Department of Information Engineering, University of Padova, Via Gradenigo 6/a, 35131 Padova, Italy.
Comput Methods Programs Biomed. 2012 Feb;105(2):120-30. doi: 10.1016/j.cmpb.2011.07.013. Epub 2011 Oct 2.
The manual analysis of the karyogram is a complex and time-consuming operation, as it requires meticulous attention to details and well-trained personnel. Routine Q-band laboratory images show chromosomes that are randomly rotated, blurred or corrupted by overlapping and dye stains. We address here the problem of robust automatic classification, which is still an open issue. The proposed method starts with an improved estimation of the chromosome medial axis, along which an established set of features is then extracted. The following novel polarization stage estimates the chromosome orientation and makes this feature set independent on the reading direction along the axis. Feature rescaling and normalizing techniques take full advantage of the results of the polarization step, reducing the intra-class and increasing the inter-class variances. After a standard neural network based classification, a novel class reassignment algorithm is employed to maximize the probability of correct classification, by exploiting the constrained composition of the human karyotype. An average 94% of correct classification was achieved by the proposed method on 5474 chromosomes, whose images were acquired during laboratory routine and comprise karyotypes belonging to slightly different prometaphase stages. In order to provide the scientific community with a public dataset, all the data we used are publicly available for download.
手工分析核型是一项复杂且耗时的工作，需要对细节有细致的关注并由训练有素的人员进行操作。常规的 Q 带实验室图像显示的染色体是随机旋转的，可能会因重叠和染料染色而模糊或损坏。我们在这里解决了稳健自动分类的问题，这仍然是一个未解决的问题。所提出的方法首先从改进的染色体中轴估计开始，然后沿着该中轴提取一组已建立的特征。接下来的新颖的极化阶段估计染色体的方向，并使这个特征集独立于沿着轴的读取方向。特征缩放和归一化技术充分利用了极化步骤的结果，减少了类内方差并增加了类间方差。在基于标准神经网络的分类之后，采用了一种新的类重新分配算法，通过利用人类核型的约束组成，最大化正确分类的概率。所提出的方法在 5474 条染色体上实现了平均 94%的正确分类，这些染色体的图像是在实验室常规采集的，包含属于稍微不同的前期阶段的核型。为了向科学界提供一个公共数据集，我们使用的所有数据都可供公开下载。
