Please use this identifier to cite or link to this item:
|Title:||DeepHistoClass: A novel strategy for confident classification of immunohistochemistry images using Deep Learning|
|Keywords:||Testis;Immunohistochemistry;Artificial intelligence;Machine learning;Histology|
|Citation:||Ghoshal B, Hikmet F, Pineau C, Tucker A, Lindskog C. DeepHistoClass: A novel strategy for confident classification of immunohistochemistry images using Deep Learning. Molecular & Cellular Proteomics. 2021 Aug 21:100140.|
|Abstract:||A multitude of efforts worldwide aim to create a single cell reference map of the human body, for fundamental understanding of human health, molecular medicine and targeted treatment. Antibody-based proteomics using immunohistochemistry (IHC) has proven to be an excellent technology for integration with large-scale single cell transcriptomics datasets. The golden standard for evaluation of IHC staining patterns is manual annotation, which is expensive and may lead to subjective errors. Artificial intelligence holds much promise for efficient and accurate pattern recognition, but confidence in prediction needs to be addressed. Here, the aim was to present a reliable and comprehensive framework for automated annotation of IHC images. We developed a multi-label classification of 7,848 complex IHC images of human testis corresponding to 2,794 unique proteins, generated as part of the Human Protein Atlas (HPA) project. Manual annotation data for eight different cell types was generated as a basis for training and testing a proposed Hybrid Bayesian Neural Network. By combining the deep learning model with a novel uncertainty metric; DeepHistoClass (DHC) confidence score; the average diagnostic performance improved from 86.9% to 96.3%. This metric not only reveals which images are reliably classified by the model, but can also be utilized for identification of manual annotation errors. The proposed streamlined workflow can be developed further for other tissue types in health and disease, and has important implications for digital pathology initiatives or large-scale protein mapping efforts such as the HPA project.|
|Description:||© 2021 Elsevier Ltd. All rights reserved. This is the accepted manuscript version of the article. The final version is available online from Elsevier at: https://doi.org/10.1016/j.mcpro.2021.100140|
|Appears in Collections:||Dept of Computer Science Research Papers|
Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.