A sustainable visual representation of available histopathological digital knowledge for breast cancer grading

  • Lamine Traore Sorbonne Universités, UPMC Univ Paris 06, INSERM, Université Paris 13, Sorbonne Paris Cité, Laboratoire d’Informatique Médicale et Ingénierie des Connaissances en eSanté (LIMICS UMR_S 1142)
  • Christel Daniel Assistance Publique-Hôpitaux de Paris (AP-HP), CCS SI Patient, Paris, France
  • Marie-Christine Jaulent Sorbonne Universités, UPMC Univ Paris 06, INSERM, Université Paris 13, Sorbonne Paris Cité, Laboratoire d’Informatique Médicale et Ingénierie des Connaissances en eSanté (LIMICS - UMR_S 1142), 15 rue de l’école de médecine, Paris, France
  • Thomas Schrader University of Applied Sciences Brandenburg Magdeburger, Department Informatics and Media, Brandenburg, Germany
  • Daniel Racoceanu Sorbonne Universités, UPMC Univ Paris 06, CNRS, INSERM, Laboratoire d’Imagerie Biomédicale (LIB), 75013, Paris, France
  • Yannick Kergosien Département d’Informatique Université de Cergy-Pontoise, Cergy-Pontoise, France

Abstract

Background

Recently, anatomic pathology (AP) has seen the introduction of several tools such as slide scanners and virtual slide technologies, creating the conditions for broader adoption of computer aided diagnosis based on whole slide images (WSI). This change brings up a number of new scientific challenges such as the sustainable management of the explicit and unambiguous semantics associated to the diagnostic interpretation of AP images by both humans (pathologists) and computers (image analysis algorithms) . In order to reduce inter-observer variability between AP reports of malignant tumors, the College of American Pathologists edited more than 60 organ-specific Cancer Checklists and associated Protocols (CAP-CC&P). Each checklist includes a set of AP observations that are expected to be reported by pathologists in organ-specific AP cancer reports. Our objective was to i) identify the available histopathological formalized knowledge from NCBO Bioportal and UMLS metathesaurus in the scope of the CAP CC&P for breast cancer grading and ii) to build a sustainable visual representation of this knowledge using UMLS semantic types.

Methods

Our methodology was applied on the two breast cancer CAP-CC&Ps dedicated to invasive carcinoma (IC) and ductal carcinoma in situ (DCIS). We focused on a subset of quantifiable AP observations of the CAP-CCs - i.e. observable entities that could be computed by image analysis tools and on the corresponding notes in the protocols that unambiguously describe how pathologists should derive a high-level observation (e.g. Nottingham score) from low-level morphological characteristics observed in images (e.g. mitotic count or glandular/tubular differentiation).The notes were annotated manually by two AP experts (gold standard) and automatically by NCBO Annotator using the 508 ontologies available on the NCBO platform. A sub-set of reference ontologies was selected based on their capacities to automatically identify concepts in the notes and compared to the subset of ontologies selected based on their capacity to identify the concepts identified by experts (gold standard). Once automatically extracted from the notes, the concepts belonging to different ontologies, were integrated into a unique graph and organized according to UMLS semantic types.

Results

The most relevant biomedical ontologies to be used for the annotation of the notes describing quantifiable observable entities of breast cancer CAP-CC&Ps are SNOMED-CT, LOINC, NCIT, NCI CaDSR Value Sets and PathLex. A visual representation integrating 25 concepts from the 5 different ontologies organized according to 11 UMLS semantic types was built to support AP experts for building a formal representation of the low-level quantifiable entities automatically extracted from the CAP-CC&Ps notes.

Conclusion

The proposed approach and tools, based on the CAP-CC&Ps, aim at supporting AP experts in building a standard-based representation of low-level morphological abnormalities observed in cancer that can be quantified using image analysis tools. This effort is complementary to the Integrating the Healthcare Enterprise (IHE) initiative building a standard-based representation of high-level AP observations required in cancer AP reports. Additional efforts are needed to achieve a workable standard-based formal representation of histopathological knowledge integrating both observable entities reported by humans (pathologists) and quantifiable entities automatically computed by machines. Providing such unique formal representation paves the way for more efficient use of computer aided diagnosis in AP as well as for the development of new biomarkers based on automatic analysis of whole slide images (WSI).

References

1. “CAP - Cancer Protocol Templates.” [Internet], College of American Pathologists, 2016. Available from: http://www.cap.org

2. Daniel C., Booker D., Beckwith B., Della Mea V., García-Rojo M., Havener L., Kennedy M., Klossa J., Laurinavicius A., Macary F., Punys V., Scharber W., Schrader T., Standards and specifications in pathology: image management, report management and terminology, Stud Health Technol Inf. 2012, 179: 105–122.

3. Haroske G., Schrader T., A reference model based interface terminology for generic observations in Anatomic Pathology Structured Reports, Diagnostic Pathology 2014, 9( 1): 4.

