Skip to content
2000
  1. Home
  2. A-Z Publications
  3. Current Medical Imaging
  4. Volume 20, Issue 1
  5. Article
Volume 20, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603
file format pdf download PDF
side by side viewer icon HTML

Abstract

Background

Chest X-ray image classification for multiple diseases is an important research direction in the field of computer vision and medical image processing. It aims to utilize advanced image processing techniques and deep learning algorithms to automatically analyze and identify X-ray images, determining whether specific pathologies or structural abnormalities exist in the images.

Objective

We present the MMPDenseNet network designed specifically for chest multi-label disease classification.

Methods

Initially, the network employs the adaptive activation function Meta-ACON to enhance feature representation. Subsequently, the network incorporates a multi-head self-attention mechanism, merging the conventional convolutional neural network with the Transformer, thereby bolstering the ability to extract both local and global features. Ultimately, the network integrates a pyramid squeeze attention module to capture spatial information and enrich the feature space.

Results

The concluding experiment yielded an average AUC of 0.898, marking an average accuracy improvement of 0.6% over the baseline model. When compared with the original network, the experimental results highlight that MMPDenseNet considerably elevates the classification accuracy of various chest diseases.

Conclusion

It can be concluded that the network, thus, holds substantial value for clinical applications.

© 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/10.2174/0115734056291283240808045952
2024-01-01
2025-04-18

  • From This Site

    /content/journals/cmir/10.2174/0115734056291283240808045952
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
The full text of this item is not currently available.

