{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T07:34:15Z","timestamp":1775547255783,"version":"3.50.1"},"reference-count":56,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T00:00:00Z","timestamp":1682553600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Sciences and Engineering Council of Canada (NSERC)","award":["496439-2017"],"award-info":[{"award-number":["496439-2017"]}]},{"name":"Natural Sciences and Engineering Council of Canada (NSERC)","award":["FR49395"],"award-info":[{"award-number":["FR49395"]}]},{"name":"CREATE-oN DuTy! Program","award":["496439-2017"],"award-info":[{"award-number":["496439-2017"]}]},{"name":"CREATE-oN DuTy! Program","award":["FR49395"],"award-info":[{"award-number":["FR49395"]}]},{"name":"Mitacs Acceleration program","award":["496439-2017"],"award-info":[{"award-number":["496439-2017"]}]},{"name":"Mitacs Acceleration program","award":["FR49395"],"award-info":[{"award-number":["FR49395"]}]},{"name":"Canada Research Chair in Multi-polar Infrared Vision (MIVIM)","award":["496439-2017"],"award-info":[{"award-number":["496439-2017"]}]},{"name":"Canada Research Chair in Multi-polar Infrared Vision (MIVIM)","award":["FR49395"],"award-info":[{"award-number":["FR49395"]}]},{"name":"Canada Foundation for Innovation","award":["496439-2017"],"award-info":[{"award-number":["496439-2017"]}]},{"name":"Canada Foundation for Innovation","award":["FR49395"],"award-info":[{"award-number":["FR49395"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In response to the growing inspection demand exerted by process automation in component manufacturing, non-destructive testing (NDT) continues to explore automated approaches that utilize deep-learning algorithms for defect identification, including within digital X-ray radiography images. This necessitates a thorough understanding of the implication of image quality parameters on the performance of these deep-learning models. This study investigated the influence of two image-quality parameters, namely signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), on the performance of a U-net deep-learning semantic segmentation model. Input images were acquired with varying combinations of exposure factors, such as kilovoltage, milli-ampere, and exposure time, which altered the resultant radiographic image quality. The data were sorted into five different datasets according to their measured SNR and CNR values. The deep-learning model was trained five distinct times, utilizing a unique dataset for each training session. Training the model with high CNR values yielded an intersection-over-union (IoU) metric of 0.9594 on test data of the same category but dropped to 0.5875 when tested on lower CNR test data. The result of this study emphasizes the importance of achieving a balance in training dataset according to the investigated quality parameters in order to enhance the performance of deep-learning segmentation models for NDT digital X-ray radiography applications.<\/jats:p>","DOI":"10.3390\/s23094324","type":"journal-article","created":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T05:10:14Z","timestamp":1682572214000},"page":"4324","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Deep Learning Neural Network Performance on NDT Digital X-ray Radiography Images: Analyzing the Impact of Image Quality Parameters\u2014An Experimental Study"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6996-4340","authenticated-orcid":false,"given":"Bata","family":"Hena","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Universit\u00e9 Laval, Quebec City, QC G1V 0A6, Canada"},{"name":"Computer Vision and Systems Laboratory, Department of Electrical and Computer Engineering, 1065, Ave de la M\u00e9decine, Universit\u00e9 Laval, Quebec City, QC G1V 0A6, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5015-8696","authenticated-orcid":false,"given":"Ziang","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Universit\u00e9 Laval, Quebec City, QC G1V 0A6, Canada"},{"name":"Computer Vision and