You are currently viewing NVIDIA : Medical Centers Tap AI , Federated Learning for Better Cancer Detection
Representation image: This image is an artistic interpretation related to the article theme.

NVIDIA : Medical Centers Tap AI , Federated Learning for Better Cancer Detection

A committee of experts from top U.S. medical centers and research institutes is harnessing NVIDIA-powered federated learning to evaluate the impact of federated learning and AI-assisted annotation to train AI models for tumor segmentation. Federated learning is a technique for developing more accurate, generalizable AI models trained on data across diverse data sources without mitigating data security or privacy. It allows several organizations to collaborate on the development of an AI model without sensitive data ever leaving their servers. “Due to privacy and data management constraints, it’s growing more and more complicated to share data from site to site and aggregate it in one place – and imaging AI is developing faster than research institutes can set up data-sharing contracts,” said John Garrett, associate professor of radiology at the University of Wisconsin-Madison. “Adopting federated learning to build and test models at multiple sites at once is the only way, practically speaking, to keep up. It’s an indispensable tool.”

**AI in Radiology: Revolutionizing Diagnosis and Treatment**
**AI for Medical Imaging:

The team’s work focuses on developing and applying AI-powered tools for medical imaging analysis. These tools are designed to assist clinicians in making more accurate diagnoses and treatment decisions. The team’s work is particularly relevant to the field of radiology, where AI is being increasingly used to assist radiologists in reading and interpreting medical images.

Federated learning, a revolutionary approach to machine learning, allows for collaborative training of models across multiple devices without sharing raw data. This program aimed to foster collaboration and accelerate research in federated learning. The program’s success was evident in the research conducted by the participating institutes.

This process is repeated until a convergence point is reached. This convergence point signifies that the global model has achieved the desired accuracy and is no longer needing updates from the client servers. Here’s a deeper look at the federated learning process:

This involved identifying and classifying each image, video, or audio file based on predefined categories. This process required significant human effort and expertise, as it involved understanding the nuances of the model’s intended use and the specific characteristics of the data. The training data was then used to train the model, which is a process of adjusting the model’s parameters to minimize the difference between its predictions and the actual values.

The team is using MONAI Label, an image-labeling tool that enables users to develop custom AI annotation apps, reducing the time and effort needed to create new datasets. Experts will validate and refine the AI-generated segmentations before they’re used for model training. Data for both the manual and AI-assisted annotation phases is hosted on Flywheel, a leading medical imaging data and AI platform that has integrated NVIDIA MONAI into its offerings. Once the project is complete, the team plans to publish their methodology, annotated datasets and pretrained model to support future work. “We’re interested in not just exploring these tools,” Garrett said, “but also publishing our work so others can learn and use these tools throughout the medical field.”

This program is designed to support the development of innovative and impactful research in various fields, including computer science, engineering, and mathematics. The program offers a range of benefits, including access to NVIDIA GPUs, software, and technical support. It also provides funding for research projects, travel expenses, and conference attendance.

Leave a Reply