A structured latent model for ovarian carcinoma subtyping from histopathology slides - PubMed (original) (raw)
A structured latent model for ovarian carcinoma subtyping from histopathology slides
Aïcha BenTaieb et al. Med Image Anal. 2017 Jul.
Abstract
Accurate subtyping of ovarian carcinomas is an increasingly critical and often challenging diagnostic process. This work focuses on the development of an automatic classification model for ovarian carcinoma subtyping. Specifically, we present a novel clinically inspired contextual model for histopathology image subtyping of ovarian carcinomas. A whole slide image is modelled using a collection of tissue patches extracted at multiple magnifications. An efficient and effective feature learning strategy is used for feature representation of a tissue patch. The locations of salient, discriminative tissue regions are treated as latent variables allowing the model to explicitly ignore portions of the large tissue section that are unimportant for classification. These latent variables are considered in a structured formulation to model the contextual information represented from the multi-magnification analysis of tissues. A novel, structured latent support vector machine formulation is defined and used to combine information from multiple magnifications while simultaneously operating within the latent variable framework. The structural and contextual nature of our method addresses the challenges of intra-class variation and pathologists' workload, which are prevalent in histopathology image classification. Extensive experiments on a dataset of 133 patients demonstrate the efficacy and accuracy of the proposed method against state-of-the-art approaches for histopathology image classification. We achieve an average multi-class classification accuracy of 90%, outperforming existing works while obtaining substantial agreement with six clinicians tested on the same dataset.
Keywords: Digital pathology; Latent representation; Machine learning; Ovarian carcinoma; Subtyping; Support vector machines.
Copyright © 2017 Elsevier B.V. All rights reserved.
Similar articles
- Towards semantic-driven high-content image analysis: an operational instantiation for mitosis detection in digital histopathology.
Racoceanu D, Capron F. Racoceanu D, et al. Comput Med Imaging Graph. 2015 Jun;42:2-15. doi: 10.1016/j.compmedimag.2014.09.004. Epub 2014 Oct 2. Comput Med Imaging Graph. 2015. PMID: 25442055 - Discriminative margin-sensitive autoencoder for collective multi-view disease analysis.
Zhang Z, Zhu Q, Xie GS, Chen Y, Li Z, Wang S. Zhang Z, et al. Neural Netw. 2020 Mar;123:94-107. doi: 10.1016/j.neunet.2019.11.013. Epub 2019 Dec 2. Neural Netw. 2020. PMID: 31837517 - Detection of temporal lobe epilepsy using support vector machines in multi-parametric quantitative MR imaging.
Cantor-Rivera D, Khan AR, Goubran M, Mirsattari SM, Peters TM. Cantor-Rivera D, et al. Comput Med Imaging Graph. 2015 Apr;41:14-28. doi: 10.1016/j.compmedimag.2014.07.002. Epub 2014 Jul 21. Comput Med Imaging Graph. 2015. PMID: 25103878 - An unsupervised feature learning framework for basal cell carcinoma image analysis.
Arevalo J, Cruz-Roa A, Arias V, Romero E, González FA. Arevalo J, et al. Artif Intell Med. 2015 Jun;64(2):131-45. doi: 10.1016/j.artmed.2015.04.004. Epub 2015 Apr 23. Artif Intell Med. 2015. PMID: 25976208 - Generating region proposals for histopathological whole slide image retrieval.
Ma Y, Jiang Z, Zhang H, Xie F, Zheng Y, Shi H, Zhao Y, Shi J. Ma Y, et al. Comput Methods Programs Biomed. 2018 Jun;159:1-10. doi: 10.1016/j.cmpb.2018.02.020. Epub 2018 Feb 23. Comput Methods Programs Biomed. 2018. PMID: 29650303
Cited by
- Artificial intelligence in digital pathology: a systematic review and meta-analysis of diagnostic test accuracy.
McGenity C, Clarke EL, Jennings C, Matthews G, Cartlidge C, Freduah-Agyemang H, Stocken DD, Treanor D. McGenity C, et al. NPJ Digit Med. 2024 May 4;7(1):114. doi: 10.1038/s41746-024-01106-8. NPJ Digit Med. 2024. PMID: 38704465 Free PMC article. Review. - Role of artificial intelligence in digital pathology for gynecological cancers.
Wang YL, Gao S, Xiao Q, Li C, Grzegorzek M, Zhang YY, Li XH, Kang Y, Liu FH, Huang DH, Gong TT, Wu QJ. Wang YL, et al. Comput Struct Biotechnol J. 2024 Mar 11;24:205-212. doi: 10.1016/j.csbj.2024.03.007. eCollection 2024 Dec. Comput Struct Biotechnol J. 2024. PMID: 38510535 Free PMC article. Review. - Revolutionizing Women's Health: A Comprehensive Review of Artificial Intelligence Advancements in Gynecology.
Brandão M, Mendes F, Martins M, Cardoso P, Macedo G, Mascarenhas T, Mascarenhas Saraiva M. Brandão M, et al. J Clin Med. 2024 Feb 13;13(4):1061. doi: 10.3390/jcm13041061. J Clin Med. 2024. PMID: 38398374 Free PMC article. Review. - Deep learning in ovarian cancer diagnosis: a comprehensive review of various imaging modalities.
Sadeghi MH, Sina S, Omidi H, Farshchitabrizi AH, Alavi M. Sadeghi MH, et al. Pol J Radiol. 2024 Jan 22;89:e30-e48. doi: 10.5114/pjr.2024.134817. eCollection 2024. Pol J Radiol. 2024. PMID: 38371888 Free PMC article. Review. - Artificial intelligence in ovarian cancer histopathology: a systematic review.
Breen J, Allen K, Zucker K, Adusumilli P, Scarsbrook A, Hall G, Orsi NM, Ravikumar N. Breen J, et al. NPJ Precis Oncol. 2023 Aug 31;7(1):83. doi: 10.1038/s41698-023-00432-6. NPJ Precis Oncol. 2023. PMID: 37653025 Free PMC article. Review.
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources
Medical