Automatic Chromosome Classification Research Articles

Enhanced label constrained contrastive learning for chromosome optical microscopic image classification

Karyotyping analysis, an indispensable means of diagnosing genetic diseases in clinical practice, entails a highly intricate process of chromosome classification. Automatic chromosome classification, in particular, poses a daunting challenge, impeding the acceleration of the diagnosis speed of karyotyping analysis. Hence, we propose a newfangled method of enhanced label-constrained contrastive learning to sensitively discriminate chromosomes. Our method incorporates a multi-scale feature perception aggregation encoder and a linear classifier and operates in two stages. The first stage involves the utilization of an encoder and projection head for chromosome representation learning. We optimally exploit label information and conduct contrastive learning on positive samples of the same category of chromosomes. Further, we fortify local irregularities by means of CutMix image augmentation and extract global and local features via multi-scale feature modules. The input perception aggregation module establishes feature dependencies and introduces a supervised loss to minimize intra-class distance and enlarge inter-class distance in the representation space. Finally, we map the learned representation to the Multi-Layer Perception (MLP) projection head for chromosome representation learning. In the second stage, we freeze the encoder, discard the projection head, and fine-tune the chromosome classification network by adding a classification layer that assigns each chromosome to a type in each patient case. We evaluate our method thoroughly on two public datasets and a private dataset, and the detailed results indicate that our proposed enhanced label-constrained contrastive learning attains the highest average accuracy of 99.272%. Our method outperforms state-of-the-art approaches, manifesting the effectiveness of our enhanced label-supervised contrastive learning, multi-scale feature integration, and feature dependency relationships. Additionally, it is also amenable to other medical image-related tasks.

Chromosome Classification Using Deep Learning Technique

Abstract: Automated chromosome classification is a critical task in cytogenetics and has been traditionally performed manually. Recent advancements in image processing and machine learning have opened new avenues for automated chromosome classification. This paper presents a novel method for straightening and classifying chromosomes, utilizing a blend of imageprocessing techniques and a convolutional neural network (CNN) algorithm. The proposed approach involves pre-processing chromosome images, which includes straightening them to eliminate any curvature caused by their natural shape and extracting features with the aid of a CNN. The design of the method allows for the training and testing of images, facilitating the prediction of chromosomal abnormalities with high accuracy. The performance of the method was evaluated using a dataset of chromosome images, demonstrating exceptional accuracy and robustness. The proposed approach was evaluated using publicly available datasets of human chromosomes and achieved an accuracy of 93% without the straightening of chromosomes and 96% after the straightening of chromosomes. This method has the potential to be applied in cytogenetics and medical diagnosis, where precise and efficient chromosome classification is vital, and the ability to straighten chromosomes can enhance the accuracy of the analysis.

Chromosome Segmentation via Data Simulation and Shape Learning.

Karyotyping, consisting of single chromosome segmentation and classification, is widely used in the cytogenetic analysis for chromosome abnormality detection. Many studies have reported automatic chromosome classification with high accuracy. Nevertheless, they usually require manual chromosome segmentation beforehand. There are two critical issues in automatic chromosome segmentation: 1) scarce annotated images for model training, and 2) multiple region combinations to form single chromosomes. In this study, two simulation strategies are proposed for training data argumentation to alleviate data scarcity. Besides, we present an optimization-based shape learning method to evaluate the shape of formed single chromosomes, which achieve the global minimum loss when segmented regions are correctly combined. Experiments on a public dataset demonstrate the effectiveness of the proposed method. The data simulation strategy has significantly increased the segmentation results by 15.8% and 46.3% of the Dice coefficient on non-overlapped and overlapped regions. Moreover, the proposed optimization-based method separates overlapped chromosomes with an accuracy of 96.2%.

CIR-Net: Automatic Classification of Human Chromosome Based on Inception-ResNet Architecture.

