TY - GEN
T1 - Tumour classification with optimized sliding window size for OCT imaging
T2 - Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXVI 2022
AU - Čiževskis, Oskars
AU - Cugmas, Blaž
AU - Viškere, Daira
AU - Melderis, Mikus
AU - Liepniece-Karele, Inta
AU - Yao, Junjie
AU - Tamošiūnas, Mindaugas
N1 - Funding Information:
This research was funded by the Latvian State Education Development Agency (1.1.1.2/VIAA/3/19/455, GoBVM), and the Latvian Council of Science (Lzp-2019/1-0254).
Publisher Copyright:
© 2022 SPIE
PY - 2022
Y1 - 2022
N2 - Skin and subcutaneous tumors are widespread in dogs and cats. Current tumor diagnostics (e.g., biopsy, fine-needle cytology) is invasive and labor-consuming. In this work, we studied ex vivo the most common canine and feline tumor OCT images using sliding window analysis and linear SVC classification, and we compared different sliding window sizes to determine the most optimal window sizes when differentiating between skin, mast cell tumours and soft tissue sarcomas. Sensitivities and specificities of all tissue classes saw an increase with increasing window size at small window size values and plateaued at around 60-80 µm, indicating the most significant tissue structures for differentiation via SWA likely lay here. Our work is the first veterinary OCT study on multiple canine and feline skin tumors to optimize the sliding window size for image pattern analysis.
AB - Skin and subcutaneous tumors are widespread in dogs and cats. Current tumor diagnostics (e.g., biopsy, fine-needle cytology) is invasive and labor-consuming. In this work, we studied ex vivo the most common canine and feline tumor OCT images using sliding window analysis and linear SVC classification, and we compared different sliding window sizes to determine the most optimal window sizes when differentiating between skin, mast cell tumours and soft tissue sarcomas. Sensitivities and specificities of all tissue classes saw an increase with increasing window size at small window size values and plateaued at around 60-80 µm, indicating the most significant tissue structures for differentiation via SWA likely lay here. Our work is the first veterinary OCT study on multiple canine and feline skin tumors to optimize the sliding window size for image pattern analysis.
KW - linear discriminant analysis
KW - mast cell tumors
KW - Optical coherence tomography
KW - sliding-window analysis
KW - soft tissue sarcomas
KW - veterinary oncology
UR - http://www.scopus.com/inward/record.url?scp=85128432497&partnerID=8YFLogxK
U2 - 10.1117/12.2607185
DO - 10.1117/12.2607185
M3 - Conference contribution
AN - SCOPUS:85128432497
VL - XXVI 2022
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXVI
A2 - Izatt, Joseph A.
A2 - Fujimoto, James G.
PB - SPIE
CY - San-Francisco
Y2 - 24 January 2022 through 26 January 2022
ER -