Parallel deep convolutional neural network for content based medical image retrieval


DICOM images which helps in diagnosis and prognosis would be critical component in health care systems. Speedy recovery of past historic DICOM images based on the given query image is becoming a critical requirement for the Laboratories and Doctors for quick inference and accurate analogy of the patient conditions. In existing, It is also identified that there is a presence of imbalanced data set which degrade the retrieval accuracy of the model which may reduce by using extract the different kinds of features. The DCNN classifiers are trained by datasets whose data distributions of individual classes are not even or similar, they have always suffered from imbalanced classification performance against classes. Through DCNN can be used to minimize the gaps in terms of accuracy and retrieval but still efficiency parallelization would be essential for faster training and retrieval time. Time complexity is always been a major issue in DCNN, to overcome the above complexity the parallelization of model or data dimension need to be adapted. In this paper, parallel deep convolutional neural network (PDCNN) model is proposed by hyper parameter optimimzation for CBMIR system. The proposed model incorporating the low level content features, high level semantic features and compact features along with DCNN features to tackle the imbalanced dataset problem and reducing the DCNN training time for DICOM images. The high-level and compact features are extracted to resolve the imbalanced dataset problem by using the following algorithms: (a) local binary pattern (LBP), (b) histogram of oriented gradients (HOG) and (c) radon. The data parallelism was adopted in the proposed DCNN model to reduce the network training time by execution of DCNN layers across multiple CPU cores on a single PC. The implementation results for the proposed model in terms of Precision, Recall and F measure values are 87%, 87% and 92% respectively.

This is a preview of subscription content, access via your institution.

Fig. 1

Source: CNN Feature Engineering workflow—

Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16


  1. Anwar S, Hwang K, Sung W (2017) Structured pruning of deep convolutional neural networks. ACM J Emerg Technol Comput Syst 13(3):32. Accessed 16 May 2019

  2. Bottou L (2010) Large-scale machine learning with stochastic gradient descent. In: Proceedings of COMPSTAT’2010. Springer, pp 177–186

  3. Bu H-H, Kim N-C, Park K-W, Kim S-H (2019) Content-based image retrieval using combined texture and color features based on multi-resolution multi-direction filtering and color autocorrelogram. J Ambient Intell Human Comput.

    Article  Google Scholar 

  4. Chen CZ (2015) From low level features to high level semantics. Pittsburgh, Pennsylvania, USA

  5. Chilimbi TM, Suzue Y, Apacible JT, Kalyanaraman K (2014) Project Adam: building an efficient and scalable deep learning training system. Accessed 17 Jul 2019

  6. Clark K, Vendt B, Smith K, Freymann J, Kirby J, Koppel P, Moore S, Phillips S, Maffitt D, Pringle M, Tarbox L, Prior F (2013) The cancer imaging archive (TCIA): maintaining and operating a public information repository. J Digit Imaging 26(6):1045–1057

    Article  Google Scholar 

  7. Dean J, Corrado G, Monga R, Chen K, Devin M, Mao MZ, Ng AY et al (2012) Large scale distributed deep networks. Accessed 17 Jul 2019

  8. Deep G, Kaur L, Gupta S (2016) Lung Nodule retrieval by integrating local binary pattern with template matching. Accessed 17 Jul 2019

  9. Elhassan T, Aljurf M (2016) Classification of imbalance data using tomek Link(T-Link) combined with random under-sampling (RUS) as a data reduction method. Glob J Technol Optimiz 1(2):1–11. Accessed 21 Jul 2019

  10. Galar MF (2012) A review on ensembles for the class imbalance problem: Bagging-, boosting-, and hybrid-based approaches. IEEE trans Syst Man Cybern 42(4):463–484

    Article  Google Scholar 

  11. Hassanzadeh H, Groza T (2014) Load balancing for imbalanced data sets: classifying scientific artefacts for evidence based medicine. In: Pacific rim international conference on artificial intelligence (pp. 972–984). Springer International Publishing

  12. Heigold G, McDermott E, Vanhoucke V, Senior AW, Bacchiani M (2014) Asynchronous stochastic optimization for sequence training of deep neural networks. Accessed 17 Jul 2019

  13. Huda S, Yearwood J, Jelinek HF, Hassan MM, Fortino G, Buckland ME (2016) A hybrid feature selection with ensemble classification for imbalanced healthcare data: a case study for brain tumor diagnosis. IEEE Access 4:9145–9154. Accessed 21 Jul 2019

  14. Kadam VJ, Jadhav SM, Vijayakumar K (2019) Breast cancer diagnosis using feature ensemble learning based on stacked Sparse Autoencoders and Softmax Regression. J Med Syst 43(8):263

    Article  Google Scholar 

  15. Keliba NT, Huylebrouck D (1990) A note on conjugate Toeplitz matrices. Linear Algebr Appl 139:103–109. Accessed 20 May 2019

