Automatic classification of chromosomes in Q-band images

SRAS-net: Low-resolution chromosome image classification based on deep learning

Prenatal karyotype diagnosis is important to determine if the foetus has genetic diseases and some congenital diseases. Chromosome classification is an important part of karyotype analysis, and the task is tedious and lengthy. Chromosome classification methods based on deep learning have achieved good results, but if the quality of the chromosome image is not high, these methods cannot learn image features well, resulting in unsatisfactory classification results. Moreover, the existing methods generally have a poor effect on sex chromosome classification. Therefore, in this work, the authors propose to use a super‐resolution network, Self‐Attention Negative Feedback Network, and combine it with traditional neural networks to obtain an efficient chromosome classification method called SRAS‐net. The method first inputs the low‐resolution chromosome images into the super‐resolution network to generate high‐resolution chromosome images and then uses the traditional deep learning model to classify the chromosomes. To solve the problem of inaccurate sex chromosome classification, the authors also propose to use the SMOTE algorithm to generate a small number of sex chromosome samples to ensure a balanced number of samples while allowing the model to learn more sex chromosome features. Experimental results show that our method achieves 97.55% accuracy and is better than state‐of‐the‐art methods.

Chromosome Classification and Straightening Based on an Interleaved and Multi-Task Network

Karyotyping is the gold standard in the detection of chromosomal abnormalities. To facilitate the diagnostic process, in this paper, a method for chromosome classification and straightening based on an interleaved and multi-task network is proposed. This method consists of three stages. In the first stage, multi-scale features are learned via an interleaved network. In the second stage, high-resolution features from the first stage are input to a convolution neural subnetwork for chromosome joint detection, and other features are fused and fed to two multi-layer perceptron subnetworks for chromosome type and polarity classification. In the third stage, the bent chromosome is straightened with the help of detected joints by two steps: first the chromosome is separated, rotated and assembled according to the detected joints; then the areas around the bending points are recovered by replacing the gaps formed in the first step with the sampled intensities from the bent chromosome. The classification of type and polarity can expedite the process of producing karyograms, which is an important step for chromosome diagnosis in clinical practice. Straightening makes the banding information of the chromosome easier to read. Classification results of the 5-fold cross validation on our dataset with 32 810 chromosomes achieve average accuracy of 98.1% for type classification and 99.8% for polarity classification. The straightening results show consistency in intensity and length of the chromosome before and after straightening.

Image processing in biodosimetry: A proposal of a generic free software platform

The scoring of chromosome aberrations is the most reliable biological method for evaluating individual exposure to ionizing radiation. However, microscopic analyses of chromosome human metaphases, generally employed to identify aberrations mainly dicentrics (chromosome with two centromeres), is a laborious task. This method is time consuming and its application in biological dosimetry would be almost impossible in case of a large scale radiation incidents. In this project, a generic software was enhanced for automatic chromosome image processing from a framework originally developed for the Framework V project Simbio, of the European Union for applications in the area of source localization from electroencephalographic signals. The platforms capability is demonstrated by a study comparing automatic segmentation strategies of chromosomes from microscopic images.

An improved classification scheme for chromosomes with missing data

Karyotyping, or the automatic classification of human chromosomes, is mostly based on the analysis of the chromosome specific banding pattern. Unfortunately, the most informative phases of the cell division cycle are composed of long chromosomes that easily overlap: the involved banding pattern information is corrupted, resulting in a drastic increase of the classification error. Assuming the availability of a probabilistic classifier, the improvement of the classification of chromosomes with corrupted data would require the additional estimation of the joint probability density of the observed and missing data for each chromosome class. Given the number of classes, the possible position and extension of the corrupted data within a chromosome, and the dimensionality of the feature space, a reliable estimation would need an impossible number of training samples. We chose to circumvent the estimation problem by developing a statistical generative model of the pattern of each class, so that the corrupted part can be substituted with a partial pattern synthetically generated from the model. This allows to obtain a Monte Carlo estimate of the maximum a posteriori probability for the class given the observation and the missing data, which reduces to a simple voting scheme if the a priori probability for each class is equal. Moreover, this Monte Carlo classification is superior to the voting scheme based on the simple imputation of the classes mean to the missing data.