References

  1. GuY. ChiJ. LiuJ. YangL. ZhangB. YuD. ZhaoY. LuX. A survey of computer-aided diagnosis of lung nodules from CT scans using deep learning.Comput. Biol. Med.202113710480610.1016/j.compbiomed.2021.10480634461501
     [Google Scholar]
  2. WangX. PengY. LuL. LuZ. BagheriM. SummersR.M ChestX-Ray8: Hospital-scale chest X-Ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases.2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)21-26 July 2017, Honolulu, HI, USA, 2017, pp. 3462-3471.10.1109/CVPR.2017.369
     [Google Scholar]
  3. YaoL. PoblenzE. DaguntsD. CovingtonB. BernardD. LymanK. Learning to diagnose from scratch by exploiting dependencies among labels.arXiv:1710.10501, 2017.10.48550/arXiv.1710.10501
     [Google Scholar]
  4. GuY. LuX. YangL. ZhangB. YuD. ZhaoY. GaoL. WuL. ZhouT. Automatic lung nodule detection using a 3D deep convolutional neural network combined with a multi-scale prediction strategy in chest CTs.Comput. Biol. Med.201810322023110.1016/j.compbiomed.2018.10.01130390571
     [Google Scholar]
  5. GuY. LuX. ZhangB. ZhaoY. YuD. GaoL. CuiG. WuL. ZhouT. Automatic lung nodule detection using multi-scale dot nodule-enhancement filter and weighted support vector machines in chest computed tomography.PLoS One2019141e021055110.1371/journal.pone.021055130629724
     [Google Scholar]
  6. KumarP. GrewalM. SrivastavaM.M. Boosted cascaded convnets for multilabel classification of thoracic diseases in chest radiographs.ChamSpringer International Publishing201854655210.1007/978‑3‑319‑93000‑8_62
     [Google Scholar]
  7. ChenB. LiJ. GuoX. LuG. DualCheXNet: dual asymmetric feature learning for thoracic disease classification in chest X-rays.Biomed. Signal Process. Control20195310155410.1016/j.bspc.2019.04.031
     [Google Scholar]
  8. GuanQ. HuangY. ZhongZ. ZhengZ. ZhengL. YangY. Diagnose like a Radiologist: Attention guided convolutional neural network for thorax disease classification.ArXiv, abs/1801.09927 ,2018.10.48550/arXiv.1801.09927
     [Google Scholar]
  9. HoT.K.K. GwakJ. Utilizing knowledge distillation in deep learning for classification of chest X-Ray abnormalities.IEEE Access2020816074916076110.1109/ACCESS.2020.3020802
     [Google Scholar]
  10. TeixeiraV. BrazL. PedriniH. DiasZ. DuaLAnet: Dual lesion attention network for thoracic disease classification in chest X-raysInternational Conference on Systems, Signals and Image Processing (IWSSIP)01-03 July 2020, Niteroi, Brazil, 2020, pp. 69-74.10.1109/IWSSIP48289.2020.9145037
     [Google Scholar]
  11. DilshadS. SinghN. AtifM. HanifA. YaqubN. FarooqW.A. AhmadH. ChuY. MasoodM.T. Automated image classification of chest X-rays of COVID-19 using deep transfer learning.Results Phys.20212810452910452910.1016/j.rinp.2021.10452934395185
     [Google Scholar]
  12. ManjuN. Manjunath AradhyaV.N. MalapriyaS. ShruthiN. Classification of chest X-Ray images for COVID-19 positive patients using transfer learning.ChamSpringer Nature Switzerland202322723510.1007/978‑3‑031‑24475‑9_20
     [Google Scholar]
  13. Al-SheikhM.H. Al DandanO. Al-ShamaylehA.S. JalabH.A. IbrahimR.W. Multi-class deep learning architecture for classifying lung diseases from chest X-Ray and CT images.Sci. Rep.20231311937310.1038/s41598‑023‑46147‑337938631
     [Google Scholar]
  14. BhusalD. PandayS.P. Multi-label classification of thoracic diseases using dense convolutional network on chest radiographs.ArXiv, abs/2202.03583, 2022.
     [Google Scholar]
  15. AgarapA.F. A.F. agarap, deep learning using rectified linear units (ReLU).ArXiv, abs/1803.08375, 2018.
     [Google Scholar]
  16. HahnloserR.H. Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit.Nature200040594795110.1038/35016072
     [Google Scholar]
  17. JarrettK. KavukcuogluK. RanzatoM.A. LeCunY. What is the best multi-stage architecture for object recognition?.2009 IEEE 12th International Conference on Computer Vision.29 September 2009 - 02 October 2009, Kyoto, Japan, 2009, pp. 2146-2153.10.1109/ICCV.2009.5459469
     [Google Scholar]
  18. NairV. HintonG.E. Rectified linear units improve restricted boltzmann machines.Proceedings of the 27th International Conference on Machine Learning (ICML-10)June 21-24, 2010, Haifa, Israe, pp.807-814.
     [Google Scholar]
  19. KrizhevskyA. SutskeverI. HintonG.E. ImageNet classification with deep convolutional neural networks.Commun. ACM2017606849010.1145/3065386
     [Google Scholar]
