LEYKEMIYA HUJAYRALARINI SEGMENTATSIYALASH UCHUN DARVOZALI KOʻP MASSHTABLI XUSUSIYATLARNI TAKOMILLASHTIRISH
DOI:
https://doi.org/10.5281/zenodo.23275423Keywords:
Leykemiya hujayralarini segmentatsiyalash, periferik qon surtmasi, tibbiy tasvirlarni segmentatsiyalash, qon hujayralarini tahlil qilish, oʻtkir limfoblastik leykemiya, gematologik tasvirlar tahliliAbstract
Periferik qon surtmasi tasvirlarida leykemiya hujayralarini segmentatsiyalash sinf ichidagi yuqori oʻzgaruvchanlik, hujayra chegaralarining aniq ifodalanmasligi va hujayralarning tez-tez bir-birini qoplashi tufayli murakkab masala boʻlib qolmoqda. Konvolyutsion va transformerga asoslangan zamonaviy usullar yuqori natijalarni koʻrsatsa-da, ular koʻpincha chegaralarni aniqlash sifatini hisoblash xarajatlari evaziga qurbon qiladi va bu ularning amaliy joriy etilishini cheklaydi. Ushbu ishda biz chegaralarni aniq modellashtirishni samarali koʻp masshtabli xususiyatlar tasviri bilan birlashtiruvchi, leykemiya hujayralarini segmentatsiyalashga moʻljallangan yangi chuqur arxitekturani taklif etamiz. Yondashuvimizning markazida struktura tafsilotlarini saqlagan holda ajratuvchi xususiyatlarni oʻrganishni kuchaytiruvchi adaptiv xususiyatlarni takomillashtirish strategiyasi turadi. Ogʻir tayanch tarmoqlar yoki global eʼtibor mexanizmlariga tayanish oʻrniga, taklif etilgan arxitektura yengil boʻlib qolgan holda ham lokal, ham kontekstual axborotni qamrab oladi. Etalon maʼlumotlar toʻplamlarida oʻtkazilgan keng koʻlamli tajribalar taklif etilayotgan usul Dice va IoU kabi bir qator baholash mezonlari boʻyicha zamonaviy modellardan ustun ekanini hamda buni sezilarli darajada kam parametrlar va past FLOPs koʻrsatkichi bilan amalga oshirishini koʻrsatadi. Ayniqsa, usul mavjud yondashuvlarning asosiy zaif tomoni hisoblangan kichik va bir-birini qoplaydigan hujayralarni segmentatsiyalashda yuqori natija beradi. Ushbu natijalar aniqlik, samaradorlik va umumlashtirish qobiliyati oʻrtasidagi qulay muvozanatni namoyish etib, usulni real klinik amaliyotga joriy etish hamda keng koʻlamli gematologik tahlil uchun istiqbolli nomzod sifatida koʻrsatadi.References
1. Gil, J.V., Fuentes, C., Verde, M.Á., Miralles, A., de Las Heras, S., Fernández, J.M., Barragán, E. and Llop, M., 2026. Phenocopies in acute lymphoblastic leukemia: Redefining leukemia subtypes in the transcriptomic era. Blood Reviews, p.101383.
2. Mei, L., Song, X., Shen, H., Lian, C., Han, S., Xu, C., Pei, H., Lei, C. and Xiong, B., 2026. Frequencydomain object detection network for leukemia diagnosis in bone marrow microscopy. Microscopy Research and Technique, 89(3), pp.386-399.
3. Ramírez-Ramírez, D., Zamora-Herrera, G., Romo-Rodríguez, R., Cuéllar Mendoza, M., Ayala-Contreras, K., López Aguilar, E., Zapata-Tarrés, M. and Pelayo, R., 2026. Taking High-Tech to the Field: Leukemia Diagnosis in Pediatric Mexican Patients from Vulnerable and Remote Regions. Diagnostics, 16(3), p.411.
4. Alkhouli, M.S. and Joshi, H., 2026. E-DCNN: Ensemble-Based Deep CNN Model for Acute Lymphoblastic Leukaemia (ALL) Classifier Using Microscopic Blood Smear Images. Journal of Multiscale Modelling, p.2640004.
5. Altalhi, S.H. and Alzahrani, S.M., 2026. Demystifying Deep Learning Decisions in Leukemia Diagnostics Using Explainable AI. Diagnostics, 16(2), p.212.
6. Ronneberger, O., Fischer, P. and Brox, T., 2015, October. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 234-241). Cham: Springer International Publishing.
7. Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N.Y., Kainz, B. and Glocker, B., 2018. Attention U-Net: Learning where to look for the pancreas. arXiv preprint arXiv:1804.03999.
8. Chen, L.C., Papandreou, G., Schroff, F. and Adam, H., 2017. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587.
9. Latha, R.S., Ramya Devi, M., Sakthivel, P. and Sreekanth, G.R., 2026. DSTL-NET: Multi-level Leukemia Stage Classification Via Dual-Stage Segmentation Based Transfer Learning Networks. International Journal of Computational Intelligence Systems.
10. Banerjee, T., Singh, D.P., Dhanabal, S., Chandar, K.P., Bommisetti, R.K., Narayan, Y., Chakole, N., Dutta, C., Bhosale, Y.H. and Singh, R.M., 2026. A Comprehensive Study of Various Hybrid Deep Learning Models for Leukaemia Classification: Comparative Analysis with Existing Studies. Archives of Computational Methods in Engineering, pp.1-34.
