References

Peer Reviewed Journal Publications

Possible strategies for use of artificial intelligence in screen-reading of mammograms, based on retrospective data from 122,969 screening examinations

Conclusion: Several theoretical scenarios with Transpara and radiologists have the potential to reduce the volume in screen-reading without affecting cancer detection substantially. Possible influence on recall and interval cancers must be evaluated in prospective studies.

Authors: M. Larsen, C.F. Aglen, S.R. Hoff, H. Lund-Hanssen, S. Hofvind

Publication: European Radiology 2022

Affiliation of Authors: Norway, The Netherlands

Data Source: Norway

View Publication

An AI-based Mammography Screening Protocol: Outcome and Radiologists Workload

Conclusion: Transpara could detect normal, moderate-risk, and suspicious mammograms in a breast cancer screening program, which may reduce the radiologist workload. Transpara performed consistently across breast densities.

 

Authors: Lauritzen A, Rodríguez-Ruiz von Euler-Chelpin MC, Lynge E, Vejborg I, Jensen AKG, Nielsen M, Karssemeijer N, Lillholm M

Publication: Radiology 2022

Affiliation of Authors: Denmark

Data Source: Denmark

View Publication

Artificial Intelligence Evaluation of 122 969 Mammography Examinations from a Population-based Screening Program

Conclusion: The proportion of screen-detected cancers not selected by Transpara at three evaluated thresholds was less than 20%. According to cancer detection, the overall performance of Transpara was promising.

Authors: Larsen M, Flåt Aglen C, Lee C, Roth Hoff S, Lund-Hanssen H, Lång K, Nygård J, Ursin G, Hofvind S

Publication: Radiology 2022

Affiliation of Authors: Norway

Data Source: Norway

View Publication

Interval Cancer Detection Using a Neural Network and Breast Density in Women with Negative Screening Mammograms

Conclusion: The combined assessment of the Transpara score and breast density measurements enabled identification of a larger proportion of women who would develop interval cancer compared with either method alone.

Authors: Wanders A, Mees W, Bun P, Janssen N, Rodríguez-Ruiz A, Ufuk Dalmış M, Karssemeijer N, van Gils C, Sechopoulos I, Mann R, van Rooden C

Publication: Radiology 2022

Affiliation of Authors: The Netherlands

Data Source: The Netherlands

View Publication

Stand-Alone Use of Artificial Intelligence for Digital Mammography and Digital Breast Tomosynthesis Screening: A Retrospective Evaluation

Conclusion: Transpara could replace radiologists’ readings in breast screening, achieving a noninferior sensitivity, with a lower recall rate for digital mammography but a higher recall rate for digital breast tomosynthesis.

Authors: J.L. Raya-Povedano, S. Romero-Martín, E. Elías-Cabot, A. Gubern-Mérida, A. Rodríguez-Ruiz, M. Álvarez-Benito

Publication: Radiology Dec 2021

Affiliation of Authors: Spain

Data Source: Spain

View Publication

Using deep learning to assist readers during the arbitration process: a lesion-based retrospective evaluation of breast cancer screening performance

Authors: Kerschke L, Weigel S, Rodriguez-Ruiz A, Karssemeijer N, Heindel W

Publication: European Radiology 2021

Affiliation of Authors: Germany, the Netherlands

Data Source:

View Publication

Impact of Artificial Intelligence Decision Support Using Deep Learning on Breast Cancer Screening Interpretation with Single-View Wide-Angle Digital Breast Tomosynthesis

Conclusion: Using a single-view digital breast tomosynthesis (DBT) and artificial intelligence setup could allow for a more effective screening program with higher performance, especially in terms of an increase in cancers detected, than using single-view DBT alone.

