{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T13:52:05Z","timestamp":1781617925797,"version":"3.54.5"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100006196","name":"University of Oulu","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100006196","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Discov Computing"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Tuberculosis (TB) is a highly contagious disease that affects millions of individuals globally. Early detection is crucial in preventing its spread and improving patient outcomes. Radiologists often utilize X-ray imaging as a diagnostic tool for tuberculosis; however, the accuracy of the results may differ depending on the radiologist\u2019s interpretation. To increase the precision of TB identification from X-ray images, a hybrid strategy combining Convolutional Neural Network, Histogram of Oriented Gradients, and Quantum Support Vector Machine (QSVM) classifier has been developed. Quantum machine learning is a rapidly growing field at the intersection of quantum computing and machine learning. By combining the strengths of both techniques, this approach aims to capture relevant features and shape and texture information of an image. The study used state-of-the-art models such as VGG16 and AlexNet, along with a handcrafted method (HOG) and a deep learning (CNN) method to detect TB from chest X-ray images. Six distinct tests were carried out by the authors to successfully diagnose tuberculosis. All models showed promise when the data was analyzed, but the best techniques involved augmentation, image preprocessing, contrast improvement, and noise filtering. The block-matching and 3D filtering approach was used to improve image edge preservation and reduce noise. In this study, Grad-CAM (gradient-weighted class activation map) was applied to the convolutional neural network model to identify the model\u2019s important features (explainability) for decision-making. This focus on Explainable AI (XAI) is crucial for clinical adoption, as it provides radiologists with visual evidence of the model\u2019s reasoning, fostering trust and enabling more informed decisions. The hybrid model was found to have achieved an exceptional level of accuracy in detecting and classifying TB, with an accuracy rate of 100% during training, 99.07% during validation, and 98.14% during testing. These results highlight the effectiveness of the hybrid model in accurately identifying TB and its potential to be a valuable tool in the fight against this disease.<\/jats:p>","DOI":"10.1007\/s10791-025-09791-z","type":"journal-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:32:57Z","timestamp":1762907577000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An explainable hybrid deep learning system for tuberculosis detection with Grad-CAM"],"prefix":"10.1007","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5869-6029","authenticated-orcid":false,"given":"Aleka Melese","family":"Ayalew","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5636-3981","authenticated-orcid":false,"given":"Nigus Wereta","family":"Asnake","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5158-0895","authenticated-orcid":false,"given":"Getnet","family":"Demil","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4422-8723","authenticated-orcid":false,"given":"Mourad","family":"Oussalah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,12]]},"reference":[{"key":"9791_CR1","unstructured":"Basic TB. Facts | TB | CDC, Centers for Disease Control and Prevention. https:\/\/www.cdc.gov\/tb\/topic\/basics\/default.htm. Accessed 4 Jun 2023."