Ontology-Driven Image Analysis for Histopathological Images

Abstract

Abstract. Ontology-based software and image processing engine must cooperate in new fields of computer vision like microscopy acquisition wherein the amount of data, concepts and processing to be handled must be properly controlled. Within our own platform, we need to extract biological objects of interest in huge size and high-content microscopy images. In addition to specific low-level image analysis procedures, we used knowledge formalization tools and high-level reasoning ability of ontology-based software. This methodology made it possible to improve the expressiveness of the clinical models, the usability of the platform for the pathologist and the sensitivity or sensibility of the low-level image analysis algorithms.

Ontologies for Liver Diseases Representation: A Systematic Literature Review

“…Also, Unified Medical Language System (UMLS 4 ), which is developed by the United States (US) National Library of Medicine (NLM), allows the organization of clinical vocabularies [2]. In the same context, we can cite also the Systematized Nomenclature of Medicine-Clinical Terms (SNOMED CT), Medical Subject Headings (MeSH 5 ), Transparent Access to Multiple Bioinformatics Information Sources (TAMBIS 6 ), Foundational Model of Anatomy (FMA), the international classification of diseases (ICD 7 ). In this article, we present a literature review that outlines the topic of using ontologies for liver diseases representation.…”

Automatic classification of histological images and histological knowledge modelling of the human cardivascular system = Clasificación automática de imágenes histológicas y modelado del conocimiento histológico del sistema cardiovascular humano

“…Ontologies and taxonomies contain relevant knowledge represented with rich structural and semantic information. Approaches that use this tools into automatic classification process are dividing in two: (i) model the relation between visual and semantic information (Wu et al, 2010;Yang et al, 2007) and (ii) use these ontologies and taxonomies in the classification algorithm (Othmani et al, 2010;Smith et al, 2015;Abdollahpour et al, 2015;Paulson et al, 2006;Breen et al, 2002). We will focus in the second group to perform the classification process using images and ontologies in the same way.…”

“…On the one hand, in histological context Othmani et al (2010) proposes to leverage the high-level reasoning and knowledge formalization ability of ontology-based software to make annotation of high-content images more efficient and interactive. The low-level image processing aims at outlining and describing general biological objects -the nuclei, the lumina and the invasive areas -in the histopathological images.…”

“…Las ontologías y taxonomías contienen conocimientos representados con información estructural y semántica. Los enfoques que utilizan estas herramientas en el proceso de clasificación automática se dividen en dos: (i) modelar la relación entre la información visual y semántica (Wu et al, 2010;Yang et al, 2007) y (ii) utilizar estas ontologías y taxonomías en el algoritmo de clasificación (Othmani et al, 2010;Smith et al, 2015;Abdollahpour et al, 2015;Paulson et al, 2006;Breen et al, 2002). Nosotros nos centraremos en el segundo grupo para llevar a cabo el proceso de clasificación, utilizando imágenes y ontologías.…”

“…En Othmani et al (2010) se propone utilizar el razonamiento de alto nivel y la formalización del conocimiento del software basado en ontologías para hacer la anotación de imágenes más eficiente e interactiva. El objetivo principal del procesamiento de imágenes de bajo nivel es describir los objetos biológicos generales -los núcleos, el lumen y lasáreas invasivasen las imágenes histopatológicas.…”