In medicine, karyotyping chromosomes is important for medical diagnostics, drug development, and biomedical research. Unfortunately, chromosome karyotyping is usually done by skilled cytologists manually, which requires experience, domain expertise, and considerable manual efforts. Therefore, automating the karyotyping process is a significant and meaningful task. This paper focuses on chromosome classification because it is critical for chromosome karyotyping. In recent years, deep learning-based methods are the most promising methods for solving the tasks of chromosome classification. Although the deep learning-based Inception architecture has yielded state-of-the-art performance in the 2015 ILSVRC challenge, it has not been used in chromosome classification tasks so far. Therefore, we develop an automatic chromosome classification approach named CIR-Net based on Inception-ResNet which is an optimized version of Inception. However, the classification performance of origin Inception-ResNet on the insufficient chromosome dataset still has a lot of capacity for improvement. Further, we propose a simple but effective augmentation method called CDA for improving the performance of CIR-Net. The experimental results show that our proposed method achieves 95.98 percent classification accuracy on the clinical G-band chromosome dataset whose training dataset is insufficient. Moreover, the proposed augmentation method CDA improves more than 8.5 percent (from 87.46 to 95.98 percent) classification accuracy comparing to other methods. In this paper, the experimental results demonstrate that our proposed method is recent the most effective solution for solving clinical chromosome classification problems in chromosome auto-karyotyping on the condition of the insufficient training dataset. Code and Dataset are available at https://github.com/CloudDataLab/CIR-Net.

Classification of Metaphase Chromosomes Using Deep Convolutional Neural Network.

Karyotype analysis has important clinical significance in the diagnosis, treatment, and prognosis of diseases such as birth defects and hematological tumors. Identifying chromosomes and their structure variations from G-banded metaphase images is an important process in karyotyping, and also is the most difficult one. Automatic chromosome classification becomes urgent in recent years since more and more samples of patients are subject to medical test such as bone marrow biopsy. With the development of artificial intelligence, convolutional neural networks (CNNs) have shown good performance in image recognition. In this study, a CNN with 6 convolutional layers, 3 pooling layers, 4 dropout layers, and 2 fully connected layers was trained using the labeled data set to classify chromosomes into 24 classes through softmax activation function mapping. The classifier gave an accuracy of 93.79% for chromosome identification. The result demonstrated that the CNN has potential application value in chromosome classification and will contribute to the construction of an automatic karyotyping platform.

Analysis of human chromosome images: Application towards an automated chromosome classification

AbstractKaryotyping is the process of arranging the chromosomes to examine the chromosomal abnormalities, a solution for birth defects. Karyotype is achieved from analyzing the metaspread chromosome images. Metaspread chromosome images generally have problem related with overlapping and touching of chromosomes with each other. Segmentation and separation of overlapping and touching chromosomes are still an open issue. The paper proposes an automated algorithm to separate the touching chromosomes and overlapping chromosomes from G‐Band metaspread images. Segmentation is performed by obtaining the interesting (concave and convex) points on the image contour. A proper hypothesis is performed for separating overlapped and touching chromosome images. The isolation of overlapping and touching metaspread chromosome image helps in accurate automated chromosome classification to obtain a karyotype. The overall accuracy of the proposed method works well for separation of touching chromosome with 97.09% and overlapped chromosome with 95%.

A survey of neural network based automated systems for human chromosome classification

Chromosome classification and karyotype establishment are important procedures for genetic diseases diagnosis. Various computer-aided systems have been developed to automate this tedious and time consuming task, which is performed manually in most cytogenetic laboratories. This paper provides a comprehensive review of past and recent research in the area of automatic chromosome classification systems. We start by reviewing methods for feature extraction, followed by a neural network based chromosome classifiers survey. We sum-up various techniques and methods in this area of research and discuss important issues and outcomes within each study for both chromosome feature extraction and classification. Although the ANN based chromosome classifiers are the main topic of this survey, a number of classifiers based on other algorithms are exposed to give an overall idea about additional techniques employed in chromosome classification.

Algorithms for Chromosome Classification

Automated chromosome classification has been an important pattern recognition problem for decades. In order to im-prove the performance of automated chromosome classification, artificial intelligence and machine learning methods have been widely used in the computer-assisted chromosome detection and classification systems. This paper is focused on these algorithms, especially on artificial neural network (ANN) and wavelet transform algorithms. The principle and the realization of these algorithms are analyzed. Results of these algorithms are compared and discussed.

Segmentation of Overlapped and Touching Human Chromosome images

Chromosomes are essential genomic information carriers. The identification of chromosome abnormalities is an essential part of diagnosis and treatment of genetic disorders such as chromosomal syndromes and many types of cancer. Currently available cytogenetic imaging software is designed to classify only normal chromosomes. The automation of chromosome analysis is involving segmentation of chromosomes and classification into 24 groups. Segmentation of the overlapped chromosomes is a major step toward the realization of homolog classification. Resolving chromosome overlaps is an unsolved problem in automated chromosome analysis. Current systems for automatic chromosome classification are mostly interactive and require human intervention. In this paper, an automatic procedure is proposed to obtain the separated chromosomes. The separations of overlapped and touching chromosomes are obtained by finding the intersecting (concave and convex) points with the help of Novel algorithm. The intersecting points are located on contour of the image and then the curvature function is used to find out concave points. Then the possible separation lines are plotted by using all concave points and finally construct the hypotheses for possible separation lines between concave points. The segmentation is carried out by means of a curvature function scheme, which proved to be successful.

