Abstract
In this paper, a brownfield Internet of Medical Things network is introduced for imaging data that can be easily scaled out depending on the objectives, functional requirements, and the number of facilities and devices connected to it. This is further used to develop a novel Content-based Medical Image Retrieval framework. The developed framework uses DenseNet-201 architecture for generating the image descriptors. Then for classification, the optimized Deep Neural Network model has been configured through a population-based metaheuristic Differential Evolution. Differential Evolution iteratively performs the joint optimization of hyperparameters and architecture of Deep Neural Networks. The competence of the proposed model is validated on three publicly available datasets: Brain Tumor MRI dataset, Covid-19 Radiography database, and Breast Cancer MRI dataset, and by comparing it with selected models over different aspects of performance evaluation. Results show that the convergence rate of the proposed framework is very fast, and it achieves at least 97.28% accuracy across all the models.
- [1] . 2020. BACKM-EHA: A novel blockchain-enabled security solution for IoMT-based e-healthcare applications. ACM Transactions on Internet Technology (TOIT), Nov. 2020.
DOI: Google ScholarDigital Library
- [2] . 2021. A comprehensive survey on multimodal medical signals fusion for smart healthcare systems. Information Fusion 76 (Dec. 2021), 355–375.
DOI: Google ScholarDigital Library
- [3] . 2022. Secure IoMT pattern recognition and exploitation for multimedia information processing using private blockchain and fuzzy logic. Transactions on Asian and Low-Resource Language Information Processing, Jan. 2022.
DOI: Google ScholarCross Ref
- [4] 1995. Query by image and video content: The QBIC system. Computer (Long Beach, Calif.) 28, 9 (1995), 23–32.
DOI: Google ScholarDigital Library
- [5] . 2020. Content-based large-scale medical image retrieval. Biomedical Information Technology (Jan. 2020), 321–368.
DOI: Google ScholarCross Ref
- [6] . 2013. Content-based medical image retrieval: A survey of applications to multidimensional and multimodality data. Journal of Digital Imaging 26, 6 (Dec. 2013), 1025.
DOI: Google ScholarCross Ref
- [7] . 2019. Content based medical image retrieval using topic and location model. Journal of Biomedical Informatics 91 (Mar. 2019), 103112.
DOI: Google ScholarDigital Library
- [8] . 2017. A new method of content based medical image retrieval and its applications to CT imaging sign retrieval. Journal of Biomedical Informatics 66 (Feb. 2017), 148–158.
DOI: Google ScholarDigital Library
- [9] Medical image retrieval using deep convolutional neural network | Elsevier Enhanced Reader. https://reader.elsevier.com/reader/sd/pii/S0925231217308445?token=5E55C43BFDCD06A47F115A6B83716EC4FE005AE32444FD860C7392A52A730A5A9C6CFAF6FAD5B2413B1FF102D4AD6A17&originRegion=eu-west-1&originCreation=20211025202112 (accessed Oct. 26, 2021).Google Scholar
- [10] . 2020. Brain Tumor Classification (MRI), [Data set]. Kaggle. Google Scholar
Cross Ref
- [11] COVID-19 Radiography Database | Kaggle. https://www.kaggle.com/tawsifurrahman/covid19-radiography-database (accessed Nov. 27, 2021).Google Scholar
- [12] Breast Cancer Patients MRI's | Kaggle. https://www.kaggle.com/uzairkhan45/breast-cancer-patients-mris (accessed Nov. 19, 2021).Google Scholar
- [13] . 2021. Recent developments of content-based image retrieval (CBIR). Neurocomputing 452 (Sep. 2021), 675–689.
DOI: Google ScholarCross Ref
- [14] . 2021. Impacts of healthcare 4.0 digital technologies on the resilience of hospitals. Technological Forecasting and Social Change 166 (May 2021), 120666.
DOI: Google ScholarCross Ref
- [15] . 2021. A meta-analysis of industry 4.0 design principles applied in the health sector. Engineering Applications of Artificial Intelligence 104 (Sep. 2021), 104377.