},{"key":"9791_CR2","doi-asserted-by":"publisher","unstructured":"Frothingham R, Stout JE, Hamilton CD. Current issues in global tuberculosis control. Int J Infect Dis. Nov. 2005;9(6):297\u2013311. https:\/\/doi.org\/10.1016\/j.ijid.2005.04.001.","DOI":"10.1016\/j.ijid.2005.04.001"},{"key":"9791_CR3","unstructured":"Tuberculosis\u2014an overview | ScienceDirect Topics. https:\/\/www.sciencedirect.com\/topics\/pharmacology-toxicology-and-pharmaceutical-science\/tuberculosis. Accessed 8 Aug 2025."},{"key":"9791_CR4","unstructured":"Tuberculosis\u2014symptoms and causes - Mayo Clinic, mayoclinic. https:\/\/www.mayoclinic.org\/diseases-conditions\/tuberculosis\/symptoms-causes\/syc-20351250. Accessed 4 Jun 2023."},{"key":"9791_CR5","unstructured":"Global Tuberculosis Report 2024. https:\/\/www.who.int\/teams\/global-programme-on-tuberculosis-and-lung-health\/tb-reports\/global-tuberculosis-report-2024. Accessed 8 Aug 2025."},{"key":"9791_CR6","doi-asserted-by":"publisher","unstructured":"Bagcchi S, WHO\u2019s Global Tuberculosis Report. 2022. Lancet Microbe. 2023;4(1):e20. https:\/\/doi.org\/10.1016\/S2666-5247(22)00359-7.","DOI":"10.1016\/S2666-5247(22)00359-7"},{"key":"9791_CR7","unstructured":"CDC. Provisional 2024 Tuberculosis Data, United States, Tuberculosis Data. https:\/\/www.cdc.gov\/tb-data\/2024-provisional\/index.html. Accessed 8 Aug 2025."},{"key":"9791_CR8","doi-asserted-by":"publisher","unstructured":"Simi Margarat G et al. Early diagnosis of tuberculosis using deep learning approach for IOT based healthcare applications. Comput Intell Neurosci. 2022;2022:1\u20139. https:\/\/doi.org\/10.1155\/2022\/3357508.","DOI":"10.1155\/2022\/3357508"},{"key":"9791_CR9","doi-asserted-by":"publisher","unstructured":"Yalew TA, Gashaw SM, Ayalew AM, Oussalah M. Deep learning-based occlusion-aware face mask detection for airborne disease control. Discov Comput. 2025;28(1):150. https:\/\/doi.org\/10.1007\/s10791-025-09684-1.","DOI":"10.1007\/s10791-025-09684-1"},{"key":"9791_CR10","doi-asserted-by":"publisher","unstructured":"Wagner J, K\u00f6hler JM, Gindele T, Hetzel L, Wiedemer JT, Behnke S. Interpretable and fine-grained visual explanations for convolutional neural networks. in. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019, pp. 9089\u20139099. https:\/\/doi.org\/10.1109\/CVPR.2019.00931.","DOI":"10.1109\/CVPR.2019.00931"},{"key":"9791_CR11","doi-asserted-by":"publisher","unstructured":"Chattopadhay A, Sarkar A, Howlader P, Balasubramanian VN. Grad-CAM++: generalized gradient-based visual explanations for deep convolutional networks, in 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), Mar. 2018, pp. 839\u2013847. https:\/\/doi.org\/10.1109\/WACV.2018.00097.","DOI":"10.1109\/WACV.2018.00097"},{"key":"9791_CR12","doi-asserted-by":"publisher","unstructured":"Aksoy G, Cattan G, Chakraborty S, Karabatak M. Quantum Machine-Based decision support system for the detection of schizophrenia from EEG records. J Med Syst. 2024;48(1):29. https:\/\/doi.org\/10.1007\/s10916-024-02048-0.","DOI":"10.1007\/s10916-024-02048-0"},{"key":"9791_CR13","unstructured":"Exploring the potential of quantum-based machine learning: a comparative study of QSVM and classical machine learning algorithms. https:\/\/ieeexplore.ieee.org\/document\/10131821. Accessed 16 Jul 2024."},{"key":"9791_CR14","doi-asserted-by":"publisher","unstructured":"Liu Y, et al. Optimized Dropkey-based Grad-CAM: toward accurate image feature localization. Sensors. 