I-Corps: Translation potential of an artificial intelligent (AI) platform to transform tumors imaged with magnetic resonance imaging (MRI) into three-dimensional (3D) models

Award ID: 2627919

This I-Corps project is based on the development of an artificial intelligence (AI) software platform that converts imaging scans of cancerous and noncancerous tumors into fully formed three dimensional (3D) models. Currently, the healthcare industry is driven by rising costs, shortages of trained professionals, and limited diagnostic capabilities. This technology is designed to improve the accuracy of tumor measurements, reduce the time radiologists spend processing images, and support clearer visualization of tumor growth over time. The goal is to enhance diagnostic quality and improve treatment planning by integrating with existing clinical workflows and producing high fidelity three-dimensional representations with human radiologist accuracy. The initial focus is aimed at brain tumor imaging, where precise volumetric information and minimal workflow disruption are especially valuable for clinicians and patients. This technology may address the current challenges to provide a scalable solution capable of improving efficiency, expanding access, and enhancing quality of care across diverse healthcare environments. This I-Corps project utilizes experiential learning coupled with first-hand investigation of the industry ecosystem to assess the translation potential of an artificial intelligence (AI)-based software to transform cancerous and non-cancerous tumors imaged with magnetic resonance imaging (MRI) into fully developed three-dimensional (3D) models. The aim is to enhance the accuracy of tumor measurements, reduce the radiologist's image processing time, and allow radiologists to review tumor growth over time in a three-dimensional space. The commercial application of the technology leverages machine learning to convert two-dimensional MRI scans into high-fidelity 3D tumor models with radiologist-level accuracy. The technology is designed to integrate into existing clinical workflows, offering reliable volumetric analysis and comprehensive clinical reports. Initially targeting the brain tumor imaging and diagnostics market, it provides significant clinical value with minimal integration burdens. By reducing measurement variability, streamlining radiology workload, and enabling longitudinal tumor assessment, the technology may improve clinical decision making and patient outcomes. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

NSF Program Director: Ruth Shuman