Systems Laboratory, Department of Electrical and Computer Engineering, 1065, Ave de la M\u00e9decine, Universit\u00e9 Laval, Quebec City, QC G1V 0A6, Canada"},{"name":"School of Engineering, University of Applied Sciences in Saarbr\u00fccken, 66117 Saarbr\u00fccken, Germany"},{"name":"Fraunhofer Institute for Nondestructive Testing IZFP, 66123 Saarbr\u00fccken, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0198-7439","authenticated-orcid":false,"given":"Clemente Ibarra","family":"Castanedo","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Universit\u00e9 Laval, Quebec City, QC G1V 0A6, Canada"},{"name":"Computer Vision and Systems Laboratory, Department of Electrical and Computer Engineering, 1065, Ave de la M\u00e9decine, Universit\u00e9 Laval, Quebec City, QC G1V 0A6, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8777-2008","authenticated-orcid":false,"given":"Xavier","family":"Maldague","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Universit\u00e9 Laval, Quebec City, QC G1V 0A6, Canada"},{"name":"Computer Vision and Systems Laboratory, Department of Electrical and Computer Engineering, 1065, Ave de la M\u00e9decine, Universit\u00e9 Laval, Quebec City, QC G1V 0A6, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,4,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Hassani, S., and Dackermann, U. (2023). A Systematic Review of Advanced Sensor Technologies for Non-Destructive Testing and Structural Health Monitoring. Sensors, 23.","DOI":"10.3390\/s23042204"},{"key":"ref_2","unstructured":"(2023, March 27). Standard Terminology for Nondestructive Examinations. Available online: https:\/\/www.astm.org\/e1316-22a.html."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"102567","DOI":"10.1016\/j.ndteint.2021.102567","article-title":"Selection of an Appropriate Non-Destructive Testing Method for Evaluating Drilling-Induced Delamination in Natural Fiber Composites","volume":"126","author":"Maleki","year":"2022","journal-title":"NDT E Int."},{"key":"ref_4","first-page":"2286","article-title":"Advances in Applications of Non-Destructive Testing (NDT): A Review","volume":"8","author":"Gupta","year":"2022","journal-title":"Adv. Mater. Process. Technol."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Patel, R., Patel, D., and Meshram, D. (2022). Department of Pharmaceutical Quality Assurance, Pioneer Pharmacy Degree College, Sayajipura, Vadodara-390019, Gujarat, India. A Review on Non-Destructive Testing (NDT) Techniques: Advances, Researches and Applicability. IJCSRR, 5.","DOI":"10.47191\/ijcsrr\/V5-i4-59"},{"key":"ref_6","unstructured":"(2021). Non-Destructive Testing\u2014Qualification and Certification of NDT Personnel (Standard No. ISO 9712:2021(En)). Available online: https:\/\/www.iso.org\/obp\/ui\/fr\/#iso:std:iso:9712:ed-5:v1:en."},{"key":"ref_7","unstructured":"(2023, March 27). Recommended Practice No. SNT-TC-1A. Available online: https:\/\/asnt.org\/MajorSiteSections\/Standards\/ASNT_Standards\/SNT-TC-1A.aspx."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Basu, S. (2023). Plant Intelligent Automation and Digital Transformation, Elsevier.","DOI":"10.1016\/B978-0-12-824457-9.00014-5"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1016\/j.procs.2022.12.332","article-title":"Human-Robot Co-Working Improvement via Revolutionary Automation and Robotic Technologies\u2013An Overview","volume":"217","author":"Ikumapayi","year":"2023","journal-title":"Procedia Comput. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"870","DOI":"10.1016\/j.procs.2023.01.362","article-title":"Literature Review of Decision Models for the Sustainable Implementation of Robotic Process Automation","volume":"219","author":"Varela","year":"2023","journal-title":"Procedia Comput. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"122448","DOI":"10.1016\/j.techfore.2023.122448","article-title":"Automation Technologies and Their Impact on Employment: A Review, Synthesis and Future Research Agenda","volume":"191","author":"Filippi","year":"2023","journal-title":"Technol. Forecast. Soc. Change"},{"key":"ref_12","unstructured":"Bertovic, M. (2015). Human Factors in Non-Destructive Testing (NDT): Risks and Challenges of Mechanised NDT. [Ph.D. Thesis, Technische Universit\u00e4t Berlin]."