LinkNet Model Based on Ensemble Learning for Breast Cancer Segmentation

Year 2025, Volume: 9 Issue: 1, 63 - 74

Furkan Atlan

https://doi.org/10.31200/makuubd.1617565

Abstract

Breast cancer is the most common type of cancer among women in many countries. Data analysis is of great importance in the diagnosis and treatment of breast cancer. Segmentation of cancer cell nuclei in histopathological images is a very costly and challenging task for experts. In this study, A LinkNet model based on ensemble learning is proposed for kernel segmentation of histopathological breast cancer images. After the images are processed with the Contrast- Limited Adaptive Histogram Equalization (CLAHE) technique, data augmentation is applied. In the encoder part of the LinkNet model, it is trained with two separate models where ResNeXT50 and Vgg19 models are placed. Afterwards, these models are combined with ensemble learning and mask prediction is performed. The 0.702 Aggregated Jaccard Index (AJI) metric result obtained in the study was found to be more successful than recent studies conducted with the same data set.

Keywords

Breast Cancer, Segmentation, Ensemble Learning, LinkNet

Meme Kanseri Segmentasyonu için Topluluk Öğrenmesine Dayalı LinkNet Modeli

Abstract

Meme kanseri birçok ülkede kadınlar arasında en sık görülen kanser türüdür. Meme kanserinin tanı ve tedavisinde verilerin analizi büyük bir önem taşımaktadır. Histopatolojik görüntülerdeki kanserli hücre çekirdeklerinin segmentasyonu, uzmanlar için oldukça maliyetli ve zorlu bir iştir. Bu çalışmada, histopatolojik meme kanseri görüntülerinin çekirdek segmentasyonu için topluluk öğrenmesine dayalı LinkNet modeli önerilmektedir. Görüntüler, Kontrast Sınırlı Adaptif Histogram Eşitleme (CLAHE) tekniği ile işlendikten sonra veri artırma uygulanır. LinkNet modelinin kodlayıcı kısmında ResNeXT50 ve Vgg19 modellerinin yerleştirildiği iki ayrı model ile eğitilir. Sonrasında, bu modeller topluluk öğrenmesi ile birleştirilir ve maske tahmini yapılır. Çalışmada elde edilen 0.702 Kümülatif Jaccard İndeks (AJI) metriği sonucu, aynı veri seti ile yapılmış son çalışmalardan daha başarılı bulunmuştur.

