Zain Shariff

Curtis Senior High School, United States

Abstract Title: Artificial Intelligence-Guided Catheter Design for Patient-Specific Coronary Vein Procedures

Biography: Zain Shariff is a student at Curtis Senior High School in Washington State. His research focuses on personalized comprehensive cardiac care powered by artificial intelligence. He created AICathDesigner, an automated approach to make a personalized catheter for coronary vein cannulation which would increase success and reduce complications of these procedures. He has been recognized nationally and has earned multiple awards and invitations for his work. His passion is bridging technology into cardiac care and improving patient outcomes.

Research Interest: CT Scans are used in medicine to identify a patient’s anatomical features non-invasively. The coronary sinus ostium is a structure used in procedures for coronary venous system access but poses a challenge to physicians with its varied anatomy. AI segmentation and additional programs could utilize CT scans to create a catheter sheath to assist physicians. A dataset was compiled of 4789 CT Scan Slices with annotated cardiac structures from the Superior Vena Cava to the Coronary Sinus Ostium. A YOLOv11XL-seg Model was trained for 778 epochs. This accurate model achieved a mAP50-95 score of 0.67656. A broader application was made, featuring the trained model, and segmentation prediction data is analyzed to curate a catheter sheath. The program outputs a .stl file for catheter sheath. This study creates a new technology that can assist physicians in coronary vein procedures. Further model training, practicality assessment, and clinical trials are required before implementation.