  20. CoşkunM. UçarA. YildirimÖ. DemirY. Face recognition based on convolutional neural network2017 International Conference on Modern Electrical and Energy Systems (MEES)15-17 November 2017, Kremenchuk, Ukraine, 2017, pp. 376-379.10.1109/MEES.2017.8248937
     [Google Scholar]
  21. YinX. LiuX. Multi-task convolutional neural network for pose-invariant face recognition.IEEE Trans. Image Process.201827296497510.1109/TIP.2017.276583029757739
     [Google Scholar]
  22. AbdAlmageedW. Face recognition using deep multi-pose representations.2016 IEEE Winter Conference on Applications of Computer Vision (WACV)07-10 March 2016, Lake Placid, NY, USA, 2016, pp. 1-9.10.1109/WACV.2016.7477555
     [Google Scholar]
  23. SimonyanK. ZissermanA. Very deep convolutional networks for large-scale image recognition.arXiv:1409.1556, 2014.10.48550/arXiv.1409.1556
     [Google Scholar]
  24. HeK. ZhangX. RenS. SunJ. Deep residual learning for image recognition.2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)27-30 June 2016, Las Vegas, NV, USA, 2016, pp. 770-778.10.1109/CVPR.2016.90
     [Google Scholar]
  25. XieS. GirshickR. DollárP. TuZ. HeK. Aggregated residual transformations for deep neural networks2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)21-26 July 2017, Honolulu, HI, USA, 2017, pp. 5987-5995.10.1109/CVPR.2017.634
     [Google Scholar]
  26. TanM. LeQ.V. EfficientNet: Rethinking model scaling for convolutional neural networks.arXiv:1905.11946, 2019.10.48550/arXiv.1905.11946
     [Google Scholar]
  27. RussakovskyO. DengJ. SuH. KrauseJ. SatheeshS. MaS. HuangZ. KarpathyA. KhoslaA. BernsteinM. BergA.C. Fei-FeiL. ImageNet large scale visual recognition challenge.Int. J. Comput. Vis.2015115321125210.1007/s11263‑015‑0816‑y
     [Google Scholar]
  28. RawatW. WangZ. Deep convolutional neural networks for image classification: A comprehensive review.Neural Comput.20172992352244910.1162/neco_a_0099028599112
     [Google Scholar]
  29. AnwarS.M. MajidM. QayyumA. AwaisM. AlnowamiM. KhanM.K. Medical image analysis using convolutional neural networks: A review.J. Med. Syst.2018421122610.1007/s10916‑018‑1088‑130298337
     [Google Scholar]
  30. AkataZ. PerronninF. HarchaouiZ. SchmidC. Label-embedding for image classification.IEEE Trans. Pattern Anal. Mach. Intell.20163871425143810.1109/TPAMI.2015.248798626452251
     [Google Scholar]
  31. RanaP. SowmyaA. MeijeringE. SongY. Data augmentation with improved regularisation and sampling for imbalanced blood cell image classification.Sci. Rep.20221211810110.1038/s41598‑022‑22882‑x36302948
     [Google Scholar]
  32. EveringhamM. Van GoolL. WilliamsC.K.I. WinnJ. ZissermanA. The pascal visual object classes (VOC) challenge.Int. J. Comput. Vis.2010882303338
     [Google Scholar]
  33. LinT-Y. MaireM. BelongieS. HaysJ. PeronaP. RamananD. DollárP. ZitnickC.L. Microsoft COCO: Common objects in context.ChamSpringer International Publishing201474075510.1007/978‑3‑319‑10602‑1_48
     [Google Scholar]
  34. GirshickR. DonahueJ. DarrellT. MalikJ. Rich feature hierarchies for accurate object detection and semantic segmentation2014 IEEE Conference on Computer Vision and Pattern Recognition23-28 June 2014, Columbus, OH, USA, 2014, pp. 580-587.10.1109/CVPR.2014.81
     [Google Scholar]
  35. GirshickR.B. FastR-C.N.N. Fast R-CNN.Comput. Sci.arXiv:1504.08083, 2015.201510.48550/arXiv.1504.08083
     [Google Scholar]
  36. UçarA. DemirY. GüzelişC. Object recognition and detection with deep learning for autonomous driving applications.Simulation201793975976910.1177/0037549717709932
     [Google Scholar]
  37. LiY. WangH. DangL.M. NguyenT.N. HanD. LeeA. JangI. MoonH. A deep learning-based hybrid framework for object detection and recognition in autonomous driving.IEEE Access2020819422819423910.1109/ACCESS.2020.3033289
     [Google Scholar]
  38. FinkM. LiuY. EngstleA. SchneiderS-A. Deep learning-based multi-scale multi-object detection and classification for autonomous driving.Fahrerassistenzsysteme 2018. BertramT. WiesbadenSpringer Fachmedien Wiesbaden2019233242
     [Google Scholar]
  39. TurayT. VladimirovaT. Toward performing image classification and object detection with convolutional neural networks in autonomous driving systems: a survey.IEEE Access202210140761411910.1109/ACCESS.2022.3147495
     [Google Scholar]
  40. 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]
