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
GLOBETECH PUBLISHING LLC

Download Mobile App




MRI AI Model Classifies Common Intracranial Tumors

By HospiMedica International staff writers
Posted on 07 Sep 2021
Print article
Image: GradCAM color maps colors showing tumor prediction (Photo courtesy of WUSTL)
Image: GradCAM color maps colors showing tumor prediction (Photo courtesy of WUSTL)
An artificial intelligence (AI) 3D model is capable of classifying a brain tumor as one of six common types from a single magnetic resonance imaging (MRI) scan, claims a new study.

To develop the GradCAM algorithm, researchers at Washington University (WUSTL; St. Louis, MO, USA), used 2,105 T1-weighted MRI scans from four publicly available datasets, split into training (1396), internal (361), and an external (348) datasets. A convolutional neural network (CNN) was trained to discriminate between healthy scans and those with tumors, classified by type (high grade glioma, low grade glioma, brain metastases, meningioma, pituitary adenoma, and acoustic neuroma). Performance of the model was then evaluated, with feature maps plotted to visualize network attention.

The internal test results showed GradCAM achieved an accuracy of 93.35% across seven imaging classes (a healthy class and six tumor classes). Sensitivities ranged from 91% to 100%, and positive predictive value (PPV) ranged from 85% to 100%. Negative predictive value (NPV) ranged from 98% to 100% across all classes. Network attention overlapped with the tumor areas for all tumor types. For the external test dataset, which included only two tumor types (high-grade glioma and low-grade glioma), GradCAM had an accuracy of 91.95%. The study was published on August 11, 2021, in Radiology: Artificial Intelligence.

“These results suggest that deep learning is a promising approach for automated classification and evaluation of brain tumors. The model achieved high accuracy on a heterogeneous dataset and showed excellent generalization capabilities on unseen testing data,” said lead author Satrajit Chakrabarty, MSc, of the department of electrical and systems engineering. “This network is the first step toward developing an artificial intelligence-augmented radiology workflow that can support image interpretation by providing quantitative information and statistics.”

Deep learning is part of a broader family of AI machine learning methods based on learning data representations, as opposed to task specific algorithms. It involves CNN algorithms that use a cascade of many layers of nonlinear processing units for feature extraction, conversion, and transformation, with each successive layer using the output from the previous layer as input to form a hierarchical representation.

Related Links:
Washington University


Print article

Channels

AI

view channel
Image: Cardiologs Holter arrhythmia diagnostic software is cloud-based, vendor-neutral and powered by AI (Photo courtesy of Cardiologs)

AI Predicts Short-Term Risk of Atrial Fibrillation Using 24-Hour Holter Recordings

Atrial Fibrillation (AFib) affects millions of people each year. However, the condition is often unrecognized and untreated. Nowadays, patients are subject to 24-hour ambulatory electrocardiograms (ECGs)... Read more

Critical Care

view channel
Image: Cutting-edge 4D flow MRI scans could revolutionize blood flow assessment in the heart (Photo courtesy of University of East Anglia)

4D Flow MRI Scans Could Revolutionize Diagnosis of Patients with Heart Failure

Researchers have developed cutting-edge imaging technology to help doctors better diagnose and monitor patients with heart failure. The state-of-the-art technology uses magnetic resonance imaging (MRI)... Read more

Surgical Techniques

view channel
Image: The Senhance surgical system with digital laparoscopy (Photo courtesy of Asensus Surgical)

Digital Laparoscopic Platform Leverages Augmented Intelligence and Machine Learning

Challenges in laparoscopic surgery can impact cost, utilization, effectiveness, and outcomes of the procedure. For instance, the inability of the surgeon to control vision can create efficiency and safety... Read more

Patient Care

view channel
Image: The biomolecular film can be picked up with tweezers and placed onto a wound (Photo courtesy of TUM)

Biomolecular Wound Healing Film Adheres to Sensitive Tissue and Releases Active Ingredients

Conventional bandages may be very effective for treating smaller skin abrasions, but things get more difficult when it comes to soft-tissue injuries such as on the tongue or on sensitive surfaces like... Read more

Health IT

view channel
Image: AI can reveal a patient`s heart health (Photo courtesy of Mayo Clinic)

AI Trained for Specific Vocal Biomarkers Could Accurately Predict Coronary Artery Disease

Earlier studies have examined the use of voice analysis for identifying voice markers associated with coronary artery disease (CAD) and heart failure. Other research groups have explored the use of similar... Read more

Business

view channel
Image: Expanding the role of autonomous robots can mitigate the shortage of physicians (Photo courtesy of Pexels)

Robot-Assisted Surgical Devices Market Driven by Increased Demand for Patient-Specific Surgeries

An aging population and accompanying retirements will cause a significant physician shortfall of 55,000 to 150,000 by 2030, creating a gap in the healthcare system. Expanding the role of autonomous robots... Read more
Copyright © 2000-2022 Globetech Media. All rights reserved.