ROI-Based Shape-Prior Reconstruction for YOLOv8n-seg-Based Fetal Cerebellum Ultrasound Segmentation
DOI:
https://doi.org/10.63158/journalisi.v8i3.1669Keywords:
Fetal Ultrasound, Medical Image Segmentation, YOLOv8n-seg, Shape-Prior Reconstruction, Boundary RefinementAbstract
Fetal cerebellum segmentation in ultrasound images is important for quantitative analysis of fetal brain development, yet it remains challenging due to speckle noise, low contrast, acoustic artifacts, and unstable anatomical boundaries. This study proposes an ROI-Based Shape-Prior Reconstruction method as a post-processing refinement stage for YOLOv8n-seg fetal cerebellum segmentation. A total of 294 fetal ultrasound images with manually annotated binary cerebellum masks were used and divided into training, validation, and testing subsets using a 70:20:10 ratio. YOLOv8n-seg generated the initial segmentation masks, while the proposed ROI-based reconstruction stage refined the foreground region using a convolutional autoencoder trained on ROI-based binary cerebellum masks. Compared with raw YOLOv8n-seg, the proposed method improved DSC from 0.9282 to 0.9302 and IoU from 0.8671 to 0.8708. Boundary performance also improved, with HD95 decreasing from 15.06 to 14.18 and ASSD decreasing from 5.38 to 5.20. Although these improvements were modest and not statistically significant, the proposed method produced smoother boundaries and more morphologically consistent segmentation outputs in the visual evaluation. These results indicate that ROI-based shape-prior reconstruction can serve as a lightweight refinement stage for improving boundary consistency in fetal cerebellum ultrasound segmentation. However, external validation with larger datasets is still required to assess generalization.
Downloads
References
[1] Z. Sun, Y. Chen, and Q. Su, “Prenatal ultrasound for the diagnosis of the cerebellar abnormalities: a meta-analysis,” The Journal of Maternal-Fetal & Neonatal Medicine, vol. 38, no. 1, Dec. 2025, doi: 10.1080/14767058.2025.2453997.
[2] N. Peñuelas et al., “Gestational age assessment by ultrasound cerebellar measurements in fetal and perinatal deaths,” Am. J. Obstet. Gynecol., vol. 232, no. 6, pp. 559.e1-559.e10, Jun. 2025, doi: 10.1016/j.ajog.2024.11.016.
[3] Q. Wang, D. Zhao, H. Ma, and B. Liu, “Advanced fetal cerebellar vermis segmentation and gestational age prediction in ultrasound imaging for prenatal neural development assessment,” Eng. Appl. Artif. Intell., vol. 164, Art. no. 113315, Jan. 2026, doi: 10.1016/j.engappai.2025.113315.
[4] O. Rainio, E. Roshan, S. M. Hosseini, R. Rehman, J. Okenwa, and R. Klén, “Deep Learning for Medical Ultrasound Image Segmentation: A Systematic Review of the Current Research,” Journal of Imaging Informatics in Medicine, Mar. 2026, doi: 10.1007/s10278-026-01931-1.
[5] L. Xiao, J. Song, X. Xie, and C. Fan, “Enhanced medical image segmentation using U-Net with residual connections and dual attention mechanism,” Eng. Appl. Artif. Intell., vol. 153, Aug. 2025, doi: 10.1016/j.engappai.2025.110794.
[6] V. Asadpour and F. Xie, “Artificial intelligence for medical imaging: a review of U-Net technology for anatomical feature analysis,” Intelligent Medicine, Feb. 2025, doi: 10.1016/j.imed.2025.07.003.
[7] K. G. Khushubu et al., “TransUNetB: An advanced Transformer–UNet framework for efficient and explainable brain tumor segmentation,” Inform. Med. Unlocked, vol. 59, Jan. 2025, doi: 10.1016/j.imu.2025.101706.
[8] Z. Cai, K. Zhou, and Z. Liao, “A Systematic Review of YOLO-Based Object Detection in Medical Imaging: Advances, Challenges, and Future Directions,” Computers, Materials & Continua, vol. 85, no. 2, pp. 2255–2303, 2025, doi: 10.32604/cmc.2025.067994.
[9] A. M. Mostafa et al., “Optimized YOLOv8 for enhanced breast tumor segmentation in ultrasound imaging,” Discover Oncology, vol. 16, no. 1, Dec. 2025, doi: 10.1007/s12672-025-02889-2.
