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
BIO-RAD LABORATORIES

Download Mobile App




Self-Teaching AI Algorithm Uses Pathology Images to Diagnose Rare Diseases

By LabMedica International staff writers
Posted on 11 Oct 2022
Print article
Image: New model acts as search engine for large databases of pathology images (Photo courtesy of Brigham and Women’s Hospital)
Image: New model acts as search engine for large databases of pathology images (Photo courtesy of Brigham and Women’s Hospital)

Rare diseases are often difficult to diagnose and predicting the best course of treatment can be challenging for clinicians. Modern electronic databases can store an immense amount of digital records and reference images, particularly in pathology through whole slide images (WSIs). However, the gigapixel size of each individual WSI and the ever-increasing number of images in large repositories, means that search and retrieval of WSIs can be slow and complicated. As a result, scalability remains a pertinent roadblock for efficient use. To solve this issue, researchers have now developed a deep learning algorithm that can teach itself to learn features which can then be used to find similar cases in large pathology image repositories.

Known as SISH (Self-Supervised Image search for Histology), the new tool developed by investigators at Brigham and Women’s Hospital (Boston, MA, USA) acts like a search engine for pathology images and has many potential applications, including identifying rare diseases and helping clinicians determine which patients are likely to respond to similar therapies. The algorithm teaches itself to learn feature representations which can be used to find cases with analogous features in pathology at a constant speed regardless of the size of the database.

In their study, the researchers tested the speed and ability of SISH to retrieve interpretable disease subtype information for common and rare cancers. The algorithm successfully retrieved images with speed and accuracy from a database of tens of thousands of whole slide images from over 22,000 patient cases, with over 50 different disease types and over a dozen anatomical sites. The speed of retrieval outperformed other methods in many scenarios, including disease subtype retrieval, particularly as the image database size scaled into the thousands of images. Even while the repositories expanded in size, SISH was still able to maintain a constant search speed.

The self-teaching algorithm, however, has some limitations including a large memory requirement, limited context awareness within large tissue slides and the fact that it is limited to a single imaging modality. Overall, the algorithm demonstrated the ability to efficiently retrieve images independent of repository size and in diverse datasets. It also demonstrated proficiency in diagnosis of rare disease types and the ability to serve as a search engine to recognize certain regions of images that may be relevant for diagnosis. This work may greatly inform future disease diagnosis, prognosis, and analysis.

“We show that our system can assist with the diagnosis of rare diseases and find cases with similar morphologic patterns without the need for manual annotations, and large datasets for supervised training,” said senior author Faisal Mahmood, PhD, in the Brigham’s Department of Pathology. “This system has the potential to improve pathology training, disease subtyping, tumor identification, and rare morphology identification.”

“As the sizes of image databases continue to grow, we hope that SISH will be useful in making identification of diseases easier,” added Mahmood. “We believe one important future direction in this area is multimodal case retrieval which involves jointly using pathology, radiology, genomic and electronic medical record data to find similar patient cases.”

Related Links:
Brigham and Women’s Hospital 

Platinum Member
COVID-19 Rapid Test
OSOM COVID-19 Antigen Rapid Test
Magnetic Bead Separation Modules
MAG and HEATMAG
Complement 3 (C3) Test
GPP-100 C3 Kit
New
Gold Member
Fully Automated Cell Density/Viability Analyzer
BioProfile FAST CDV

Print article

Channels

Clinical Chemistry

view channel
Image: The 3D printed miniature ionizer is a key component of a mass spectrometer (Photo courtesy of MIT)

3D Printed Point-Of-Care Mass Spectrometer Outperforms State-Of-The-Art Models

Mass spectrometry is a precise technique for identifying the chemical components of a sample and has significant potential for monitoring chronic illness health states, such as measuring hormone levels... Read more

Hematology

view channel
Image: The CAPILLARYS 3 DBS devices have received U.S. FDA 510(k) clearance (Photo courtesy of Sebia)

Next Generation Instrument Screens for Hemoglobin Disorders in Newborns

Hemoglobinopathies, the most widespread inherited conditions globally, affect about 7% of the population as carriers, with 2.7% of newborns being born with these conditions. The spectrum of clinical manifestations... Read more

Immunology

view channel
Image: The AI predictive model identifies the most potent cancer killing immune cells for use in immunotherapies (Photo courtesy of Shutterstock)

AI Predicts Tumor-Killing Cells with High Accuracy

Cellular immunotherapy involves extracting immune cells from a patient's tumor, potentially enhancing their cancer-fighting capabilities through engineering, and then expanding and reintroducing them into the body.... Read more

Microbiology

view channel
Image: The T-SPOT.TB test is now paired with the Auto-Pure 2400 liquid handling platform for accurate TB testing (Photo courtesy of Shutterstock)

Integrated Solution Ushers New Era of Automated Tuberculosis Testing

Tuberculosis (TB) is responsible for 1.3 million deaths every year, positioning it as one of the top killers globally due to a single infectious agent. In 2022, around 10.6 million people were diagnosed... Read more
Copyright © 2000-2024 Globetech Media. All rights reserved.