Skip to content
2000
Volume 20, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603
file format pdf download PDF
side by side viewer icon HTML

Abstract

Background

Artificial intelligence-based aided diagnostic systems for pulmonary nodules can be divided into subtasks such as nodule detection, segmentation, and benign and malignant differentiation. Most current studies are limited to single-target tasks. However, aided diagnosis aims to distinguish benign from malignant pulmonary nodules, which requires the fusion of multiple-scale features and comprehensive discrimination based on the results of multiple learning tasks.

Objective

This study focuses on the aspects of model design, network structure, and constraints and proposes a novel model that integrates the learning tasks of pulmonary nodule detection, segmentation, and classification under weakly supervised conditions.

Methods

The main innovations include the following three aspects: (1) a two-dimensional sequence detection model based on a ConvLSTM (Convolutional Long Short-Term Memory) network and U-shaped structure network is proposed to obtain the context space features of image slices fully; (2) a differential diagnosis of benign and malignant pulmonary nodules based on multitask learning is proposed, which uses the annotated data of different types of tasks to mine the potential common features among tasks; and (3) an optimization strategy incorporating prior knowledge of computed tomography images and dynamic weight adjustment of multiple tasks is proposed to ensure that each task can efficiently complete training and learning.

Results

Experiments on the LIDC-IDRI and LUNA16 datasets showed that our proposed method achieved a final competition performance metric score of 87.80% for nodule detection and a Dice similarity coefficient score of 83.95% for pulmonary nodule segmentation.

Conclusion

The cross-validation results of the LIDC-IDRI and LUNA16 datasets show that our model achieved 87.80% of the final competition performance metric score for nodule detection and 83.95% of the DSC score for pulmonary nodule segmentation, representing the optimal result for that dataset.

© 2024 The Author(s). Published by Bentham Science Publisher.
This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: https://creativecommons.org/licenses/by/4.0/legalcode. This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Loading

Article metrics loading...

/content/journals/cmir/10.2174/0115734056252399231011042326
2024-01-01
2025-09-12

  • From This Site

    /content/journals/cmir/10.2174/0115734056252399231011042326
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

/deliver/fulltext/cmir/20/1/CMIR-20-E15734056252399.html?itemId=/content/journals/cmir/10.2174/0115734056252399231011042326&mimeType=html&fmt=ahah