DOI: Google ScholarCross Ref
- [16] . 2014. Efficient and robust large medical image retrieval in mobile cloud computing environment. Information Sciences 263 (Apr. 2014), 60–86.
DOI: Google ScholarDigital Library
- [17] . 2021. Strategizing secured image storing and efficient image retrieval through a new cloud framework. Journal of Network and Computer Applications 192 (Oct. 2021), 103167.
DOI: Google ScholarDigital Library
- [18] . 2018. A cloud-based framework for large-scale traditional Chinese medical record retrieval. Journal of Biomedical Informatics 77 (Jan. 2018), 21–33.
DOI: Google ScholarCross Ref
- [19] . 2019. SSIR: Secure similarity image retrieval in IoT. Information Sciences 479 (Apr. 2019), 153–163.
DOI: Google ScholarCross Ref
- [20] . 2016. Privacy-preserving content-based image retrieval in the cloud. Proceedings of the IEEE Symposium on Reliable Distributed Systems 2016-January (Jan. 2016), 11–20.
DOI: Google ScholarDigital Library
- [21] . 2017. A privacy-preserving content-based image retrieval method in cloud environment. Journal of Visual Communication and Image Representation 43 (Feb. 2017), 164–172.
DOI: Google ScholarDigital Library
- [22] . 2019. Deep learning–based multimedia analytics. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 15, 1s (Jan. 2019).
DOI: Google ScholarCross Ref
- [23] . 2021. Deep convolutional features for image retrieval. Expert Systems with Applications 177 (Sep. 2021), 114940.
DOI: Google ScholarDigital Library
- [24] . 2020. An efficient image descriptor for image classification and CBIR. Optik (Stuttg) 214 (Jul. 2020), 164833.
DOI: Google ScholarCross Ref
- [25] . 2021. CBIR using features derived by deep learning. ACM/IMS Transactions on Data Science (TDS), 2, 3 (Aug. 2021), 1–24.
DOI: Google ScholarDigital Library
- [26] . 2018. Crime scene investigation image retrieval with fusion CNN features based on transfer learning. ACM International Conference Proceeding Series (Mar. 2018), 68–72.
DOI: Google ScholarCross Ref
- [27] . 2019. From selective deep convolutional features to compact binary representations for image retrieval. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 15, 2 (Jun. 2019).
DOI: Google ScholarCross Ref
- [28] . 2020. Image retrieval using multi-scale CNN features pooling. ICMR 2020 - Proceedings of the 2020 International Conference on Multimedia Retrieval (Jun. 2020), 311–315.
DOI: Google ScholarCross Ref
- [29] . 2019. Hyperparameter optimization (2019). 3–33.
DOI: Google ScholarCross Ref
- [30] . 2017. An improved incremental constructive single-hidden-layer feedforward networks for extreme learning machine based on particle swarm optimization. Neurocomputing 228 (Mar. 2017), 133–142.
DOI: Google ScholarCross Ref
- [31] . 2019. Hyperparameter optimization of deep neural network using univariate dynamic encoding algorithm for searches. Knowledge-Based Systems 178 (Aug. 2019), 74–83.
DOI: Google ScholarDigital Library
- [32] . 2021. Optimizing CNN-LSTM neural networks with PSO for anomalous query access control. Neurocomputing 456 (Oct. 2021), 666–677.
DOI: Google ScholarDigital Library
- [33] . 2021. EA-based hyperparameter optimization of hybrid deep learning models for effective drug-target interactions prediction. Expert Systems with Applications 185 (Dec. 2021), 115525.
