Robust band profile extraction using constrained nonparametric machine-learning technique

ChromEDA: Chromosome classification by ensemble framework based domain adaptation

The precise identification of chromosomal abnormalities based on microscopy images in clinics heavily relies on manual analysis by karyotype experts, which is expensive and labor-intensive. Therefore, there is an urgent need for automatic classification technologies. However, current deep learning-based methods require a large amount of annotated data to achieve satisfactory performance. Additionally, there are domain shifts between datasets obtained from different instruments and clinical agencies, which hinders the utilization of existing public data resources. To overcome these challenges, we propose a novel ensemble learning framework called ChromEDA. This method incorporates soft pseudo-label learning, adversarial learning, and angle classification learning strategies to mitigate the domain shift. To evaluate its performance, we conducted cross-domain classification experiments using both public and private datasets. The results demonstrate that ChromEDA effectively addresses the domain shift issue and outperforms existing methods in cross-domain chromosome classification tasks. RESEARCH HIGHLIGHTS: The research transferred an unsupervised cross-domain algorithm into the chromosome microscopic image processing area, which can support fast and efficient deployment in equipment such as microscopies. To our knowledge, it is the first domain adaption application in chromosome image analysis. The research designed an ensemble learning framework-based chromosome classification model to alleviate the domain shift between different domains. It is a combination of soft pseudo-label learning, adversarial learning, and self-supervised angle recognition, which can significantly reduce the annotation requirements for chromosomal image processing. The results find that for chromosomes sharing the same centromere position category, banding information may contribute more to within-group classification. Thus, banding pattern information is encouraged to be considered for more precise classification of chromosomes.

Geometric correction of deformed chromosomes for automatic Karyotyping

Automatic Karyotyping is the process of classifying chromosomes from an unordered karyogram into their respective classes to create an ordered karyogram. Automatic karyotyping algorithms typically perform geometrical correction of deformed chromosomes for feature extraction; these features are used by classifier algorithms for classifying the chromosomes. Karyograms of bone marrow cells are known to have poor image quality. An example of such karyograms is the Lisbon-K(1) (LK(1)) dataset that is used in our work. Thus, to correct the geometrical deformation of chromosomes from LK(1), a robust method to obtain the medial axis of the chromosome was necessary. To address this problem, we developed an algorithm that uses the seed points to make a primary prediction. Subsequently, the algorithm computes the distance of boundary from the predicted point, and the gradients at algorithm-specified points on the boundary to compute two auxiliary predictions. Primary prediction is then corrected using auxiliary predictions, and a final prediction is obtained to be included in the seed region. A medial axis is obtained this way, which is further used for geometrical correction of the chromosomes. This algorithm was found capable of correcting geometrical deformations in even highly distorted chromosomes with forked ends.