Abstract
Fetal vascular malperfusion (FVM) is an important pathological factor leading to adverse pregnancy outcomes, but current manual diagnosis faces challenges such as high subjectivity and low efficiency. To address these problems, this paper proposes a joint analysis strategy based on data augmentation and deep learning model improvement. Using MONAI-based data augmentation it increases the number of FVM histopathology images while embedding a LocalWindow attention mechanism to enhance the YOLOv11 model. The experimental results show that this synergistic strategy of data augmentation and model improvement yields optimal recognition performance, with the F1 score, mAP50, and mAP50-95 increased by 7.84%, 6.53%, and 6.63%, respectively, compared with the YOLOv11 baseline model. This study indicates that a strategy combining data augmentation with model structural improvement can effectively enhance detection performance for FVM and provides a useful reference for the development of intelligent diagnostic tools for FVM in clinical practice.
Data availability
We have made the complete source code associated with this study open source. It has been uploaded to GitHub and is available at: https://github.com/zzsjbme/FVM_YOLOv11_LocalWindows.
References
Heider, A. Fetal vascular malperfusion. Arch. Pathol. Lab. Med. 141, 1484–1489 (2017).
Slack, J. C. & Boyd, T. K. Fetal vascular malperfusion due to long and hypercoiled umbilical cords resulting in recurrent second-trimester pregnancy loss: a case series and literature review. Pediatr. Dev. Pathol. 24, 12–18 (2021).
Redline, R. W. & Ravishankar, S. Fetal vascular malperfusion, an update. APMIS 126, 561–569 (2018).
Turowski, G. et al. The structure and utility of the placental pathology report. APMIS 126, 638–646 (2018).
Khong, T. Y. et al. Sampling and definitions of placental lesions: Amsterdam placental workshop group consensus statement. Arch. Pathol. Lab. Med. 140, 698–713 (2016).
Peck, M. et al. Review of diagnostic error in anatomical pathology and the role and value of second opinions in error prevention. J. Clin. Pathol. 71, 995–1000 (2018).
Chen, W., Luo, J., Zhang, F. & Tian, Z. A review of object detection: datasets, performance evaluation, architecture, applications and current trends. Multimed Tools Appl. 83, 65603–65661 (2024).
Feng, Y. et al. Review of object detection algorithm improvement in deep learning. J Comput. Eng. Appl 59 (2023).
Chen, X. HD-YOLO: real-time detection of benign and malignant endometrial lesions using YOLO11. Signal. Image Video Process. 19, 535 (2025).
Li, H. et al. An algorithm for cardiac disease detection based on magnetic resonance imaging. Sci. Rep. 15, 4053 (2025).
Wu, W. et al. Enhancing placental pathology detection with GAMatrix-YOLOv8 model. Heliyon 11 (2025).
Vanea, C. et al. Mapping cell-to-tissue graphs across human placenta histology whole slide images using deep learning with HAPPY. Nat. Commun. 15, 2710 (2024).
Lee, Y. J., Lee, M. Y., Chung, J. H., Won, H. S. & Park, B. Birth weight prediction using artificial intelligence-based placental assessment from macroscopic photo: a retrospective study. Placenta (2025).
Andreasen, L. A., Feragen, A., Christensen, A. N., Sperling, L. & Tolsgaard, M. G. Multi-centre deep learning for placenta segmentation in obstetric ultrasound with multi-observer and cross-country generalization. Sci. Rep. 13, 2221 (2023).
Fujii, Y. et al. Effectiveness of data-augmentation on deep learning in evaluating rapid on-site cytopathology at endoscopic ultrasound-guided fine needle aspiration. Sci. Rep. 14, 22441 (2024).
Hong, J. E., Kim, Y. E., Kang, Y. S., Park, J. Y. & Yu, H. W. SMOTE-augmented machine learning model predicts recurrent and metastatic breast cancer from Microbiome analysis. Sci. Rep. 15, 33096 (2025).
Marouf, M. et al. Realistic in Silico generation and augmentation of single-cell RNA-seq data using generative adversarial networks. Nat. Commun. 11, 166 (2020).
Zhang, L., Jindal, B., Alaa, A., Clifton, D. A. & Yang, Y. Generative AI enables medical image segmentation in ultra low-data regimes. Nat. Commun. 16, 6486 (2025).
Mobadersany, P., Cooper, L. A. D. & Goldstein, J. A. GestAltNet: aggregation and attention to improve deep learning of gestational age from placental whole-slide images. Lab. Invest. 101, 942–951 (2021).
Parathanath, A. J. & Anu, M. CBMNet: a dual-attention enhanced ConvNeXt model for accurate GV black type I–III classification in intraoral periapical radiographs. Sci. Rep. 15, 39287 (2025).
Abrar, M., Salam, A., Ullah, F. & Alraddady, F. Al-Otaibi, A. N. Enhancing brain tumor segmentation using attention based convolutional UNet on MRI images. Sci. Rep. 15, 36603 (2025).