4. Bodenreider O., “Biomedical Ontologies in Action: Role in Knowledge Management, Data Integration and Decision Support,” Yearb. Med. Inform. 2008, 67–79.

5. Rubin D. L., Shah N. H., Noy N. F., “Biomedical ontologies: a functional perspective,” Brief. Bioinform. 2007, 9(1):75–90.

6. Gruber T. R., A Translation Approach to Portable Ontology Specifications, Knowl Acquis 1993, 5(2):199–220.

7. “Protege-OWL 3.x Support - Ontologies on Image Processing... any idea!” [Internet]. [Accessed: 16-Oct-2015]. Available: http://protege-project.136.n4.nabble.com/Ontologies-on-Image-Processing-any-ideatd417.html

8. Musen M. A., Noy N. F., Shah N. H., Whetzel P. L., Chute C. G., Story M.-A., Smith B., and the NCBO team, The National Center for Biomedical Ontology, J. Am. Med. Inform. Assoc. 2012, 19:2, 190–195.

9. Whetzel P. L., Noy N. F., Shah N. H., Alexander P. R., Nyulas C., Tudorache T., Musen M. A., “BioPortal: enhanced functionality via new Web services from the National Center for Biomedical Ontology to access and use ontologies in software applications,” Nucleic Acids Res. 2011, 39:W541–W545.

10. Bodenreider O., “The Unified Medical Language System (UMLS): integrating biomedical terminology.” [Internet]. [Accessed: 17-Dec-2015]. Available: http://nar.oxfordjournals.org

11. “Semantic Types and Groups.” [Internet]. Bethesda (MD): National Library of Medicine (US) [ Updated: 27-Apr-2015; Accessed: 17-Apr-2016]. Available: https://metamap.nlm.nih.gov/SemanticTypesAndGroups.shtml

12. “Current Semantic Types.” [Internet]. Bethesda (MD): National Library of Medicine (US). [Accessed: 17- Apr-2016]. Available: https://www.nlm.nih.gov/research/umls/META3_current_semantic_types.html

13. Jonquet C., Musen M. A., Shah N. H., Building a biomedical ontology recommender web service, J. Biomed. Semant. 2010, 1:1, S1.

14. “Ontology Recommender | bioontology.org.” [Internet]. Stanford (CA): The National Center for Biomedical Ontology (US). [Accessed: 10-Dec-2015]. Available: http://www.bioontology.org/ontology-recommender

15. “Annotator | NCBO BioPortal.” [Internet]. Stanford (CA): The National Center for Biomedical Ontology (US). [Accessed: 11-Dec-2015]. Available: http://bioportal.bioontology.org/annotator

16. Shah N. H., Bhatia N., Jonquet C., Rubin D., Chiang A. P., Musen M. A., Comparison of concept recognizers for building the Open Biomedical Annotator, BMC Bioinformatics 2009, 10:9, S14.

17. “UMLS REST API Home Page.” [Internet]. Bethesda (MD): National Library of Medicine (US) [Accessed: 26-May-2016]. Available: https://documentation.uts.nlm.nih.gov/rest/home.html

18. “MindMaple - Mind Mapping Software - Improve Brainstorming Techniques.” [Internet]. Santa Clara (CA): MindMaple Inc. [Accessed: 17-Apr-2016]. Available: http://www.mindmaple.com/Products/Features/

19. “Welcome to Python.org,” Python.org. [Internet]. Beaverton (OR): Python Software Foundation. [Accessed: 26-May-2016]. Available: https://www.python.org/

20. “jq.” [Internet]. GITHub. [Accessed: 26-May-2016]. Available: https://stedolan.github.io/jq/

21. Emden R., Gansner, “Graphviz | Graphviz - Graph Visualization Software.” [Internet]. [Accessed: 20-May-2016]. Available: http://www.graphviz.org/

22. “JSON.” [Internet]. ECMA International, 2013. [Accessed: 26-May-2016]. Available: http://json.org/

23. Racoceanu D., Capron F., Towards Semantic-Driven High-Content Image Analysis. An Operational Instantiation for Mitosis Detection in Digital Histopathology, Comput. Med. Imaging Graph., 2014.

24. Traore L., et al. Sustainable formal representation of breast cancer grading histopathological knowledge, Diagnostic Pathology 2016, 1:154.
Published
2016-06-28
How to Cite
TRAORE, Lamine et al. A sustainable visual representation of available histopathological digital knowledge for breast cancer grading. Diagnostic Pathology, [S.l.], v. 2, n. 1, june 2016. ISSN 2364-4893. Available at: <http://www.diagnosticpathology.eu/content/index.php/dpath/article/view/109>. Date accessed: 20 sep. 2017. doi: https://doi.org/10.17629/www.diagnosticpathology.eu-2016-2:109.
Section
Research

Keywords

Breast cancer grading, semantic annotation, knowledge formalization and modeling, standardization, computer aided diagnosis, high-content image exploration, digital pathology