Kenneth C. Young
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Kenneth C. Young has a total of 149 co-authors. Here are the top co-authors by number of shared publications:
- Alistair Mackenzie
Royal Surrey NHS Foundation Trust, Guildford GU2 7XX, UK
12 shared publications David R. Dance
National Coordinating Centre for the Physics in Mammography, Royal Surrey NHS Foundation Trust, Guildford, UK
8 shared publications- David R. Dance
National Coordinating Centre for the Physics in Mammography (NCCPM), Level B, St Luke's Wing, Royal Surrey County Hospital, Guildford GU2 7XX, UK; Department of Physics, University of Surrey, Guildford GU2 7XH, UK
5 shared publications - Hilde Bosmans
Department of Imaging and Pathology, KU Leuven, Leuven, Belgium
5 shared publications - Lucy M. Warren
National Co-ordinating Centre for the Physics of Mammography, Royal Surrey County Hospital NHS Foundation Trust, Guildford GU2 7XX, UK
5 shared publications Lucy M. Warren
National Coordinating Centre for the Physics in Mammography, Royal Surrey NHS Foundation Trust, Guildford, UK
4 shared publications
Latest Publications
- Top Cited PapersOpen Access
- 10 March 2026
- Published by Springer Nature in Nature Cancer
- Vol. 7 (3) , 494-506
Diagnostic accuracy, fairness and clinical implementation of AI for breast cancer screening: results of multicenter retrospective and prospective technical feasibility studies
Artificial intelligence (AI) promises to enhance breast cancer screening. Here we evaluated Google’s mammography AI system (version 1.2) across two phases: a retrospective study using 115,973 mammograms from five National Health Service screening services with 39-month follow-up and prospective noninterventional feasibility deployment at 12 sites (9,266 cases). The primary endpoint was AI sensitivity and specificity versus first reader using a 5% noninferiority margin. The secondary endpoints were performance versus second or consensus readers and breast-level analyses. Retrospectively, AI achieved superior sensitivity (0.541 versus 0.437 for first reader, P < 0.001) and noninferior specificity (0.943 versus 0.952, P < 0.001). Cancer detection rate increased from 7.54 to 9.33 per 1,000 women, with AI detecting 25.0% of interval cancers. Performance was particularly strong for first screens (39.3% fewer recalls, 8.8% higher detection) and invasive cancers. No systematic demographic disparities were observed. Simulated second-reader replacement reduced reading time by 32% while increasing detection by 17.7%. Prospective deployment confirmed technical feasibility but revealed a distribution shift requiring threshold recalibration. Implementation requires adaptive calibration and continuous monitoring to ensure safety and equity.
- 10 March 2026
- Published by Springer Nature in Nature Cancer
- Vol. 7 (3) , 494-506
Top Cited PapersOpen AccessDiagnostic accuracy, fairness and clinical implementation of AI for breast cancer screening: results of multicenter retrospective and prospective technical feasibility studies
Artificial intelligence (AI) promises to enhance breast cancer screening. Here we evaluated Google’s mammography AI system (version 1.2) across two phases: a retrospective study using 115,973 mammograms from five National Health Service screening services with 39-month follow-up and prospective noninterventional feasibility deployment at 12 sites (9,266 cases). The primary endpoint was AI sensitivity and specificity versus first reader using a 5% noninferiority margin. The secondary endpoints were performance versus second or consensus readers and breast-level analyses. Retrospectively, AI achieved superior sensitivity (0.541 versus 0.437 for first reader, P < 0.001) and noninferior specificity (0.943 versus 0.952, P < 0.001). Cancer detection rate increased from 7.54 to 9.33 per 1,000 women, with AI detecting 25.0% of interval cancers. Performance was particularly strong for first screens (39.3% fewer recalls, 8.8% higher detection) and invasive cancers. No systematic demographic disparities were observed. Simulated second-reader replacement reduced reading time by 32% while increasing detection by 17.7%. Prospective deployment confirmed technical feasibility but revealed a distribution shift requiring threshold recalibration. Implementation requires adaptive calibration and continuous monitoring to ensure safety and equity.
