Abstract
Intraoperative frozen section pathological diagnosis of lung adenocarcinoma serves as the gold standard for determining the extent of surgical resection. Due to the dual constraints of intraoperative time limitations and the challenge of manually assessing tumor invasion volume in three-dimensional space, current manual diagnostic approaches and weakly supervised deep learning methods have demonstrated suboptimal diagnostic accuracy. To enhance the accuracy of intraoperative pathological diagnosis of lung adenocarcinoma and provide more precise recommendations for intraoperative resection extent to thoracic surgeons, we have developed a Hybrid-Supervised Framework for Lung Adenocarcinoma (HSFLA). This framework accomplishes the following processes: hybrid-supervised diagnosis of 2D whole slide images (WSIs), automatic annotation of tumor invasive regions, registration of consecutive WSIs, and 3D reconstruction and volume calculation of tumor invasive areas. We evaluated HSFLA on a dataset comprising 1161 WSIs from two centers and three subtypes, achieving an accuracy of 95.6%, which represents a significant improvement over manual review (84.7%) and weakly supervised learning (66.2% ± 3.0%). The consistency of its invasive area automatic annotations with manual pixel annotations was 86.6%. Furthermore, HSFLA’s concordance with spatial transcriptomics samples demonstrated its interpretability at the genetic level. Utilizing HSFLA’s automatic annotation functionality provided pathologists with a safe and effective diagnostic aid, improving their manual diagnostic accuracy by 22.9% (n = 3). We also applied HSFLA in real-world clinical settings for prospective study. Compared to manual diagnosis alone, the “human-machine interaction” diagnostic mode provided more appropriate surgical recommendations for 5 patients (among 70). Overall, HSFLA demonstrates the potential clinical utility of artificial intelligence in supporting intraoperative pathological assessment and surgical decision-making, and may serve as a paradigm for future innovations in AI-assisted clinical workflows.
Similar content being viewed by others
Data availability
The complete dataset (include WSIs and manual annotations) and code associated with this study will be made publicly available. Access link: https://github.com/MedFLung/HSFLA.
References
Barta, J. A., Powell, C. A. & Wisnivesky, J. P. Global epidemiology of lung cancer. Ann. Glob. Health. 85 (2019).
Siegel, R. L., Giaquinto, A. N. & Jemal, A. Cancer statistics, 2024. CA Cancer J. Clin. 74, 12–49 (2024).
Travis, W. D. et al. International association for the study of lung cancer/american thoracic society/european respiratory society international multidisciplinary classification of lung adenocarcinoma. J. Thorac. Oncol. 6, 244–285 (2011).
Travis, W. D., Brambilla, E., Burke, A. P., Marx, A., & Nicholson, A. G. (Eds.). WHO Classification of Tumours of the Lung, Pleura, Thymus and Heart (4th ed.). (International Agency Research Cancer, 2015).
Russell, P. A. et al. Does lung adenocarcinoma subtype predict patient survival? A clinicopathologic study based on the new International Association for the Study of Lung Cancer/American Thoracic Society/European Respiratory Society international multidisciplinary lung adenocarcinoma classification. J. Thorac. Oncol. 6, 1496–1504 (2011).
Zheng, M. Classification and pathology of lung cancer. Surg. Oncol. Clin. 25, 447–468 (2016).
Rosai, J. Rosai and Ackerman’s Surgical Pathology e-book (Elsevier Health Sciences, 2011).
Nakhleh, R. E. Quality in surgical pathology communication and reporting. Arch. Pathol. Lab. Med. 135, 1394–1397 (2011).
Azari, F., Kennedy, G. & Singhal, S. Intraoperative detection and assessment of lung nodules. Surg. Oncol. Clin. North Am. 29, 525 (2020).
Farahani, N. et al. Three-dimensional imaging and scanning: current and future applications for pathology. J. Pathol. Inform. 8, 36 (2017).