2023;23(20):8351. https:\/\/doi.org\/10.3390\/s23208351.","DOI":"10.3390\/s23208351"},{"key":"9791_CR15","doi-asserted-by":"publisher","unstructured":"Hassan E, Saber A, El-Sappagh S, El-Rashidy N. Optimized ensemble deep learning approach for accurate breast cancer diagnosis using transfer learning and grey Wolf optimization. Evol Syst. 2025;16(2):59. https:\/\/doi.org\/10.1007\/s12530-025-09686-w.","DOI":"10.1007\/s12530-025-09686-w"},{"key":"9791_CR16","doi-asserted-by":"publisher","unstructured":"Duong LT, Le NH, Tran TB, Ngo VM, Nguyen PT. Detection of tuberculosis from chest X-ray images: boosting the performance with vision transformer and transfer learning. Expert Syst Appl. 2021;184:115519. https:\/\/doi.org\/10.1016\/j.eswa.2021.115519.","DOI":"10.1016\/j.eswa.2021.115519"},{"key":"9791_CR17","doi-asserted-by":"publisher","unstructured":"Andayani U, Rahmat RF, Sylviana Pasi N, Siregar B, Syahputra MF, Muchtar MA. Identification of the tuberculosis (TB) disease based on XRay images using probabilistic neural network (PNN). J Phys Conf Ser. 2019;1235(1):012056. https:\/\/doi.org\/10.1088\/1742-6596\/1235\/1\/012056.","DOI":"10.1088\/1742-6596\/1235\/1\/012056"},{"key":"9791_CR18","doi-asserted-by":"publisher","unstructured":"Iqbal A, Usman M, Ahmed Z. Tuberculosis chest X-ray detection using CNN-based hybrid segmentation and classification approach. Biomed Signal Process Control. 2023;84:104667. https:\/\/doi.org\/10.1016\/j.bspc.2023.104667.","DOI":"10.1016\/j.bspc.2023.104667"},{"key":"9791_CR19","doi-asserted-by":"publisher","unstructured":"Verma G, Kumar A, Dixit S. Early detection of tuberculosis using hybrid feature descriptors and deep learning network. Pol J Radiol. 2023;88: e445\u2013e454. https:\/\/doi.org\/10.5114\/pjr.2023.131732.","DOI":"10.5114\/pjr.2023.131732"},{"key":"9791_CR20","doi-asserted-by":"publisher","unstructured":"Hadhoud Y et al. From binary to multi-class classification: a two-step hybrid CNN-ViT model for chest disease classification based on X-ray images. Diagnostics. 2024;14(23):2754. https:\/\/doi.org\/10.3390\/diagnostics14232754.","DOI":"10.3390\/diagnostics14232754"},{"key":"9791_CR21","doi-asserted-by":"publisher","unstructured":"Chandra TB, Verma K, Singh BK, Jain D, Netam SS. Automatic detection of tuberculosis related abnormalities in chest X-ray images using hierarchical feature extraction scheme. Expert Syst Appl. 2020;158:113514.https:\/\/doi.org\/10.1016\/j.eswa.2020.113514.","DOI":"10.1016\/j.eswa.2020.113514"},{"key":"9791_CR22","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/978-3-031-82377-0_8","volume-title":"Intelligent Systems, Blockchain, and communication technologies","author":"A Abdelhamid","year":"2025","unstructured":"Abdelhamid A, Akinniyi O, Saleh GA, Khalifa F. Lung disease detection using Scale-Invariant weighted ensemble neural architecture. In: Abdelgawad A, Jamil A, Hameed AA, editors. Intelligent Systems, Blockchain, and communication technologies. Cham: Springer Nature Switzerland; 2025. pp. 83\u201394. https:\/\/doi.org\/10.1007\/978-3-031-82377-0_8."},{"key":"9791_CR23","unstructured":"Tuberculosis (TB) chest X-ray database. https:\/\/www.kaggle.com\/datasets\/tawsifurrahman\/tuberculosis-tb-chest-xray-dataset. Accessed 8 Oct 2025."},{"key":"9791_CR24","unstructured":"Tuberculosis (TB) chest X-ray database | Kaggle. https:\/\/www.kaggle.com\/datasets\/tawsifurrahman\/tuberculosis-tb-chest-xray-dataset. Accessed 6 Jun 2023."