Annotation of multiple regions of interest across the whole mouse brain is an indispensable process for quantitative evaluation of a multitude of study endpoints in neuroscience digital pathology. Prior experience and domain expert knowledge are the key aspects for image annotation quality and consistency. At present, image annotation is often achieved manually by certified pathologists or trained technicians, limiting the total throughput of studies performed at neuroscience digital pathology labs. It may also mean that simpler and quicker methods of examining tissue samples are used by non-pathologists, especially in the early stages of research and preclinical studies. To address these limitations and to meet the growing demand for image analysis in a pharmaceutical setting, we developed AnNoBrainer, an open-source software tool that leverages deep learning, image registration, and standard cortical brain templates to automatically annotate individual brain regions on 2D pathology slides. Application of AnNoBrainer to a published set of pathology slides from transgenic mice models of synucleinopathy revealed comparable accuracy, increased reproducibility, and a significant reduction (~ 50%) in time spent on brain annotation, quality control and labelling compared to trained scientists in pathology. Taken together, AnNoBrainer offers a rapid, accurate, and reproducible automated annotation of mouse brain images that largely meets the experts' histopathological assessment standards (> 85% of cases) and enables high-throughput image analysis workflows in digital pathology labs.

Data Science MSD Czech Republic s r o Prague Czech Republic

Discovery Informatics MSD Czech Republic s r o Na Valentince 4 FIVE Building Prague 5 Smichov Prague 150 00 Czech Republic

Global Software Development MSD Czech Republic s r o Prague Czech Republic

Neuroscience Discovery Merck and Co Inc Rahway NJ USA

Zobrazit více v PubMed

Aberman, K., Liao, J., Shi, M., Lischinski, D., Chen, B., & Cohen-Or, D. (2018). Neural best-buddies: Sparse cross-domain correspondence. ACM Transactions on Graphics,37(4), 1–14. http://arxiv.org/abs/1805.04140

Baxi, V., Edwards, R., Montalto, M., & Saha, S. (2022). Digital pathology and artificial intelligence in translational medicine and clinical practice. Modern Pathology,35(1), 23–32. https://www.nature.com/articles/s41379-021-00919-2 PubMed PMC

Belfiore, R., Rodin, A., Ferreira, E., Velazquez, R., Branca, C., Caccamo, A., & Oddo, S. (2019). Temporal and regional progression of Alzheimer’s disease‐like pathology in 3xTg‐AD mice. Aging Cell,18(1). https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6351836/ PubMed PMC

Buslaev, A., Iglovikov, V. I., Khvedchenya, E., Parinov, A., Druzhinin, M., & Kalinin, A. A. (2020). Albumentations: fast and flexible image augmentations. Information,11(2), 125. http://arxiv.org/abs/1809.06839

Carey, H. et al. (2023). DeepSlice: rapid fully automatic registration of mouse brain imaging to a volumetric atlas. PubMed PMC

Carrigan, A. J., Charlton, A., Wiggins, M. W., Georgiou, A., Palmeri, T., & Curby, K. M. (2022). Cue utilisation reduces the impact of response bias in histopathology. Applied Ergonomics,98, 103590. https://linkinghub.elsevier.com/retrieve/pii/S0003687021002374 PubMed

Ekvall, M. (2024). Spatial landmark detection and tissue registration with deep learning. Nature Methods. PubMed PMC

Fainstein, N., Dori, D., Frid, K., Fritz, A. T., Shapiro, I., Gabizon, R., & Ben-Hur, T. (2016). Chronic progressive neurodegeneration in a transgenic mouse model of prion disease. Frontiers in Neuroscience,10, 510. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5104746/ PubMed PMC

Fricker, M., Tolkovsky, A. M., Borutaite, V., Coleman, M., & Brown, G. C. (2018). Neuronal Cell Death. Physiological Reviews,98(2), 813–880. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5966715/ PubMed PMC

He, K., Gkioxari, G., Dollár, P., & Girshick, R. (2017). Mask R-CNN. https://arxiv.org/abs/1703.06870 PubMed

He, K., Zhang, X., Ren, S., & Sun, J. (2015). Deep Residual Learning for Image Recognition. http://arxiv.org/abs/1512.03385

Kiwitz, K., Schiffer, C., Spitzer, H., Dickscheid, T., & Amunts, K. (2020). Deep learning networks reflect cytoarchitectonic features used in brain mapping. Scientific Reports, 10(1), 22039. https://www.nature.com/articles/s41598-020-78638-y PubMed PMC

Kuhn, H. W. (2005). The Hungarian method for the assignment problem. Naval Research Logistics, 7–21.