Authors: M.C. Pinto, A. Rodriguez-Ruiz, K. Pedersen, S. Hofvind, J. Wicklein, S. Kappler, R. M. Mann, I. Sechopoulos

Publication: Radiology 2021; 000:1–8

Affiliation of Authors: Germany, the Netherlands, Norway, Spain

Data Source: The Netherlands

View Publication

AI-based Strategies to Reduce Workload in Breast Cancer Screening with Mammography and Tomosynthesis: a retrospective evaluation.

Conclusion: Transpara breast AI can help reduce radiologists’ workload by up to 70% in both 2D and 3D mammography, without reducing the quality of the screening program

Authors: J.L. Raya-Povedano, S. Romero-Martín, E. Elías-Cabot, A. Gubern-Mérida, A. Rodríguez-Ruiz, M. Álvarez-Benito

Publication: Radiology: 1–9 (2021)

Affiliation of Authors: Spain, the Netherlands

Data Source: Spain

View Publication

Impact of artificial intelligence support on accuracy and reading time in breast tomosynthesis image interpretation : a multi-reader multi-case study

Conclusion: Radiologists improved their cancer detection accuracy in digital breast tomosynthesis (DBT) when using an AI system for support, while simultaneously reducing reading time.

 

Authors: S.L. van Winkel, A. Rodríguez-Ruiz, L. Appelman, A. Gubern-Mérida, N. Karssemeijer, J. Teuwen, A.J.T. Wanders, I. Sechopoulos, R.M. Mann

Publication: European Radiology 2021

Affiliation of Authors: The Netherlands

Data Source: USA

View Publication

Can artificial intelligence reduce the interval cancer rate in mammography screening?

Conclusion: The use of AI in screen reading has the potential to reduce the rate of interval cancer without supplementary screening modalities.

Authors: K. Lång, S. Hofvind, A. Rodríguez-Ruiz, I. Andersson

Publication: European Radiology 2021

Affiliation of Authors: Sweden, Norway, the Netherlands

Data Source: 4 screening sites in Sweden

View Publication

Artificial intelligence for breast cancer detection in mammography: experience of use of the ScreenPoint Medical Transpara system in 310 Japanese women Breast Cancer

Conclusion: Transpara showed a high performance in a study population of women with dense breasts.

 

Authors: M. Sasaki, M. Tozaki, A. Rodríguez-Ruiz, D. Yotsumoto, Y. Ichiki, A. Terawaki, S. Oosako, Y. Sagara, Y. Sagara

Publication: Breast Cancer: 27, 642–651 (2020)

Affiliation of Authors: Japan, the Netherlands

Data Source: Japan

View Publication

Identifying normal mammograms in a large screening population using artificial intelligence

Conclusion: Transpara has the potential to improve mammography screening efficiency by correctly identifying a proportion of a screening population as cancer-free, and reducing false positives.

Authors: 5. K. Lång, M. Dustler, V. Dahlblom, A. Åkesson, I. Andersson, S. Zackrisson

Publication: European Radiology: 31(3): 1687-1692 (2020)

Affiliation of Authors: Sweden

Data Source: Sweden

View Publication

Can we reduce the workload of mammographic screening by automatic identification of normal exams with artificial intelligence? A feasibility study

Conclusion: It is possible to automatically pre-select exams using Transpara to significantly reduce the breast cancer screening reading workload without affecting screening outcomes.

 

Authors: A. Rodriguez-Ruiz, K. Lång, A. Gubern-Merida, J. Teuwen, M. Broeders, G. Gennaro, P. Clauser, T. Helbich, M. Chevalier, T. Mertelmeier, M.G. Wallis, I. Andersson, S. Zackrisson, I. Sechopoulos, R.M. Mann

Publication: European Radiology: 29, 4825–4832 (2019)

Affiliation of Authors: the Netherlands, Sweden, Italy, Switzerland, Austria, Spain, Germany, UK

Data Source: the Netherlands, Sweden, Italy, Switzerland, Austria, Spain, Germany, USA

View Publication

Detection of breast cancer using mammography: Impact of an Artificial Intelligence support system

Conclusion: Radiologists improved their cancer detection performance at mammography when using Transpara for support, without requiring additional reading time.

