Validation of deep learning enabled software MetronMind to measure vertebral heart size and vertebral left atrial size in dogs

Katharine Tess Sykes, Sonya G Gordon, John J Craig, Sonya Wesselowski, Alice H Watson · 2026

Read Validation of deep learning enabled software MetronMind to measure vertebral heart size and vertebral left atrial size in dogs by Katharine Tess Sykes, Sonya G Gordon, John J Craig, Sonya Wesselowski, Alice H Watson (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0339253.txt.

Description

Katharine Sykes and four colleagues validate an artificial intelligence tool for reading dog chest X-rays. Their 2026 study concerns two measurements vets take from radiographs. One estimates overall heart size, the other the size of the left atrium. Human measurers vary noticeably, both between observers and within repeats. The software, called MetronMind, promises consistency and speed. The study used over one thousand client-owned dogs of eighty breeds.

Two manual measuring methods were compared first. They agreed almost perfectly, with negligible bias between them. The software's readings were then benchmarked against a trained observer's. Statistical checks included correlation and agreement plots across right and left side images. Dogs varied widely in heart size, chest shape, and image quality, which makes the test realistic. Reliable automated measurement could standardise heart screening in busy clinics and flag enlargement earlier.

Catalog record

CREATORKatharine Tess Sykes, Sonya G Gordon, John J Craig, Sonya Wesselowski, Alice H Watson
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE36294
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0339253

Browse the full library · About the Tower of Babel