Library Subscription: Guest
Begell Digital Portal Begell Digital Library eBooks Journals References & Proceedings Research Collections
Critical Reviews™ in Oncogenesis
SJR: 0.631 SNIP: 0.503 CiteScore™: 2.2

ISSN Print: 0893-9675
ISSN Online: 2162-6448

Critical Reviews™ in Oncogenesis

DOI: 10.1615/CritRevOncog.v14.i2-3.10
pages 89-164

Statistical Nuclear Texture Analysis in Cancer Research: A Review of Methods and Applications

Birgitte Nielsen
Institute for Medical Informatics, Rikshospitalet University Hospital; and Centre for Cancer Biomedicine, University of Oslo, Oslo, Norway
Fritz Albregtsen
Department of Informatics, University of Oslo, Norway
Havard E. Danielsen
Institute for Medical Informatics, Rikshospitalet University Hospital; Centre for Cancer Biomedicine, Department of Informatics, University of Oslo, Oslo, Norway

ABSTRACT

In digital pathology, the field of nuclear texture analysis gives information about the spatial arrangement of the pixel gray levels in a digitized microscopic nuclear image, providing statistical texture measures that may be used as quantitative tools for diagnosis and prognosis of human cancer. In the present work, we have reviewed nuclear texture analysis in human cancer research, with emphasis on (i) statistical texture analysis methods, (ii) methods for feature evaluation and feature set selection, (iii) classification methods and error estimation, and (iv) the recent literature in the field, focusing on diagnosis- and prognosis-related applications. The application study covers the period from 1995 to 2007. In order to find nuclear features that discriminate robustly between cases from different diagnostic or prognostic classes, a statistical evaluation of features must be performed, and this demands careful experimental design. The present review reveals that it is quite common to evaluate a large number of features on a limited learning set of clinical material, without testing the chosen classifier on an independent validation data set. This easily leads to overoptimistic results. Out of 160 papers, we found only 30 papers in which the classifier was evaluated on an independent validation data set. Even in these studies, some good results have been hampered by small validation groups. However, it is encouraging to note that those publications meeting the requirements of an optimal study are generally showing good results. Thus, it is well documented that nuclear texture analysis is showing promising results as a novel diagnostic and/or prognostic marker. Hopefully, we will soon see that these promising studies will be replicated in large, prospective, multicenter trials.


Articles with similar content:

Experimental Design Issues in Clinical Research of Musculoskeletal Pain Disabilities
Critical Reviews™ in Physical and Rehabilitation Medicine, Vol.12, 2000, issue 2
Robert J. Gatchel, Matt Maddrey
Viscosupplementation for Knee Osteoarthritis: Current Evidence and Recommendations
Journal of Long-Term Effects of Medical Implants, Vol.23, 2013, issue 2-03
Beate Hanson, Nathan Evaniew, Mitchell Winemaker
OPTIMAL UNCERTAINTY QUANTIFICATION OF A RISK MEASUREMENT FROM A THERMAL-HYDRAULIC CODE USING CANONICAL MOMENTS
International Journal for Uncertainty Quantification, Vol.10, 2020, issue 1
Fabrice Gamboa, Bertrand Iooss, M. Keller, Jerome Stenger
High-Resolution Spatio-Temporal Functional Neuroimaging of Brain Activity
Critical Reviews™ in Biomedical Engineering, Vol.30, 2002, issue 4-6
Bin He, J. Lian
The Control of Gait and Posture After Limb-Saving Surgery in Musculoskeletal Oncology
Critical Reviews™ in Physical and Rehabilitation Medicine, Vol.17, 2005, issue 3
R. P. H. Veth, E. de Visser, H. W. B. Schreuder, J. Duysens