IDEAS home Printed from https://ideas.repec.org/a/plo/pone00/0341750.html

MLND-IU: A multi-stage detection model of subcentimeter lung nodule with improved U-Net++

Author

Listed:
  • Huilan Wen
  • Xiaoqing Luo
  • Bin Zhong
  • Yang Xiao
  • Dengfeng Chen
  • Lianmin Zhu

Abstract

To address the challenges of high miss rates in subcentimeter nodules, false positives caused by vascular adhesion, and insufficient multi-scale feature fusion in lung CT analysis, a multi-stage detection model named MLND-IU, which incorporates an improved U-Net++ architecture, is proposed. The three-stage framework begins with an enhanced RetinaNet optimized by a dynamic focal loss to generate candidate regions with high sensitivity while mitigating class imbalance. The second stage introduces AG-UNet++ with a novel Dense Attention Bridging Module (DABM), which employs a tensor product fusion of channel and deformable spatial attention across densely connected skip pathways to amplify feature representation for 3–5 mm nodules. The final stage employs a 3D Contextual Pyramid Module (3D-CPM) to integrate multi-slice morphological and contextual features, thereby reducing vascular false positives. Ablation studies indicated that the second stage improved the Dice coefficient by 21.1% compared with the first stage (paired t-test, p

Suggested Citation

  • Huilan Wen & Xiaoqing Luo & Bin Zhong & Yang Xiao & Dengfeng Chen & Lianmin Zhu, 2026. "MLND-IU: A multi-stage detection model of subcentimeter lung nodule with improved U-Net++," PLOS ONE, Public Library of Science, vol. 21(2), pages 1-31, February.
    • Handle: RePEc:plo:pone00:0341750
    DOI: 10.1371/journal.pone.0341750
    as

    Download full text from publisher

    File URL: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0341750
    Download Restriction: no
    File URL: https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0341750&type=printable
    Download Restriction: no
    File URL: https://libkey.io/10.1371/journal.pone.0341750?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Keshun, You & Puzhou, Wang & Peng, Huang & Yingkui, Gu, 2025. "A sound-vibration physical-information fusion constraint-guided deep learning method for rolling bearing fault diagnosis," Reliability Engineering and System Safety, Elsevier, vol. 253(C).
    2. Keshun, You & Guangqi, Qiu & Yingkui, Gu, 2024. "Optimizing prior distribution parameters for probabilistic prediction of remaining useful life using deep learning," Reliability Engineering and System Safety, Elsevier, vol. 242(C).
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Tao, Haohan & Jia, Peng & Wang, Xiangyu & Wang, Liquan, 2024. "Reliability analysis of subsea control module based on dynamic Bayesian network and digital twin," Reliability Engineering and System Safety, Elsevier, vol. 248(C).
    2. Zheng, Yu & Chen, Liang & Bao, Xiangyu & Zhao, Fei & Zhong, Jingshu & Wang, Chenhan, 2025. "Prediction model optimization of gas turbine remaining useful life based on transfer learning and simultaneous distillation pruning algorithm," Reliability Engineering and System Safety, Elsevier, vol. 253(C).
    3. Wang, Enxiu & Lei, Zihao & Wen, Guangrui & Liu, Zimin & Su, Yu & Zhang, Zhifen & Chen, Xuefeng, 2026. "A physics-constrained Bayesian neural network for machinery remaining useful life prediction and uncertainty quantification," Reliability Engineering and System Safety, Elsevier, vol. 266(PB).
    4. Zhu, Ting & Chen, Zhen & Zhou, Di & Xia, Tangbin & Pan, Ershun, 2024. "Adaptive staged remaining useful life prediction of roller in a hot strip mill based on multi-scale LSTM with multi-head attention," Reliability Engineering and System Safety, Elsevier, vol. 248(C).
    5. Xiao, Dasheng & Lin, Zhifu & Yu, Aiyang & Tang, Ke & Xiao, Hong, 2024. "Data-driven method embedded physical knowledge for entire lifecycle degradation monitoring in aircraft engines," Reliability Engineering and System Safety, Elsevier, vol. 247(C).
    6. Zhu, Jingbao & Sun, Wentao & Li, Shanyou & Yao, Kunpeng & Song, Jindong, 2024. "Threshold-based earthquake early warning for high-speed railways using deep learning," Reliability Engineering and System Safety, Elsevier, vol. 250(C).
    7. Keshun, You & Puzhou, Wang & Peng, Huang & Yingkui, Gu, 2025. "A sound-vibration physical-information fusion constraint-guided deep learning method for rolling bearing fault diagnosis," Reliability Engineering and System Safety, Elsevier, vol. 253(C).
    8. Wu, Jinxin & He, Deqiang & Li, Jiayi & Miao, Jian & Li, Xianwang & Li, Hongwei & Shan, Sheng, 2024. "Temporal multi-resolution hypergraph attention network for remaining useful life prediction of rolling bearings," Reliability Engineering and System Safety, Elsevier, vol. 247(C).
    9. Li, Xuanlin & Hu, Yawei & Wang, Hang & Liu, Yongbin & Liu, Xianzeng & Lu, Huitian, 2025. "A closed-form continuous-depth neural-based hybrid difference features re-representation network for RUL prediction," Reliability Engineering and System Safety, Elsevier, vol. 253(C).
    10. Nengpeng Duan & Yun Zeng & Fang Dao & Shuxian Xu & Xianglong Luo, 2025. "Fault Diagnosis of Hydro-Turbine Based on CEEMDAN-MPE Preprocessing Combined with CPO-BILSTM Modelling," Energies, MDPI, vol. 18(6), pages 1-27, March.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:plo:pone00:0341750. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: plosone (email available below). General contact details of provider: https://journals.plos.org/plosone/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.