Hierarchical Classification of Breast Cancer Cells Using MIBI Images and Machine Learning

• Daniel de Sousa Luz UFPI / IFPI
• Mano Joseph Mathew Efrei Paris Pantheon-Assas University
• Thiago José Barbosa Lima UFPI
• Romuere Rodrigues Veloso e Silva UFPI
• Antonio Oseas de Carvalho Filho UFPI
• Flávio Henrique Duarte de Araújo UFPI

DOI: https://doi.org/10.5753/sbcas.2025.7290

Abstract

Breast cancer is one of the leading causes of mortality among women worldwide, with diagnosis often occurring too late. Early detection is crucial to prevent advanced stages and improve prognosis. Aggressive subtypes, like triple-negative breast cancer (TNBC), require personalized therapies based on tumor profiling. Analyzing the tumor microenvironment is challenging due to the complexity of identifying tissue components. Advances in computer vision and deep learning have enabled image segmentation and classification methods. This study proposes a method for classifying cells by general type and immune identity. The approach was tested on TNBC images and showed promising AUC results for classifying cells into general (0.9998) and immune (0.9994) types.

References

American Cancer Society (2025). Triple-negative Breast Cancer. Acessado em: 1 fev. 2025. American Cancer Society.

Amitay, Yael et al. (2023). “CellSighter: a neural network to classify cells in highly multiplexed images”. Em: Nature Communications 14.1. ISSN: 2041-1723.

Anderson, Nicole M. e M. Celeste Simon (2020). “The tumor microenvironment”. Em: Current Biology 30.16, R921–R925. ISSN: 0960-9822.

Bajaj, Sweta et al. (2024). “Automated Single Cell Phenotyping of Time-of-Flight Secondary Ion Mass Spectrometry Tissue Images”. Em: Journal of the American Society for Mass Spectrometry 35.12, pp. 3126–3134. ISSN: 1879-1123.

Bortolomeazzi, Michele et al. (2022). “A SIMPLI (Single-cell Identification from MultiPLexed Images) approach for spatially-resolved tissue phenotyping at single-cell resolution”. Em: Nature Communications 13.1. ISSN: 2041-1723.

Derakhshan, Fatemeh e Jorge S Reis-Filho (2022). “Pathogenesis of triple-negative breast cancer”. Em: Annual Review of Pathology: Mechanisms of Disease 17.1, pp. 181–204.

Fei, Nanyi et al. (2021). “Z-Score Normalization, Hubness, and Few-Shot Learning”. Em: 2021 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, pp. 142–151.

Hong, Jin-Hyuk e Sung-Bae Cho (2008). “A probabilistic multi-class strategy of one-vs.-rest support vector machines for cancer classification”. Em: Neurocomputing 71.16–18, pp. 3275–3281. ISSN: 0925-2312.

Keren, Leeat et al. (2019). “MIBI-TOF: A multiplexed imaging platform relates cellular phenotypes and tissue structure”. Em: Science Advances 5.10. ISSN: 2375-2548.

Lahiri, Aditya et al. (2023). “Drug Target Identification in Triple Negative Breast Cancer Stem Cell Pathways: A Computational Study of Gene Regulatory Pathways Using Boolean Networks”. Em: IEEE Access 11, pp. 56672–56690. ISSN: 2169-3536.

Li, Yun et al. (2022). “Recent advances in therapeutic strategies for triple-negative breast cancer”. Em: Journal of hematology & oncology 15.1, p. 121.

Lima, Thiago et al. (2023). “Automatic classification of pulmonary nodules in computed tomography images using pre-trained networks and bag of features”. Em: Multimedia Tools and Applications 82.27, pp. 42977–42993. ISSN: 1573-7721.

Luz, Daniel S. et al. (2022). “Automatic detection metastasis in breast histopathological images based on ensemble learning and color adjustment”. Em: Biomedical Signal Processing and Control 75, p. 103564. ISSN: 1746-8094.

Luz et al. (2023). “Malignant breast lesions detection in histopathological images based on the combination of bioinspired texture descriptors and deep features”. Em: Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization 11.5, pp. 1889–1896. ISSN: 2168-1171.

Pang, Minxing et al. (2024). “CelloType: a unified model for segmentation and classification of tissue images”. Em: Nature Methods 22.2, pp. 348–357. ISSN: 1548-7105.

Powers, David M. W. (2020). “Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation”. Em.

Ptacek, Jason et al. (2020). “Multiplexed ion beam imaging (MIBI) for characterization of the tumor microenvironment across tumor types”. Em: Laboratory Investigation 100.8, pp. 1111–1123. ISSN: 0023-6837.

Shrestha, Prem, Nicholas Kuang e Ji Yu (2023). “Efficient end-to-end learning for cell segmentation with machine generated weak annotations”. Em: Communications Biology 6.1. ISSN: 2399-3642.

Studebaker, Gerald A. (1985). “A “Rationalized” Arcsine Transform”. Em: Journal of Speech, Language, and Hearing Research 28.3, pp. 455–462. ISSN: 1558-9102.

Zagami, Paola e Lisa Anne Carey (2022). “Triple negative breast cancer: Pitfalls and progress”. Em: NPJ breast cancer 8.1, p. 95.