Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Mar 11;151(3):106.
doi: 10.1007/s00432-025-06150-9.

Chronic lymphocytic leukemia (CLL) screening and abnormality detection based on multi-layer fluorescence imaging signal enhancement and compensation

Lemin Shi  1   2 , Ping Gong  2 , Mingye Li  3   4 , Dianxin Song  2 , Hao Zhang  2 , Zhe Wang  2 , Xin Feng  5
Affiliations

Chronic lymphocytic leukemia (CLL) screening and abnormality detection based on multi-layer fluorescence imaging signal enhancement and compensation

Lemin Shi et al. J Cancer Res Clin Oncol. .

Abstract

Purpose: Fluorescence in situ hybridization (FISH) plays a critical role in cancer screening but faces challenges in signal clarity and manual intervention. This study aims to enhance FISH signal clarity, improve screening efficiency, and reduce false negatives through an automated image acquisition and signal enhancement framework.

Methods: An automated workflow was developed, integrating a dynamic signal enhancement method that optimizes global and local features. An improved Cycle-GAN network was introduced, incorporating residual connections and layer-wise supervision to accurately model and compensate for complex signal characteristics. Key metrics such as signal brightness, edge gradients, contrast improvement index (CII), and structural similarity index (SSIM) were used to evaluate performance.

Results: The proposed method increased weak signal brightness by 49.02%, edge gradients by 48.61%, and CII by 32.52%. The SSIM reached 0.996, indicating high fidelity to original signals.

Conclusion: Visual analysis demonstrated clearer, more continuous, and uniform fluorescence signals, effectively mitigating fragmentation and uneven distribution. These improvements reduced false negatives and enhanced genomic abnormality detection accuracy. The proposed method significantly improves FISH signal clarity and stability, providing reliable support for cancer screening, genomic abnormality detection, molecular typing, prognosis evaluation, and targeted treatment planning.

Keywords: Fluorescence in situ hybridization (FISH); feature enhancement; cyclic generative adversarial network (Cycle-GAN); cancer screening.

PubMed Disclaimer

Conflict of interest statement

Declarations. Conflict of interest: The authors declare no conflicts of interest. The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript; or in the decision to publish the results. Ethical approval: The study was conducted in accordance with the Declaration of Helsinki, and approved by the Ethics Committee of Fudan University Zhongshan Hospital (protocol code: 2022–021, date of approval: 14/02/2022). Consent to participate: Patient consent was waived due to unidentifiable information.

Figures

Fig. 1
Fig. 1
Fluorescence microscope. a Image Acquisition. b Collection principle, Scale bar: 50 μm
Fig. 2
Fig. 2
Fluorescence Signal Enhancement Method
Fig. 3
Fig. 3
Overall Network Structure
Fig. 4
Fig. 4
Network compensation for this article
Fig. 5
Fig. 5
Comparison of 3D Reconstruction Results
See this image and copyright information in PMC

References

    1. Abdelhedi F, Chalas C, Petit JM, Abid N, Mokadem E, Hizem S, Kamoun H, Keskes L, Dupont JM (2019) Altered three-dimensional organization of sperm genome in DPY19L2-deficient globozoospermic patients. J Assist Reprod Genet 36:69–77. 10.1007/s10815-018-1342-y - PMC - PubMed
    1. Agrawal D, Yadav AC, Tyagi PK (2024) Low-light and hazy image enhancement using retinex theory and wavelet transform fusion. Multimedia Tools Appl. 10.1007/s11042-024-18459-7
    1. Bloehdorn J, Braun A, Taylor-Weiner A, Jebaraj BMC, Robrecht S, Krzykalla J, Pan H, Giza A, Akylzhanova G, Holzmann K, Scheffold A, Johnston HE, Yeh RF, Klymenko T, Tausch E, Eichhorst B, Bullinger L, Fischer K, Weisser M, Robak T, Schneider C, Gribben J, Dahal LN, Carter MJ, Elemento O, Landau DA, Neuberg DS, Cragg MS, Benner A, Hallek M, Wu CJ, Döhner H, Stilgenbauer S, Mertens D (2021) Multi-platform profiling characterizes molecular subgroups and resistance networks in chronic lymphocytic leukemia. Nat Commun 12:5395. 10.1038/s41467-021-25403-y - PMC - PubMed
    1. Bouilhol E, Savulescu AF, Lefevre E, Dartigues B, Brackin R, Nikolski M (2022) DeepSpot: a deep neural network for RNA spot enhancement in single-molecule fluorescence in-situ hybridization microscopy images. Biol Imaging 2:e4. 10.1017/s2633903x22000034 - PMC - PubMed
    1. Chen Y, Lin H, Zhang W, Chen W, Zhou Z, Heidari AA, Chen H, Xu G (2024) ICycle-GAN: Improved cycle generative adversarial networks for liver medical image generation. Biomed Signal Process Control 92:106100. 10.1016/j.bspc.2024.106100

MeSH terms

LinkOut - more resources