AI System Uses Pathology Images to Diagnose Rare Diseases

A new AI tool developed by scientists at the Mahmood Lab at Brigham and Women’s Hospital uses artificial intelligence to train the system to identify potential patients with rare diseases by comparing pathology images from a patient to large repositories of similar images.

The so-called Self-Supervised Image search for Histology, or SISH, acts like a search engine for pathology images and can identify rare diseases and help clinicians determine therapies a patient is most likely to respond to for treatment. The researchers discussed the system in a paper in Nature Biomedical Engineering.

“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 of the Brigham’s Department of Pathology. “This system has the potential to improve pathology training, disease subtyping, tumor identification, and rare morphology identification.”

Modern electronic databases can store an immense number of digital records and reference images, particularly in pathology through whole slide images. However, the large size of each individual image and the increasing number of images in large repositories means that search and retrieval can be slow and complicated.

To enable scalability and efficient use, the researchers at the Brigham developed SISH, which teaches itself to learn features in pathology that can be used to identify cases with analogous qualities 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 more than 22,000 patient cases, with more than 50 different disease types and more than 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 researchers acknowledge that the algorithm has some limitations including the need for a large amount of memory, limited context awareness within large tissue slides, and the fact that it is limited to a single imaging modality.

Nevertheless, 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.

“As the sizes of image databases continue to grow, we hope that SISH will be useful in making identification of diseases easier,” said 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.”

Author: Rare Daily Staff