{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T19:26:48Z","timestamp":1785266808731,"version":"3.55.0"},"reference-count":35,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T00:00:00Z","timestamp":1781395200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"European Partnership on Metrology, co-financed by the European Union\u2019s Horizon Europe Research and Innovation Programme and by the Participating States"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background: Artificial Intelligence (AI) software in mammography is trained on a set of processed images and may be less effective when applied to images acquired on different systems or systems with different processing and\/or acquisition settings. The aim of this work was to undertake a retrospective audit of a large number of mammography systems in the United Kingdom and identify the number of differences in image acquisition and processing factors. Methods: Images of the TORMAM phantom are acquired as part of the routine quality control programme. Data from the DICOM header of these images were extracted to provide a snapshot in time of the system configurations. A longitudinal audit of DICOM header data for all of the Hologic systems was tested by one medical physics department (MPD1) over 14 years. Results: We received results from 28 UK medical physics services for 498 systems. There were 7 different models of mammography systems, each with up to 7 different versions of acquisition workstation software. Each mammographic model had multiple image processing versions, including bespoke settings. The GE had two dose settings, while Siemens systems had a range of doses from 80% to 150% of the standard dose. In the longitudinal audit, there were between 2 and 6 software versions in concurrent use on the Hologic systems tested by MPD1. Conclusions: This study showed the heterogeneity of system setup across the UK in a single year, as well as changes to system setup over time. These differences may affect the outcomes of both AI and human readers. There are responsibilities on AI suppliers, mammography equipment manufacturers, breast-screening units, and medical physics services to ensure outcomes are not adversely affected by differences or changes in mammography equipment configurations.<\/jats:p>","DOI":"10.3390\/diagnostics16121842","type":"journal-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:44:58Z","timestamp":1781484298000},"page":"1842","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A National Audit of Mammography Systems Settings That May Affect the Output of Artificial Intelligence Software"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4545-8018","authenticated-orcid":false,"given":"Alistair","family":"Mackenzie","sequence":"first","affiliation":[{"name":"Medical Physics Department, Royal Surrey NHS Foundation Trust, Guildford GU2 7XX, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"Loveland","sequence":"additional","affiliation":[{"name":"Medical Physics Department, Royal Surrey NHS Foundation Trust, Guildford GU2 7XX, UK"},{"name":"Diagnostic Radiology Physics, Maidstone and Tunbridge Wells NHS Trust, Maidstone ME16 9QQ, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leila","family":"Farshadi","sequence":"additional","affiliation":[{"name":"Medical Physics Department, Royal Surrey NHS Foundation Trust, Guildford GU2 7XX, UK"},{"name":"Radiological Sciences Unit, Imperial College Healthcare NHS Trust, London W6 8RF, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7298-0709","authenticated-orcid":false,"given":"Carlijn","family":"Roozemond","sequence":"additional","affiliation":[{"name":"Dutch Expert Centre for Screening (LRCB), Wijchenseweg 101, 6538 SW Nijmegen, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7006-1376","authenticated-orcid":false,"given":"Ruben E.","family":"van Engen","sequence":"additional","affiliation":[{"name":"Dutch Expert Centre for Screening (LRCB), Wijchenseweg 101, 6538 SW Nijmegen, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e243688","DOI":"10.1148\/radiol.243688","article-title":"Influence of AI Decision Support on Radiologists\u2019 Performance and Visual Search in Screening Mammography","volume":"316","author":"Gommers","year":"2025","journal-title":"Radiology"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e175","DOI":"10.1016\/S2589-7500(24)00267-X","article-title":"Screening Performance and Characteristics of Breast Cancer Detected in the Mammography Screening with Artificial Intelligence Trial (MASAI): A Randomised, Controlled, Parallel-Group, Non-Inferiority, Single-Blinded, Screening Accuracy Study","volume":"7","author":"Josefsson","year":"2025","journal-title":"Lancet Digit. Health"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1038\/s43018-026-01127-0","article-title":"Diagnostic Accuracy, Fairness and Clinical Implementation of AI for Breast Cancer Screening: Results of Multicenter Retrospective and Prospective Technical Feasibility Studies","volume":"7","author":"Kelly","year":"2026","journal-title":"Nat. Cancer"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/s43018-026-01126-1","article-title":"Prospective Evaluation of Artificial Intelligence Integration into Breast Cancer Screening in Multiple Workflow Settings: The GEMINI Study","volume":"7","author":"Lip","year":"2026","journal-title":"Nat. Cancer"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"e222733","DOI":"10.1148\/radiol.222733","article-title":"Comparison of Mammography AI Algorithms with a Clinical Risk Model for 5-Year Breast Cancer Risk Prediction: An Observational Study","volume":"307","author":"Arasu","year":"2023","journal-title":"Radiology"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"369","DOI":"10.2214\/AJR.21.27071","article-title":"Artificial Intelligence (AI) for Screening Mammography, from the AJR Special Series on AI Applications","volume":"219","author":"Lamb","year":"2022","journal-title":"Am. J. Roentgenol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1093\/jbi\/wbaf027","article-title":"Bias in Artificial Intelligence: Impact on Breast Imaging","volume":"7","author":"Net","year":"2025","journal-title":"J. Breast Imaging"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2239","DOI":"10.1016\/j.acra.2023.12.006","article-title":"Artificial Intelligence for Breast Cancer Detection on Mammography: Factors Related to Cancer Detection","volume":"31","author":"Yoen","year":"2024","journal-title":"Acad. Radiol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"e250281","DOI":"10.1148\/ryai.250281","article-title":"Breast Cancers Detected and Missed by AI-CAD: Results from the AI-STREAM Trial","volume":"8","author":"Chang","year":"2025","journal-title":"Radiol. Artif. Intell."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1987","DOI":"10.1088\/0031-9155\/57\/7\/1987","article-title":"Characterization of the Effects of the FineView Algorithm for Full Field Digital Mammography","volume":"57","author":"Urbanczyk","year":"2012","journal-title":"Phys. Med. Biol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"765","DOI":"10.1118\/1.3077121","article-title":"Evaluation of Clinical Image Processing Algorithms Used in Digital Mammography","volume":"36","author":"Zanca","year":"2009","journal-title":"Med. Phys."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"387","DOI":"10.2214\/AJR.13.11812","article-title":"The Effect of Image Processing on the Detection of Cancers in Digital Mammography","volume":"203","author":"Warren","year":"2014","journal-title":"Am. J. Roentgenol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e220146","DOI":"10.1148\/ryai.220146","article-title":"Impact of Different Mammography Systems on Artificial Intelligence Performance in Breast Cancer Screening","volume":"5","author":"Colosimo","year":"2023","journal-title":"Radiol. Artif. Intell."},{"key":"ref_14","first-page":"37401","article-title":"Knowledge-Based In Silico Models and Dataset for the Comparative Evaluation of Mammography AI for a Range of Breast Characteristics, Lesion Conspicuities and Doses","volume":"36","author":"Sizikova","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1038\/s41746-025-01623-0","article-title":"Simulating Mismatch between Calibration and Target Population in AI for Mammography the Retrospective VAIB Study","volume":"8","author":"Schurz","year":"2025","journal-title":"npj Digit. Med."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Hickman, A.J., Gomes, S., Warren, L.M., Smith, N.A.S., and Shenton-Taylor, C. (2025). Assessing the Generalisation of Artificial Intelligence across Mammography Manufacturers. PLoS Digit. Health, 4.","DOI":"10.1371\/journal.pdig.0000973"},{"key":"ref_17","first-page":"183","article-title":"The Impact of Common Image Quality Issues in Screening Mammograms on Commercial AI-CAD Models","volume":"Volume 13928","author":"Verboom","year":"2026","journal-title":"Proceedings of the Medical Imaging 2026: Image Perception, Observer Performance, and Technology Assessment, Vancouver, BC, Canada, 15\u201320 February 2026"},{"key":"ref_18","first-page":"232","article-title":"Survey of Image Processing Settings Used for Mammography Systems in the United Kingdom: How Variable Is It?","volume":"Volume 13174","author":"Mackenzie","year":"2024","journal-title":"Proceedings of the 17th International Workshop on Breast Imaging (IWBI 2024), Chicago, IL, USA, 9\u201312 June 2024"},{"key":"ref_19","unstructured":"(2026, February 28). NEMA DICOM Standard PS3.6: Data Dictionary. Available online: https:\/\/dicom.nema.org\/medical\/dicom\/current\/output\/html\/part06.html#PS3.6."},{"key":"ref_20","unstructured":"Kulama, E., Burch, A., Castellano, I., Lawinski, C.P., Marshall, N.W., and Young, K.C. (2009). Commissioning and Routine Testing of Full Field Digital Mammography Systems, NHS Cancer Screening Programmes. NHSBSP Equipment Report 0604, Version 3."