This paper is concerned with auto- matic segmentation of high resolution digitized metaphases. This includes auto- matic detection and rejection of inter- phase nuclei, stain debris, and other “noise”; automatic detection and seg- mentation of touching and overlapping chromosome clusters; and automatic re- jection of cells which are evaluated as be- ing incomplete, or incorrectly segmented, or where the cell is otherwise unsuitable for further analysis. In this paper, a rule-based approach is described which treats the cell as a whole rather than as a series of individual chro- mosomes or clusters. The rules adapt classification and segmentation parame- ters for each cell. Initially, different sets of parameters are chosen according to the staining method of the cells, and the goal of the segmentation. A chromosome number predictor is used to guide the ad- aptation of the parameters and to esti- mate the performance. The adaptation is iterative, and the self-adjustment will stop when either a satisfactory result is achieved or if the cell is rejected. The method was implemented on both a Sun workstation and a Cytoscan, a commer- cial machine for chromosome analysis. Seven hundred and thirteen cells from real data have been tested. A success rate of 90-95% has been achieved. The proce- dure has been implemented in an auto- matic aberration scoring system for rou- tine use.