[10] J. Chen et al., “A deep learning-based multimodal medical imaging model for breast cancer screening,” Sci. Rep., vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-99535-2.
[11] H. Qiu, C. Zhong, C. Gao, and C. Huang, “Boundary-enhanced local-global collaborative network for medical image segmentation,” Sci. Rep., vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-93875-9.
[12] B. Li, W. Zhou, and H. Li, “A hybrid CNN-Transformer network integrating multiscale spatially detailed features for medical image segmentation,” PLoS One, vol. 21, no. 4, Art. no. e0345549, Apr. 2026, doi: 10.1371/journal.pone.0345549.
[13] Y. Zhou et al., “Efficient few-shot medical image segmentation via self-supervised variational autoencoder,” Med. Image Anal., vol. 104, Aug. 2025, doi: 10.1016/j.media.2025.103637.
[14] X. Yu, L. Teng, D. Zhang, J. Zheng, and H. Chen, “Attention correction feature and boundary constraint knowledge distillation for efficient 3D medical image segmentation,” Expert Syst. Appl., vol. 262, Mar. 2025, doi: 10.1016/j.eswa.2024.125670.
[15] P. Zhang, Y. Cheng, and S. Tamura, “Shape prior-constrained deep learning network for medical image segmentation,” Comput. Biol. Med., vol. 180, Sep. 2024, doi: 10.1016/j.compbiomed.2024.108932.
[16] A. Vatanparast, M. Fateh, H. Mashayekhi, and S. Ferdowsi, “SS_CASE_UNet: an attention-enhanced semi-supervised framework for fetal cerebellum segmentation in ultrasound images,” Sci. Rep., vol. 15, no. 1, Art. no. 44536, Dec. 2025, doi: 10.1038/s41598-025-28201-4.
[17] T. Wang et al., “DCCE-UNet: a difference and context-aware contrast enhanced framework for ultrasound image segmentation,” BMC Med. Imaging, vol. 25, no. 1, Dec. 2025, doi: 10.1186/s12880-025-01954-0.
[18] X. Xiao et al., “Deep Learning-Based Medical Ultrasound Image and Video Segmentation Methods: Overview, Frontiers, and Challenges,” Sensors, vol. 25, no. 8, Apr. 2025, doi: 10.3390/s25082361.
[19] D. Dai, C. Dong, H. Huang, F. Liu, Z. Li, and S. Xu, “Improving the performance of medical image segmentation with instructive feature learning,” Med. Image Anal., vol. 107, Jan. 2026, doi: 10.1016/j.media.2025.103818.
[20] Q. He et al., “Masked pretraining of U-Net for ultrasound image segmentation,” Sci. Rep., vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-11688-2.
[21] F. Neha, D. Bhati, D. K. Shukla, S. M. Dalvi, N. Mantzou, and S. Shubbar, “An analytics-driven review of U-Net for medical image segmentation,” Healthcare Analytics, vol. 8, p. 100416, Dec. 2025, doi: 10.1016/j.health.2025.100416.
[22] H. Liu, Y. Chen, R. Wang, M. Li, and Z. Li, “MFA-Deeplabv3+: an improved lightweight semantic segmentation algorithm based on Deeplabv3+,” Complex and Intelligent Systems, vol. 11, no. 10, Oct. 2025, doi: 10.1007/s40747-025-02028-y.
[23] A. Garbaz, Y. Oukdach, S. Charfi, M. El Ansari, L. Koutti, and M. Salihoun, “GSAC-UFormer: Groupwise Self-Attention Convolutional Transformer-Based UNet for Medical Image Segmentation,” Cognit. Comput., vol. 17, no. 2, Apr. 2025, doi: 10.1007/s12559-025-10425-1.
[24] Y. Gao, Y. Jiang, Y. Peng, F. Yuan, X. Zhang, and J. Wang, “Medical Image Segmentation: A Comprehensive Review of Deep Learning-Based Methods,” Tomography, vol. 11, no. 5, p. 52, Apr. 2025, doi: 10.3390/tomography11050052.
[25] R. Sapkota et al., “YOLO advances to its genesis: a decadal and comprehensive review of the You Only Look Once (YOLO) series,” Artif. Intell. Rev., vol. 58, no. 9, Sep. 2025, doi: 10.1007/s10462-025-11253-3.
[26] C. Natarajan, S. Rajendran, M. S. Vinmathi, and R. M. Gomathi, “ROI-guided relational YOLO–SegNet transformer for lightweight bone tumor segmentation and classification from X-ray images,” Sci. Rep., vol. 16, no. 1, Art. no. 14603, Mar. 2026, doi: 10.1038/s41598-026-44297-8.