- Top Cited PapersOpen Access
- 10 March 2026
- Published by Springer Nature in Nature Cancer
- Vol. 7 (3) , 507-521
Impact of using artificial intelligence as a second reader in breast screening including arbitration
The impact of incorporating artificial intelligence (AI) into a double-read breast-screening workflow, including arbitration, is unclear. This retrospective study included 50,000 representative women from two NHS breast-screening centers. All the women had long-term follow-up, allowing us to determine whether use of AI leads to earlier cancer detection. Cases requiring arbitration (8,732 cases) were read by 22 readers in a reader study, following their normal arbitration workflow. Overall, after arbitration, replacing the second reader with AI was noninferior (5% margin) to two human readers in terms of sensitivity and specificity ( P < 0.001) while offering a workload benefit. Arbitration improved the specificity of the AI arm by overruling cases incorrectly recalled by the AI tool; however, it also overruled the AI tool recall decision for some interval and next-round cancers. Further development of the AI tool alongside improvement in its explainability could lead to the earlier detection of cancers.
- 10 March 2026
- Published by Springer Nature in Nature Cancer
- Vol. 7 (3) , 507-521
Top Cited PapersOpen AccessImpact of using artificial intelligence as a second reader in breast screening including arbitration
The impact of incorporating artificial intelligence (AI) into a double-read breast-screening workflow, including arbitration, is unclear. This retrospective study included 50,000 representative women from two NHS breast-screening centers. All the women had long-term follow-up, allowing us to determine whether use of AI leads to earlier cancer detection. Cases requiring arbitration (8,732 cases) were read by 22 readers in a reader study, following their normal arbitration workflow. Overall, after arbitration, replacing the second reader with AI was noninferior (5% margin) to two human readers in terms of sensitivity and specificity ( P < 0.001) while offering a workload benefit. Arbitration improved the specificity of the AI arm by overruling cases incorrectly recalled by the AI tool; however, it also overruled the AI tool recall decision for some interval and next-round cancers. Further development of the AI tool alongside improvement in its explainability could lead to the earlier detection of cancers.
- 1 July 2024
- Published by Radiological Society of North America (RSNA) in Radiology: Artificial Intelligence
- Vol. 6 (4) , e230431
Deep Learning for Breast Cancer Risk Prediction: Application to a Large Representative UK Screening Cohort
"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop an artificial intelligence (AI) deep learning tool capable of predicting future breast cancer risk from a current negative screening mammographic examination and to evaluate the model on data from the UK National Health Service Breast Screening Program. Materials and Methods The OPTIMAM Mammography Imaging Database contains screening data, including mammograms and information on interval cancers, for > 300,000 women who attended screening at three different sites in the UK from 2012 onward. Cancer-free screening examinations from women aged 50-70 years were obtained and classified as risk-positive or risk-negative based on the occurrence of cancer within 3 years of the original examination. Examinations with confirmed cancer and images containing implants were excluded. From the resulting 5264 risk-positive and 191488 risk-negative examinations, training (n = 89285) validation (n = 2106) and test (n = 39351) datasets were produced for model development and evaluation. The AI model was trained to predict future cancer occurrence based on screening mammograms and patient age. Performance was evaluated on the test dataset using the area under the receiver operating characteristic curve (AUC) and compared across subpopulations to assess potential biases. Interpretability of the model was explored, including with saliency maps. Results On the hold-out test set, the AI model achieved an overall AUC of 0.70 (95% CI: 0.69, 0.72). There was no evidence of a difference in performance across the three sites, between patient ethnicities or across age-groups Visualization of saliency maps and sample images provided insights into the mammographic features associated with AI-predicted cancer risk. Conclusion The developed AI tool showed good performance on a multisite, UK-specific dataset. ©RSNA, 2024.