DOI: Google ScholarDigital Library
- [34] . 2021. NAS-HPO-Bench-II: A benchmark dataset on joint optimization of convolutional neural network architecture and training hyperparameters. Proceedings of Machine Learning Research 157 (Oct. 2021), 2021–2021, Accessed: Nov. 18, 2021. [Online]. Available: https://arxiv.org/abs/2110.10165v1.Google Scholar
- [35] Hybrid MPSO-CNN: Multi-level Particle Swarm optimized hyperparameters of Convolutional Neural Network | Elsevier Enhanced Reader. https://reader.elsevier.com/reader/sd/pii/S2210650221000249?token=B5B32FD8229AC3B54C50F0F701993F44EF29B8ADC367DF6A8AE00CB693189BAAECB648D86F67A3295BE2D23281B6D45C&originRegion=eu-west-1&originCreation=20211025202330 (accessed Oct. 26, 2021).Google Scholar
- [36] . 2021. An intelligent Telugu handwritten character recognition using multi-objective mayfly optimization with deep learning based densenet model. Transactions on Asian and Low-Resource Language Information Processing, (Aug. 2021).
DOI: Google ScholarCross Ref
- [37] . 2017. A genetic programming approach to designing convolutional neural network architectures. GECCO 2017 - Proceedings of the 2017 Genetic and Evolutionary Computation Conference (Jul. 2017), 497–504.
DOI: Google ScholarCross Ref
- [38] . 2019. Adaptive optimization based neural network for classification of stuttered speech. ACM International Conference Proceeding Series (Jan. 2019), 93–98.
DOI: Google ScholarCross Ref
- [39] . 2020. Driver identification using optimized deep learning model in smart transportation. ACM Transactions on Internet Technology, Apr. 2020.
DOI: Google ScholarCross Ref
- [40] . 2020. Hybrid Wolf-Bat algorithm for optimization of connection weights in multi-layer perceptron. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 16, 1s (Apr. 2020).
DOI: Google ScholarCross Ref
- [41] . 2017. Neural network topology and weight optimization through neuro differential evolution (Jul. 2017). 213–214.
DOI: Google ScholarCross Ref
- [42] . 2014. Optimization of neural network through genetic algorithm searches for the prediction of international crude oil price based on energy products prices. Proceedings of the 11th ACM Conference on Computing Frontiers, CF 2014, 2014.
DOI: Google ScholarCross Ref
- [43] . 2021. Optimizing hyperparameters and performance analysis of LSTM model in detecting fake news on social media. Transactions on Asian and Low-Resource Language Information Processing, Dec. 2021.
DOI: Google ScholarCross Ref
- [44] . Densely Connected Convolutional Networks.Google Scholar
- [45] . 2020. Differential evolution for neural networks optimization. Mathematics 8, 1 (2020), 1–16.
DOI: Google ScholarCross Ref
- [46] 2020. Can AI help in screening viral and COVID-19 pneumonia? IEEE Access 8 (2020), 132665–132676.
DOI: Google ScholarCross Ref
- [47] 2021. Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images. Computers in Biology and Medicine 132 (May 2021), 104319.
DOI: Google ScholarDigital Library
Index Terms
Optimized Deep-Neural Network for Content-based Medical Image Retrieval in a Brownfield IoMT Network
Recommendations
Optimized neural network ensemble by combination of particle swarm optimization and differential evolution
ISNN'13: Proceedings of the 10th international conference on Advances in Neural Networks - Volume Part IThe Neural-Network Ensemble (NNE) is a very effective method where the outputs of separately trained neural networks are combined to perform the prediction. In this paper, we introduce the improved Neural Network Ensemble (INNE) in which each component ...
Medical image retrieval using deep convolutional neural network
Selection of publicly available medical images having 24 classes and 5 modalities.Classification of multimodal medical images by deep convolutional neural network.Content based medical image retrieval using with and without class predictions.Improved ...
Relevance feedback for content-based image retrieval using Bayesian network
VIP '05: Proceedings of the Pan-Sydney area workshop on Visual information processingRelevance feedback is a powerful query modification technique in the field of content-based image retrieval. The key issue in relevance feedback is how to effectively utilize the feedback information to improve the retrieval performance. This paper ...






Comments