Pinaya, W. H. L. et al. Generative AI for medical imaging: extending the MONAI framework. Preprint at (2023). https://arxiv.org/abs/2307.15208
Cardoso, M. J. et al. Monai: an open-source framework for deep learning in healthcare. Preprint at (2022). https://arxiv.org/abs/2211.02701
Khanam, R. & Hussain, M. YOLOv11: an overview of the key architectural enhancements. Preprint at (2024). https://arxiv.org/abs/2410.17725
Liu, X. et al. EfficientViT: memory efficient vision transformer with cascaded group attention. In Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. 14420–14430 (2023).
Liu, Z. et al. Swin transformer: hierarchical vision transformer using shifted windows. In Proc. IEEE/CVF Int. Conf. Comput. Vis. 10012–10022 (2021).
Bolya, D., Foley, S., Hays, J. & Hoffman, J. Tide: a general toolbox for identifying object detection errors. In Eur. Conf. Comput. Vis. 558–573Springer, Cham, (2020).
Chen, P. Effects of the entropy weight on TOPSIS. Expert Syst. Appl. 168, 114186 (2021).
Zhou, X. & Lu, M. Risk evaluation of dynamic alliance based on fuzzy analytic network process and fuzzy TOPSIS. (2012).
Woolson, R. F. Wilcoxon signed-rank test. In Wiley Encyclopedia of Clinical Trials 1–3 (Wiley, (2007).
Guo, M. H. et al. SegNeXt: rethinking convolutional attention design for semantic segmentation. Adv. Neural Inf. Process. Syst. 35, 1140–1156 (2022).
Misra, D., Nalamada, T., Arasanipalai, A. U. & Hou, Q. Rotate to attend: convolutional triplet attention module. In Proc. IEEE/CVF Winter Conf. Appl. Comput. Vis. 3139–3148 (2021).
Huang, H. et al. Channel prior convolutional attention for medical image segmentation. Comput. Biol. Med. 178, 108784 (2024).
Hou, Q., Zhou, D. & Feng, J. Coordinate attention for efficient mobile network design. In Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. 13713–13722 (2021).
Liu, Y., Shao, Z. & Hoffmann, N. Global attention mechanism: retain information to enhance channel-spatial interactions. Preprint at (2021). https://arxiv.org/abs/2112.05561
Abdollahi, B., Tomita, N. & Hassanpour, S. Data augmentation in training deep learning models for medical image analysis. In Deep Learners and Deep Learner Descriptors for Medical Applications 167–180 (Springer, Cham, (2020).
Nalepa, J., Marcinkiewicz, M. & Kawulok, M. Data augmentation for brain-tumor segmentation: a review. Front. Comput. Neurosci. 13, 83 (2019).
Shorten, C. & Khoshgoftaar, T. M. A survey on image data augmentation for deep learning. J. Big Data. 6, 1–48 (2019).
Frid-Adar, M. et al. GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification. Neurocomputing 321, 321–331 (2018).
Saldanha, J. et al. Data augmentation using variational autoencoders for improvement of respiratory disease classification. PLoS One. 17, e0266467 (2022).
Hussain, I., Tan, S. & Huang, J. Few-shot based learning recaptured image detection with multi-scale feature fusion and attention. Pattern Recognit. 161, 111248 (2025).
Zhou, T. et al. Dense convolutional network and its application in medical image analysis. Biomed. Res. Int. 2384830 (2022). (2022).
Shou, Y. et al. Object detection in medical images based on hierarchical transformer and mask mechanism. Comput. Intell. Neurosci. 5863782 (2022). (2022).
Guo, L. & Zhou, X. IMMP-YOLO: a real-time object detection algorithm incorporating image enhancement and pruning strategy. In 2024 8th CAA Int. Conf. Vehicular Control and Intelligence (CVCI) 1–6IEEE, (2024).
Chen, Y. & Li, D. Disease detection on exterior surfaces of buildings using deep learning in China. Sci. Rep. 15, 8564 (2025).
Acknowledgements
We thank the doctors from the Department of Obstetrics and Gynecology and the Department of Pathology at the Huizhou First Maternal and Child Health Care Hospital for their assistance in clinical information collection and blood testing.
Funding
This work was supported by [the Guangdong Basic and Applied Research Foundation] grant numbers [2023A1515140146; 2022A1515110138; 2023A1515140184; 2024A1515140193].
Author information
Authors and Affiliations
Contributions
Xuxuan Li and Zhifa Jiang contributed equally and were jointly responsible for the original draft, Resources, Methodology, and Conceptualization. Fengchao Chen: Writing – review & editing, Visualization. Jingwen Liu: Resources, Methodology, Investigation. Jianfeng Peng: Writing – original draft, Formal analysis. Ruoping Lin and Xiangyun Ye: Resources, Investigation, Data curation. Zhen Zhang: Supervision, Methodology, Conceptualization. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethical approval
This study was approved by the Medical Ethics Committee of Huizhou First Maternal and Child Health Care Hospital (Ethics Approval No. 20240328A14), and all participants provided written informed consent. All methods were performed in accordance with the relevant guidelines and regulations.
Consent for publication
Not applicable.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Zhifa Jiang is Co-first author.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Li, X., Jiang, Z., Chen, F. et al. Automated detection of fetal vascular malperfusion via data augmentation and algorithm improvement. Sci Rep (2026). https://doi.org/10.1038/s41598-026-39942-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-39942-1
