In this article, I am examining the role of categorization in understanding. The problem arises from well-known distinction between explanation and understanding, which has been for a century pursued in hermeneutic tradition. Categorization belongs to explanatory endeavor and its role in understanding is unclear. In order to delimit the scope of inquiry I am focusing on the weakest kind of categorization, so called categorization ad hoc. I am examining the hypothesis to the effect that categorization plays its role in hermeneutic circle as some sort of preunderstanding. Eventually, however, I reject this hypothesis. It is because it leads to hermeneutic paradox: The notion of pre-understanding has a meaning only in the context of full-fledged understanding, which is an unattainable ideal. Such ideal cannot be used as a personal criterion of the quality of one’s understanding. There is a tension between the feeling of understanding and the scarcity of personal means to justify this feeling. I am suggesting that similar, albeit weaker effect occurs also in more elaborate, scientific categorizations. What is really wrong in the passage from categorization to understanding is some form of self-understanding: We do not know whether we understand better, or at all when we put some categorical order onto our experience. We do not seem to have the required meta-understanding.
This paper proposes a new approach to the processing and analysis of medical images. We introduce the term and methodology of medical data understanding, as a new step in the way of starting from image processing, and followed by analysis and classification (recognition). The general view of the situation of the new technology of machine perception and image understanding in the context of the more well known and classic techniques of image processing, analysis, segmentation and classification is shown below