Skip to main content
2025 ACVIM Forum Main banner
Final Program


2025 Event Program
Icon Legend
This session is not on your agenda.
This session is on your agenda. Click again to remove it.
Presentation Icons
ACVIM Resident Research Award Eligible
ACVIM Resident Research Award Eligible
Additional Fees May Be Required
Additional Fees May Be Required
By Invite Only
By Invite Only
Capturing for On Demand
Capturing for On Demand
Cardiology Research Abstract Award Eligible
Cardiology Research Abstract Award Eligible
ERC Approved Lecture for ACVIM Residency
ERC Approved Lecture for ACVIM Residency
Livestream
Livestream
One Health
One Health
Pre-Registration Required
Pre-Registration Required
Research Abstract
Research Abstract
Specialty Symposium
Specialty Symposium
ACVIM Resident Research Award Winner
ACVIM Resident Research Award Winner
Cardiology Research Abstract Award Winner
Cardiology Research Abstract Award Winner
Rate ePoster

Small Animal Internal Medicine

Assessment of an Evolved Deep Learning Artificial Intelligence Algorithm for Canine/Feline Urine Sediment Samples

(NU23) Assessment of an Evolved Deep Learning Artificial Intelligence Algorithm for Canine/feline Urine Sediment Samples

Thursday, June 19, 2025
5:30 PM - 7:00 PM ET
Location: Exhibit Hall Poster Park - Poster Stand
Poster

    Research Abstract - Physical Poster Presenter(s)

  • Cory D. Penn, DVM (he/him/his)

    Head of Vetscan Imagyst, Immunoassay, and Virtual Laboratory
    Zoetis Global Diagnostics - Medical Affairs
    Parsippany, NJ, United States

Abstract:

Background: Urine sediment exam is vital to a complete urinalysis. A deep learning artificial intelligence (AI) tool for consistent evaluation of urine sediment samples can provide rapid, in-clinic results. Hypothesis/

Objectives: Vetscan Imagyst® AI Urine Sediment v2.0 will accurately identify red blood cells, white blood cells, struvite crystals, calcium oxalate dihydrate crystals, and rod-shaped and cocci bacteria in agreement with digital review by ACVP-boarded clinical pathologists (ACVP-CPs). Animals: Urine samples included client-owned dogs and cats undergoing urinalysis for any reason submitted to Zoetis Reference Laboratories. Some samples were artificially created by spiking donor urine with necessary elements (e.g., RBC from whole blood). A total of 175 urine samples (canine, 56%; feline, 44%) were evaluated.

Methods: Samples were prepped via the Vetscan Imagyst® preparation method, scanned, and evaluated digitally by 3 blinded ACVP-CPs who recorded results for urine elements as an average of 10, 40X fields. Algorithm performance and agreement were calculated as compared to ACVP-CP results.

Results: Accuracy, sensitivity, and specificity for urine sediment object classes ranged from 91-95%, 89-95%, and 85-96%, respectively (Table 1). Agreement between Vetscan Imagyst® AI Urine Sediment v2.0 and ACVP-CPs was good to excellent (Table 2). Conclusions and Clinical Importance: Vetscan Imagyst® AI Urine Sediment v2.0 was comparable to ACVP-CPs in the identification and semi-quantitative agreement of elements in urine sediment. In-clinic utilization of Vetscan Imagyst® AI Urine Sediment v2.0 can provide a diagnostic tool for urine sediment evaluation.