1. Conceptual data sampling for breast cancer histology image classification
- Author
-
Eman Rezk, Ali Jaoua, Nan Zhang, Fahad Islam, Nasir M. Rajpoot, Gautam Das, Zainab Awan, and Somaya Al Maadeed
- Subjects
Adult ,Computer science ,Histopathology ,Health Informatics ,Sample (statistics) ,Breast Neoplasms ,02 engineering and technology ,Data sampling ,computer.software_genre ,030218 nuclear medicine & medical imaging ,Set (abstract data type) ,03 medical and health sciences ,0302 clinical medicine ,0202 electrical engineering, electronic engineering, information engineering ,Image Processing, Computer-Assisted ,Humans ,Image segmentation ,Measure (data warehouse) ,Contextual image classification ,Formal concept analysis ,Models, Theoretical ,Computer Science Applications ,Sample size determination ,Data analysis ,Breast cancer classification ,020201 artificial intelligence & image processing ,Female ,Data mining ,RG ,computer - Abstract
Data analytics have become increasingly complicated as the amount of data has increased. One technique that is used to enable data analytics in large datasets is data sampling, in which a portion of the data is selected to preserve the data characteristics for use in data analytics. In this paper, we introduce a novel data sampling technique that is rooted in formal concept analysis theory. This technique is used to create samples reliant on the data distribution across a set of binary patterns. The proposed sampling technique is applied in classifying the regions of breast cancer histology images as malignant or benign. The performance of our method is compared to other classical sampling methods. The results indicate that our method is efficient and generates an illustrative sample of small size. It is also competing with other sampling methods in terms of sample size and sample quality represented in classification accuracy and F1 measure. 1 2017 Elsevier Ltd This contribution was made possible by NPRP grant #07- 794-1-145 from the Qatar National Research Fund (a member of Qatar Foundation). The statements made herein are solely the responsibility of the authors. Scopus
- Published
- 2017