},{"key":"ref_21","unstructured":"(2026, May 31). PristinaTM Mammography System. Available online: https:\/\/www.gehealthcare.com\/en-gb\/products\/mammography\/senographe-pristina."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"799.e1","DOI":"10.1016\/j.crad.2017.03.024","article-title":"Image Processing Can Cause Some Malignant Soft-Tissue Lesions to Be Missed in Digital Mammography Images","volume":"72","author":"Warren","year":"2017","journal-title":"Clin. Radiol."},{"key":"ref_23","unstructured":"(2026, May 29). 3Dimensions Mammography System, Hologic. Available online: https:\/\/www.hologic.com\/package-inserts\/breast-skeletal-health-products\/3dimensions-mammography-system."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"055017","DOI":"10.1088\/2057-1976\/ace911","article-title":"A Comparison of Physical Image Quality of Two Hologic Digital Mammography Systems That Utilise Linear and 2D Anti-Scatter Grids","volume":"9","author":"Moore","year":"2023","journal-title":"Biomed. Phys. Eng. Express"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"821","DOI":"10.1007\/s00330-014-3422-4","article-title":"Comparison of a Flexible versus a Rigid Breast Compression Paddle: Pain Experience, Projected Breast Area, Radiation Dose and Technical Image Quality","volume":"25","author":"Broeders","year":"2015","journal-title":"Eur. Radiol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"e232680","DOI":"10.1148\/radiol.232680","article-title":"Pain Experience and Image Quality with Curved versus Standard Compression for Breast Cancer Screening Mammography: A Randomized Controlled Trial","volume":"312","author":"Tetteroo","year":"2024","journal-title":"Radiology"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"P10","DOI":"10.1186\/bcr2962","article-title":"Image Quality and Compression Force: The Forgotten Link in Optimisation of Digital Mammography?","volume":"13","author":"Grant","year":"2011","journal-title":"Breast Cancer Res."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"6270","DOI":"10.1002\/mp.15171","article-title":"The Impact on Lesion Detection via a Multi-Vendor Study: A Phantom-Based Comparison of Digital Mammography, Digital Breast Tomosynthesis, and Synthetic Mammography","volume":"48","author":"Vancoillie","year":"2021","journal-title":"Med. Phys."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"684","DOI":"10.1148\/radiol.13122567","article-title":"Digital Compared with Screen-Film Mammography: Performance Measures in Concurrent Cohorts within an Organized Breast Screening Program","volume":"268","author":"Chiarelli","year":"2013","journal-title":"Radiology"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"874","DOI":"10.1007\/s00330-015-3885-y","article-title":"Breast Cancer Detection Rates Using Four Different Types of Mammography Detectors","volume":"26","author":"Mackenzie","year":"2016","journal-title":"Eur. Radiol."},{"key":"ref_31","unstructured":"Perry, N., Broeders, M., de Wolf, C., T\u00f6rnberg, S., Holland, R., and von Karsa, L. (2013). EUREF European Guidelines for Quality Assurance in Breast Cancer Screening and Diagnosis, Office for Official Publications of the European Communities."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"20230104","DOI":"10.1259\/bjr.20230104","article-title":"Successes and Challenges in Extracting Information from DICOM Image Databases for Audit and Research","volume":"96","author":"Mackenzie","year":"2023","journal-title":"Br. J. Radiol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1537","DOI":"10.1118\/1.1916183","article-title":"Extracting Data from a DICOM File","volume":"32","author":"Riddle","year":"2005","journal-title":"Med. Phys."},{"key":"ref_34","first-page":"280","article-title":"Quality of DICOM Header Information for Image Categorization","volume":"Volume 4685","author":"Gueld","year":"2002","journal-title":"Proceedings of the Medical Imaging 2002: PACS and Integrated Medical Information Systems: Design and Evaluation, San Diego, CA, USA, 26\u201328 February 2002"},{"key":"ref_35","unstructured":"Santos, M., Basti\u00e3o, L., Costa, C., Silva, A., and Rocha, N. (2013). Clinical Data Mining in Small Hospital PACS: Contributions for Radiology Department Improvement. Healthcare Administration: Concepts, Methodologies, Tools, and Applications, IGI Global. Chapter 16."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/12\/1842\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T01:09:13Z","timestamp":1781485753000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/12\/1842"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,14]]},"references-count":35,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["diagnostics16121842"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16121842","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,14]]}}}