LaFerla, F. M., & Green, K. N. (2012). Animal models of alzheimer disease. Cold Spring Harbor Perspectives in Medicine,2(11). https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3543097/ PubMed PMC

Lein, E. S., Hawrylycz, M. J., Ao, N., Ayres, M., Bensinger, A., Bernard, A., et al. (2007). Genome-wide atlas of gene expression in the adult mouse brain. Nature,445(7124), 168–176. http://www.nature.com/articles/nature05453 PubMed

Müller, R., Kornblith, S., & Hinton, G. E. (2020). When does label smoothing help. http://arxiv.org/abs/1906.02629

Rauf, A., Badoni, H., Abu-Izneid, T., Olatunde, A., Rahman, M. M., Painuli, S, et al. (2022). Neuroinflammatory Markers: Key Indicators in the Pathology of Neurodegenerative Diseases. Molecules,27(10), 3194. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9146652/ PubMed PMC

Sandkühler, R., Jud, C., Andermatt, S., & Cattin, P. C. (2020). AirLab: Autograd Image Registration Laboratory. http://arxiv.org/abs/1806.09907

Saravanan, C., Schumacher, V., Brown, D., Dunstan, R., Galarneau, J. R., Odin, M., & Mishra, S. (2017). Meeting Report: Tissue-based Image Analysis. Toxicologic Pathology,45(7), 983–1003. 10.1177/0192623317737468 PubMed

Schultz, M. K. Jr., Gentzel, R., Usenovic, M., Gretzula, C., Ware, C., Parmentier-Batteur, S., . . . & Zariwala, H. A. (2018). Pharmacogenetic neuronal stimulation increases human tau pathology and trans-synaptic spread of tau to distal brain regions in mice. Neurobiology of Disease. PubMed

Shiffman, S., Basak, S., Kozlowski, C., & Fuji, R. N. (2018). An automated mapping method for Nissl-stained mouse brain histologic sections. Journal of Neuroscience Methods,308, 219–227. https://linkinghub.elsevier.com/retrieve/pii/S0165027018302413 PubMed

Spires-Jones, T. L., Attems, J., & Thal, D. R. (2017). Interactions of pathological proteins in neurodegenerative diseases. Acta Neuropathologica,134(2), 187–205. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5508034/ PubMed PMC

Talo, M. (2019). Automated classification of histopathology images using transfer learning. Artificial Intelligence in Medicine,101, 101743. https://linkinghub.elsevier.com/retrieve/pii/S0933365719307110 PubMed

Tan, M., & Le, Q. (2020). EfficientNet: Rethinking model scaling for convolutional neural networks. http://arxiv.org/abs/1905.11946

Technavio. (2022). Digital pathology market by product, application and geography - forecast and analysis 2023–2027. https://www.technavio.com/report/digital-pathology-market-size-industry-analysis

Xu, X., Yue, G., Hui, G., Zhao, F., Wenjuan, S., Anan, L., Miao, R., Jing, Y., & Qingming, L. (2020). Automated Brain Region Segmentation for Single Cell Resolution Histological Images Based on Markov Random Field. Neuroinformatics,18(2), 181–197. 10.1007/s12021-019-09432-z PubMed

Yates, S. C., Groeneboom, N. E., Coello, C., Lichtenthaler, S. F., Kuhn, P. H., Demuth, H. U., Hartlage-Rübsamen, M. et al. (2019). QUINT: Workflow for Quantification and Spatial Analysis of Features in Histological Images From Rodent Brain. Frontiers in Neuroinformatics,13, 75. 10.3389/fninf.2019.00075/full PubMed PMC

Zhuang, F., Qi, Z., Duan, K., Xi, D., Zhu, Y., Zhu, H., Xiong, H., & He, Q. (2021). A Comprehensive Survey on Transfer Learning. Proceedings of the IEEE (institute of Electrical and Electronics Engineers Inc.),109(1), 43–76.