11. Dhalla, S., Mittal, A. and Gupta, S., 2026. LeukoSegmenter: A Double Encoder-decoder Based Network for Leukocyte Segmentation From Blood Smear Images. International Journal of Information Technology & Decision Making.
12. Kumar, K. and Verma, V.S., 2026. Next-Generation AI Frameworks for Leukemia Detection: Techniques, Dataset, Challenges, and Future Research Horizons. Archives of Computational Methods in Engineering, pp.1-27.
13. Isensee, F., Petersen, J., Klein, A., Zimmerer, D., Jaeger, P.F., Kohl, S., Wasserthal, J., Koehler, G., Norajitra, T., Wirkert, S. and Maier-Hein, K.H., 2018. nnu-net: Self-adapting framework for u-net-based medical image segmentation. arXiv preprint arXiv:1809.10486.
14. Jan, Z., Shabir, M., Farman, H., Rahman, A. and M. Nasralla, M., 2025. Deep learning based semantic segmentation of leukemia effected white blood cell. PLoS One, 20(5), p.e0320596.
15. Ponnusamy, U. and Perumal, V., 2026. Comprehensive review on learning models of leukemia detection based on morphological information. Leukemia & Lymphoma, 67(2), pp.255-281.
16. Ou, C., Hu, Z., Wang, X., Cao, K. and Wang, Y., 2026. MTLL: A Novel Multi-Task Learning Approach for Lymphocytic Leukemia Classification and Nucleus Segmentation. Electronics, 15(7), p.1419.
17. Al-Rahaawi, A.F., ATASOY, N.A. and Atasoy, F., 2026. DFF-U-NET: Deep features fusion u-net for bone marrow cells classification using advanced feature selection techniques. Biomedical Signal Processing and Control, 112, p.108600.
18. Zhou, Z., Rahman Siddiquee, M.M., Tajbakhsh, N. and Liang, J., 2018, September. Unet++: A nested u-net architecture for medical image segmentation. In International Workshop on Deep Learning in Medical Image Analysis(pp. 3-11). Cham: Springer International Publishing.
19. Huang, H., Lin, L., Tong, R., Hu, H., Zhang, Q., Iwamoto, Y., Han, X., Chen, Y.W. and Wu, J., 2020, May. Unet 3+: A full-scale connected u-net for medical image segmentation. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1055-1059). IEEE.
20. Ayesha, N. and Khalidi, H., 2026. A Vision Transformer with a Self-Attention Mechanism for High-Accuracy Blood Cell Classification. Engineering, Technology & Applied Science Research, 16(1), pp.32557-32563.
21. Ou, C., Hu, Z., Wang, X., Cao, K. and Wang, Y., 2026. MTLL: A Novel Multi-Task Learning Approach for Lymphocytic Leukemia Classification and Nucleus Segmentation. Electronics, 15(7), p.1419.
22. Wu, L.W., Huang, C.R. and Ouyang, Y.C., 2026. Segmentation domain adaptation for enhanced white blood cell classification using spatial co-occurrence feature embedding. Biomedical Signal Processing and Control, 112, p.108529.
23. Ramesh, M., Billa, N., Rejeti, V.K.K. and Cherukuri, P., 2025. Blast Cell Segmentation and Leukemia Classification using Hybrid Deep Kronecker WideResNet using Blood Smear Images. Computational Biology and Chemistry, p.108800.
24. Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Lu, L., Yuille, A.L. and Zhou, Y., 2021. TransUNet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306.
25. Cao, H., Wang, Y., Chen, J., Jiang, D., Zhang, X., Tian, Q. and Wang, M., 2022, October. Swin-UNet: UNetlike pure transformer for medical image segmentation. In European Conference on Computer Vision (pp. 205-218). Cham: Springer Nature Switzerland.
26. Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M. and Luo, P., 2021. SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in Neural Information Processing Systems, 34, pp.12077-12090.
27. Cheng, B., Misra, I., Schwing, A.G., Kirillov, A. and Girdhar, R., 2022. Masked-attention mask transformer for universal image segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition(pp. 1290-1299).
28. Li, F., Zhang, H., Xu, H., Liu, S., Zhang, L., Ni, L.M. and Shum, H.Y., 2023. Mask DINO: Towards a unified transformer-based framework for object detection and segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 3041-3050).
29. Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.Y. and Dollár, P., 2023. Segment Anything. In Proceedings of the IEEE/CVF International Conference on Computer Vision(pp. 4015-4026).
30. Ke, L., Ye, M., Danelljan, M., Tai, Y.W., Tang, C.K. and Yu, F., 2023. Segment anything in high quality. Advances in Neural Information Processing Systems, 36, pp.29914-29934.
31. Cheng, Z., Wei, Q., Zhu, H., Wang, Y., Qu, L., Shao, W. and Zhou, Y., 2024. Unleashing the potential of SAM for medical adaptation via hierarchical decoding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 3511-3522).
32. Ghaderzadeh, M., Aria, M., Hosseini, A., Asadi, F., Bashash, D. and Abolghasemi, H., 2022. A fast and efficient CNN model for B-ALL diagnosis and its subtypes classification using peripheral blood smear images. International Journal of Intelligent Systems, 37(8), pp.5113-5133.