- 1 July 2024
- Published by Radiological Society of North America (RSNA) in Radiology: Artificial Intelligence
- Vol. 6 (4) , e230431
Deep Learning for Breast Cancer Risk Prediction: Application to a Large Representative UK Screening Cohort
"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop an artificial intelligence (AI) deep learning tool capable of predicting future breast cancer risk from a current negative screening mammographic examination and to evaluate the model on data from the UK National Health Service Breast Screening Program. Materials and Methods The OPTIMAM Mammography Imaging Database contains screening data, including mammograms and information on interval cancers, for > 300,000 women who attended screening at three different sites in the UK from 2012 onward. Cancer-free screening examinations from women aged 50-70 years were obtained and classified as risk-positive or risk-negative based on the occurrence of cancer within 3 years of the original examination. Examinations with confirmed cancer and images containing implants were excluded. From the resulting 5264 risk-positive and 191488 risk-negative examinations, training (n = 89285) validation (n = 2106) and test (n = 39351) datasets were produced for model development and evaluation. The AI model was trained to predict future cancer occurrence based on screening mammograms and patient age. Performance was evaluated on the test dataset using the area under the receiver operating characteristic curve (AUC) and compared across subpopulations to assess potential biases. Interpretability of the model was explored, including with saliency maps. Results On the hold-out test set, the AI model achieved an overall AUC of 0.70 (95% CI: 0.69, 0.72). There was no evidence of a difference in performance across the three sites, between patient ethnicities or across age-groups Visualization of saliency maps and sample images provided insights into the mammographic features associated with AI-predicted cancer risk. Conclusion The developed AI tool showed good performance on a multisite, UK-specific dataset. ©RSNA, 2024.
- 7 September 2022
- Published by World Scientific Pub Co Pte Ltd
- p. 587-603
Perspectives on the Development of Physics in the 21st Century
- 7 September 2022
- Published by World Scientific Pub Co Pte Ltd
- p. 587-603
Perspectives on the Development of Physics in the 21st Century
- 1 July 2022
- Published by Oxford University Press (OUP) in British Journal of Radiology
- Vol. 95 (1135) , 20211400
Radiation doses in the United Kingdom breast screening programmes 2016–2019
Objectives: To record the radiation doses involved in UK breast screening and to identify any changes since previous publications related to technical factors and the population screened. Methods: Mammographic exposure factors for 68,998 women imaged using 411 X-ray sets spread across the UK were compiled. Local output and half value layer measurements for each X-ray set were used to estimate mean glandular dose (MGD) using the standard UK method. Results: Mean MGDs in digital mammography have increased by 11% since 2010–12 for both medio-lateral oblique (MLO) and cranio-caudal (CC) views. The mean compressed breast thickness (CBT) has increased (4.8% CC, 5.2% MLO) over the same period. The mean MLO CBT value of 62.4 ± 0.1 mm is outside the 50 to 60 mm range used for diagnostic reference levels. The increase in MGD is consistent with the CBT changes. The mean MGD in the 50 to 60 mm CBT range is 1.44 ± 0.03 mGy for MLO views. CBT varies with age and peaks at 51. Conclusions: Mean CBT has increased with time, and this has increased mean MGDs for digital mammography. CBT also varies with age. Advances in knowledge: Updated average MGDs in the UK are provided. There is evidence that breast size is increasing in the UK and that mean CBT is affected by age-related changes in the breast.
- 1 July 2022
- Published by Oxford University Press (OUP) in British Journal of Radiology
- Vol. 95 (1135) , 20211400
Radiation doses in the United Kingdom breast screening programmes 2016–2019
Objectives: To record the radiation doses involved in UK breast screening and to identify any changes since previous publications related to technical factors and the population screened. Methods: Mammographic exposure factors for 68,998 women imaged using 411 X-ray sets spread across the UK were compiled. Local output and half value layer measurements for each X-ray set were used to estimate mean glandular dose (MGD) using the standard UK method. Results: Mean MGDs in digital mammography have increased by 11% since 2010–12 for both medio-lateral oblique (MLO) and cranio-caudal (CC) views. The mean compressed breast thickness (CBT) has increased (4.8% CC, 5.2% MLO) over the same period. The mean MLO CBT value of 62.4 ± 0.1 mm is outside the 50 to 60 mm range used for diagnostic reference levels. The increase in MGD is consistent with the CBT changes. The mean MGD in the 50 to 60 mm CBT range is 1.44 ± 0.03 mGy for MLO views. CBT varies with age and peaks at 51. Conclusions: Mean CBT has increased with time, and this has increased mean MGDs for digital mammography. CBT also varies with age. Advances in knowledge: Updated average MGDs in the UK are provided. There is evidence that breast size is increasing in the UK and that mean CBT is affected by age-related changes in the breast.
