We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

Features Partner Sites Information LinkXpress
Sign In
Advertise with Us

Download Mobile App




Events

ATTENTION: Due to the COVID-19 PANDEMIC, many events are being rescheduled for a later date, converted into virtual venues, or altogether cancelled. Please check with the event organizer or website prior to planning for any forthcoming event.

Next-Generation Artificial Intelligence to Improve Medical Imaging Diagnostics

By MedImaging International staff writers
Posted on 01 Mar 2023
Print article
Image: New project creates next-gen AI to improve diagnostics (Photo courtesy of University of Houston)
Image: New project creates next-gen AI to improve diagnostics (Photo courtesy of University of Houston)

Despite the remarkable advancements in artificial intelligence (AI), studies have found that it may not be able to improve the accuracy of medical diagnoses. It is therefore vital that next generation computer-aided diagnosis algorithms need to be both interactive and highly accurate in order to utilize the true potential of AI in improving medical diagnosis.

The University of Houston (Houston, TX, USA) has recently been awarded a grant from the National Cancer Institute for their upcoming project of creating a new AI system that will focus on improving diagnostics for lung cancer. This project plans on developing an AI-human collaboration framework, which will utilize eye-gaze tracking, intention reverse-engineering and reinforcement learning to determine when and how an AI system should interact with radiologists in order to make a medical diagnosis.

The primary focus of this project is to create a user-friendly and minimally interfering interface which will enable radiologist-AI interaction. It will be focusing on two major clinical applications: detection of lung nodules and pulmonary embolism. Lung cancer ranks as the second most common cancer, and pulmonary embolism is the third most common cause of cardiovascular death. This project will further investigate questions that have been largely under-explored, such as when and how AI systems should interact with radiologists and how to model radiologist visual scanning processes.

“Studying how AI can help radiologists reduce these diseases' diagnostic errors will have significant clinical impacts,” said Hien Van Nguyen, University of Houston associate professor of electrical and computer engineering, who is leading the project. “Our approaches are creative and original because they represent a substantive departure from the existing algorithms. Instead of continuously providing AI predictions, our system uses a gaze-assisted reinforcement learning agent to determine the optimal time and type of information to present to radiologists. Our project will advance the strategies for designing user interfaces for doctor-AI interaction by combining gaze-sensing and novel AI methodologies.”

Related Links:
University of Houston

Gold Supplier
SBRT Phantom with Removable Spine
E2E SBRT Phantom with Removable Spine Model 036S-CVXX-xx
New
Ultrasound System
Ultimus 9E
New
Ceiling-Mounted Digital X-Ray System
DigitalDiagnost C50
New
Mini PACS
QXLink

Print article

Channels

MRI

view channel
Image: New scan measures tumor oxygen levels in real-time to help guide treatment (Photo courtesy of ICR)

Oxygen-Enhanced MRI Technology Allows Cancer Doctors to See Inside Tumors

Since the 1950s, researchers have been aware of the difficulty in effectively treating tumors deprived of oxygen, a problem that is further exacerbated when treating them with radiotherapy.... Read more

Ultrasound

view channel
Image: New focused ultrasound is effective for treating Parkinson’s, movement disorders (Photo courtesy of Pexels)

New Focused Ultrasound Treatment Proves Effective for Parkinson’s Disease Patients

Parkinson's disease is a neurological condition characterized by the loss of dopamine neurons within the brain. While medications such as levodopa can be effective in managing this condition, some patients... Read more

Nuclear Medicine

view channel
Image: Tracking radiation treatment in real time promises safer, more effective cancer therapy (Photo courtesy of Pexels)

Real-Time 3D Imaging Provides First-of-Its-Kind View of X-Rays Hitting Inside Body During Radiation Therapy

Radiation is used in treatment for hundreds of thousands of cancer patients each year, bombarding an area of the body with high energy waves and particles, usually X-rays. The radiation can kill cancer... Read more

Imaging IT

view channel
Image: The new Medical Imaging Suite makes healthcare imaging data more accessible, interoperable and useful (Photo courtesy of Google Cloud)

New Google Cloud Medical Imaging Suite Makes Imaging Healthcare Data More Accessible

Medical imaging is a critical tool used to diagnose patients, and there are billions of medical images scanned globally each year. Imaging data accounts for about 90% of all healthcare data1 and, until... Read more
Copyright © 2000-2023 Globetech Media. All rights reserved.