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1109\/TASE.2017.2675709","article-title":"Automating High-Precision X-ray and Neutron Imaging Applications with Robotics","volume":"15","author":"Hashem","year":"2018","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1007\/s10921-021-00842-1","article-title":"Automated Defect Recognition of Castings Defects Using Neural Networks","volume":"41","year":"2022","journal-title":"J. Nondestruct. Eval."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1016\/j.jmsy.2021.05.008","article-title":"A Review on Recent Advances in Vision-Based Defect Recognition towards Industrial Intelligence","volume":"62","author":"Gao","year":"2022","journal-title":"J. Manuf. Syst."},{"key":"ref_16","unstructured":"Zhao, J.D. (2020). Robotic Non-Destructive Testing of Manmade Structures: A Review of the Literature. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"108338","DOI":"10.1016\/j.knosys.2022.108338","article-title":"A Nondestructive Automatic Defect Detection Method with Pixelwise Segmentation","volume":"242","author":"Yang","year":"2022","journal-title":"Knowl. -Based Syst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"166342","DOI":"10.1016\/j.ijleo.2021.166342","article-title":"An Autonomous Technique for Weld Defects Detection and Classification Using Multi-Class Support Vector Machine in X-Radiography Image","volume":"231","author":"Malarvel","year":"2021","journal-title":"Optik"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/j.ndteint.2016.11.003","article-title":"Automated Detection of Welding Defects in Pipelines from Radiographic Images DWDI","volume":"86","author":"Boaretto","year":"2017","journal-title":"NDT E Int."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"105636","DOI":"10.1016\/j.engappai.2022.105636","article-title":"Deep Learning-Based Detection of Aluminum Casting Defects and Their Types","volume":"118","author":"Parlak","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"113966","DOI":"10.1016\/j.microrel.2020.113966","article-title":"Automated Defect Detection of Insulated Gate Bipolar Transistor Based on Computed Laminography Imaging","volume":"115","author":"Li","year":"2020","journal-title":"Microelectron. Reliab."},{"key":"ref_22","unstructured":"Naddaf-Sh, M.-M., Naddaf-Sh, S., Zargarzadeh, H., Zahiri, S.M., Dalton, M., Elpers, G., and Kashani, A.R. (2021). Fault Diagnosis and Prognosis Techniques for Complex Engineering Systems, Elsevier."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1016\/j.cja.2019.09.017","article-title":"Successes and Challenges in Non-Destructive Testing of Aircraft Composite Structures","volume":"33","author":"Towsyfyan","year":"2020","journal-title":"Chin. J. Aeronaut."},{"key":"ref_24","unstructured":"(2023, March 27). Search Results for: \u201cStandard Guide for the Qualification and Control of the Assisted Defect Recognition of Digital Radiographic Test Data\u201d. Available online: https:\/\/www.astm.org\/catalogsearch\/result\/?q=Standard+Guide+for+the+Qualification+and+Control+of+the+Assisted+Defect+Recognition+of+Digital+Radiographic+Test+Data."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1134\/S1061830919010121","article-title":"Contrast Enhancement of Industrial Radiography Images by Gabor Filtering with Automatic Noise Thresholding","volume":"55","author":"Yahaghi","year":"2019","journal-title":"Russ. J. Nondestruct. Test."},{"key":"ref_26","unstructured":"(2013). Non-Destructive Testing\u2014Image Quality of Radiographs\u2014Part 4: Experimental Evaluation of Image Quality Values and Image Quality Tables (Standard No. ISO 19232-4:2013(En)). Available online: https:\/\/www.iso.org\/obp\/ui\/#iso:std:iso:19232:-4:ed-2:v1:en."