EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MTLL: A Novel Multi-Task Learning Approach for Lymphocytic Leukemia Classification and Nucleus Segmentation

Cuisi Ou, Zhigang Hu, Xinzheng Wang, Kaiwen Cao, Yipei Wang

Electronics · 28.03.2026 · 15 (7) · 1419

DOI: 10.3390/electronics15071419 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 28.03.2026. Verfasst von Cuisi Ou und 4 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the key specialized research and development breakthrough of Henan province, the key scientific research projects of Henan colleges and universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Bone marrow cell classification and nucleus segmentation in microscopic images are fundamental tasks for computer-aided diagnosis of lymphocytic leukemia. However, bone marrow cells from different subtypes exhibit high morphological similarity, and structural information is often constrained under optical microscopic imaging, posing challenges for stable and effective feature representation. To address this issue, we propose MTLL (Multitask Model on Lymphocytic Leukemia), a novel multitask approach that performs cell classification and nucleus segmentation within a unified network to exploit their complementary information. The model constructs a hybrid backbone for shared feature representation based on a CNN-Transformer architecture, in which Fuse-MBConv modules are tightly integrated with multilayer multi-scale transformers to enable deep fusion of local texture and global semantic information. For the segmentation branch, we design an AM (Atrous Multilayer Perceptron) decoder that combines atrous spatial pyramid pooling with multilayer perceptrons to fuse multi-scale information and accurately delineate nucleus boundaries. The classification branch incorporates prior knowledge of cell nuclei structures to capture subtle variations in cellular morphology and texture, thereby enhancing the model’s ability to distinguish between leukemia subtypes. Experimental results demonstrate that the MTLL model significantly outperforms existing advanced single-task and multi-task models in both lymphocytic leukemia classification and cell nucleus segmentation. These results validate the effectiveness of the multi-task feature-sharing strategy for lymphocytic leukemia diagnosis using bone marrow microscopic images.

Förderung

  • the key specialized research and development breakthrough of Henan province
  • the key scientific research projects of Henan colleges and universities

Zitieren

APA

Ou, C., Hu, Z., Wang, X., Cao, K., & Wang, Y. (2026). MTLL: A Novel Multi-Task Learning Approach for Lymphocytic Leukemia Classification and Nucleus Segmentation. Electronics, 15(7), 1419. https://doi.org/10.3390/electronics15071419

Vancouver

Ou C, Hu Z, Wang X, Cao K, Wang Y. MTLL: A Novel Multi-Task Learning Approach for Lymphocytic Leukemia Classification and Nucleus Segmentation. Electronics. 2026;15(7):1419. doi:10.3390/electronics15071419

BibTeX
@article{Ou2026,
  author = {Ou, Cuisi and Hu, Zhigang and Wang, Xinzheng and Cao, Kaiwen and Wang, Yipei},
  title = {MTLL: A Novel Multi-Task Learning Approach for Lymphocytic Leukemia Classification and Nucleus Segmentation},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {7},
  pages = {1419},
  doi = {10.3390/electronics15071419}
}
Kostenlos starten →