  41. HuH. GuJ. ZhangZ. DaiJ. WeiY. Relation networks for object detection.2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition18-23 June 2018, Salt Lake City, UT, USA, 2018, pp. 3588-3597.10.1109/CVPR.2018.00378
     [Google Scholar]
  42. HariharanB. ArbeláezP. GirshickR. MalikJ. Simultaneous detection and segmentation.Computer Vision – ECCV 2014. FleetD. PajdlaT. SchieleB. TuytelaarsT. ChamSpringer International Publishing201429731210.1007/978‑3‑319‑10584‑0_20
     [Google Scholar]
  43. DaiJ. HeK. SunJ. Instance-aware semantic segmentation via multi-task network cascades.2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)27-30 June 2016, Las Vegas, NV, USA, 2016, pp. 3150-3158.10.1109/CVPR.2016.343
     [Google Scholar]
  44. HeK. GkioxariG. Mask R-CNN.2017 IEEE international conference on computer vision (ICCV)22-29 October 2017, Venice, Italy, 2017, pp. 2980-2988.10.1109/ICCV.2017.322
     [Google Scholar]
  45. HafizA.M. BhatG.M. A survey on instance segmentation: state of the art.Int. J. Multimed. Inf. Retr.20209317118910.1007/s13735‑020‑00195‑x
     [Google Scholar]
  46. WangX. ZhangR. ShenC. KongT. LiL. SOLO: A simple framework for instance segmentation.IEEE Trans. Pattern Anal. Mach. Intell.202244118587860110.1109/TPAMI.2021.311111634516372
     [Google Scholar]
  47. TianZ. ShenC. ChenH. Conditional convolutions for instance segmentation.Computer Vision – ECCV 2020. VedaldiA. BischofH. BroxT. FrahmJ-M. ChamSpringer International Publishing2020282298
     [Google Scholar]
  48. HuangG. LiuZ. MaatenL.V.D. WeinbergerK.Q. Densely connected convolutional networks.2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)21-26 July 2017, Honolulu, HI, USA, 2017, pp. 2261-2269.10.1109/CVPR.2017.243
     [Google Scholar]
  49. SergeyI. ChristianS. Batch normalization: Accelerating deep network training by reducing internal covariate shift.PMLR201544845610.48550/arXiv.1502.03167
     [Google Scholar]
  50. LecunY. BottouL. BengioY. HaffnerP. Gradient-based learning applied to document recognition.Proc. IEEE199886112278232410.1109/5.726791
     [Google Scholar]
  51. MaasA.L. Rectifier nonlinearities improve neural network acoustic models.Proceedings of the 30th International Conference on Machine Learning Atlanta, Georgia, USA, 2013, pp. 1-6.
     [Google Scholar]
  52. HeK. ZhangX. RenS. SunJ. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification.2015 IEEE International Conference on Computer Vision (ICCV)07-13 December 2015, Santiago, Chile, 2015, pp. 1026-1034.10.1109/ICCV.2015.123
     [Google Scholar]
  53. ClevertD.A. UnterthinerT. HochreiterS. Fast and accurate deep network learning by exponential linear units (ELUs).Machine LearningarXiv:1511.07289, 2015.10.48550/arXiv.1511.07289
     [Google Scholar]
  54. MaN. ZhangX. SunJ. Funnel activation for visual recognition.Computer Vision – ECCV 2020. VedaldiA. BischofH. BroxT. FrahmJ-M. ChamSpringer International Publishing2020351368
     [Google Scholar]
  55. MaN. ZhangX. LiuM. SunJ. Activate or Not: Learning customized activation.2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)20-25 June 2021, Nashville, TN, USA, 2021, pp. 8028-8038.10.1109/CVPR46437.2021.00794
     [Google Scholar]
  56. VaswaniA. ShazeerN.M. ParmarN. UszkoreitJ. JonesL. GomezA.N. KaiserL. PolosukhinI. Attention is all you need.Computat. Language. Mach. Learn. arXiv:1706.03762, 2017.10.48550/arXiv.1706.03762
     [Google Scholar]
  57. SrinivasA. LinT.Y. ParmarN. ShlensJ. AbbeelP. VaswaniA. Bottleneck transformers for visual recognition.2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)20-25 June 2021, Nashville, TN, USA, 2021, pp. 16514-16524.10.1109/CVPR46437.2021.01625
     [Google Scholar]
  58. JangE. GuS.S. PooleB. Categorical reparameterization with gumbel-softmax.arXiv:1611.01144, 2016.10.48550/arXiv.1611.01144
     [Google Scholar]
  59. ShawP. UszkoreitJ. VaswaniA. Self-attention with relative position representations.North American Chapter of the Association for Computational Linguistics2018
     [Google Scholar]
  60. BelloI. ZophB. LeQ. VaswaniA. ShlensJ. Attention augmented convolutional networks2019 IEEE/CVF International Conference on Computer Vision (ICCV)20193285329410.1109/ICCV.2019.00338
     [Google Scholar]
  61. CaoZ. HidalgoG. SimonT. WeiS.E. SheikhY. OpenPose: Realtime multi-person 2d pose estimation using part affinity fields.IEEE Trans. Pattern Anal. Mach. Intell.202143117218610.1109/TPAMI.2019.292925731331883
