Chromosome classification using backpropagation neural networks

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.

Feasibility Study on Automatic Interpretation of Radiation Dose Using Deep Learning Technique for Dicentric Chromosome Assay

The interpretation of radiation dose is an important procedure for both radiological operators and persons who are exposed to background or artificial radiations. Dicentric chromosome assay (DCA) is one of the representative methods of dose estimation that discriminates the aberration in chromosomes modified by radiation. Despite the DCA-based automated radiation dose estimation methods proposed in previous studies, there are still limitations to the accuracy of dose estimation. In this study, a DCA-based automated dose estimation system using deep learning methods is proposed. The system is comprised of three stages. In the first stage, a classifier based on a deep learning technique is used for filtering the chromosome images that are not appropriate for use in distinguishing the chromosome; 99% filtering accuracy was achieved with 2,040 test images. In the second stage, the dicentric rate is evaluated by counting and identifying chromosomes based on the Feature Pyramid Network, which is one of the object detection algorithms based on deep learning architecture. The accuracies of the neural networks for counting and identifying chromosomes were estimated at over 97% and 90%, respectively. In the third stage, dose estimation is conducted using the dicentric rate and the dose-response curve. The accuracies of the system were estimated using two independent samples; absorbed doses ranging from 1- 4 Gy agreed well within a 99% confidential interval showing highest accuracy compared to those in previous studies. The goal of this study was to provide insights towards achieving complete automation of the radiation dose estimation, especially in the event of a large-scale radiation exposure incident.

Feature selection for the automated detection of metaphase chromosomes: performance comparison using a receiver operating characteristic method

BACKGROUND

The purpose of this study is to identify a set of features for optimizing the performance of metaphase chromosome detection under high throughput scanning microscopy. In the development of computer-aided detection (CAD) scheme, feature selection is critically important, as it directly determines the accuracy of the scheme. Although many features have been examined previously, selecting optimal features is often application oriented.

METHODS

In this experiment, 200 bone marrow cells were first acquired by a high throughput scanning microscope. Then 9 different features were applied individually to group captured images into the clinically analyzable and unanalyzable classes. The performance of these different methods was assessed by a receiving operating characteristic (ROC) method.

RESULTS

The results show that using the number of labeled regions on each acquired image is suitable for the first on-line CAD scheme. For the second off-line CAD scheme, it would be suggested to combine four feature extraction methods including the number of labeled regions, average regions area, average region pixel value, and the standard deviation of either region distance or circularity.

CONCLUSION

This study demonstrates an effective method of feature selection and comparison to facilitate the optimization of the CAD schemes for high throughput scanning microscope in the future.

Neural network approaches to grade adult depression

Depression is a common but worrying psychological disorder that adversely affects one's quality of life. It is more ominous to note that its incidence is increasing. On the other hand, screening and grading of depression is still a manual and time consuming process that might be biased. In addition, grades of depression are often determined in continuous ranges, e.g., 'mild to moderate' and 'moderate to severe' instead of making them more discrete as 'mild', 'moderate', and 'severe'. Grading as a continuous range is confusing to the doctors and thus affecting the management plan at large. Given this practical issue, the present paper attempts to differentiate depression grades more accurately using two neural net learning approaches-'supervised', i.e., classification with Back propagation neural network (BPNN) and Adaptive Network-based Fuzzy Inference System (ANFIS) classifiers, and 'unsupervised', i.e., 'clustering' technique with Self-organizing map (SOM), built in MATLAB 7. The reason for using the supervised and unsupervised learning approaches is that, supervised learning depends exclusively on domain knowledge. Supervision may induce biasness and subjectivities related to the decision-making. Finally, the performance of BPNN and ANFIS are compared and discussed. It was observed that ANFIS, being a hybrid system, performed much better compared to the BPNN classifier. On the other hand, SOM-based clustering technique is also found useful in constructing three distinct clusters. It also assists visualizing the multidimensional data clusters into 2-D.

