Fully automatic chromosome segmentation

Abstract

This paper is concerned with automatic segmentation of high resolution digitized metaphases. This includes automatic detection and rejection of interphase nuclei, stain debris, and other "noise"; automatic detection and segmentation of touching and overlapping chromosome clusters; and automatic rejection of cells which are evaluated as being 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 chromosomes or clusters. The rules adapt classification and segmentation parameters 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 adaptation of the parameters and to estimate 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 commercial 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 procedure has been implemented in an automatic aberration scoring system for routine use. Q 1994 Wiley-Liss, Inc.

A hybrid technique for overlapped chromosome segmentation of G-band mataspread images automatic

“…In this paper used the linear least squares fit method [2] to create the missing paths on the overlapping chromosome images. Figure 8 shown the results of create the missing paths.…”

“…An example of compound approach Ji [2] proposed the rule base of the chromosome segmentation in which consist adapt classification and segmentation parameter for each cell. Popescu et al [3] proposed an automatic chromosome segmentation in which used the four feature of segmentation such as the cross section sequence graphs, an oversegmentation and the `pale path' concept for banded chromosomes.…”

Automatic segmentation of chromosomes in Q-band images

“…Charters and Graham [12] tried to integrate the segmentation and classification steps to resolve overlaps and adjacencies, but trained and tested their algorithm on simulated overlaps. Ji [4] is still the only one who has proposed a method for automatically segmenting both touching and overlapping clusters. Using the same general framework of [4], we show how a local thresholding strategy coupled with a cascade of geometric-and intensity-based algorithm can overcome the limitations and drawbacks of previously proposed methods for chromosome segmentation.…”

“…Most of the studies aimed at the development of cytogenetics systems for analysis of banded chromosome preparations, have concentrated on metaphase chromosomes, avoiding the segmentation difficulties arising from touches and overlaps in the prophase and prometaphase cells. The first step that has to be taken in analysing a chromosome image is the segmentation of chromosomes and chromosome clusters from the image background: the main methods used to segment cytogenetic images are based on the evaluation of a global threshold by means of the Otsu method [3], or on a global threshold with a re-thresholding scheme based [4], [5], k-means clustering binarization [6], or finally The work has been partially funded by TesiImaging SrL, Milano, Italy. Authors are with the Dept.…”

Mass Detection in Lung CT Images Using Region Growing Segmentation and Decision Making Based on Fuzzy Inference System and Artificial Neural Network

“…For the third step, some researches concentrate only on disentangling of touching clusters using dark paths [6] or using geometric shape [4] and some researches concentrate only on separation of overlapping chromosomes by using different methods, such as Watershed segmentation method [7,8] or using shape of clusters [9], curvature of the cluster boundaries [10], chromosome skeleton [11] banded images [12,13]. In this research, the dark paths and geometric shape of clusters are used to separate touching and overlapping clusters…”