References

  1. PerlR.M. GrimmerR. HeppT. HorgerM.S. Can a novel deep neural network improve the computer-aided detection of solid pulmonary nodules and the rate of false-positive findings in comparison to an established machine learning computer-aided detection?Invest. Radiol.202156210310810.1097/RLI.000000000000071332796198
     [Google Scholar]
  2. KernD MastmeyerA. 3D bounding box detection in volumetric medical image data: A systematic literature review.arXiv:2012.057452020
     [Google Scholar]
  3. TaghanakiS A AbhishekK CohenJ P Deep semantic segmentation of natural and medical images: A review.arXiv:1910.076552019
     [Google Scholar]
  4. JcaB StcD LongY A ResGANet: Residual group attention network for medical image classification and segmentation.Med. Image Anal.202176102313
     [Google Scholar]
  5. CrawshawM . Multi-task learning with deep neural networks: A survey.arXiv:2009.097962020
     [Google Scholar]
  6. KrizhevskyA. SutskeverI. HintonG.E. ImageNet classification with deep convolutional neural networks.Adv. Neural Inf. Process. Syst.20122522012
     [Google Scholar]
  7. SimonyanK. ZissermanA. Very deep convolutional networks for large-scale image recognition.Comput. Sci.2014
     [Google Scholar]
  8. SzegedyC LiuW JiaY Going deeper with convolutions.arXiv:1409.48422015
     [Google Scholar]
  9. HeK. ZhangX. RenS. Deep residual learning for image recognition.arXiv:1512.033852015
     [Google Scholar]
  10. IandolaF. MoskewiczM. KarayevS. DenseNet: Implementing efficient ConvNet descriptor pyramids.arXiv:1404.18692014
     [Google Scholar]
  11. GirshickR. DonahueJ. DarrellT. Rich feature hierarchies for accurate object detection and semantic segmentation.arXiv:1311.25242013
     [Google Scholar]
  12. HeK. ZhangX. RenS. SunJ. Spatial pyramid pooling in deep convolutional networks for visual recognition.IEEE Trans. Pattern Anal. Mach. Intell.20153791904191610.1109/TPAMI.2015.238982426353135
     [Google Scholar]
  13. GirshickR. Fast R-CNN.International Conference on Computer Vision. IEEE Computer Society, 2015
     [Google Scholar]
  14. RenS. HeK. GirshickR. SunJ. Faster R-CNN: Towards real-time object detection with region proposal networks.IEEE Trans. Pattern Anal. Mach. Intell.20173961137114910.1109/TPAMI.2016.257703127295650
     [Google Scholar]
  15. RedmonJ. DivvalaS. GirshickR. You only look once: Unified, real-time object detection.arXiv:1506.026402016
     [Google Scholar]
  16. ShelhamerE. LongJ. DarrellT. Fully convolutional networks for semantic segmentation.IEEE Trans. Pattern Anal. Mach. Intell.201739464065110.1109/TPAMI.2016.257268327244717
     [Google Scholar]
  17. ZhaoH ShiJ QiX Pyramid scene parsing network.arXiv:1612.011052016
     [Google Scholar]
  18. TranP V A fully convolutional neural network for cardiac segmentation in short-axis MRI.arXiv:1604.004942016
     [Google Scholar]
  19. RonnebergerO FischerP BroxT. U-Net: Convolutional networks for biomedical image segmentation.Medical Image Computing and Computer-Assisted Intervention (MICCAI)Springer, LNCS20159351234241
     [Google Scholar]
  20. YuL YangX HaoC Volumetric ConvNets with mixed residual connections for automated prostate segmentation from 3D MR images.Proceedings of the AAAI Conference on Artificial Intelligence2017311
     [Google Scholar]
  21. ZhouZ SiddiqueeMMR TajbakhshN UNet++: A nested U-net architecture for medical image segmentation.arXiv:1807.101652018
     [Google Scholar]
  22. AbrahamN KhanN M A novel focal tversky loss function with improved attention U-Net for lesion segmentation.arXiv:1810.078422019
     [Google Scholar]
  23. ZhouX WangD KrhenbühlP Objects as Points.arXiv:1904.078502019
     [Google Scholar]
  24. HeuerF MantowskyS BukhariS S MultiTask-CenterNet (MCN): Efficient and diverse multitask learning using an anchor free approach.arXiv:2108.050602021
     [Google Scholar]
  25. WuD LiaoM ZhangW YOLOP: You only look once for panoptic driving perception.arXiv:2108.112502021
     [Google Scholar]
  26. TangH. ZhangC. XieX. NoduleNet: Decoupled false positive reduction for pulmonary nodule detection and segmentation.MICCAI.2019
     [Google Scholar]
  27. The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative(IDRI): a completed reference database of lung nodules on CT scans.American Association of Physicists in Medicine20112
     [Google Scholar]
  28. SetioA. TraversoA. BelT.D. Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge.Med Image Anal.20174211310.1016/j.media.2017.06.015
     [Google Scholar]
  29. KundelH.L. BerbaumK.S. DorfmanD.D. Receiver operating characteristic analysis in medical imaging.J. ICRU2008811210.1093/jicru_ndn00324174477
     [Google Scholar]
  30. WuB. ZhenZ. WangJ. Joint learning for pulmonary nodule segmentation, attributes and malignancy prediction.2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)04-07 April 2018Washington, DC, USA2018
     [Google Scholar]
  31. ArestaG. JacobsC. AraújoT. CunhaA. RamosI. van GinnekenB. CampilhoA. iW-Net: An automatic and minimalistic interactive lung nodule segmentation deep network.Sci. Rep.2019911159110.1038/s41598‑019‑48004‑831406194
     [Google Scholar]
  32. WangS. ZhouM. LiuZ. LiuZ. GuD. ZangY. DongD. GevaertO. TianJ. Central focused convolutional neural networks: Developing a data-driven model for lung nodule segmentation.Med. Image Anal.20174017218310.1016/j.media.2017.06.01428688283
     [Google Scholar]
  33. TangH KimD R XieX Automated pulmonary nodule detection using 3D deep convolutional neural networks.arXiv:1903.098762019
     [Google Scholar]
  34. TangH. LiuX. XieX. An end-to-end framework for integrated pulmonary nodule detection and false positive reduction.2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)08-11 April 2019Venice, Italy2019
     [Google Scholar]
  35. ZhuW LiuC FanW DeepLung: 3D deep convolutional nets for automated pulmonary nodule detection and classification.arXiv:1709.055382017
     [Google Scholar]
  36. ShiX. Convolutional LSTM network: A machine learning approach for precipitation nowcasting.Adv. Neural Inf. Process. Syst.2015
     [Google Scholar]
  37. XuY.Q. SunY.F. YangZ.X. MiaoJ.X. YangY. H2FA R-CNN: Holistic and hierarchical feature alignment for cross-domain weakly supervised object detection.2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)18-24 June 2022New Orleans, LA, USA202210.1109/CVPR52688.2022.01393
     [Google Scholar]
  38. XuY. ZhouC. YuX. YangY. Cyclic self-training with proposal weight modulation for cross-supervised object detection.IEEE Trans. Image Process.2023321992200210.1109/TIP.2023.326175237015123
     [Google Scholar]
/content/journals/cmir/10.2174/0115734056252399231011042326
Loading
Differential Diagnosis of Benign and Malignant Pulmonary Nodules in CT Images Based on Multitask Learning
Curr. Med. Imaging 20, e15734056252399 (2024); https://doi.org/10.2174/0115734056252399231011042326
/content/journals/cmir/10.2174/0115734056252399231011042326
/content/journals/cmir/10.2174/0115734056252399231011042326
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): Artificial intelligence; Benign and malignant classification; Multitask learning; Nodules detection; Semantic segmentation; Weakly supervised learning

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test