EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DeepKaryo-Check: a two-stage automated screening framework for chromosomal numerical and structural abnormalities in clinical karyotype analysis

Wenjing Li, Xiaoyan Liang, Hongjian Yu, Liang Sun

Frontiers in Cell and Developmental Biology · 01.07.2026 · 14

DOI: 10.3389/fcell.2026.1836850 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Cell and Developmental Biology, online erschienen am 01.07.2026. Verfasst von Wenjing Li und 3 weiteren Autor:innen. Beteiligte Einrichtung: Binzhou People's Hospital Affiliated to Shandong First Medical University/College of Medical Information and Artificial Intelligence, Shandong First …. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Chromosomal abnormalities, including numerical abnormalities such as aneuploidy and structural abnormalities such as microdeletions and complex rearrangements, remain challenging to detect in a stable and reliable manner using automated methods in clinical karyotype analysis. This difficulty is primarily attributable to substantial non-rigid chromosome deformation, variability in sample preparation and imaging conditions, and the persistent scarcity of abnormal cases in real-world clinical datasets, all of which hinder the construction of generalizable morphological representations. In clinical practice, limited sample size is a common condition rather than an exception, which further intensifies the trade-off between sensitivity and specificity in automated screening systems. Therefore, achieving robust high-specificity screening under small-sample conditions is a central problem in the automated analysis of chromosomal abnormalities. In this study, we focus on cytogenetic image analysis and propose a structured modeling framework designed for clinical screening scenarios. Recent advances in multi-omics and machine learning have enabled more comprehensive characterization of disease states. Although the present work primarily focuses on cytogenetic imaging, the proposed framework provides an extensible basis for future integration with heterogeneous biological data.

Methods

We propose a multi-stage automated chromosomal analysis framework, termed DeepKaryo-Check , which integrates explicit geometric priors with consistency-based deep representation learning. The framework first exploits the relatively stable spatial organization of clinical karyotype images to perform geometry-guided anchoring of chromosomal instances and impose basic structural constraints, thereby reducing variability introduced by slide preparation and imaging. Individual chromosomes are then geometrically normalized and represented as one-dimensional width-profile sequences. On this basis, explicit difference modeling and multi-instance aggregation are employed to assess structural consistency between homologous chromosomes at the patient level, supporting the identification of fine-grained structural abnormalities such as microdeletions. All decision thresholds are determined exclusively through cross-validation within the training data, while the independent test set remains fully isolated prior to evaluation.

Results

In the independent Stage I test set of 520 karyotype images, including 260 normal and 260 numerically abnormal images, DeepKaryo-Check achieved an accuracy of 95.19%. The framework correctly classified 249 of 260 normal images and 246 of 260 abnormal images. The independent Stage II test cohort included 45 patients, comprising 29 patients without structural abnormalities and 16 patients with structural abnormalities. At the locked high-specificity threshold, the patient-level ROC-AUC was 0.9978 and the PR-AUC was 0.9963. All 29 patients without structural abnormalities were correctly classified, while 13 of 16 patients with structural abnormalities were identified, corresponding to a sensitivity of 0.8125 and a specificity of 1.000. Three patients with structural abnormalities were missed, and no patient without a structural abnormality was classified as positive.

Conclusion

These findings indicate that explicitly incorporating domain-relevant geometric priors into automated analysis workflows can improve the reliability of chromosomal structural abnormality screening under sample-limited conditions. DeepKaryo-Check is not intended to replace definitive clinical diagnosis, but rather to serve as a proof-of-concept screening and prioritization tool that supports early decision-making in automated karyotype analysis when data are constrained, providing methodological guidance for subsequent large-scale, multi-center validation studies.

Schlagwörter

Stichwörter der Autor:innen

case prioritizationchromosomal abnormalitiesclinical karyotype analysisclinical screeningdeep learninggeometric normalizationproof-of-concept study

Autor:innen und Institutionen

  • Binzhou People's Hospital Affiliated to Shandong First Medical University/College of Medical Information and Artificial Intelligence, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, Sh…

Zitieren

APA

Li, W., Liang, X., Yu, H., & Sun, L. (2026). DeepKaryo-Check: a two-stage automated screening framework for chromosomal numerical and structural abnormalities in clinical karyotype analysis. Frontiers in Cell and Developmental Biology, 14. https://doi.org/10.3389/fcell.2026.1836850

Vancouver

Li W, Liang X, Yu H, Sun L. DeepKaryo-Check: a two-stage automated screening framework for chromosomal numerical and structural abnormalities in clinical karyotype analysis. Frontiers in Cell and Developmental Biology. 2026;14. doi:10.3389/fcell.2026.1836850

BibTeX
@article{Li2026,
  author = {Li, Wenjing and Liang, Xiaoyan and Yu, Hongjian and Sun, Liang},
  title = {DeepKaryo-Check: a two-stage automated screening framework for chromosomal numerical and structural abnormalities in clinical karyotype analysis},
  journal = {Frontiers in Cell and Developmental Biology},
  year = {2026},
  volume = {14},
  doi = {10.3389/fcell.2026.1836850}
}
Kostenlos starten →