Histopatoloji Görüntülerinden Meme Kanseri Tespiti İçin MambaVision Modelinin Performans Değerlendirmesi

Öz

Meme kanserinin doğru ve erken teşhisi, hasta sonuçlarının iyileştirilmesi için kritik öneme sahiptir. Histopatolojik görüntü analizi, klinik değerlendirme için altın standart olmaya devam etmektedir. Bu çalışmada, meme histopatoloji görüntülerinin ikili sınıflandırması için görsel durum uzayı ve transformer temelli hibrit bir model olan MambaVision'ın kullanımı araştırılmaktadır. Farklı ölçeklerdeki ve önceden eğitilmiş dört MambaVision varyantı, iyi ve kötü huylu doku örneklerini tespit etmek için kullanılmıştır. Önerilen modeller çapraz entropi kaybı ile iki aşamalı bir öğrenme oranı planı kullanılarak yeniden eğitilmiş ve modellerin performansı kesinlik, duyarlılık, F1 skoru ve doğruluk kullanılarak değerlendirilmiştir. Yapılan deneylerde, tüm modeller tutarlı bir şekilde yüksek sınıflandırma performansı sergilerken, Büyük varyant %99,7 ile en yüksek doğruluğa ve hatasız duyarlılık değerine ulaşmıştır. Karışıklık matrisi analizi, modellerin klinik uygulamalarda kritik bir husus olan yanlış negatifleri en aza indirme konusundaki güvenilirliğini daha da vurgulamıştır. Literatürdeki mevcut derin öğrenme yaklaşımlarıyla karşılaştırıldığında, MambaVision tüm benzer yöntemlerden daha iyi performans göstererek hem ince taneli hücresel özellikleri hem de büyük ölçekli doku bağlamını modellemedeki etkinliğini doğrulamıştır. Sonuçlar, MambaVision'ın bilgisayar destekli meme kanseri teşhisi için ölçeklenebilir ve doğru bir çözüm sunduğunu ve dijital patolojide kullanım için güçlü bir potansiyele sahip olduğunu göstermektedir.

Anahtar Kelimeler

• Meme Kanseri
• MambaVision
• Histopatolojik Görüntü Sınıflandırma
• Derin Öğrenme

Performance Evaluation of MambaVision in Breast Cancer Detection from Histopathology Images

Abstract

Accurate and early diagnosis of breast cancer is critical to improving patient outcomes, and histopathological image analysis remains the gold standard for clinical assessment. In this study, we explore the use of MambaVision, a hybrid visual state space and transformer model, for binary classification of breast histopathology images. Four pretrained MambaVision variants—Tiny, Small, Base, and Large—were fine-tuned and evaluated on a benchmark dataset to distinguish between benign and malignant tissue samples. The proposed models were trained using a two-stage learning rate schedule with cross-entropy loss, and performance was assessed using precision, recall, F1-score, and accuracy. Our experiments demonstrate consistently high classification performance across all model scales, with the Large variant achieving the highest accuracy of 99.7% and perfect recall. Confusion matrix analysis further highlights the models’ reliability in minimizing false negatives, a critical consideration in clinical applications. When compared to several existing deep learning approaches in the literature, MambaVision outperforms all competing methods, confirming its effectiveness in modeling both fine-grained cellular features and large-scale tissue context. The results suggest that MambaVision offers a scalable and accurate solution for computer-aided breast cancer diagnosis, with strong potential for deployment in digital pathology workflows.

Keywords

• Breast Cancer
• MambaVision
• Histopathological Image Classification
• Deep Learning

