Computer-Aided Decision Support and 3D Models in Pancreatic Cancer Surgery: A Pilot Study

Area of Science:

• Hepatopancreatobiliary surgery
• Medical imaging analysis
• Surgical oncology

Background:

• Preoperative planning for pancreatic head cancer is challenging, demanding specialized expertise.
• Assessing tumor resectability, particularly concerning vascular involvement, is critical for surgical success.
• Existing methods may not fully capture the complexities of tumor anatomy and its relation to vital structures.

Purpose of the Study:

• To evaluate the added value of 3D patient models and CAD algorithms in determining pancreatic head tumor resectability.
• To compare the performance of experts using CT scans alone versus CT scans with 3D models and CAD.
• To assess the impact on perceived preoperative needs, decision-making quality, and confidence.

Main Methods:

• A pilot study involving 14 hepatopancreatobiliary experts from eight institutions.
• A crossover design was used, with experts assessing resectable and borderline resectable cases.
• Participants were divided into three groups: controls (CT scan), 3D group (CT scan and 3D models), and CAD group (CT scan, 3D models, and CAD).

Main Results:

• The CAD group showed a significantly improved perceived ability to determine tumor-vessel contact degrees and length compared to controls.
• Experts in the CAD group predicted lower degrees of tumor-vessel contact for borderline resectable tumors.
• The 3D group demonstrated higher confidence in predicting the need for vascular resection across all cases.

Conclusions:

• Computer-aided detection, incorporating 3D models, enhances experts' accuracy in assessing vessel involvement in pancreatic cancer.
• These advanced visualization techniques support the development of improved diagnostic and therapeutic strategies for pancreatic cancer.
• The findings suggest a potential role for CAD and 3D modeling in optimizing preoperative planning and surgical outcomes.