Cell Nuclear Segmentation of B-ALL Images Based on MSFF-SegNeXt.

Abstract

Purpose: The diagnosis and treatment of B-Lineage Acute Lymphoblastic Leukemia (B-ALL) typically rely on cytomorphologic analysis of bone marrow smears. However, traditional morphological analysis methods require manual operation, leading to challenges such as high subjectivity and low efficiency. Accurate segmentation of individual cell nuclei is crucial for obtaining detailed morphological characterization data, thereby improving the objectivity and consistency of diagnoses.

Patients and methods: To enhance the accuracy of nucleus segmentation of lymphoblastoid cells in B-ALL bone marrow smear images, the Multi-scale Feature Fusion-SegNeXt (MSFF-SegNeXt) model is hereby proposed, building upon the SegNeXt framework. This model introduces a novel multi-scale feature fusion technique that effectively integrates edge feature maps with feature representations across different scales. Integrating the Edge-Guided Attention (EGA) module in the decoder further enhances the segmentation process by focusing on intricate edge details. Additionally, Hamburger structures are strategically incorporated at various stages of the network to enhance feature expression.

Results: These combined innovations enable MSFF-SegNeXt to achieve superior segmentation performance on the SN-AM dataset, as evidenced by an accuracy of 0.9659 and a Dice coefficient of 0.9422.

Conclusion: The results show that MSFF-SegNeXt outperforms existing models in managing the complexities of cell nucleus segmentation, particularly in capturing detailed edge structures. This advancement offers a robust and reliable solution for subsequent morphological analysis of B-ALL single cells.