References

1. [1] D. Trapani, O. Ginsburg, T. Fadelu, N. U. Lin, M. Hassett, A. M. Ilbawi, B. O. Anderson and G. Curigliano, "Global challenges and policy solutions in breast cancer control," Cancer Treatment Reviews, vol. 104, p. 102339, 2022.
2. [2] L. Wilkinson and T. Gathani, "Understanding breast cancer as a global health concern," The British Journal of Radiology, vol. 95, no. 1130, 2022.
3. [3] L. Wang, "Early Diagnosis of Breast Cancer," Sensors, vol. 17, no. 7, p. 1572, 2017.
4. [4] F. A. Zeiser, C. A. da Costa, A. V. Roehe, R. d. R. Righi and N. M. C. Marques, "Breast cancer intelligent analysis of histopathological data: A systematic review," Applied Soft Computing, vol. 113, p. 107886, 2021.
5. [5] T. T. Brunyé, E. Mercan, D. L. Weaver and J. G. Elmore, "Accuracy is in the eyes of the pathologist: The visual interpretive process and diagnostic accuracy with digital whole slide images," Journal of Biomedical Informatics, vol. 66, pp. 171-179, 2017.
6. [6] S. Nam, Y. Chong, C. K. Jung, T.-Y. Kwak, J. Y. Lee, J. Park, M. J. Rho and H. Go, "Introduction to digital pathology and computer-aided pathology," Journal of Pathology and Translational Medicine, vol. 54, no. 2, pp. 125-134, 2020.
7. [7] D. Komura and S. Ishikawa, "Machine Learning Methods for Histopathological Image Analysis," Computational and Structural Biotechnology Journal, vol. 16, pp. 34-42, 2018.
8. [8] A. Jalalian, S. Mashohor, R. Mahmud, B. Karasfi, M. Saripan and A. Ramli, "Foundation and methodologies in computer-aided diagnosis systems for breast cancer detection," EXCLI Journal, vol. 16, pp. 113-137, 2017.