- 8 June 2022
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 9 (03) , 033504-19
Development of an algorithm to convert mammographic images to appear as if acquired with different technique factors
A key step in the setting up of a mammography system is optimization, i.e., to ensure that the quality of the images is sufficient for an accurate diagnosis for as low a dose as reasonably practicable. There are a number of choices of factors to be made in optimization such as the tube voltage, anode, and filter materials, the use of an anti-scatter grid, and the air kerma at the detector. The technique factors will affect the signal level and the difference in signal between adipose and glandular tissues and any lesions. Noise arising from the detector can affect the visibility of low contrast objects in an image. The dominant detector noise is quantum noise, which is dependent on the signal level and x-ray spectra incident on the detector.1 A method used for optimization of the tube voltage and anode/filter combination for mammography is to image a block of polymethyl methacrylate (PMMA) with a low-contrast object, such as 0.2-mm thick aluminum, over a range of technique factors and use a figure of merit based on the contrast-to-noise ratio (CNR) and breast dose.2,3 Such measurements have indicated that digital systems should use anode/filter combinations that produce higher beam energies than those traditionally used in screen/film mammography (e.g., molybdenum/molybdenum or molybdenum/rhodium).3
- 8 June 2022
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 9 (03) , 033504-19
Development of an algorithm to convert mammographic images to appear as if acquired with different technique factors
A key step in the setting up of a mammography system is optimization, i.e., to ensure that the quality of the images is sufficient for an accurate diagnosis for as low a dose as reasonably practicable. There are a number of choices of factors to be made in optimization such as the tube voltage, anode, and filter materials, the use of an anti-scatter grid, and the air kerma at the detector. The technique factors will affect the signal level and the difference in signal between adipose and glandular tissues and any lesions. Noise arising from the detector can affect the visibility of low contrast objects in an image. The dominant detector noise is quantum noise, which is dependent on the signal level and x-ray spectra incident on the detector.1 A method used for optimization of the tube voltage and anode/filter combination for mammography is to image a block of polymethyl methacrylate (PMMA) with a low-contrast object, such as 0.2-mm thick aluminum, over a range of technique factors and use a figure of merit based on the contrast-to-noise ratio (CNR) and breast dose.2,3 Such measurements have indicated that digital systems should use anode/filter combinations that produce higher beam energies than those traditionally used in screen/film mammography (e.g., molybdenum/molybdenum or molybdenum/rhodium).3
- 30 July 2021
- Published by Springer Nature in European Radiology
- Vol. 32 (2) , 806-814
Virtual clinical trial to compare cancer detection using combinations of 2D mammography, digital breast tomosynthesis and synthetic 2D imaging
Objectives This study was designed to compare the detection of subtle lesions (calcification clusters or masses) when using the combination of digital breast tomosynthesis (DBT) and synthetic mammography (SM) with digital mammography (DM) alone or combined with DBT. Methods A set of 166 cases without cancer was acquired on a DBT mammography system. Realistic subtle calcification clusters and masses in the DM images and DBT planes were digitally inserted into 104 of the acquired cases. Three study arms were created: DM alone, DM with DBT and SM with DBT. Five mammographic readers located the centre of any lesion within the images that should be recalled for further investigation and graded their suspiciousness. A JAFROC figure of merit (FoM) and lesion detection fraction (LDF) were calculated for each study arm. The visibility of the lesions in the DBT images was compared with SM and DM images. Results For calcification clusters, there were no significant differences (p > 0.075) in FoM or LDF. For masses, the FoM and LDF were significantly improved in the arms using DBT compared to DM alone (p < 0.001). On average, both calcification clusters and masses were more visible on DBT than on DM and SM images. Conclusions This study demonstrated that masses were detected better with DBT than with DM alone and there was no significant difference (p = 0.075) in LDF between DM&DBT and SM&DBT for calcifications clusters. Our results support previous studies that it may be acceptable to not acquire digital mammography alongside tomosynthesis for subtle calcification clusters and ill-defined masses. Key Points • The detection of masses was significantly better using DBT than with digital mammography alone. • The detection of calcification clusters was not significantly different between digital mammography and synthetic 2D images combined with tomosynthesis. • Our results support previous studies that it may be acceptable to not acquire digital mammography alongside tomosynthesis for subtle calcification clusters and ill-defined masses for the imaging technology used.
