Digital Pathology Solution Resolves the Tissue Floater Conundrum

There are currently several measures a pathologist can employ to troubleshoot the tissue floater problem. Akin to forensic analysis, some laboratories have implemented molecular techniques (e.g., DNA fingerprinting for tissue identity testing) to try resolve this problem by dissecting, testing, and then comparing the molecular results of the tissue floater to the adjacent patient sample on the glass slide.

Clinical Pathologists at the University of Michigan (Ann Arbor, MI, USA) and their colleagues demonstrated the feasibility of using an image search tool to resolve the tissue floater conundrum. A glass slide was produced containing two separate hematoxylin and eosin (H&E)-stained tissue floaters. This fabricated slide was digitized along with the two slides containing the original tumors used to create these floaters. These slides were then embedded into a dataset of 2,325 whole slide images comprising a wide variety of H&E stained diagnostic entities. Digital slides were broken up into patches and the patch features converted into barcodes for indexing and easy retrieval. A deep learning-based image search tool was employed to extract features from patches via barcodes, hence enabling image matching to each tissue floater.

All three slides were then entirely digitized at ×40 magnification using an Aperio AT2 whole slide scanner (Leica Biosystems, Richmond, IL, USA). The quality of these digital slides was checked to avoid inclusion of unique identifiers All the slides were then entirely digitized at ×40 magnification using an Aperio AT2 scanner. The quality of these digital slides was checked to avoid inclusion of unique identifiers. These whole slide images (WSIs) included cases from a wide variety of anatomic sites (e.g., colon, brain, thyroid, prostate, breast, kidney, salivary gland, skin, soft tissue, etc.) exhibiting varied diagnostic pathologic entities (i.e., reactive, inflammatory, benign neoplasms, and malignancies).

The scientists reported that there was a very high likelihood of finding a correct tumor match for the queried tissue floater when searching the digital database. Search results repeatedly yielded a correct match within the top three retrieved images. The retrieval accuracy improved when greater proportions of the floater were selected. The time to run a search was completed within several milliseconds. The image search results for matching tissue floaters when using the UPMC 300 WSI pilot dataset showed that the median rank best result for both the bladder and colon tumor was 1 (95% CI =1) when selecting 5% up to 100% of the floater region.

The authors concluded that using an image search tool offers pathologists an additional method to rapidly resolve the tissue floater conundrum, especially for those laboratories that have transitioned to going fully digital for primary diagnosis. The study was published on July 15, 2020 in the journal Archives of Pathology & Laboratory Medicine.