     [Google Scholar]
  62. RamachandranP. ParmarN. VaswaniA. BelloI. LevskayaA. ShlensJ. Stand-alone self-attention in vision models.arXiv:1906.05909, 2019.10.48550/arXiv.1906.05909
     [Google Scholar]
  63. ZhangH. ZuK. LuJ. ZouY. MengD. EPSANet: An efficient pyramid squeeze attention block on convolutional neural network.Computer Vision – ACCV 2022. WangL. GallJ. ChinT-J. SatoI. ChellappaR. ChamSpringer Nature Switzerland202354155710.1007/978‑3‑031‑26313‑2_33
     [Google Scholar]
  64. IrvinJ.A. RajpurkarP. KoM. YuY. Ciurea-IlcusS. ChuteC. MarklundH. HaghgooB. BallR.L. ShpanskayaK.S. SeekinsJ. MongD.A. HalabiS.S. SandbergJ.K. JonesR. LarsonD.B. LanglotzC. PatelB.N. LungrenM.P. NgA. CheXpert: A large chest radiograph dataset with uncertainty labels and expert comparison.AAAI Conf. Artif. Intell.2019330159059710.1609/aaai.v33i01.3301590
     [Google Scholar]
  65. KingmaD.P. BaJ. A method for stochastic optimization.CoRR, abs/1412.6980, 2014.10.48550/arXiv.1412.6980
     [Google Scholar]
  66. CarionN. MassaF. SynnaeveG. UsunierN. KirillovA. ZagoruykoS. End-to-end object detection with transformers.ArXiv, abs/2005.12872 ,2020.10.1007/978‑3‑030‑58452‑8_13
     [Google Scholar]
  67. DosovitskiyA. BeyerL. KolesnikovA. WeissenbornD. ZhaiX. UnterthinerT. DehghaniM. MindererM. HeigoldG. GellyS. UszkoreitJ. HoulsbyN. An Image is Worth 16x16 Words: Transformers for image recognition at scale.ArXiv, abs/2010.11929, 2020.10.48550/arXiv.2010.11929
     [Google Scholar]
  68. GneitingT. VogelP. Receiver operating characteristic (ROC) curves: Equivalences, beta model, and minimum distance estimation.Mach. Learn.202211162147215910.1007/s10994‑021‑06115‑2
     [Google Scholar]
  69. ChenY. DaiX. LiuM. ChenD. YuanL. LiuZ. Dynamic ReLU.Computer Vision – ECCV 2020. VedaldiA. BischofH. BroxT. FrahmJ-M. ChamSpringer International Publishing202035136710.1007/978‑3‑030‑58529‑7_21
     [Google Scholar]
  70. WangQ. WuB. ZhuP. LiP. ZuoW. HuQ. ECA-Net: Efficient channel attention for deep convolutional neural networks.2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)13-19 June 2020, Seattle, WA, USA, 2020, pp. 11531-11539.10.1109/CVPR42600.2020.01155
     [Google Scholar]
  71. HuJ. ShenL. Squeeze-and-excitation networks.IEEE Transac. Patt. Anal. Machine Intell.20184287132714110.1109/TPAMI.2019.2913372
     [Google Scholar]
  72. YangL. ZhangR-Y. LiL. XieX. SimA.M. A simple, parameter-free attention module for convolutional neural networks.Proceed. 38th In. Conf. Machine Learn.20211391186311874
     [Google Scholar]
  73. YeW. YaoJ. XueH. LiY. Weakly supervised lesion localization with probabilistic-CAM Pooling.arXiv:2005.14480, 2020.10.48550/arXiv.2005.14480
     [Google Scholar]
  74. ZhouB. KhoslaA. LapedrizaA. OlivaA. TorralbaA. Learning deep features for discriminative localization2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)27-30 June 2016, Las Vegas, NV, USA, 2016, pp. 2921-2929.10.1109/CVPR.2016.319
     [Google Scholar]
  75. Seyyed-KalantariL. LiuG. McDermottM. ChenI.Y. GhassemiM. CheXclusion: Fairness gaps in deep chest X-ray classifiers.Pac. Symp. Biocomput.20212623224310.48550/arXiv.2003.0082733691020
     [Google Scholar]
  76. SeiboldC. ReißS. SarfrazM.S. StiefelhagenR. KleesiekJ. Breaking with fixed set pathology recognition through report-guided contrastive trainingMedical Image Computing and Computer Assisted Intervention – MICCAI 2022. MICCAI 2022.Springer202210.1007/978‑3‑031‑16443‑9_66
     [Google Scholar]
  77. ChongC.F. WangY. NgB. LuoW. YangX. Image projective transformation rectification with synthetic data for smartphone-captured chest X-ray photos classification.Comput. Biol. Med.202316410727710.1016/j.compbiomed.2023.10727737517323
     [Google Scholar]
/content/journals/cmir/10.2174/0115734056291283240808045952
Loading
Multi-disease X-ray Image Classification of the Chest Based on Global and Local Fusion Adaptive Networks
Curr. Med. Imaging 20, e15734056291283 (2024); https://doi.org/10.2174/0115734056291283240808045952
/content/journals/cmir/10.2174/0115734056291283240808045952
/content/journals/cmir/10.2174/0115734056291283240808045952
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): Adaptive activation function; Attention mechanism; Chest X-ray image classification; Medical image processing; Multi-headed self-attention; Multiple diseases of the chest

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