Liu, S. et al. Precise diagnosis of intraoperative frozen section is an effective method to guide resection strategy for peripheral small-sized lung adenocarcinoma. J. Clin. Oncol. 34, 307–313 (2016).
Carbonneau, M.-A. et al. Multiple instance learning: a survey of problem characteristics and applications. Pattern Recognit. 77, 329–353 (2018).
Ilse, M., Tomczak, J. & Welling, M. Attention-based deep multiple instance learning. In International Conference on Machine Learning (PMLR, 2018).
Quellec, G. et al. Multiple-instance learning for medical image and video analysis. IEEE Rev. Biomed. Eng. 10, 213–234 (2017).
Li, B., Li, Y. & Eliceiri, K. W. Dual-stream multiple instance learning network for whole slide image classification with self-supervised contrastive learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (IEEE, 2021).
Zhou, Z.-H. A brief introduction to weakly supervised learning. Natl. Sci. Rev. 5, 44–53 (2018).
Nojima, S. et al. CUBIC pathology: three-dimensional imaging for pathological diagnosis. Sci. Rep. 7, 9269 (2017).
Wodzinski, M. et al. RegWSI: Whole slide image registration using combined deep feature-and intensity-based methods: Winner of the ACROBAT 2023 challenge. Comput. Methods Programs Biomed. 250, 108187 (2024).
Nicholson, A. G. et al. The 2021 WHO classification of lung tumors: impact of advances since 2015. J. Thorac. Oncol. 17, 362–387 (2022).
Lu, M. Y. et al. Data-efficient and weakly supervised computational pathology on whole-slide images. Nat. Biomed. Eng. 5, 555–570 (2021).
Campanella, G. et al. Clinical-grade computational pathology using weakly supervised deep learning on whole slide images. Nat. Med. 25, 1301–1309 (2019).
Shao, Z. et al. Transmil: transformer based correlated multiple instance learning for whole slide image classification. Adv. Neural Inf. Process. Syst. 34, 2136–2147 (2021).
Lin, T. et al. Interventional bag multi-instance learning on whole-slide pathological images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (IEEE, 2023).
Lin, W. et al. Boosting multiple instance learning models for whole slide image classification: a model-agnostic framework based on counterfactual inference. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI, 2024).
Zhang, H. et al. Dtfd-mil: Double-tier feature distillation multiple instance learning for histopathology whole slide image classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (IEEE, 2022).
Koonce, B. “ResNet 50.” Convolutional Neural Networks with Swift for Tensorflow: Image Recognition and Dataset Categorization, 63–72 (Apress, 2021).
Chen, R. J. et al. Towards a general-purpose foundation model for computational pathology. Nat. Med. 30, 850–862 (2024).
Neidlinger, P. et al. Benchmarking foundation models as feature extractors for weakly supervised computational pathology. Nat. Biomed. Eng. 9, 1–11 (2025).
Zhang, H. et al. Customized transformer for lymph node metastasis prediction from lung adenocarcinoma histology in a multicentric study. NPJ Precision Oncol. 10, 16 (2025).
LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. nature 521, 436–444 (2015).
Acknowledgements
Thanks to the First Affiliated Hospital of China Medical University for agreeing this research. This study did not receive funding.
Author information
Authors and Affiliations
Contributions
Jianwei Zhao was responsible for writing manuscripts, developing models, and collecting data. Junyan Zhang was responsible for experimental testing and manuscript writing. Yihao Wang was responsible for writing the manuscript and drawing. Xinwen Zhong and Xiaojiao Guan jointly revised the manuscript and supervised the work. Jianwei Zhao and Junyan Zhang have made equal contributions.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary information
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
Zhao, J., Zhang, J., Wang, Y. et al. Hybrid supervised deep learning for lung adenocarcinoma diagnosis to optimize surgical strategies. npj Precis. Onc. (2026). https://doi.org/10.1038/s41698-026-01441-x
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41698-026-01441-x
