eprintid: 1575672 rev_number: 20 eprint_status: archive userid: 608 dir: disk0/01/57/56/72 datestamp: 2017-09-29 11:32:13 lastmod: 2021-10-04 02:01:59 status_changed: 2017-09-29 11:32:13 type: article metadata_visibility: show creators_name: Sparks, R creators_name: Madabhushi, A title: Out-of-Sample Extrapolation utilizing Semi-Supervised Manifold Learning (OSE-SSL): Content Based Image Retrieval for Histopathology Images ispublished: pub divisions: UCL divisions: B04 divisions: C05 divisions: F42 note: This work is licensed under a Creative Commons Attribution 4.0 International License. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in the credit line; if the material is not included under the Creative Commons license, users will need to obtain permission from the license holder to reproduce the material. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ abstract: Content-based image retrieval (CBIR) retrieves database images most similar to the query image by (1) extracting quantitative image descriptors and (2) calculating similarity between database and query image descriptors. Recently, manifold learning (ML) has been used to perform CBIR in a low dimensional representation of the high dimensional image descriptor space to avoid the curse of dimensionality. ML schemes are computationally expensive, requiring an eigenvalue decomposition (EVD) for every new query image to learn its low dimensional representation. We present out-of-sample extrapolation utilizing semi-supervised ML (OSE-SSL) to learn the low dimensional representation without recomputing the EVD for each query image. OSE-SSL incorporates semantic information, partial class label, into a ML scheme such that the low dimensional representation co-localizes semantically similar images. In the context of prostate histopathology, gland morphology is an integral component of the Gleason score which enables discrimination between prostate cancer aggressiveness. Images are represented by shape features extracted from the prostate gland. CBIR with OSE-SSL for prostate histology obtained from 58 patient studies, yielded an area under the precision recall curve (AUPRC) of 0.53±0.03 comparatively a CBIR with Principal Component Analysis (PCA) to learn a low dimensional space yielded an AUPRC of 0.44±0.01. date: 2016-06-06 date_type: published publisher: NATURE PUBLISHING GROUP official_url: http://doi.org/10.1038/srep27306 oa_status: green full_text_type: pub language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1207910 doi: 10.1038/srep27306 lyricists_name: Sparks, Rachel lyricists_id: RESPA71 actors_name: Bracey, Alan actors_id: ABBRA90 actors_role: owner full_text_status: public publication: Scientific Reports volume: 6 article_number: 27306 pages: 15 issn: 2045-2322 citation: Sparks, R; Madabhushi, A; (2016) Out-of-Sample Extrapolation utilizing Semi-Supervised Manifold Learning (OSE-SSL): Content Based Image Retrieval for Histopathology Images. Scientific Reports , 6 , Article 27306. 10.1038/srep27306 <https://doi.org/10.1038/srep27306>. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/1575672/1/srep27306.pdf