Dry Lab Research: Artificial Intelligence & 3D Printing
Research Areas
Recent Work
3D Printing to Increase the Allograft Liver Pool
This is a collaborative study between Intermountain (Manuel I. Rodriguez-Davalos MD, PI), and, Stanford University (Carlos O. Esquivel MD, Ph.D. PI).
Project Summary: Organ shortage has reached epidemic proporsions in the US. Approximately 1 of 6 patients on the waiting list for a liver transplant run out of time before having the opportunity of a life saving transplant. To increase the donor pool, segmental grafts have been used for quite some time; however, this type of transplants is performed infrequently. The main barriers to increase utilization of segmental grafts are a scarcity of experienced surgeons to perform the procedure, and a lack of standardized imaging evaluation of the donor as well as a refined knowledge of the size match between the donor and recipient. This project seeks to 1) develop a tool with the capacity to evaluate anatomical suitability (ie, volume measurements and 3D modeling) of potential donors for segmental grafts in an objective, reproducible and rapid manner by using artificial intelligence (AI) through identificacion of liver anatomical landmarks with minimal human intervention; 2) utilize biomimicry simulation materials and specialized image processing platforms to adjust current 3D printing techniques and create realistic 3D liver models with the goal of training fellows and young surgeons to procure these graft types; and 3) utilize traditional 3D printing techniques with the patients in our waitlists that could benefit from segmental grafts and have a “Liver 3D library” that will enhance a comprehensive preoperative planning. We are convinced that this research proposal will strive to fulfill both institutional missions, as this collaborative effort aims to explore an innovative approach to help this patient population live the healthiest lives possible.
The photographs show a 3D printing of a human liver from a person who is donating the right lobe to a recipient. This provides a road map of the geographic distribution of the hepatic veins and the anatomic distribution of the hepatic artery. The arrow points to a replaced left hepatic artery coming off the left gastric artery. This anomaly will not interfere with using the right lobe for transplantation.
Artificial Intelligence (AI) technology has the potential to facilitate surgical decision making
Our initial project is to train an AI algorithm to quantitatively and reproducibly evaluate steatosis and other features of donor biopsies to assess their impact on transplantation.
Specifically, we aim to 1) test the ability of AI models to determine the degree of steatosis; 2) recalibrate the association of steatosis with post-transplantation outcomes, and 3) to train AI to identify additional features of biopsies associated with post-transplantation outcomes.
Models will be tested on additional slides and compared to the pathologists’ labeling. Scoring by the AI model will be correlated with early post-liver transplantation outcomes to build a predictive model of the impact of steatosis on outcomes. We hope that these results will be to enable identification of livers suitable for transplant and reduce wrongly discard grafts. Subsequently, we will use this AI infrastructure to address other surgical challenges.