TY - JOUR
T1 - Bridging clinic and wildlife care with AI-powered pan-species computational pathology
AU - AbdulJabbar, Khalid
AU - Castillo, Simon P.
AU - Hughes, Katherine
AU - Davidson, Hannah
AU - Boddy, Amy M.
AU - Abegglen, Lisa M.
AU - Minoli, Lucia
AU - Iussich, Selina
AU - Murchison, Elizabeth P.
AU - Graham, Trevor A.
AU - Spiro, Simon
AU - Maley, Carlo C.
AU - Aresu, Luca
AU - Palmieri, Chiara
AU - Yuan, Yinyin
N1 - Funding Information:
This study is funded by National Institutes of Health grant U54 CA217376 (Y.Y., A.M.B., L.M.A., T.A.G., C.C.M.). We acknowledge additional support from National Institutes of Health grant R01 CA185138 (Y.Y.), Cancer Research UK Career Establishment Award C45982/A21808 (Y.Y.), Cancer Research UK Early Detection Program Award C9203/A28770 (Y.Y.), Cancer Research UK Sarcoma Accelerator C56167/A29363 (Y.Y.), Cancer Research UK Brain tumour Award C25858/A28592 (Y.Y. and S.P.C.), Rosetrees Trust A2714 (Y.Y.), Children’s Cancer and Leukaemia Group CCLGA201906 (Y.Y.), The Royal Marsden Hospital, the ICR National Institute of Health Research Biomedical Research Centre (Y.Y.) and Department of Pediatrics Research Enterprise, University of Utah (L.M.A.). The authors wish to thank Edmund Flach from the Zoological Society of London, as well as external pathologists Mark Stidworthy, Daniella Denk, Cheryl Sangster, and Ann Pocknell. L.M.A. acknowledges support from the Department of Pediatrics Research Enterprise (University of Utah).
Funding Information:
This study is funded by National Institutes of Health grant U54 CA217376 (Y.Y., A.M.B., L.M.A., T.A.G., C.C.M.). We acknowledge additional support from National Institutes of Health grant R01 CA185138 (Y.Y.), Cancer Research UK Career Establishment Award C45982/A21808 (Y.Y.), Cancer Research UK Early Detection Program Award C9203/A28770 (Y.Y.), Cancer Research UK Sarcoma Accelerator C56167/A29363 (Y.Y.), Cancer Research UK Brain tumour Award C25858/A28592 (Y.Y. and S.P.C.), Rosetrees Trust A2714 (Y.Y.), Children’s Cancer and Leukaemia Group CCLGA201906 (Y.Y.), The Royal Marsden Hospital, the ICR National Institute of Health Research Biomedical Research Centre (Y.Y.) and Department of Pediatrics Research Enterprise, University of Utah (L.M.A.). The authors wish to thank Edmund Flach from the Zoological Society of London, as well as external pathologists Mark Stidworthy, Daniella Denk, Cheryl Sangster, and Ann Pocknell. L.M.A. acknowledges support from the Department of Pediatrics Research Enterprise (University of Utah).
Publisher Copyright:
© 2023, The Author(s).
PY - 2023/12
Y1 - 2023/12
N2 - Cancers occur across species. Understanding what is consistent and varies across species can provide new insights into cancer initiation and evolution, with significant implications for animal welfare and wildlife conservation. We build a pan-species cancer digital pathology atlas (panspecies.ai) and conduct a pan-species study of computational comparative pathology using a supervised convolutional neural network algorithm trained on human samples. The artificial intelligence algorithm achieves high accuracy in measuring immune response through single-cell classification for two transmissible cancers (canine transmissible venereal tumour, 0.94; Tasmanian devil facial tumour disease, 0.88). In 18 other vertebrate species (mammalia = 11, reptilia = 4, aves = 2, and amphibia = 1), accuracy (range 0.57–0.94) is influenced by cell morphological similarity preserved across different taxonomic groups, tumour sites, and variations in the immune compartment. Furthermore, a spatial immune score based on artificial intelligence and spatial statistics is associated with prognosis in canine melanoma and prostate tumours. A metric, named morphospace overlap, is developed to guide veterinary pathologists towards rational deployment of this technology on new samples. This study provides the foundation and guidelines for transferring artificial intelligence technologies to veterinary pathology based on understanding of morphological conservation, which could vastly accelerate developments in veterinary medicine and comparative oncology.
AB - Cancers occur across species. Understanding what is consistent and varies across species can provide new insights into cancer initiation and evolution, with significant implications for animal welfare and wildlife conservation. We build a pan-species cancer digital pathology atlas (panspecies.ai) and conduct a pan-species study of computational comparative pathology using a supervised convolutional neural network algorithm trained on human samples. The artificial intelligence algorithm achieves high accuracy in measuring immune response through single-cell classification for two transmissible cancers (canine transmissible venereal tumour, 0.94; Tasmanian devil facial tumour disease, 0.88). In 18 other vertebrate species (mammalia = 11, reptilia = 4, aves = 2, and amphibia = 1), accuracy (range 0.57–0.94) is influenced by cell morphological similarity preserved across different taxonomic groups, tumour sites, and variations in the immune compartment. Furthermore, a spatial immune score based on artificial intelligence and spatial statistics is associated with prognosis in canine melanoma and prostate tumours. A metric, named morphospace overlap, is developed to guide veterinary pathologists towards rational deployment of this technology on new samples. This study provides the foundation and guidelines for transferring artificial intelligence technologies to veterinary pathology based on understanding of morphological conservation, which could vastly accelerate developments in veterinary medicine and comparative oncology.
UR - http://www.scopus.com/inward/record.url?scp=85153918412&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85153918412&partnerID=8YFLogxK
U2 - 10.1038/s41467-023-37879-x
DO - 10.1038/s41467-023-37879-x
M3 - Article
C2 - 37100774
AN - SCOPUS:85153918412
SN - 2041-1723
VL - 14
JO - Nature Communications
JF - Nature Communications
IS - 1
M1 - 2408
ER -