[27] L. Li, S. Lian, Z. Luo, B. Wang, and S. Li, “Contour-aware consistency for semi-supervised medical image segmentation,” Biomed. Signal Process. Control, vol. 89, Mar. 2024, doi: 10.1016/j.bspc.2023.105694.
[28] A. L. Y. Hung et al., “A Neural Conditional Random Field Model Using Deep Features and Learnable Functions for End-to-End MRI Prostate Zonal Segmentation,” Machine Learning for Biomedical Imaging, vol. 3, no. August 2025, pp. 261–286, Aug. 2025, doi: 10.59275/j.melba.2025-gc4c.
[29] K. Dong et al., “Position-aware representation learning with anatomical priors for enhanced pancreas tumor segmentation,” Neurocomputing, vol. 616, Feb. 2025, doi: 10.1016/j.neucom.2024.128881.
[30] H. Abudukelimu et al., “DVF-YOLO-Seg: A two-stage breast mass segmentation model with enhanced feature extraction and small lesion detection,” Digit. Health, vol. 11, May 2025, doi: 10.1177/20552076251374192.
[31] H. Jebril, T. Pinetz, and H. Bogunović, “Shape Prior for Quality Assessment in OCTA via Denoising Autoencoders at the Segmentation Level,” IEEE Access, vol. 13, pp. 187467–187476, 2025, doi: 10.1109/ACCESS.2025.3625745.
[32] F. A. Zaman, M. Jacob, A. Chang, K. Liu, M. Sonka, and X. Wu, “Latent diffusion for medical image segmentation: End-to-end learning for fast sampling and accuracy,” Biomed. Signal Process. Control, vol. 114, Apr. 2026, doi: 10.1016/j.bspc.2025.109380.
[33] S. Gül, G. Cetinel, B. M. Aydin, D. Akgün, and R. Öztaş Kara, “YOLOSAMIC: A Hybrid Approach to Skin Cancer Segmentation with the Segment Anything Model and YOLOv8,” Diagnostics, vol. 15, no. 4, Feb. 2025, doi: 10.3390/diagnostics15040479.
[34] M. Alzubaidi, M. Agus, M. Makhlouf, F. Anver, K. Alyafei, and M. Househ, “Large-scale annotation dataset for fetal head biometry in ultrasound images,” Data Brief, vol. 51, Art. no. 109708, Dec. 2023, doi: 10.1016/j.dib.2023.109708.
[35] M. Yeung, E. Sala, C.-B. Schönlieb, and L. Rundo, “Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation,” Computerized Medical Imaging and Graphics, vol. 95, p. 102026, Jan. 2022, doi: 10.1016/j.compmedimag.2021.102026.
[36] D. Müller, I. Soto-Rey, and F. Kramer, “Towards a guideline for evaluation metrics in medical image segmentation,” BMC Res. Notes, vol. 15, Art. no. 210, Dec. 2022, doi: 10.1186/s13104-022-06096-y.
[37] A. A. Taha and A. Hanbury, “Metrics for evaluating 3D medical image segmentation: Analysis, selection, and tool,” BMC Med. Imaging, vol. 15, no. 1, Aug. 2015, doi: 10.1186/s12880-015-0068-x.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Information Systems and Informatics
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors Declaration
- The Authors certify that they have read, understood, and agreed to the Journal of Information Systems and Informatics (JournalISI) submission guidelines, policies, and submission declaration. The submission has been prepared using the provided template.
- The Authors certify that all authors have approved the publication of this manuscript and that there is no conflict of interest.
- The Authors confirm that the manuscript is their original work, has not received prior publication, is not under consideration for publication elsewhere, and has not been previously published.
- The Authors confirm that all authors listed on the title page have contributed significantly to the work, have read the manuscript, attest to the validity and legitimacy of the data and its interpretation, and agree to its submission.
- The Authors confirm that the manuscript is not copied from or plagiarized from any other published work.
- The Authors declare that the manuscript will not be submitted for publication in any other journal or magazine until a decision is made by the journal editors.
- If the manuscript is finally accepted for publication, the Authors confirm that they will either proceed with publication immediately or withdraw the manuscript in accordance with the journal’s withdrawal policies.
- The Authors agree that, upon publication of the manuscript in this journal, they transfer copyright or assign exclusive rights to the publisher, including commercial rights