  16. Khatami A, Babaie M (2017) Parallel deep solutions for image retrieval from imbalanced medical imaging archives. Appl Soft Comput 63:197–205

    Article  Google Scholar 

  17. Li M, Andersen DG, Park JW, Smola AJ, Ahmed A, Josifovski V, Long J, Shekita EJ, Su B-Y (2014) Scaling distributed machine learning with the parameter server. In: Proceeding OSDI'14 proceedings of the 11th USENIX conference on operating systems design and implementation, pp 583–598

  18. Müller H (2005) The use of MedGIFT and EasyIR for Image in accessing multilingual information repositories, LNCS 4022. Springer, Berlin

    Google Scholar 

  19. Nguyen LD, Gao R, Lin D, Lin Z (2019) Biomedical image classification based on a feature concatenation and ensemble of deep CNNs. J Ambient Intell Human Comput.

    Article  Google Scholar 

  20. Ojala T, Pietikäinen M, Mäenpää T (2000) Gray scale and rotation invariant texture classification with local binary patterns. Lecture notes in computer science, 404–420. Accessed 17 Jul 2019

  21. Petrov D, Marshall N, Cockmartin L, Bosmans H (2018) First results with a deep learning (feed-forward CNN) approach for daily quality control in digital breast tomosynthesis. Accessed 16 Jul 2019

  22. Razzaghi T, Roderick O, Safro I, Marko N (2015) Fast imbalanced classification of healthcare data with missing values. arXiv: Mach Learn 2005:774–781. Accessed 21 Jul 2019

  23. Srilakshmi GKL et al (2016) Feature Analysis for medical image modality classifier. In: Tadepalligudem, Andhrapradesh, India: 3rd International Conference on Electrical, Electronics, Engineering Trends, Communication, Optimization and Sciences

  24. Stephen NJ (2002) The class imbalance problem: a systematic study. Intell Data Anal 6:429–449

    Article  Google Scholar 

  25. Vijayakumar K, Arun C (2017) Automated risk identification using NLP in cloud based development environments. J Ambient Intell Human Comput.

    Article  Google Scholar 

  26. Vijayakumar K, Pradeep Mohan Kumar K, Jesline D (2019) Implementation of software agents and advanced AoA for disease data analysis. J Med Syst 43(8):274

    Article  Google Scholar 

  27. Wan X, Liu J, Cheung WK, Tong T (2014) Learning to improve medical decision making from imbalanced data without a priori cost. BMC Med Inf Decis Making 14(1):111–111. Accessed 21 Jul 2019

  28. Yamaguchi M, Fujita H, Uemura M, Asai Y, Wakae H, Ishifuro M (2004) Development and evaluation of a new gray-scale test pattern to adjust gradients of thoracic CT imaging. Eur Radiol 14(12):2357–2361. Accessed 16 Jul 2019

  29. Yan Y, Chen M, Shyu M-L, Chen S-C (2015) Deep learning for imbalanced multimedia data classification. Inf Syst Manag 2015:483–488. Accessed 21 Jul 2019

  30. Yu M, Lin Z, Narra K, Li S, Li Y, Kim NS, Avestimehr S et al (2018) GradiVeQ: vector quantization for bandwidth-efficient gradient aggregation in distributed CNN training. arXiv: Learning 2018:5123–5133. Accessed 16 Jul 2016

  31. Zhang L, Yang H (2018) Imbalanced biomedical data classification using self-adaptive multilayer ELM combined with dynamic GAN. Biomed Eng Online 17:1181.

    Article  Google Scholar 

  32. Zhang L, Yang H, Jiang Z (2018) Imbalanced biomedical data classification using self-adaptive multilayer ELM combined with dynamic GAN. Biomed Eng Online 17(1):181

    Article  Google Scholar 

  33. Zhao WI (2001) Negotiating the semantic gap: from feature maps tosemantic landscapes. Pattern Recogn 35:593–600

    Article  Google Scholar 

  34. Zhao Y, Wong ZS-Y (2018) A framework of rebalancing imbalanced healthcare data for rare events’ classification: a case of look-alike sound-alike mix-up incident detection. J Healthcare Eng.

    Article  Google Scholar 

  35. Zhu X, Wang Q, Li P, Zhang XY, Wang L (2018) Learning region wise deep feature representation for image analysis. J Ambient Intell Human Comput.

    Article  Google Scholar 

Download references

Author information



Corresponding author

Correspondence to P. Haripriya.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Haripriya, P., Porkodi, R. Parallel deep convolutional neural network for content based medical image retrieval. J Ambient Intell Human Comput 12, 781–795 (2021).

Download citation


  • Deep convolutional neural network
  • Deep learning
  • Parallelization
  • Overlapping