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"166472","DOI":"10.1016\/j.nima.2022.166472","article-title":"Quantitative Optimization of X-ray Image Acquisition with Respect to Object Thickness and Anode Voltage\u2014A Comparison Using Different Converter Screens","volume":"1031","author":"Ullherr","year":"2022","journal-title":"Nucl. Instrum. Methods Phys. Res. Sect. A Accel. Spectrometers Detect. Assoc. Equip."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"109437","DOI":"10.1016\/j.radphyschem.2021.109437","article-title":"X-ray Spectra and Gamma Factors from 70 to 120 KV X-ray Tube Voltages","volume":"184","year":"2021","journal-title":"Radiat. Phys. Chem."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1016\/j.ajodo.2007.02.053","article-title":"Image Quality Produced by Different Cone-Beam Computed Tomography Settings","volume":"133","author":"Kwong","year":"2008","journal-title":"Am. J. Orthod. Dentofac. Orthop."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"3354","DOI":"10.1038\/s41598-022-07376-0","article-title":"The Effect of a Variable Focal Spot Size on the Contrast Channels Retrieved in Edge-Illumination X-ray Phase Contrast Imaging","volume":"12","author":"Astolfo","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.acra.2019.08.018","article-title":"A Review of Perceptual Expertise in Radiology-How It Develops, How We Can Test It, and Why Humans Still Matter in the Era of Artificial Intelligence","volume":"27","author":"Waite","year":"2020","journal-title":"Acad. Radiol."},{"key":"ref_32","unstructured":"(2023, March 28). Standard Practice for Design, Manufacture and Material Grouping Classification of Wire Image Quality Indicators (IQI) Used for Radiology. Available online: https:\/\/www.astm.org\/e0747-18.html."},{"key":"ref_33","unstructured":"Ewert, U., Zscherpel, U., Vogel, J., Zhang, F., Long, N.X., and Nguyen, T.P. (2018, January 11\u201315). Visibility of Image Quality Indicators (IQI) by Human Observers in Digital Radiography in Dependence on Measured MTFs and Noise Power Spectra. Proceedings of the ECNDT 2018-12th European Conference on Non-Destructive Testing (ECNDT 2018), Gothenburg, Sweden."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1007\/s12194-016-0381-2","article-title":"Investigation of Noise Sources for Digital Radiography Systems","volume":"10","author":"Ergun","year":"2017","journal-title":"Radiol. Phys. Technol."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"110600","DOI":"10.1016\/j.ejrad.2022.110600","article-title":"The Principles and Effectiveness of X-ray Scatter Correction Software for Diagnostic X-ray Imaging: A Scoping Review","volume":"158","author":"Sayed","year":"2023","journal-title":"Eur. J. Radiol."},{"key":"ref_36","unstructured":"Sy, E., Samboju, V., and Mukhdomi, T. (2023). StatPearls, StatPearls Publishing."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"6S","DOI":"10.1016\/j.jvs.2010.05.138","article-title":"Radiation Physics","volume":"53","author":"Tonnessen","year":"2011","journal-title":"J. Vasc. Surg."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"393","DOI":"10.6028\/jres.040.029","article-title":"Absorption of X-rays in air","volume":"40","author":"Day","year":"1948","journal-title":"J. Res. Natl. Bur. Stand."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Liu, J., and Kim, J.H. (2022). A Novel Sub-Pixel-Shift-Based High-Resolution X-ray Flat Panel Detector. Coatings, 12.","DOI":"10.3390\/coatings12070921"},{"key":"ref_40","first-page":"2201034","article-title":"A Review of X-Ray Imaging at the BAM Line (BESSY II)","volume":"23","author":"Kupsch","year":"2023","journal-title":"Adv. Eng. Mater."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"101823","DOI":"10.1016\/j.bspc.2019.101823","article-title":"Cupping Artifacts Correction for Polychromatic X-ray Cone-Beam Computed Tomography Based on Projection Compensation and Hardening Behavior","volume":"57","author":"Yang","year":"2020","journal-title":"Biomed. Signal Process. Control."