A pilot study for a non-invasive system for detection of malignancy in canine subcutaneous and cutaneous masses using machine learning

Dank G, Buber T, Polliack G, Aviram G, Rice A, Yehudayoff A, Kent MS. A pilot study for a non-invasive system for detection of malignancy in canine subcutaneous and cutaneous masses using machine learning. Front Vet Sci. 2023;10. doi:10.3389/fvets.2023.1109188

This study evaluated the performance of the HT Vista, an AI-based thermal imaging system, for detecting malignancy in canine cutaneous and subcutaneous masses. Forty-five dogs with 69 masses were examined, with thermal data from the masses and adjacent healthy tissue analyzed by an AI algorithm. Cytology or biopsy results were compared to train the system, achieving an accuracy of 90%, sensitivity of 93%, and specificity of 88%. The study suggests the potential for this non-invasive technology to assist clinicians in determining the need for further diagnostics in dogs with suspicious masses.