- 30 July 2021
- Published by Springer Nature in European Radiology
- Vol. 32 (2) , 806-814
Virtual clinical trial to compare cancer detection using combinations of 2D mammography, digital breast tomosynthesis and synthetic 2D imaging
Objectives This study was designed to compare the detection of subtle lesions (calcification clusters or masses) when using the combination of digital breast tomosynthesis (DBT) and synthetic mammography (SM) with digital mammography (DM) alone or combined with DBT. Methods A set of 166 cases without cancer was acquired on a DBT mammography system. Realistic subtle calcification clusters and masses in the DM images and DBT planes were digitally inserted into 104 of the acquired cases. Three study arms were created: DM alone, DM with DBT and SM with DBT. Five mammographic readers located the centre of any lesion within the images that should be recalled for further investigation and graded their suspiciousness. A JAFROC figure of merit (FoM) and lesion detection fraction (LDF) were calculated for each study arm. The visibility of the lesions in the DBT images was compared with SM and DM images. Results For calcification clusters, there were no significant differences (p > 0.075) in FoM or LDF. For masses, the FoM and LDF were significantly improved in the arms using DBT compared to DM alone (p < 0.001). On average, both calcification clusters and masses were more visible on DBT than on DM and SM images. Conclusions This study demonstrated that masses were detected better with DBT than with DM alone and there was no significant difference (p = 0.075) in LDF between DM&DBT and SM&DBT for calcifications clusters. Our results support previous studies that it may be acceptable to not acquire digital mammography alongside tomosynthesis for subtle calcification clusters and ill-defined masses. Key Points • The detection of masses was significantly better using DBT than with digital mammography alone. • The detection of calcification clusters was not significantly different between digital mammography and synthetic 2D images combined with tomosynthesis. • Our results support previous studies that it may be acceptable to not acquire digital mammography alongside tomosynthesis for subtle calcification clusters and ill-defined masses for the imaging technology used.
- 1 October 2020
- Published by Elsevier in European Journal of Radiology
- Vol. 131, 109216
Mammography dose estimates do not reflect any specific patient's breast dose
- 1 October 2020
- Published by Elsevier in European Journal of Radiology
- Vol. 131, 109216
Mammography dose estimates do not reflect any specific patient's breast dose
- 23 March 2019
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 6 (01) , 015503-8
Model and human observer reproducibility for detection of microcalcification clusters in digital breast tomosynthesis images of three-dimensionally structured test object
We compare the reproducibility of the human observers and a channelized Hotelling observer (CHO), when reading digital breast tomosynthesis (DBT) images of a physical phantom containing a breast simulating structured background and calcification clusters at three dose levels. The phantom is scanned 217 times on a Siemens Inspiration DBT system. Volumes of interest, with and without the calcification targets, are extracted and the human observers’ percentage of correct (PC) scores is evaluated using a four-alternative forced choice method. A two-layer CHO is developed using the human observer results. The first layer consists of a localizing CHO that identifies the most conspicuous calcifications using two Laguerre–Gauss channels. Then a CHO with eight Gabor channels estimates the PC score for the calcification cluster. Observer reproducibility is estimated by bootstrapping, and the standard deviation (SD) is used as a figure of merit. The CHO closely approximated the human observer results for all the three dose levels with a correlation of >0.97. For the larger calcification cluster sizes, both observers have similar reproducibility, whereas the CHO is more reproducible for the smaller calcifications, with a maximum of 5.5 SD against 13.1 SD for the human observers. The developed CHO is a good candidate for automated reading of the calcification clusters of the structured phantom, with better reproducibility than the human readers for small calcifications.
