ORNL researchers develop 'multitasking' AI tool to extract cancer data in record time

ORNL researchers develop 'multitasking' AI tool to extract cancer data in record time

Press releases may be edited for formatting or style | February 13, 2020 Artificial Intelligence Health IT

To build an efficient multitask CNN, they called on the world's most powerful and smartest supercomputer--the 200-petaflop Summit supercomputer at ORNL, which has over 27,600 deep learning-optimized GPUs.

The team started by developing two types of multitask CNN architectures--a common machine learning method known as hard parameter sharing and a method that has shown some success with image classification known as cross-stitch. Hard parameter sharing uses the same few parameters across all tasks, whereas cross-stitch uses more parameters fragmented between tasks, resulting in outputs that must be "stitched" together.

THE (LEADER) IN MEDICAL IMAGING TECHNOLOGY SINCE 1982. SALES-SERVICE-REPAIR

Special-Pricing Available on Medical Displays, Patient Monitors, Recorders, Printers, Media, Ultrasound Machines, and Cameras.This includes Top Brands such as SONY, BARCO, NDS, NEC, LG, EDAN, EIZO, ELO, FSN, PANASONIC, MITSUBISHI, OLYMPUS, & WIDE.


To train and test the multitask CNNs with real health data, the team used ORNL's secure data environment and over 95,000 pathology reports from the Louisiana Tumor Registry. They compared their CNNs to three other established AI models, including a single-task CNN.

"In addition to offering HPC and scientific computing resources, ORNL has a place to train and store secure data--all of these together are very important," Alawad said.

During testing they found that the hard parameter sharing multitask model outperformed the four other models (including the cross-stitch multitask model) and increased efficiency by reducing computing time and energy consumption. Compared with the single-task CNN and conventional AI models, the hard sharing parameter multitask CNN completed the challenge in a fraction of the time and most accurately classified each of the five cancer characteristics.

"The next step is to launch a large-scale user study where the technology will be deployed across cancer registries to identify the most effective ways of integration in the registries' workflows. The goal is not to replace the human but rather augment the human," Tourassi said.


The research team included Tourassi, Alawad, Shang Gao, John X. Qiu, Hong Jun Yoon, and J. Blair Christian from ORNL; Lynne Penberthy from NCI; Brent Mumphrey and Xiao-Cheng Wu from the Louisiana Tumor Registry; and Linda Coyle from Information Management Services, Inc.

JDACS4C partners include NCI and ORNL, as well as Frederick National Laboratory for Cancer Research and Argonne, Los Alamos, and Lawrence Livermore national laboratories.

UT-Battelle LLC manages ORNL for DOE's Office of Science. The Office of Science is the single largest supporter of basic research in the physical sciences in the United States and is working to address some of the most pressing challenges of our time.

Back to HCB News

You Must Be Logged In To Post A Comment