IDX-EFFİCİENTUNET: HİSTOPATOLOJİK GÖRÜNTÜLERDE ÇEKİRDEK SEGMENTASYONU İÇİN INDEX-DRİVEN ETİKETLEME MEKANİZMASINA SAHİP EFFİCİENTNETB7 TABANLI U-NET YÖNTEMİ

Furkan Atlan; Emrah Hançer

doi:10.17780/ksujes.1682089

TR EN

IDX-EFFİCİENTUNET: HİSTOPATOLOJİK GÖRÜNTÜLERDE ÇEKİRDEK SEGMENTASYONU İÇİN INDEX-DRİVEN ETİKETLEME MEKANİZMASINA SAHİP EFFİCİENTNETB7 TABANLI U-NET YÖNTEMİ

Öz

Histopatolojik görüntülerde hücre çekirdeklerinin doğru şekilde segmentasyonu, kanserin erken tanısı ve sınıflandırılması açısından büyük önem taşımaktadır. Bu çalışmada, U-Net temelli bir çekirdek segmentasyon modeli geliştirilmiş ve derin özellik çıkarımı için EfficientNetB7 kodlayıcı kullanılmıştır. Model, farklı çözünürlük seviyelerinden gelen bilgileri bütünleştirerek, karmaşık hücresel yapılardan anlamlı öznitelikler çıkarmakta ve segmentasyon doğruluğunu artırmaktadır. Ayrıca, eğitim verilerinde etiket tutarsızlıklarını ortadan kaldırmak üzere, maske sınıflarını otomatik olarak sayısal değerlere eşleyen “Index-Driven” adlı bir etiketleme mekanizması önerilmiştir. Bu yaklaşım, özellikle birden fazla kaynaktan elde edilen verilerin tekil sınıf temelli ikili segmentasyon için tutarlı biçimde hazırlanmasını sağlamaktadır. Gerçekleştirilen deneysel çalışmalar, bu mimari ve etiketleme bütünlüğünün, modelin segmentasyon doğruluğunu anlamlı düzeyde artırdığını ve literatürdeki yöntemlerle rekabet edebilecek bir performans sunduğunu göstermektedir.

Anahtar Kelimeler

IDX-EFFICIENTUNET: AN EFFICIENTNETB7-ENHANCED U-NET METHOD WITH INDEX-DRIVEN LABELING FOR NUCLEI SEGMENTATION IN HISTOPATHOLOGY IMAGES

Abstract

Accurate segmentation of cell nuclei in histopathology images is essential for early cancer diagnosis and classification. In this study, we propose a U-Net-based segmentation model that incorporates an EfficientNetB7 encoder to enable deep feature extraction across multiple resolution levels. The architecture effectively captures complex cellular structures and enhances segmentation precision through rich multi-scale representations. To address label inconsistencies across datasets, we introduce an Index-Driven labeling mechanism that automatically maps semantic class annotations to numerical values. This strategy ensures consistent binary labeling, particularly when integrating heterogeneous mask sources into a unified training pipeline. Experimental results demonstrate that the integration of this architecture and labeling strategy significantly enhances the model’s segmentation accuracy and provides a performance that is competitive with existing methods in the literature.

