in CT images. Achieving a dice similarity coefficient of 93.82% and an average symmetric surface distance error of 1.12 mm on multiple datasets, this model integrates clinical expertise with user interaction. By using advanced techniques like rotary position embedding and a mixture of experts mechanism, […]
Artificial intelligence enhances precision and safety in surgery
The integration of artificial intelligence (AI) in surgical medicine is revolutionizing the field, enhancing the precision and safety of procedures. AI aids in preoperative diagnosis, real-time navigation during surgery, and postoperative management. Specific case studies demonstrate significant improvements in surgical outcomes, such as reduced complications and faster recoveries. However, challenges including cost, data security, and […]
Enhanced assessment of blood supply during colorectal surgery
Integrating biophysical modeling and machine learning significantly improves intraoperative assessment of intestinal perfusion in laparoscopic low anterior rectal resection. An analysis of 68 patients demonstrated that the automated model outperformed traditional scoring methods, achieving a root mean square error of 2.47 and a mean absolute error of 1.99. This innovative approach offers a quantitative framework, […]
AI Tool Enhances Prediction of Liver Resection Complexity
An advanced AI tool has been developed to predict intraoperative liver resection complexity (LRC) using preoperative CT scans. By generating 3D models of anatomy, including tumors and vascular structures, the tool outperforms traditional predictions made by surgeons. With an accuracy of 79.4% and an AUC of 85.1%, it provides significant improvements in forecasting surgical complexity. […]
DeepGuide enhances membrane visualization in surgery.
DeepGuide, a novel navigation system, significantly improved mesenteric integrity rates from 75% to 98% during laparoscopic radical resections in a study involving 60 patients. The system demonstrated superior signal-to-background ratios (2.30 ± 0.15) compared to conventional illumination (1.32 ± 0.16). Additionally, immunofluorescence analyses confirmed collagen enrichment aligned with 385 nm-excited autofluorescence properties. This innovative tool […]
AI Successfully Predicts Major Surgery Needs in Trauma Patients
An artificial intelligence model demonstrated a significant ability to predict the need for major surgery in trauma patients, achieving an ROC-AUC of 0.80-0.86. Specifically, predictions for neurosurgery reached an ROC-AUC of 0.90-0.95, while vascular and abdominal surgeries had scores of 0.69-0.88 and 0.77-0.84, respectively. This predictive capability, utilizing prehospital data, could enhance the early triage […]