},{"key":"9791_CR25","doi-asserted-by":"publisher","unstructured":"Ayalew AM, Oussalah M, Abuhayi BM, Bezabh YA. Smart breast cancer detection: enhancing early breast cancer diagnosis-transitioning from convolutional neural network to involutional neural network and using smart wearable devices. Sens Imaging. Mar. 2025;26(1):26. https:\/\/doi.org\/10.1007\/s11220-025-00561-1.","DOI":"10.1007\/s11220-025-00561-1"},{"key":"9791_CR26","doi-asserted-by":"publisher","unstructured":"Asnake NW, Ayalew AM, Engda AA. Detection of oral squamous cell carcinoma cancer using AlexNet on histopathological images. Discov Appl Sci. 2025;7(3):155. https:\/\/doi.org\/10.1007\/s42452-025-06514-3.","DOI":"10.1007\/s42452-025-06514-3"},{"key":"9791_CR27","doi-asserted-by":"publisher","unstructured":"Yahya AA, et al. BM3D image denoising algorithm based on an adaptive filtering. Multimed Tools Appl. 2020;79:27\u20138. https:\/\/doi.org\/10.1007\/s11042-020-08815-8.","DOI":"10.1007\/s11042-020-08815-8"},{"key":"9791_CR28","doi-asserted-by":"publisher","unstructured":"Chen Q, Wu D. Image denoising by bounded block matching and 3D filtering. Signal Process. 2010;90(9):2778\u20132783. https:\/\/doi.org\/10.1016\/j.sigpro.2010.03.016.","DOI":"10.1016\/j.sigpro.2010.03.016"},{"key":"9791_CR29","unstructured":"Brownlee J. How to configure image data augmentation in Keras, MachineLearningMastery.com. https:\/\/machinelearningmastery.com\/how-to-configure-image-data-augmentation-when-training-deep-learning-neural-networks\/. Accessed 21 Jun 2023."},{"key":"9791_CR30","doi-asserted-by":"publisher","unstructured":"Mahmood T, Saba T, Rehman A, Alamri FS. Harnessing the power of radiomics and deep learning for improved breast cancer diagnosis with multiparametric breast mammography. Expert Syst Appl. Sept. 2024;249:123747. https:\/\/doi.org\/10.1016\/j.eswa.2024.123747.","DOI":"10.1016\/j.eswa.2024.123747"},{"key":"9791_CR31","doi-asserted-by":"publisher","unstructured":"Muhammad D, Salman M, Keles A, Bendechache M. ALL diagnosis: can efficiency and transparency coexist? An explainble deep learning approach. Sci Rep. 2025;15(1):12812. https:\/\/doi.org\/10.1038\/s41598-025-97297-5.","DOI":"10.1038\/s41598-025-97297-5"},{"key":"9791_CR32","doi-asserted-by":"publisher","unstructured":"Ayalew AM et al. InvNets: A Novel Approach for Parkinson Disease Detection Using Involution Neural Networks. In: 2024 Second International Conference Computational and Characterization Techniques in Engineering & Sciences (IC3TES), Lucknow, India: IEEE, Nov. 2024, pp. 1\u20137. https:\/\/doi.org\/10.1109\/IC3TES62412.2024.10877493.","DOI":"10.1109\/IC3TES62412.2024.10877493"},{"key":"9791_CR33","doi-asserted-by":"publisher","unstructured":"Ayalew AM, Salau AO, Abeje BT, Enyew B. Detection and classification of COVID-19 disease from X-ray images using convolutional neural networks and histogram of oriented gradients. Biomed Signal Process. Control. 2022;74:103530. https:\/\/doi.org\/10.1016\/j.bspc.2022.103530","DOI":"10.1016\/j.bspc.2022.103530"},{"key":"9791_CR34","doi-asserted-by":"publisher","unstructured":"Smart Malaria Classification. A Novel Machine Learning Algorithms for Early Malaria Monitoring and Detecting Using IoT-Based Healthcare Environment | Sensing and Imaging. Accessed: Oct. 09, 2025. [Online]. Available: https:\/\/link.springer.com\/article\/https:\/\/doi.org\/10.1007\/s11220-024-00503-3","DOI":"10.1007\/s11220-024-00503-3"},{"key":"9791_CR35","doi-asserted-by":"publisher","unstructured":"Zhang X et al. A hardware-oriented histogram of oriented gradients algorithm and its VLSI implementation. Jpn J Appl Phys. 2017;56(4S):04CF01. https:\/\/doi.org\/10.7567\/JJAP.56.04CF01.","DOI":"10.7567\/JJAP.56.04CF01"},{"key":"9791_CR36","doi-asserted-by":"publisher","unstructured":"Dalal N, Triggs B. Histograms of oriented gradients for human