9. [9] C. Kaushal, S. Bhat, D. Koundal and A. Singla, "Recent Trends in Computer Assisted Diagnosis (CAD) System for Breast Cancer Diagnosis Using Histopathological Images," IRBM, vol. 40, no. 4, pp. 211-227, 2019.
10. [10] P. Wang, X. Hu, Y. Li, Q. Liu and X. Zhu, "Automatic cell nuclei segmentation and classification of breast cancer histopathology images," Signal Processing, vol. 122, pp. 1-13, 2016.
11. [11] F. A. Spanhol, L. S. Oliveira, C. Petitjean and L. Heutte, "A Dataset for Breast Cancer Histopathological Image Classification," IEEE Transactions on Biomedical Engineering, vol. 63, no. 7, pp. 1455-1462, 2016.
12. [12] B. Ehteshami Bejnordi, J. Lin, B. Glass, M. Mullooly, G. L. Gierach, M. E. Sherman, N. Karssemeijer, J. van der Laak and A. H. Beck, "Deep learning-based assessment of tumor-associated stroma for diagnosing breast cancer in histopathology images," in 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), Melbourne, VIC, Australia, 2017.
13. [13] A. A. Cruz-Roa, J. E. Arevalo Ovalle, A. Madabhushi and F. A. González Osorio, "A Deep Learning Architecture for Image Representation, Visual Interpretability and Automat," in Medical Image Computing and Computer-Assisted Intervention–MICCAI 2013: 16th International Conference, Nagoya, Japan, 2013.
14. [14] R. Kumar, R. Srivastava and S. Srivastava, "Detection and Classification of Cancer from Microscopic Biopsy Images Using Clinically Significant and Biologically Interpretable Features," Journal of Medical Engineering, vol. 2015, no. 1, pp. 1-14, 2015.
15. [15] C. Sommer, L. Fiaschi, F. A. Hamprecht and D. W. Gerlich, "Learning-based mitotic cell detection in histopathological images," in Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), Tsukuba, Japan, 2012.
16. [16] S. Issac Niwas, P. Palanisamy, R. Chibbar and W. J. Zhang, "An Expert Support System for Breast Cancer Diagnosis using Color Wavelet Features," Journal of Medical Systems, vol. 36, no. 5, pp. 3091-3102, 2012.
17. [17] A. Basavanhally, S. Ganesan, M. Feldman, N. Shih, C. Mies, J. Tomaszewski and A. Madabhushi, "Multi-Field-of-View Framework for Distinguishing Tumor Grade in ER+ Breast Cancer From Entire Histopathology Slides," IEEE Transactions on Biomedical Engineering, vol. 60, no. 8, pp. 2089-2099, 2013.
18. [18] M. Cooper, Z. Ji and R. G. Krishnan, "Machine learning in computational histopathology: Challenges and opportunities," Genes, Chromosomes and Cancer, vol. 62, no. 9, pp. 540-556, 2023.
19. [19] M. Yusoff, T. Haryanto, H. Suhartanto, W. A. Mustafa, J. M. Zain and K. Kusmardi, "Accuracy Analysis of Deep Learning Methods in Breast Cancer Classification: A Structured Review," Diagnostics, vol. 13, no. 4, p. 683, 2023.
20. [20] M. Rahman, K. Deb, P. K. Dhar and a. T. Shimamura, "ADBNet: An Attention-Guided Deep Broad Convolutional Neural Network for the Classification of Breast Cancer Histopathology Images," IEEE Access, vol. 12, pp. 133784-133809, 2024.
21. [21] C. Xu, K. Yi, N. Jiang, X. Li, M. Zhong and Y. Zhang, "MDFF-Net: A multi-dimensional feature fusion network for breast histopathology image classification," Computers in Biology and Medicine, vol. 165, p. 107385, 2023.
22. [22] D. Addo, S. Zhou, K. Sarpong, O. T. Nartey, M. A. Abdullah, C. C. Ukwuoma and M. A. Al-antari, "A hybrid lightweight breast cancer classification framework using the histopathological images," Biocybernetics and Biomedical Engineering, vol. 44, no. 1, pp. 31-54, 2024.
23. [23] S. U. R. Khan, M. Zhao, S. Asif, X. Chen and Y. Zhu, "GLNET: global–local CNN's-based informed model for detection of breast cancer categories from histopathological slides," The Journal of Supercomputing, vol. 80, no. 6, pp. 7316-7348, 2024.
24. [24] Z. He, M. Lin, Z. Xu, Z. Yao, H. Chen, A. Alhudhaif and F. Alenezi, "Deconv-transformer (DecT): A histopathological image classification model for breast cancer based on color deconvolution and transformer architecture," Information Sciences, vol. 608, pp. 1093-1112, 2022.
25. [25] P. Bhowal, S. Sen, J. D. Velasquez and R. Sarkar, "Fuzzy ensemble of deep learning models using choquet fuzzy integral, coalition game and information theory for breast cancer histology classification," Expert Systems with Applications, vol. 190, p. 116167, 2022.
26. [26] A. Gu, K. Goel and C. Ré, "Efficiently Modeling Long Sequences with Structured State Spaces," arXiv preprint arXiv:2111.00396, 2021.
27. [27] A. Gu and T. Dao, "Mamba: Linear-Time Sequence Modeling with Selective State Spaces," arXiv preprint arXiv:2312.00752, 2023.
28. [28] A. Hatamizadeh and J. Kautz, "MambaVision: A Hybrid Mamba-Transformer Vision Backbone," arXiv preprint arXiv:2407.08083, 2024.
29. [29] A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Köpf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai and S. Chintala, "PyTorch: an imperative style, high-performance deep learning library," in NIPS'19: 33rd International Conference on Neural Information Processing Systems, Vancouver, BC, Canada, 2019.
30. [30] J. Li, K. Wang and X. Jiang, "Robust Multi-Subtype Identification of Breast Cancer Pathological Images Based on a Dual-Branch Frequency Domain Fusion Network," Sensors, vol. 25, no. 1, p. 240, 2025.
31. [31] A. H. Abdulwahhab, O. Bayat and A. A. Ibrahim, "HAFMAB-Net: hierarchical adaptive fusion based on multilevel attention-enhanced bottleneck neural network for breast histopathological cancer classification," Signal, Image and Video Processing, vol. 19, no. 5, p. 410, 2025.
32. [32] V. Patel, V. Chaurasia, R. Mahadeva and S. P. Patole, "GARL-Net: Graph Based Adaptive Regularized Learning Deep Network for Breast Cancer Classification," IEEE Access, vol. 11, pp. 9095-9112, 2023.
33. [33] A. Fiaz, B. Raza, M. Faheem and A. Raza, "A deep fusion‐based vision transformer for breast cancer classification," Healthcare Technology Letters, vol. 11, no. 6, pp. 471-484, 2024.
34. [34] R. Maurya, N. N. Pandey, M. K. Dutta and M. Karnati, "FCCS-Net: Breast cancer classification using Multi-Level fully Convolutional-Channel and spatial attention-based transfer learning approach," Biomedical Signal Processing and Control, vol. 94, p. 106258, 2024.
35. [35] V. Sreelekshmi, K. Pavithran and J. J. Nair, "SwinCNN: An Integrated Swin Transformer and CNN for Improved Breast Cancer Grade Classification," IEEE Access, vol. 12, pp. 68697-68710, 2024.
36. [36] L. Liu, Y. Wang, P. Zhang, H. Qiao, T. Sun, H. Zhang, X. Xu and H. Shang, "Collaborative Transfer Network for Multi-Classification of Breast Cancer Histopathological Images," IEEE Journal of Biomedical and Health Informatics, vol. 28, no. 1, pp. 110-121, 2024.