Abstract
The World Health Organization (WHO) has identified breast cancer and tuberculosis (TB) as major global health issues. While breast cancer is a top killer of women, TB is an infectious disease caused by a single bacterium with a high mortality rate. Since both TB and breast cancer are curable, early screening ensures treatment. Medical imaging modalities, such as chest X-ray radiography and ultrasound, are widely used for diagnosing TB and breast cancer. Artificial intelligence (AI) techniques are applied to supplement the screening process for effective and early treatment due to the global shortage of radiologists and oncologists. These techniques fast-track the screening process leading to early detection and treatment. Deep learning (DL) is the most used technique producing outstanding results. Despite the success of these DL models in the automatic detection of TB and breast cancer, the suggested models are task-specific, meaning they are disease-oriented. Again, the complexity and weight of the DL applications make it difficult to apply the models on edge devices. Motivated by this, a Multi Disease Visual Attention Condenser Network (MD-VACNet) got proposed for multiple disease identification from different medical image modalities. The network architecture got designed automatically through a machine-driven design exploration with generative synthesis. The proposed MD-VACNet is a lightweight stand-alone visual recognition deep neural network based on VAC with a self-attention mechanism to run on edge devices. In the experiment, TB was identified based on chest X-ray images and breast cancer was based on ultrasound images. The suggested model achieved a 98.99% accuracy score, a 99.85% sensitivity score, and a 98.20% specificity score on the x-ray radiographs for TB diagnosis. The model also produced a cutting-edge performance on breast cancer classification into benign and malignant, with accuracy, sensitivity and specificity scores of 98.47%, 98.42%, and 98.31%, respectively. Regarding model architectural complexity, MD-VACNet is simple and lightweight for edge device implementation.
Similar content being viewed by others
Data availability
The chest x-ray images containing tuberculosis and the breast cancer ultrasound image datasets that support the experiment of this study were accessed from the Kaggle repository https://www.kaggle.com/search?q=NLM+dataset and https://www.kaggle.com/datasets/tawsifurrahman/tuberculosis-tb-chest-xray-dataset.
References
World Health Organization (2020) Global tuberculosis report, Geneva
Byra M (2021) Breast mass classification with transfer learning based on scaling of deep representations. Biomed Sign Process Control 69:102828. https://doi.org/10.1016/j.bspc.2021.102828
Zahoor S, Shoaib U, Lali IU (2022) Breast cancer mammograms classification using deep neural network and entropy-controlled whale optimization algorithm”. Diagnostics 12:557. https://doi.org/10.3390/diagnostics12020557
Puttagunta MK, Ravi S (2021) Detection of tuberculosis based on deep learning based methods. J Phys Conf Ser 1767(1):012004. https://doi.org/10.1088/1742-6596/1767/1/012004
Ayaz M, Shaukat F, Raja G (2021) Ensemble learning based automatic detection of tuberculosis in chest X-ray images using hybrid feature descriptors. Phys Eng Sci Med 44(1):183–194
Iqbal A, Usman M, Ahmed Z (2022) An efficient deep learning-based framework for tuberculosis detection using chest X-ray images”. Tuberculosis 136:102234. https://doi.org/10.1016/j.tube.2022.102234
Duwairi R, Melhem A (2023) A deep learning-based framework for automatic detection of drug resistance in tuberculosis patients. Egypt Inform J 24(1):139–148
Huang PW, Ouyang H, Hsu BY, Chang YR, Lin YC et al (2023) Deep-learning based breast cancer detection for cross-staining histopathology images. Heliyon 9(2):e13171. https://doi.org/10.1016/j.heliyon.2023.e13171
Sheeba A, Kumar PS, Ramamoorthy M, Sasikala S (2023) Microscopic image analysis in breast cancer detection using ensemble deep learning architectures integrated with web of things. Biomed Signal Process Control 79(2):104048. https://doi.org/10.1016/j.bspc.2022.104048
Sahu A, Das PK, Meher S (2023) High accuracy hybrid CNN classifiers for breast cancer detection using mammogram and ultrasound datasets. Biomed Signal Process Control 80(1):104292. https://doi.org/10.1016/j.bspc.2022.104292
Mukherjee P, Roy CK, Roy SK (2022) OCFormer: One-class transformer network for image classification. Xiv:2204.11449v1 [cs.CV]. https://doi.org/10.48550/arXiv.2204.11449
Kotei E, Thirunavukarasu R (2022) Ensemble technique coupled with deep transfer learning framework for automatic detection of tuberculosis from chest X-ray radiographs”. Healthcare 10:2335. https://doi.org/10.3390/healthcare10112335
Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. arXiv:2005.12872v3 [cs.CV]. https://doi.org/10.48550/arXiv.2005.12872
Wang Y, Zhang X, Yang T, Sun J (2022) Anchor DETR: query design for transformer-based detector. In: Proc. association for the advancement of artificial intelligence, AAAI, California, pp 2567–2575. https://doi.org/10.48550/arXiv.2109.07107
Chen X, Sun S, Bai N, Han K, Liu Q et al (2021) A deep learning-based auto-segmentation system for organs-at-risk on whole-body computed tomography images for radiation therapy. Radiother Oncol 160:175–184. https://doi.org/10.1016/j.radonc.2021.04.019
Su Y, Liu Q, Xie W, Hu P (2022) YOLO-LOGO: a transformer-based YOLO segmentation model for breast mass detection and segmentation in digital mammograms. Comput Methods Prog Biomed 221:106903. https://doi.org/10.1016/j.cmpb.2022.106903
Lecun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444
Bhaskaran KL, Osei RS, Kotei E, Agbezuge EY, Ankora C et al (2022) A survey on big data in pharmacology, toxicology and pharmaceutics. Big Data Cogn Comput 6(4):161. https://doi.org/10.3390/bdcc6040161
Kotei E, Thirunavukarasu R (2022) Computational techniques for the automated detection of mycobacterium tuberculosis from digitized sputum smear microscopic images: A systematic review. Progress Biophys Mol Biol 171:4–16. https://doi.org/10.1016/j.pbiomolbio.2022.03.004
Thirunavukarasu R, Doss GP, Gnanasambandan R, Gopikrishnan M, Palanisamy V (2022) Towards computational solutions for precision medicine based big data healthcare system using deep learning models: a review. Comput Biol Med 149:106020. https://doi.org/10.1016/j.compbiomed.2022.106020
Kotei E, Thirunavukarasu R (2023) A systematic review of transformer-based pre-trained language models through self-supervised learning. Information 14(3):187. https://doi.org/10.3390/info14030187
Duong LT, Le NH, Tran TB, Ngo VM, Nguyen PT (2021) Detection of tuberculosis from chest Xray images:boosting the performance with vision transformer and transfer learning. Expert Syst Appl 184:115519. https://doi.org/10.1016/j.eswa.2021.115519
Sandler M, Howard A, Zhu M, Zhmoginov A (2018) MobileNetV2: inverted residuals and linear bottlenecks. In: Proc. IEEE/CVF conference on computer vision and pattern recognition, CVPR, Salt Lake City, UT, pp 4510–4520. https://doi.org/10.1109/CVPR.2018.00474
Azizi S, Mustafa B, Ryan F, Beaver Z, Freyberg J et al (2021) Big self-supervised models advance medical image classification. In: Proc. international conference on computer vision, ICCV, Montreal, QC, Canada, pp 3458–3468. https://doi.org/10.1109/ICCV48922.2021.00346
Rajaraman S, Zamzmi G, Folio LR, Antani S (2022) Detecting tuberculosis-consistent findings in lateral chest x-rays using an ensemble of CNNs and vision transformers. Front Gen 13:1–13. https://doi.org/10.3389/fgene.2022.864724
Dai Y, Gao Y, Liu F (2021) Transmed: Transformers advance multi-modal medical image classification. Diagnostics 11(8):1–15
Wong A, Famouri M, Shafiee MJ (2020) AttendNets: tiny deep image recognition neural networks for the edge via visual attention condensers. arXiv:2009.14385v1 [cs.CV]. https://doi.org/10.48550/arXiv.2009.14385
Momeny M, Neshat AA, Gholizadeh A, Jafarnezhad A, Rahmanzadeh E et al (2022) Greedy Autoaugment for classification of mycobacterium tuberculosis image via generalized deep CNN using mixed pooling based on minimum square rough entropy. Comput Biol Med 141:105175. https://doi.org/10.1016/j.compbiomed.2021.105175
Aljaddouh B, Malathi D (2022) Trends of using machine learning for detection and classification of respiratory diseases: Investigation and analysis. Mater Today Proc 62:4651–4658. https://doi.org/10.1016/j.matpr.2022.03.120
Apostolopoulos ID, Mpesiana TA (2020) Covid-19: automatic detection from X-ray images utilizing transfer learning with convolutional neural networks. Phys Eng Sci Med 43(2):635–640
Hooda R, Sofat S, Kaur S, Mittal A, Meriaudeau F (2017) Deep-learning: a potential method for tuberculosis detection using chest radiography. In: Proc. IEEE international conference on signal and image processing applications, ICSIPA, Kuching, Malaysia, pp 497–502. https://doi.org/10.1109/ICSIPA.2017.8120663
Jaeger S, Candemir S, Antani S, Wáng YX, Lu P-X et al (2014) Two public chest X-ray datasets for computer-aided screening of pulmonary diseases. Quant Imag Med Surg 4(6):475–7
Akbar S, GhaniHaider N, Tariq H (2019) Tuberculosis diagnosis using x-ray images. Int J Adv Res 7(4):689–696
Guo R, Passi K, Jain CK (2020) Tuberculosis diagnostics and localization in chest x-rays via deep learning models. Front Artif Intell 3:583427. https://doi.org/10.3389/frai.2020.583427
Abideen Z, Ghafoor M, Munir K, Saqib M, Ullah A et al (2020) Uncertainty assisted robust tuberculosis identification with bayesian convolutional neural networks. IEEE Access 8:22812–22825. https://doi.org/10.1109/ACCESS.2020.2970023