Application of Ensemble Machines of Neural Networks to Chromosome Classification

This work presents approaches to the automatic classification of metaphase chromosomes using several perceptron neural network techniques on neural networks function as committee machines. To represent the banding patterns, only chromosome gray level profiles are exploited. The other inputs to the ensemble machines of the network are the chromosome size and centromeric index. It is shown that, without much effort, the classification performances of the four networks are found to be similar to the ones of a well-developed parametric classifier. Four parallel networks trained for the four different aspects of the data set, the gray level profile vector, Fourier coefficients of gray level profiles, 3D data of chromosome length – centromeric index – total gray levels, and 4D data obtained by the addition of average gray levels. Then the classification results of differently trained neural networks (i.e., experts), are combined by the use of a genuine ensemble-averaging to produce an overall output by the combiner. We discuss the flexibility of the classifier developed, its potential for development, and how it may be improved to suit the current needs in karyotyping.

A modular framework for the automatic classification of chromosomes in Q-band images

Abstract 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.

Chromosome classification based on the band profile similarity along approximate medial axis

Automated chromosome classification is an essential task in cytogenetics and has been an important pattern recognition problem. Numerous attempts were made in the past to characterize chromosomes for the purposes of clinical and cancer cytogenetics research. It is important to determine good features and develop feature extraction schemes for chromosome classification. In this paper we propose efficient approaches for medial axis determination and profile matching of human chromosomes without identifying centromeres. The medial axis determination is based on simple cross-section analysis. The features of the band profile obtained along the axis are then used to classify a chromosome based on a subsequence matching technique. Using a special indexing structure, we are able to perform fast similarity search and dynamic insertion and deletion over the established subsequence database of chromosome profiles. According to the experimental results, the developed adaptive system can automatically and efficiently determine the medial axis of a given chromosomes, and achieve satisfactory classification results.

Patella sex determination by 3D statistical shape models and nonlinear classifiers

Sex determination is one of the essential steps in personal identification of an individual from skeletal remains. Most elements of the skeleton have been subjected to discriminant function analysis for sex estimation, but little work has been done in terms of the patella. This paper proposes a new sex determination method from the patella using a novel automated feature extraction technique. A dataset of 228 patellae (95 females and 133 males) was amassed from the William M. Bass Donated Skeletal Collection from the University of Tennessee and was subjected to noninvasive high resolution computed tomography (CT). After the CT data were segmented, a set of features was automatically extracted, normalized, and ranked. The segmentation process with surface smoothing minimizes the noise from enthesophytes and ultimately allows our methods to distinguish variations in patellar morphology. These features include geometric features, moments, principal axes, and principal components. A feature vector of dimension 45 for each subject was then constructed. A set of statistical and supervised neural network classification methods were used to classify the sex of the patellar feature vectors. Nonlinear classifiers such as neural networks have been used in previous research to analyze several medical diagnosis problems, including quantitative tissue characterization and automated chromosome classification. In this paper, different classification methods were compared. Classification success ranged from 83.77% average classification rate using labels from a Fuzzy C-Means (FCM) clustering step, to 90.3% for linear discriminant classification (LDC). We obtained results of 96.02% and 93.51% training and testing classification rates, respectively, using feed-forward backpropagation neural networks (NN). These promising results using newly developed features and the application of nonlinear classifiers encourage the usage of these methods in forensic anthropology for identifying the sex of an individual from incomplete skeletons retaining at least one patella.

Segmentation of Overlapping Chromosome Images Using Computational Geometry

Current systems for automatic chromosome classification are interactive and require human intervention for correct separation between touching and overlapping chromosomes. Special separation methods are required to segregate chromosomes because they are non-rigid objects. This study develops a new technique to separate overlapping chromosomes based on computational geometry. This technique requires the identification of all possible cut points from the contour line of overlapping chromosomes, using Voronoi diagrams and Delaunay triangulations to select the four target cut points and cut overlapping chromosomes into two chromosomes. We test our algorithm on 35 overlapping chromosome images and find that 28 out of 35 overlapping chromosomes images can be separated correctly (i.e. 80.0 %). Three out of the 35 images are separate incorrectly (i.e. 8.6 %) and four out of 35 images are not separable by our algorithm (i.e. 11.4 %).