Keywords

Meme kanseri, Segmentasyon, Topluluk Öğrenmesi, LinkNet

References

• Prabhu, S., Prasad, K., Robels-Kelly, A., & Lu, X. (2022). AI-based carcinoma detection and classification using histopathological images: A systematic review. Computers in Biology and Medicine, 142, 105209.
• Abdelsamea, M. M., Zidan, U., Senousy, Z., Gaber, M. M., Rakha, E., & Ilyas, M. (2022). A survey on artificial intelligence in histopathology image analysis. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 12(6), e1474.
• Bakkouri, I., Afdel, K., Benois-Pineau, J., & Initiative, G. C. F. T. A. S. D. N. (2022). BG-3DM2F: Bidirectional gated 3D multi-scale feature fusion for Alzheimer’s disease diagnosis. Multimedia Tools and Applications, 81(8), 10743-10776.
• Aswathy, M. A., & Jagannath, M., (2017). Detection of breast cancer on digital histopathology images: Present status and future possibilities. Informatics in Medicine Unlocked, 8, 74-79.
• Bray, F., Ferlay, J., Soerjomataram, I., Siegel, R. L., Torre, L. A., & Jemal, A. (2018). Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians, 68(6), 394-424.
• Ferlay, J., Colombet, M., Soerjomataram, I., Parkin, D. M., Piñeros, M., Znaor, A., & Bray, F. (2021). Cancer statistics for the year 2020: An overview. International Journal of Cancer, 149(4), 778-789.
• T.C. Sağlık Bakanlığı Halk Sağlığı Genel Müdürlüğü. Türkiye Kanser İstatistikleri 2018. Erişim adresi: https://hsgm.saglik.gov.tr/tr/kanser-istatistikleri.html, 2024.
• Abdel-Halim, C. N., Rosenberg, T., Dyrvig, A. K., Høilund-Carlsen, P. F., Sørensen, J. A., Rohde, M., & Godballe, C. (2021). Diagnostic accuracy of imaging modalities in detection of histopathological extranodal extension: A systematic review and meta-analysis. Oral Oncology, 114, 105169.
• Naylor, P., Laé, M., Reyal, F., & Walter, T. (2018). Segmentation of nuclei in histopathology images by deep regression of the distance map. IEEE Transactions on Medical Imaging, 38(2), 448-459.
• Lee, H., Park, J., & Hwang, J. Y., (2020). Channel attention module with multiscale grid average pooling for breast cancer segmentation in an ultrasound image. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 67(7), 1344-1353.
• Tsochatzidis, L., Koutla, P., Costaridou, L., & Pratikakis, I. (2021). Integrating segmentation information into CNN for breast cancer diagnosis of mammographic masses. Computer Methods and Programs in Biomedicine, vol. 200, pp. 105913.
• Qin, C., Wu, Y., Zeng, J., Tian, L., Zhai, Y., Li, F., & Zhang, X. (2022). Joint transformer and multi-scale CNN for DCE-MRI breast cancer segmentation. Soft Computing, 26(17), 8317-8334.
• Huang, R., Xu, Z., Xie, Y., Wu, H., Li, Z., Cui, Y., ... & Wang, Y., (2023). Joint-phase attention network for breast cancer segmentation in DCE-MRI. Expert Systems with Applications, 224, 119962.
• Samudrala, S., & Mohan, C. K. (2024). Semantic segmentation of breast cancer images using DenseNet with proposed PSPNet. Multimedia Tools and Applications, 83(15), 46037-46063.
• Imtiaz, T., Fattah, S. A., & Saquib, M., (2023). ConDANet: Contourlet driven attention network for automatic nuclei segmentation in histopathology images. IEEE Access.
• Chaurasia, A., & Culurciello, E., (2017). Linknet: Exploiting encoder representations for efficient semantic segmentation. In 2017 IEEE Visual Communications and Image Processing (VCIP), 1-4, IEEE.
• Tanwar, S., & Singh, J. (2023). ResNext50 based convolution neural network-long short term memory model for plant disease classification. Multimedia Tools and Applications, vol. 82(19), 29527-29545.
• Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
• Zhang, J., Li, C., Kosov, S., Grzegorzek, M., Shirahama, K., Jiang, T., ... & Li, H. (2021). LCU-Net: A novel low- cost U-Net for environmental microorganism image segmentation. Pattern Recognition, 115, 107885.
• Hancer, E., Traore, M., Samet, R., Yıldırım, Z., & Nemati, N. (2023). An imbalance-aware nuclei segmentation methodology for H&E stained histopathology images. Biomedical Signal Processing and Control, 83, 104720.
• Liu, W., He, Q., & He, X. (2022). Weakly supervised nuclei segmentation via instance learning. In 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), 1-5, IEEE.
• Chanchal, A. K., Lal, S., & Kini, J. (2022). Deep structured residual encoder-decoder network with a novel loss function for nuclei segmentation of kidney and breast histopathology images. Multimedia Tools and Applications, 81(7), 9201-9224.
• Li, X., Pi, J., Lou, M., Qi, Y., Li, S., Meng, J., & Ma, Y. (2023). Multi-level feature fusion network for nuclei segmentation in digital histopathological images. The Visual Computer, 39(4), 1307-1322.
• Imtiaz, T., Fattah, S. A., & Kung, S. Y. (2023). BAWGNet: Boundary aware wavelet guided network for the nuclei segmentation in histopathology images. Computers in Biology and Medicine, 165, 107378.
• Gour, M., Jain, S., & Kumar, T. S. (2024). Robust nuclei segmentation with encoder‐decoder network from the histopathological images. International Journal of Imaging Systems and Technology, 34(4), e23111.
• Kadaskar, M., & Patil, N. (2024). ANet: Nuclei instance segmentation and classification with attention-based network. SN Computer Science, 5(4), 348.
• Dhamale, A., Rajalakshmi, R., & Balasundaram, A. (2025). Dual multi scale networks for medical image segmentation using contrastive learning. Image and Vision Computing, 154, 105371.
• Aumente-Maestro, C., Díez, J., & Remeseiro, B. (2025). A multi-task framework for breast cancer segmentation and classification in ultrasound imaging. Computer Methods and Programs in Biomedicine, 260, 108540.