- 23 March 2019
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 6 (01) , 015503-8
Model and human observer reproducibility for detection of microcalcification clusters in digital breast tomosynthesis images of three-dimensionally structured test object
We compare the reproducibility of the human observers and a channelized Hotelling observer (CHO), when reading digital breast tomosynthesis (DBT) images of a physical phantom containing a breast simulating structured background and calcification clusters at three dose levels. The phantom is scanned 217 times on a Siemens Inspiration DBT system. Volumes of interest, with and without the calcification targets, are extracted and the human observers’ percentage of correct (PC) scores is evaluated using a four-alternative forced choice method. A two-layer CHO is developed using the human observer results. The first layer consists of a localizing CHO that identifies the most conspicuous calcifications using two Laguerre–Gauss channels. Then a CHO with eight Gabor channels estimates the PC score for the calcification cluster. Observer reproducibility is estimated by bootstrapping, and the standard deviation (SD) is used as a figure of merit. The CHO closely approximated the human observer results for all the three dose levels with a correlation of >0.97. For the larger calcification cluster sizes, both observers have similar reproducibility, whereas the CHO is more reproducible for the smaller calcifications, with a maximum of 5.5 SD against 13.1 SD for the human observers. The developed CHO is a good candidate for automated reading of the calcification clusters of the structured phantom, with better reproducibility than the human readers for small calcifications.
- 1 October 2018
- Published by Oxford University Press (OUP) in British Journal of Radiology
- Vol. 91 (1090) , 20170246
Mammography cancer detection: comparison of single 8MP and pair of 5MP reporting monitors
Objective:To compare breast cancer detection using a single 8MP display with using a standard pair of 5MP monitors.Methods:An observer study was carried out in which mammograms were read using full field views only, and again with the additional use of magnified quadrant views. Seven observers read 300 cases, one view per breast, using each display type. Cases comprised 100 normal cases and 200 cases with cancers of subtle or very subtle appearance: 100 with malignant calcification clusters and 100 with non-calcified lesions. JAFROC software was used to analyse the results.Results:When mammograms were viewed full field only, observers performed better (p = 0.050) in detecting malignant calcification clusters when using the pair of 5MP monitors compared with a single 8MP monitor. This result became non-significant when results were generalised to a population of readers.Performance in detecting calcification clusters was improved by using quadrant view in addition to full field view when using either the p...
- 1 October 2018
- Published by Oxford University Press (OUP) in British Journal of Radiology
- Vol. 91 (1090) , 20170246
Mammography cancer detection: comparison of single 8MP and pair of 5MP reporting monitors
Objective:To compare breast cancer detection using a single 8MP display with using a standard pair of 5MP monitors.Methods:An observer study was carried out in which mammograms were read using full field views only, and again with the additional use of magnified quadrant views. Seven observers read 300 cases, one view per breast, using each display type. Cases comprised 100 normal cases and 200 cases with cancers of subtle or very subtle appearance: 100 with malignant calcification clusters and 100 with non-calcified lesions. JAFROC software was used to analyse the results.Results:When mammograms were viewed full field only, observers performed better (p = 0.050) in detecting malignant calcification clusters when using the pair of 5MP monitors compared with a single 8MP monitor. This result became non-significant when results were generalised to a population of readers.Performance in detecting calcification clusters was improved by using quadrant view in addition to full field view when using either the p...