Medical imaging is a technique of producing images of the human body. It plays an essential role in allowing medical professionals to provide accurate information about a patients anatomy, especially when dealing with tumors. The output image, i.e., MRI image is processed to be more beneficial to medical doctors using image segmentation and 3D model construction. Although image segmentation has been through phases of improvement over the last decade, this procedure of segmenting images and creating 3-D models of specific organs can be prolonged and repetitive.
The overarching goal of this research project is to streamline the process of converting MRI images of pelvic organs into 3-D model objects. The project was separated into two learning stages: understanding basic 3-D model construction and the creation of an AI model.
The goal for the Fall 2021 semester was to learn the basics of 3-D modeling using 3D Slicer, 3-D visualization software, and experimenting with Nvidia AIAA, an API (application programming interface) that allows users to conveniently create 3-D model objects using trained data to automate it. With the results obtained in the previous semester, the Spring 2022 semester focused on creating our own AI model trained using our own data– which are MRI images of pelvic organs.
The team is currently in the process of training their own AI model using Clara Train SDK, a framework used by Nvidia in training their AI models for different organs.
|Dr. Mathias Brieu||Clientfirstname.lastname@example.org|
|Dr. Negin Forouzesh||Advisoremail@example.com|
|Ralph Belleca||Project Lead, Front-Endfirstname.lastname@example.org|
|Nicol Barrios||Back-end Leademail@example.com|
|Silvano Medina||Documentation Lead, Backfirstname.lastname@example.org|
|Mary Semerdjian||Front-end Leademail@example.com|
|Jason Tejada||Customer Liaison, Backfirstname.lastname@example.org|