New features for automatic classification of human chromosomes: A feasibility study

Karyotyping, a standard method for presenting pictures of the human chromosomes for diagnostic purposes, is a long standing, yet common technique in cytogenetics. Automating the chromosome classification process is the first step in designing an automatic karyotyping system. The main aim in this study was to define a new group of features for better representation and classification of chromosomes. Width, position and the average intensity of the two most eye-catching regions of each chromosome (that we call characteristic bands) are the new proposed features. The concept of a characteristic band is based on the expert cytogeneticists’ method in classification of the chromosomes. The length, centromeric index (CI) and an index of overall darkness or brightness of the image (NAGD) were also included in the final nine-dimensional feature vectors describing each chromosome. To automatically find the characteristic bands and calculate the new features, different windows in chromosome’s density profile were scored based on their intensity and width. As a feasibility study, our work was focused on classification of chromosomes in group E. Three layer artificial neural networks were employed to classify each chromosome in one of the three possible classes (chromosomes 16, 17 and 18). The best results obtained were accurate classification of up to 98.6% of chromosomes. Particularly a six-dimensional subset of the features showed reproducibly high performances in classification experiments. The results of this feasibility study show that new features inspired from human expert’s classification method are potentially capable of improving the accuracy of the karyotyping systems.

Supervised parametric and non-parametric classification of chromosome images

This paper describes a fully automatic chromosome classification algorithm for Multiplex Fluorescence In Situ Hybridization (M-FISH) images using supervised parametric and non-parametric techniques. M-FISH is a recently developed chromosome imaging method in which each chromosome is labelled with 5 fluors (dyes) and a DNA stain. The classification problem is modelled as a 25-class 6-feature pixel-by-pixel classification task. The 25 classes are the 24 types of human chromosomes and the background, while the six features correspond to the brightness of the dyes at each pixel. Maximum likelihood estimation, nearest neighbor and k-nearest neighbor methods are implemented for the classification. The highest classification accuracy is achieved with the k-nearest neighbor method and k = 7 is an optimal value for this classification task.

Polarity-free automatic classification of chromosomes

Automatic classification of the chromosomes of a metaphase eukaryotic cell under a light microscope into their biological classes is usually done in three steps: First, their centromeres are estimated in order to find their polarities, next a number of features are extracted from profiles of the oriented chromosomes, and finally the feature sets are assigned to classes. The first step is prone to errors since it is often not easy to detect the centromere. If it is determined on the wrong half of the chromosome then polarity is false leading to erroneous features in the second step and often to a misclassification. We reduce the error rate by applying the recently developed Bayesian method of variants to the profiles; applied to polarities, this method uses two feature sets for each chromosome, one for each polarity. We also take another look at feature extraction from profiles further reducing the error rate. Applied to the profiles of the Edinburgh MRC chromosome analysis system the most accurate methods reported here achieve cross-validation error rates below 1%.

Automatic classification of chromosomes by means of quadratically asymmetric statistical distributions

We use quadratically asymmetric distributions as introduced in Ritter [1, 2] as statistical models of human chromosomes for automatic constrained Bayesian classification into their 24 classes. These distributions are able to reflect asymmetries in the data. Moreover, we design algorithms for constrained classification of cells with missing and extra chromosomes (trisomies). Applied to the Edinburgh features of the large Copenhagen data set Cpr, the best classifier reported here reduces the cross-validation error rate from 2.7% (classical normal model) to 1.2% with respect to chromosomes. On the average, five out of six cells are completely correctly classified.

Mouse chromosome classification by radial basis function network with fast orthogonal search

This paper provides the results of our study on automatic classification of mouse chromosomes. A radial basis function neural network was compared with a multi-layer perceptron and a probabilistic neural network. The networks were trained and tested with 3723 chromosomes presented to each network as 30-point banding profiles. The radial basis function classifier trained with the fast orthogonal search learning rule provided the best unconstrained classification error rate of 12.7% which was obtained with a training set of 2250 chromosomes.

Outliers in statistical pattern recognition and an application to automatic chromosome classification

We propose a heuristic method of parameter estimation in mixture models for data with outliers and design a Bayesian classifier for assignment of m objects to n ⩾ m classes under constraints. This method of outlier handling combined with the classifier is applied to the well-known problem of automatic, constrained classification of chromosomes into their biological classes. We show that it decreases the error rate relative to the classical, normal, model by more than 50%. When applied to the Edinburgh feature data of the large Copenhagen image data set Cpr our best classifier yields an error rate close to 1.3% relative to chromosomes; 4 out of 5 cells are correctly classified.