Classifier-assisted metric for chromosome pairing

Cytogenetics plays a central role in the detection of chromosomal abnormalities and in the diagnosis of genetic diseases. A karyogram is an image representation of human chromosomes arranged in order of decreasing size and paired in 23 classes. In this paper we propose an approach to automatically pair the chromosomes into a karyogram, using the information obtained in a rough SVM-based classification step, to help the pairing process mainly based on similarity metrics between the chromosomes. Using a set of geometric and band pattern features extracted from the chromosome images, the algorithm is formulated on a Bayesian framework, combining the similarity metric with the results from the classifier. The solution is obtained solving a mixed integer program. Two datasets with contrasting quality levels and 836 chromosomes each were used to test and validate the algorithm. Relevant improvements with respect to the algorithm described by the authors in [1] were obtained with average paring rates above 92%, close to the rates obtained by human operators.

Automated classification of metaphase chromosomes: optimization of an adaptive computerized scheme

We developed and tested a new automated chromosome karyotyping scheme using a two-layer classification platform. Our hypothesis is that by selecting most effective feature sets and adaptively optimizing classifiers for the different groups of chromosomes with similar image characteristics, we can reduce the complexity of automated karyotyping scheme and improve its performance and robustness. For this purpose, we assembled an image database involving 6900 chromosomes and implemented a genetic algorithm to optimize the topology of multi-feature based artificial neural networks (ANN). In the first layer of the scheme, a single ANN was employed to classify 24 chromosomes into seven classes. In the second layer, seven ANNs were adaptively optimized for seven classes to identify individual chromosomes. The scheme was optimized and evaluated using a "training-testing-validation" method. In the first layer, the classification accuracy for the validation dataset was 92.9%. In the second layer, classification accuracy of seven ANNs ranged from 67.5% to 97.5%, in which six ANNs achieved accuracy above 93.7% and only one had lessened performance. The maximum difference of classification accuracy between the testing and validation datasets is <1.7%. The study demonstrates that this new scheme achieves higher and robust performance in classifying chromosomes.

A rule-based computer scheme for centromere identification and polarity assignment of metaphase chromosomes

Automatic centromere identification and polarity assignment are two key factors in the automatic karyotyping of human chromosomes. A multi-stage rule-based computer scheme has been investigated to automatically detect centomeres and determine polarities for both abnormal and normal metaphase chromosomes. The scheme first implements a modified thinning algorithm to identify the medial axis of a chromosome and extracts three feature profiles. Based on a set of pre-optimized classification rules, the scheme adaptively identifies the centromere and then assigns corresponding polarity. An image dataset of 2287 chromosomes acquired from 24 abnormal and 26 normal Giemsa metaphase cells is utilized to optimize and test the scheme. The overall accuracy is 91.4% for centromere identification and 97.4% for polarity assignment. The experimental results demonstrate that our scheme can be successfully applied to diverse chromosomes, which include those severely bent and abnormal chromosomes extracted from cancer cells.

A study for the hierarchical artificial neural network model for Giemsa-stained human chromosome classification

A hierarchical multi-layer neural network with an error back-propagation training algorithm has been adopted for the automatic classification of Giemsa-stained human chromosomes. The first step classifies chromosomes data into 7 major groups based on their morphological features such as relative length, relative area, centromeric index, and 80 density profiles. The second step classifies each 7 major groups into 24 subgroups using each group classifier. The classification error decreased by using two steps of classification and the classification error was 5.9%. The result of this study shows that a hierarchical multi-layer neural network can be accepted as an automatic human chromosome classifier.

A novel dengue fever (DF) and dengue haemorrhagic fever (DHF) analysis using artificial neural network (ANN)

Dengue fever (DF) is an acute febrile viral disease frequently presented with headache, bone or joint and muscular pains, and rash. A significant percentage of DF patients develop a more severe form of disease, known as dengue haemorrhagic fever (DHF). DHF is the complication of DF. The main pathophysiology of DHF is the development of plasma leakage from the capillary, resulting in haemoconcentration, ascites, and pleural effusion that may lead to shock following defervescence of fever. Therefore, accurate prediction of the day of defervescence of fever is critical for clinician to decide on patient management strategy. To date, no known literature describes of any attempt to predict the day of defervescence of fever in DF patients. This paper describes a non-invasive prediction system for predicting the day of defervescence of fever in dengue patients using artificial neural network. The developed system bases its prediction solely on the clinical symptoms and signs and uses the multilayer feed-forward neural networks (MFNN). The results show that the proposed system is able to predict the day of defervescence in dengue patients with 90% prediction accuracy.