Keywords

Kaynakça

Ahmad, I., Xia, Y., Cui, H., & Islam, Z. U. (2023). DAN-NucNet: A dual attention based framework for nuclei segmentation in cancer histology images under wild clinical conditions. Expert Systems with Applications, 213, 118945. https://doi.org/10.1016/j.eswa.2022.118945
Basu, A., Senapati, P., Deb, M., Rai, R., & Dhal, K. G. (2024). A survey on recent trends in deep learning for nucleus segmentation from histopathology images. Evolving Systems, 15(1), 203-248. https://doi.org/10.1007/s12530-023-09491-3
Brixtel, R., Bougleux, S., Lézoray, O., Caillot, Y., Lemoine, B., Fontaine, M., ... & Renouf, A. (2022). Whole slide image quality in digital pathology: review and perspectives. IEEE Access, 10, 131005-131035. https://doi.org/10.1109/ACCESS.2022.3227437
Chen, J., Wang, R., Dong, W., He, H., & Wang, S. (2025). HistoNeXt: dual-mechanism feature pyramid network for cell nuclear segmentation and classification. BMC Medical Imaging, 25(1), 9. https://doi.org/10.1186/s12880-025-01550-2
Deshmukh, G., Susladkar, O., Makwana, D., & Mittal, S. (2022). FEEDNet: A feature enhanced encoder-decoder LSTM network for nuclei instance segmentation for histopathological diagnosis. Physics in Medicine & Biology, 67(19), 195011. https://doi.org/10.1088/1361-6560/ac8594
Dogar, G. M., Shahzad, M., & Fraz, M. M. (2023). Attention augmented distance regression and classification network for nuclei instance segmentation and type classification in histology images. Biomedical Signal Processing and Control, 79, 104199. https://doi.org/10.1016/j.bspc.2022.104199
Gabdullin, M. T., Mukasheva, A., Koishiyeva, D., Umarov, T., Bissembayev, A., Kim, K. S., & Kang, J. W. (2024). Automatic cancer nuclei segmentation on histological images: comparison study of deep learning methods. Biotechnology and Bioprocess Engineering, 29(6), 1034-1047. https://doi.org/10.1007/s12257-024-00130-5
Graham, S., Vu, Q. D., Raza, S. E. A., Azam, A., Tsang, Y. W., Kwak, J. T., & Rajpoot, N. (2019). Hover-net: Simultaneous segmentation and classification of nuclei in multi-tissue histology images. Medical image analysis, 58, 101563. https://doi.org/10.1016/j.media.2019.101563

