Similar Image Search for Histopathology: SMILY

TL;DR

SMILY is a deep learning-based reverse image search tool that effectively retrieves histopathology images with similar features, aiding pathologists in efficiently exploring large image datasets for diagnosis and research.

Contribution

Introduces SMILY, a novel deep learning method for histopathology image retrieval that does not require specific annotations, improving search efficiency in large datasets.

Findings

SMILY retrieves images with similar histologic features and diagnoses.

Pathologists rated SMILY's results as relevant and accurate.

SMILY performs comparably to manual searches in accuracy.

Abstract

The increasing availability of large institutional and public histopathology image datasets is enabling the searching of these datasets for diagnosis, research, and education. Though these datasets typically have associated metadata such as diagnosis or clinical notes, even carefully curated datasets rarely contain annotations of the location of regions of interest on each image. Because pathology images are extremely large (up to 100,000 pixels in each dimension), further laborious visual search of each image may be needed to find the feature of interest. In this paper, we introduce a deep learning based reverse image search tool for histopathology images: Similar Medical Images Like Yours (SMILY). We assessed SMILY's ability to retrieve search results in two ways: using pathologist-provided annotations, and via prospective studies where pathologists evaluated the quality of SMILY search results. As a negative control in the second evaluation, pathologists were blinded to whether search results were retrieved by SMILY or randomly. In both types of assessments, SMILY was able to retrieve search results with similar histologic features, organ site, and prostate cancer Gleason grade compared with the original query. SMILY may be a useful general-purpose tool in the pathologist's arsenal, to improve the efficiency of searching large archives of histopathology images, without the need to develop and implement specific tools for each application.