PathoFusion: an open-source AI framework for recognition of pathomorphological features and mapping of immunohistochemical data

Simple item page
dc.contributor.authorBao, GQen_AU
dc.contributor.authorWang, XYen_AU
dc.contributor.authorXu, Ren_AU
dc.contributor.authorLoh, Cen_AU
dc.contributor.authorAdeyinka, ODen_AU
dc.contributor.authorPieris, DAen_AU
dc.contributor.authorCherepanoff, Sen_AU
dc.contributor.authorGracie, Gen_AU
dc.contributor.authorLee, Men_AU
dc.contributor.authorMcDonald, KLen_AU
dc.contributor.authorNowak, AKen_AU
dc.contributor.authorBanati, RBen_AU
dc.contributor.authorBuckland, MEen_AU
dc.contributor.authorGraeber, MBen_AU
dc.date.accessioned2021-04-23T02:51:17Zen_AU
dc.date.available2021-04-23T02:51:17Zen_AU
dc.date.issued2021-02-04en_AU
dc.date.statistics2021-03-15en_AU
dc.description.abstractWe have developed a platform, termed PathoFusion, which is an integrated system for marking, training, and recognition of pathological features in whole-slide tissue sections. The platform uses a bifocal convolutional neural network (BCNN) which is designed to simultaneously capture both index and contextual feature information from shorter and longer image tiles, respectively. This is analogous to how a microscopist in pathology works, identifying a cancerous morphological feature in the tissue context using first a narrow and then a wider focus, hence bifocal. Adjacent tissue sections obtained from glioblastoma cases were processed for hematoxylin and eosin (H&E) and immunohistochemical (CD276) staining. Image tiles cropped from the digitized images based on markings made by a consultant neuropathologist were used to train the BCNN. PathoFusion demonstrated its ability to recognize malignant neuropathological features autonomously and map immunohistochemical data simultaneously. Our experiments show that PathoFusion achieved areas under the curve (AUCs) of 0.985 ± 0.011 and 0.988 ± 0.001 in patch-level recognition of six typical pathomorphological features and detection of associated immunoreactivity, respectively. On this basis, the system further correlated CD276 immunoreactivity to abnormal tumor vasculature. Corresponding feature distributions and overlaps were visualized by heatmaps, permitting high-resolution qualitative as well as quantitative morphological analyses for entire histological slides. Recognition of more user-defined pathomorphological features can be added to the system and included in future tissue analyses. Integration of PathoFusion with the day-to-day service workflow of a (neuro)pathology department is a goal. The software code for PathoFusion is made publicly available. © 2021 by the Authors.en_AU
dc.identifier.articlenumber617en_AU
dc.identifier.citationBao, G., Wang, X., Xu, R., Loh, C., Adeyinka, O. D., Pieris, D. A., Cherepanoff, S., Gracie, G., Lee, M., McDonald, K. L., Nowak, A., K., Banati, R., Buckland, M. E., & Graeber, M. B. (2021). PathoFusion: an open-source AI framework for recognition of pathomorphological features and mapping of immunohistochemical data. Cancers, 13(4), 617. doi:10.3390/cancers13040617en_AU
dc.identifier.issn2072-6694en_AU
dc.identifier.issue4en_AU
dc.identifier.journaltitleCancersen_AU
dc.identifier.urihttps://doi.org/10.3390/cancers13040617en_AU
dc.identifier.urihttps://apo.ansto.gov.au/dspace/handle/10238/10710en_AU
dc.identifier.volume13en_AU
dc.language.isoenen_AU
dc.publisherMDPIen_AU
dc.subjectArtificial intelligenceen_AU
dc.subjectNeural networksen_AU
dc.subjectProteinsen_AU
dc.subjectNeoplasmsen_AU
dc.subjectGliomasen_AU
dc.subjectHematoxylinen_AU
dc.subjectEosinen_AU
dc.titlePathoFusion: an open-source AI framework for recognition of pathomorphological features and mapping of immunohistochemical dataen_AU
dc.typeJournal Articleen_AU
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
cancers-13-00617-v2.pdf
Size:
6.26 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Journal Articles