Chouhan V, Singh SK, Khamparia A, Gupta D, Tiwari P et al (2020) A novel transfer learning based approach for pneumonia detection in chest X-ray images. Appl Sci 10(2):559. https://doi.org/10.3390/app10020559
Rahman T, Khandakar A, Kadir MA, Islam KR, Islam KF et al (2020) Reliable tuberculosis detection using chest X-ray with deep learning, segmentation and visualization. IEEE Access 8:191586–191601. https://doi.org/10.1109/ACCESS.2020.3031384
Sahlol AT, Elaziz MA, Jamal AT, Damaševičius R, HassanOF, (2020) A novel method for detection of tuberculosis in chest radiographs using artificial ecosystem-based optimisation of deep neural network features. Symmetry (Basel) 12(7):1146. https://doi.org/10.3390/sym12071146
Kaggle (2018) RSNA Pneumonia detection challenge 2020. https://www.kaggle.com/datasets/sovitrath/rsnapneumonia-detection-2018
Spanhol FA, Oliveira LS, Petitjean C, Heutte L (2016) A dataset for breast cancer histopathological image classification. IEEE Trans Biomed Eng 63(7):1455–1462
Benhammou Y, Tabik S, Achchab B, Herrera F (2018) A first study exploring the performance of the state-of-the art CNN model in the problem of breast cancer. In: Proc. ACM international conference on learning and optimization algorithms: theory and applications, LOPAL, Rabat, Morocco, pp 1–6. https://doi.org/10.1145/3230905.3230940
Silva LF, Saade DCM, Sequeiros GO, Silva AC, Paiva AC et al (2014) A new database for breast research with infrared image. J Med Imag Health Inform 4(1):92–100
Roslidar R, Saddami K, Arnia F, Syukri M, Munadi K (2019) A study of fine-tuning CNN models based on thermal imaging for breast cancer classification. In: Proc IEEE international conference on cybernetics and computational intelligence, CYBERNETICSCOM, Banda Aceh, Indonesia, pp 77–81. https://doi.org/10.1109/CYBERNETICSCOM.2019.8875661
Khan MHM, Jahangeer NB, Dullull W, Nathire S, Gao X et al (2021) Multi- class classification of breast cancer abnormalities using Deep Convolutional Neural Network (CNN). PLoS One 16:1–15. https://doi.org/10.1371/journal.pone.0256500
Sawyer-Lee R, Gimenez F, Hoogi A, Rubin D (2016) Curated breast imaging subset of digital database for screening mammography (CBIS-DDSM) [Data set]. The Cancer Imaging Archive. https://doi.org/10.7937/K9/TCIA.2016.7O02S9CY
Liu H, Cui G, Luo Y, Guo Y, Zhao L et al (2022) Artificial intelligence-based breast cancer diagnosis using ultrasound images and grid-based deep feature generator. Int J Gen Med 15:2271–2282. https://doi.org/10.2147/IJGM.S347491
Al-Dhabyani W, Gomaa M, Khaled H, Fahmy A (2020) Dataset of breast ultrasound images. Data Br 28:104863. https://doi.org/10.1016/j.dib.2019.104863
Lambert Z, Petitjean C, Dubray B, Kuan S (2020) SegTHOR: Segmentation of thoracic organs at risk in CT images. In: Proc. tenth international conference on image processing theory, tools and applications, IPTA, Paris, France, pp 1–6. https://doi.org/10.1109/IPTA50016.2020.9286453
Kaggle (2020) Tuberculosis (TB) Chest X-ray Database. https://www.kaggle.com/datasets/tawsifurrahman/tuberculosis-tb-chest-xray-dataset
Bello I, Zoph B, Le Q, Vaswani A, Shlens J (2019) Attention augmented convolutional networks. In: Proc. IEEE/CVF international conference on computer vision, ICCV, Seoul, Korea (South), pp 3285–3294. https://doi.org/10.1109/ICCV.2019.00338
Hu J, Shen L, Albanie S, Sun G, Wu E (2020) Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell 42(8):2011–2023
Wong A, Shafiee MJ, Chwyl B, Li F (2018) FermiNets: learning generative machines to generate efficient neural networks via generative synthesis. arXiv:1809.05989v2 [cs.NE]. https://doi.org/10.48550/arXiv.1809.05989
Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W et al (2017) MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861v1 [cs.CV]. https://doi.org/10.48550/arXiv.1704.04861
Zoph B, Vasudevan V, Shlens J, Le QV (2018) Learning transferable architectures for scalable image recognition. In: Proc. IEEE/CVF conference on computer vision and pattern recognition, CVPR, Salt Lake City, UT, pp 8697–8710. https://doi.org/10.1109/CVPR.2018.00907
Tan M, Le QV (2019) EfficientNet: rethinking model scaling for convolutional neural networks. arXiv:1905.11946v5 [cs.LG]. https://doi.org/10.48550/arXiv.1905.11946
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest
The authors declare that they have no conflicts of interest to report regarding the present study.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Kotei, E., Thirunavukarasu, R. Visual attention condenser model for multiple disease detection from heterogeneous medical image modalities. Multimed Tools Appl 83, 30563–30585 (2024). https://doi.org/10.1007/s11042-023-16625-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-16625-x