detection. In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), San Diego, CA, USA: IEEE, 2005, pp. 886\u2013893. https:\/\/doi.org\/10.1109\/CVPR.2005.177.","DOI":"10.1109\/CVPR.2005.177"},{"key":"9791_CR37","doi-asserted-by":"publisher","unstructured":"Nalepa J, Kawulok M. Selecting training sets for support vector machines: a review. Artif Intell Rev. 2019;52(2):857\u2013900. https:\/\/doi.org\/10.1007\/s10462-017-9611-1.","DOI":"10.1007\/s10462-017-9611-1"},{"key":"9791_CR38","doi-asserted-by":"publisher","unstructured":"Bansal R, Rajput NK, Khanna M. Enhancing quantum support vector machine for healthcare applications using custom feature maps. Knowl Based Syst. 2025;320:113669. https:\/\/doi.org\/10.1016\/j.knosys.2025.113669.","DOI":"10.1016\/j.knosys.2025.113669"},{"key":"9791_CR39","doi-asserted-by":"publisher","unstructured":"Mahmood T, Saba T, Rehman A. Breast cancer diagnosis with MFF-HistoNet: a multi-modal feature fusion network integrating CNNs and quantum tensor networks. J Big Data. 2025;12(1):60. https:\/\/doi.org\/10.1186\/s40537-025-01114-9.","DOI":"10.1186\/s40537-025-01114-9"},{"key":"9791_CR40","doi-asserted-by":"publisher","unstructured":"Zhang R, Wang J, Jiang N, Wang Z. Quantum support vector machine without iteration. Inf Sci. 2023;635:25\u201341. https:\/\/doi.org\/10.1016\/j.ins.2023.03.106.","DOI":"10.1016\/j.ins.2023.03.106"},{"key":"9791_CR41","unstructured":"Learning G. Everything you need to know about VGG16, Medium. https:\/\/medium.com\/@mygreatlearning\/everything-you-need-to-know-about-vgg16-7315defb5918. Accessed 24 Jun 2023."},{"key":"9791_CR42","unstructured":"Saxena S. Introduction to the architecture of Alexnet, Analytics Vidhya. https:\/\/www.analyticsvidhya.com\/blog\/2021\/03\/introduction-to-the-architecture-of-alexnet\/. Accessed 24 Jun 2023."},{"key":"9791_CR43","doi-asserted-by":"publisher","unstructured":"Li S, Li T, Sun C, Yan R, Chen X. Multilayer Grad-CAM: an effective tool towards explainable deep neural networks for intelligent fault diagnosis. J Manuf Syst. 2023;69:20\u201330. https:\/\/doi.org\/10.1016\/j.jmsy.2023.05.027.","DOI":"10.1016\/j.jmsy.2023.05.027"},{"key":"9791_CR44","doi-asserted-by":"publisher","unstructured":"Kadry S, Srivastava G, Rajinikanth V, Rho S, Kim Y. Tuberculosis detection in chest radiographs using spotted hyena algorithm optimized deep and handcrafted features. Comput Intell Neurosci. 2022;2022:1\u201312. https:\/\/doi.org\/10.1155\/2022\/9263379.","DOI":"10.1155\/2022\/9263379"},{"key":"9791_CR45","doi-asserted-by":"publisher","unstructured":"Acharya V et al. AI-assisted tuberculosis detection and classification from chest X-rays using a deep learning normalization-free network model. Comput Intell Neurosci. 2022;2022:1\u201319. https:\/\/doi.org\/10.1155\/2022\/2399428.","DOI":"10.1155\/2022\/2399428"}],"container-title":["Discover Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-025-09791-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10791-025-09791-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-025-09791-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T12:55:46Z","timestamp":1781614546000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10791-025-09791-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,12]]},"references-count":45,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["9791"],"URL":"https:\/\/doi.org\/10.1007\/s10791-025-09791-z","relation":{},"ISSN":["2948-2992"],"issn-type":[{"value":"2948-2992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,12]]},"assertion":[{"value":"1 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}],"article-number":"262"}}