Addressing Delicate and Variable Cancer Morphology in Spectral Histopathology Using Canine Visceral Hemangiosarcoma

Patharee Oungsakul, David Perez-Guaita, Alok K. Shah, David Duffy, Bayden R. Wood, Helle Bielefeldt-Ohmann, Michelle M. Hill

Research output: Contribution to journalArticleResearchpeer-review

5 Citations (Scopus)


Spectral histopathology has shown promise for the classification and diagnosis of tumors with defined morphology, but application in tumors with variable or diffuse morphologies is yet to be investigated. To address this gap, we evaluated the application of Fourier transform infrared (FTIR) imaging as an accessory diagnostic tool for canine hemangiosarcoma (HSA), a vascular endothelial cell cancer that is difficult to diagnose. To preserve the delicate vascular tumor tissue structure, and potential classification of single endothelial cells, paraffin removal was not performed, and a partial least square discrimination analysis (PLSDA) and Random Forest (RF) models to classify different tissue types at individual pixel level were established using a calibration set (24 FTIR images from 13 spleen specimens). Next, the prediction capability of the PLSDA model was tested with an independent test set (n= 11), resulting in 74% correct classification of different tissue types at an individual pixel level. Finally, the performance of the FTIR spectropathology and chemometric algorithm for diagnosis of HSA was established in a blinded set of tissue samples (n= 24), with sensitivity and specificity of 80 and 81%, respectively. Taken together, these results show that FTIR imaging without paraffin removal can be applied to tumors with diffuse morphology, and this technique is a promising tool to assist in canine splenic HSA differential diagnosis.

Original languageEnglish
Pages (from-to)12187-12194
Number of pages8
JournalAnalytical Chemistry
Issue number36
Publication statusPublished - 14 Sept 2021

Cite this