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
Detecto

Download Mobile App




AI Medical Diagnostic Algorithm for MRI Image Analysis Uses Self-Learning Across Hospitals

By HospiMedica International staff writers
Posted on 01 Sep 2022
Print article
Image: AI-based federated diagnostic algorithm efficiently learns across hospitals with data protection compliance (Photo courtesy of Pexels)
Image: AI-based federated diagnostic algorithm efficiently learns across hospitals with data protection compliance (Photo courtesy of Pexels)

Healthcare is currently being revolutionized by artificial intelligence. With precise AI solutions, doctors can be supported in diagnosis. However, such algorithms require a considerable amount of data and the associated radiological specialist findings for training. The creation of such a large, central database, however, places special demands on data protection. Additionally, the creation of the findings and annotations, for example the marking of tumors in an MRI image, is very time-consuming. To overcome these challenges, researchers have developed an algorithm that is able to learn independently across different medical institutions. The key feature of the algorithm is that it is "self-learning", i.e. it does not require extensive, time-consuming findings or markings by radiologists in the MRI images.

A multidisciplinary team from the Technical University of Munich (TUM, Munich, Germany) collaborated with other clinicians and researchers to develop an AI-based medical diagnostic algorithm for MRI images of the brain, without any data annotated or processed by a radiologist. Furthermore, this algorithm was to be trained "federally": In this way, the algorithm "comes to the data", so that the medical image data requiring special protection could remain in the respective clinic and did not have to be collected centrally. The federated algorithm was trained on more than 1,500 MR scans of healthy study participants from four institutions while maintaining data privacy.

The algorithm then was used to analyze more than 500 patient MRI scans to detect diseases such as multiple sclerosis, vascular disease, and various forms of brain tumors that the algorithm had never seen before. This opens up new possibilities for developing efficient AI-based federated algorithms that learn autonomously while protecting privacy. In their study, the researchers were able to show that the federated AI algorithm they developed outperformed any AI algorithm trained using only data from a single institution. To pool knowledge about MRI images of the brain, the research team trained the AI algorithm in different and independent medical institutions without violating data privacy or collecting data centrally. By protecting patient data while reducing radiologists' workloads, the researchers believe their federated AI technology will significantly advance digital medicine.

"Once this algorithm learns what MRI images of the healthy brain look like, it will be easier for it to detect disease. To achieve this requires intelligent computational aggregation and coordination between the participating institutes," said Prof. Dr. Albarqouni. PD Dr. Benedikt Wiestler, senior physician at TUM's University Hospital, who was involved in the study. "Training the model on data from different centers contributes significantly to the fact that our algorithm detects diseases much more robustly than other algorithms that are only trained with data from one center."

 

 

BMP Whole Blood Analyzer: GEM Premier ChemSTAT
Gold Supplier
High-Density Lipoprotein Containing Cholesterol Assay
HDL-c direct FS
New
3 & 5-Part All-In-One Auto Hematology Analyzer
SMT-50
New
Plastic Jerricans
Diamond RealSeal Jerricans

Print article
Radcal

Channels

AI

view channel
Image: AI transforms smartwatch ECG signals into a diagnostic tool for heart failure (Photo courtesy of Pexels)

AI-Based Smartwatch Accurately Detects Heart Failure Using ECG Signals

People with a weak heart pump might not have symptoms, but this common form of heart disease affects about 2% of the population and 9% of people over 60. When the heart cannot pump enough oxygen-rich blood,... Read more

Critical Care

view channel
Image: PATHFAST is a compact immunoanalyzer with superior assay performance (Photo courtesy of PHC Europe)

Benchtop Immunoanalyzer Delivers Lab Quality Results for Cardiology, Intensive Care and Emergency Wards at POC

A compact immunoanalyzer with superior assay performance combines the accuracy of a full-scale lab analyzer with the flexibility of a mobile solution, making it an ideal analysis system for laboratories,... Read more

Surgical Techniques

view channel
Image: Bioelectric medicine could stem excessive blood loss (Photo courtesy of Pexels)

Wearable Neurostimulation Solution Could Stem Excessive Blood Loss in the OR

A wearable neurostimulation solution focused on lessening excessive blood loss could save precious time for surgical teams in the operating room. A collaboration between Spark Biomedical, Inc.... Read more

Patient Care

view channel
Image: The digital stretcher scales are designed specifically for emergent situations in hospitals and emergency rooms (Photo courtesy of DETECTO)

Portable High-Capacity Digital Stretcher Scales Provide Precision Weighing for Patients in ER

For emergency arrivals into a hospital, time is of the essence for gathering patient weights. Now, digital stretcher scales specifically designed for emergent situations in hospitals and emergency rooms... Read more

Health IT

view channel
Image: Using digital data can improve health outcomes (Photo courtesy of Unsplash)

Electronic Health Records May Be Key to Improving Patient Care, Study Finds

When a patient gets transferred from a hospital to a nearby specialist or rehabilitation facility, it is often difficult for personnel at the new facility to access the patient’s electronic health records... Read more

Business

view channel
Image: The global visualization instruments for MIS market is estimated to surpass USD 21 billion by 2031 (Photo courtesy of Pexels)

Global Visualization Instruments for MIS Market Driven by Increasing Demand for Endoscopy Procedures

The last few years have witnessed an increase in patient preference for medical surgeries that involve fewer incisions. As a result, the demand for visualization instruments, which aid in achieving improved... Read more
Copyright © 2000-2022 Globetech Media. All rights reserved.