Guan, B., Chu, G., Wang, Z., Li, J., & Yi, B. (2025). Instance-level semantic segmentation of nuclei based on multimodal structure encoding. BMC bioinformatics, 26(1), 42. https://doi.org/10.1186/s12859-025-06066-8
Hancer, E., Traoré, 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. https://doi.org/10.1016/j.bspc.2023.104720
Kadaskar, M., & Patil, N. (2024). ANet: Nuclei Instance Segmentation and Classification with Attention-Based Network. SN Computer Science, 5(4), 348. https://doi.org/10.1007/s42979-024-02661-3
Ke, J., Lu, Y., Shen, Y., Zhu, J., Zhou, Y., Huang, J., ... & Shen, D. (2023). Clusterseg: A crowd cluster pinpointed nucleus segmentation framework with cross-modality datasets. Medical Image Analysis, 85, 102758. https://doi.org/10.1016/j.media.2023.102758
Kumar, N., Verma, R., Sharma, S., Bhargava, S., Vahadane, A., & Sethi, A. (2017). A dataset and a technique for generalized nuclear segmentation for computational pathology. IEEE transactions on medical imaging, 36(7), 1550-1560. https://doi.org/10.1109/TMI.2017.2677499
Liu, A., Zhang, Y., Xia, Y., Wan, X., Zhou, L., Song, W., ... & Yuan, X. (2024). Classes U-Net: A method for nuclei segmentation of photoacoustic histology imaging based on information entropy image classification. Biomedical Signal Processing and Control, 91, 105932. https://doi.org/10.1016/j.bspc.2023.105932
Moncayo, R., Martel, A. L., & Romero, E. (2023). Removing non-nuclei information from histopathological images: A preprocessing step towards improving nuclei segmentation methods. Journal of Pathology Informatics, 14, 100315. https://doi.org/10.1016/j.jpi.2023.100315
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. https://doi.org/10.1109/TMI.2018.2865709
Nunes, J. D., Montezuma, D., Oliveira, D., Pereira, T., & Cardoso, J. S. (2024). A survey on cell nuclei instance segmentation and classification: Leveraging context and attention. Medical Image Analysis, 103360. https://doi.org/10.1016/j.media.2024.103360
Raza, S. E. A., Cheung, L., Shaban, M., Graham, S., Epstein, D., Pelengaris, S., ... & Rajpoot, N. M. (2019). Micro-Net: A unified model for segmentation of various objects in microscopy images. Medical image analysis, 52, 160-173. https://doi.org/10.1016/j.media.2018.12.003
Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18 (pp. 234-241). Springer international publishing. https://doi.org/10.1007/978-3-319-24574-4_28
Roy, A., Pramanik, P., Kaplun, D., Antonov, S., & Sarkar, R. (2024). AWGUNET: Attention-aided wavelet guided u-net for nuclei segmentation in histopathology images. In 2024 IEEE International Symposium on Biomedical Imaging (ISBI) (pp. 1-4). IEEE. https://doi.org/10.1109/ISBI56570.2024.10635449
Ruan, H. (2024). A Color-Aware Unsupervised Segmentation Network for Nuclei in Histopathology Images. In 2024 4th International Conference on Electronic Information Engineering and Computer Communication (EIECC) (pp. 627-631). IEEE. https://doi.org/10.1109/EIECC64539.2024.10929140
Senapati, P., Basu, A., Deb, M., & Dhal, K. G. (2024). Sharp dense u-net: an enhanced dense u-net architecture for nucleus segmentation. International Journal of Machine Learning and Cybernetics, 15(6), 2079-2094. https://doi.org/10.1007/s13042-023-02017-y
Shah, H. A., & Kang, J. M. (2023). An optimized multi-organ cancer cells segmentation for histopathological images based on CBAM-residual U-Net. IEEE Access, 11, 111608-111621. https://doi.org/10.1109/ACCESS.2023.3295914
Traoré, M., Hancer, E., Samet, R., Yıldırım, Z., & Nemati, N. (2024). CompSegNet: An enhanced U-shaped architecture for nuclei segmentation in H&E histopathology images. Biomedical Signal Processing and Control, 97, 106699. https://doi.org/10.1016/j.bspc.2024.106699
Trinh, M. N., Nguyen, V. D., Pham, V. T., & Tran, T. T. (2023). An EffcientNet-encoder U-Net joint residual refinement module with Tversky–Kahneman Baroni–Urbani–Buser loss for biomedical image segmentation. Biomedical Signal Processing and Control, 83, 104631. https://doi.org/10.1016/j.bspc.2023.104631
Wang, T., Lei, Y., Fu, Y., Wynne, J. F., Curran, W. J., Liu, T., & Yang, X. (2021). A review on medical imaging synthesis using deep learning and its clinical applications. Journal of applied clinical medical physics, 22(1), 11-36. https://doi.org/10.1002/acm2.13121
Yuan, R., Zhang, W., Dong, X., & Zhang, W. (2025). Crns: CLIP-driven referring nuclei segmentation. The Journal of Supercomputing, 81(1), 174. https://doi.org/10.1007/s11227-024-06692-8
Yue, G., Ma, X., Li, W., An, Z., & Yang, C. (2025). 2MSPK-Net: A nuclei segmentation network based on multi-scale, multi-dimensional attention, and SAM prior knowledge. Biomedical Signal Processing and Control, 100, 107140. https://doi.org/10.1016/j.bspc.2024.107140
Zhou, Y., Onder, O. F., Dou, Q., Tsougenis, E., Chen, H., & Heng, P. A. (2019). Cia-net: Robust nuclei instance segmentation with contour-aware information aggregation. In Information Processing in Medical Imaging: 26th International Conference, IPMI 2019, Hong Kong, China, June 2–7, 2019, Proceedings 26 (pp. 682-693). Springer International Publishing. https://doi.org/10.1007/978-3-030-20351-1_53

Ayrıntılar

Birincil Dil

Türkçe

Konular

Yapay Zeka (Diğer)

Bölüm

Araştırma Makalesi

Yazarlar

Furkan Atlan ^*
0000-0003-1602-1941
Türkiye

Emrah Hançer
0000-0002-3213-5191
Türkiye

Yayımlanma Tarihi

3 Eylül 2025

Gönderilme Tarihi

22 Nisan 2025

Kabul Tarihi

17 Temmuz 2025

Yayımlandığı Sayı

Yıl 2025 Cilt: 28 Sayı: 3

DOI

https://doi.org/10.17780/ksujes.1682089

IZ

https://izlik.org/JA95WS55JF

Kaynak Göster

RIS / Bibtex

APA

Atlan, F., & Hançer, E. (2025). IDX-EFFİCİENTUNET: HİSTOPATOLOJİK GÖRÜNTÜLERDE ÇEKİRDEK SEGMENTASYONU İÇİN INDEX-DRİVEN ETİKETLEME MEKANİZMASINA SAHİP EFFİCİENTNETB7 TABANLI U-NET YÖNTEMİ. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 28(3), 1427-1439. https://doi.org/10.17780/ksujes.1682089