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"82","DOI":"10.53730\/ijpse.v6n2.9656","article-title":"Effect of X-ray Tube Voltage Variation to Value of Contrast to Noise Ratio (CNR) on Computed Tomography (CT) Scan at RSUD Bali Mandara","volume":"6","author":"Dewi","year":"2022","journal-title":"IJPSE"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"022008","DOI":"10.1088\/1742-6596\/1567\/2\/022008","article-title":"Radiation Exposure Factors Optimization of X-ray Digital Radiography for Watermarked Art Pottery Inspection","volume":"1567","author":"Listiaji","year":"2020","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"121","DOI":"10.4028\/p-ldt93t","article-title":"The Influence of X-ray Tube Current-Time Variations Toward Signal to Noise Ratio (SNR) in Digital Radiography: A Phantom Study","volume":"913","author":"Utami","year":"2023","journal-title":"Appl. Mech. Mater."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"894643","DOI":"10.1155\/2010\/894643","article-title":"Digital Radiography Using Digital Detector Arrays Fulfills Critical Applications for Offshore Pipelines","volume":"2010","author":"Moreira","year":"2010","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"976","DOI":"10.1016\/j.radi.2021.02.014","article-title":"Anode Heel Effect: Does It Impact Image Quality in Digital Radiography? A Systematic Literature Review","volume":"27","author":"Kusk","year":"2021","journal-title":"Radiography"},{"key":"ref_47","first-page":"C04018","article-title":"Image Recovery by Removing Stochastic Artefacts Identified as Local Asymmetries","volume":"7","author":"Osterloh","year":"2012","journal-title":"J. Inst."},{"key":"ref_48","unstructured":"(2023, April 13). ImageJ. Available online: https:\/\/imagej.net\/ij\/index.html."},{"key":"ref_49","unstructured":"(2022). Non-Destructive Testing of Welds\u2014Radiographic Testing\u2014Part 2: X- and Gamma-Ray Techniques with Digital Detectors (Standard No. ISO 17636-2:2022(En)). Available online: https:\/\/www.iso.org\/obp\/ui\/#iso:std:iso:17636:-2:ed-2:v2:en."},{"key":"ref_50","unstructured":"(2023, March 29). CVAT. Available online: https:\/\/www.cvat.ai\/."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Navab, N., Hornegger, J., Wells, W.M., and Frangi, A.F. (2015). Medical Image Computing and Computer-Assisted Intervention 2015, Springer International Publishing.","DOI":"10.1007\/978-3-319-24571-3"},{"key":"ref_52","first-page":"102685","article-title":"An Attention-Based U-Net for Detecting Deforestation within Satellite Sensor Imagery","volume":"107","author":"John","year":"2022","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_53","unstructured":"Tokime, R.B., Maldague, X., and Perron, L. (2019, January 23\u201324). Automatic Defect Detection for X-ray Inspection: A U-Net Approach for Defect Segmentation. Proceedings of the Digital Imaging and Ultrasonics for NDT 2019, New Orleads, LA, USA."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"1990","DOI":"10.1002\/ima.22803","article-title":"Automatic Semantic Segmentation for Dental Restorations in Panoramic Radiography Images Using U-Net Model","volume":"32","author":"Oztekin","year":"2022","journal-title":"Int. J. Imaging Syst. Tech."},{"key":"ref_55","first-page":"1","article-title":"U-Net-Based Medical Image Segmentation","volume":"2022","author":"Yin","year":"2022","journal-title":"J. Healthc. Eng."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Wei, Z., Osman, A., Valeske, B., and Maldague, X. (2023). Pulsed Thermography Dataset for Training Deep Learning Models. Appl. Sci., 13.","DOI":"10.20944\/preprints202301.0483.v1"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/9\/4324\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:24:25Z","timestamp":1760124265000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/9\/4324"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,27]]},"references-count":56,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2023,5]]}},"alternative-id":["s23094324"],"URL":"https:\/\/doi.org\/10.3390\/s23094324","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,27]]}}}