In radiology (as well as pathology), clustering groups data, which may correspond to sets of images, reports or patients, by similarities in terms of various attributes or features without being explicitly programmed about final labels to group by. Thus clustering has the potential to reveal similarities in data overlooked by humans.
Practically speaking, clustering has proven useful in segmentation algorithms for radiology, which are used to identify different tissue types and/or differentiate pathological and normal tissue. However clustering algorithms are researched in other areas such as natural language processing of reports 1.
Some of the more commonly used algorithms of clustering in radiology, which have been in use for decades for the task of segmentation, include Fuzzy C mean clustering and K means clustering 2,3.
- 1. Saeed Hassanpour, Curtis P. Langlotz. Unsupervised Topic Modeling in a Large Free Text Radiology Report Repository. (2016) Journal of Digital Imaging. 29 (1): 59. doi:10.1007/s10278-015-9823-3 - Pubmed
- 2. G. B. Coleman and H. C. Andrews, “Image Segmentation by Clustering,” Proceedings of the IEEE, Vol. 67, No. 5, 1979, pp. 773-785. http://dx.doi.org/10.1109/PROC.1979.11327
- 3. J. C. Bezdek, L. O. Hall, L. P. Clarke. Review of MR image segmentation techniques using pattern recognition. (1993) Medical Physics. 20 (4): 1033. doi:10.1118/1.597000 - Pubmed