 

Authors: A. Rodriguez-Ruiz, E. Krupinski, J-J. Mordang, K. Schilling, S.H. Heywang-Köbrunner, I. Sechopoulos, R.M. Mann 

Publication: Radiology: 290 (2), 305-314 (2019)

Affiliation of Authors: the Netherlands, USA, Germany

Data Source: US, Germany

View Publication

Stand-alone artificial intelligence for breast cancer detection in mammography: Comparison with 101 radiologists

Conclusion: Transpara achieved a cancer detection accuracy comparable to an average breast radiologist in this retrospective setting.

Authors: A. Rodriguez-Ruiz, K. Lång, A. Gubern-Merida, M. Broeders, G. Gennaro, P. Clauser, T. Helbich, M. Chevalier, T. Tan, T. Mertelmeier, W. Wallis, I. Andersson, S. Zackrisson, R. Mann, I. Sechopoulos 

Publication: Journal of the National Cancer Institute: 111(9):djy222 (2019)

Affiliation of Authors: the Netherlands, Switzerland, Italy, Austria, Spain, UK, Sweden, USA, Germany

Data Source: the Netherlands, Sweden, Italy, Switzerland, Austria, Spain, Germany, USA

View Publication

International Conference Proceedings

Robust multi-vendor breast region segmentation using deep learning

Conclusion: Transpara can provide robust breast region segmentations in a multimodal multi-vendor setting.

Authors: K Dercksen, M Kallenberg, J Kroes

Publication: Proc. SPIE 11513, 15th International Workshop on Breast Imaging (IWBI2020), 115131A (22 May 2020); doi: 10.1117/12.2564108

Affiliation of Authors: The Netherlands

Data Source: The Netherlands

View Publication

Artificial intelligence together with mechanical imaging in mammography

 

Conclusion: Mechanical imaging (MI) estimates the relative stiffness of suspicious breast abnormalities by measuring the distribution of pressure on the compressed breast. MI combined with Transpara has the potential to increase the accuracy of mammography screening.

 

Authors: Bejnö, G. Hellgren, A. Rodriguez-Ruiz, P. R. Bakic, S. Zackrisson, A. Tingberg, M. Dustler

Publication: Proc. SPIE 11513, 15th International Workshop on Breast Imaging (IWBI2020), 1151320 (22 May 2020); doi: 10.1117/12.2564107

Affiliation of Authors: Sweden, the Netherlands, USA

Data Source: Sweden

View Publication

Can AI serve as an independent second reader of mammograms? a simulation study

Conclusion: Using Transpara as a second reader in a double reading setting, workload could be reduced by 44%, without an impact in sensitivity and with a possible specificity increase by 5.3%.

Authors: Rodríguez-Ruiz, K. Lång, A. Gubern-Merida, M. Broeders, G. Gennaro, P. Clauser, T. Helbich, T. Mertelmeier, M. Chevalier, M. Wallis, I. Andersson, S. Zackrisson, R. M. Mann, I. Sechopoulos

Publication: Proc. SPIE 11513, 15th International Workshop on Breast Imaging (IWBI2020), 115130O (22 May 2020); doi: 10.1117/12.2564114

Affiliation of Authors: the Netherlands, Switzerland, Italy, Austria, Spain, UK, Sweden, USA, Germany

Data Source: the Netherlands, Sweden, Italy, Switzerland, Austria, Spain, Germany, USA

View Publication

Personalised breast cancer screening with selective addition of digital breast tomosynthesis through artificial intelligence

Conclusion: Using DBT only for cases marked as highly suspicious by Transpara in mammography could be an alternative to a complete DBT screening. If adding DBT for women with Transpara Score 10 in mammography, 12% of the women would have DBT added and 26% more cancers would be detected, with a 21% increase in false positives.

Authors: V. Dahlblom, A. Tingberg, S. Zackrisson, M. Dustler

Publication: Proc. SPIE 11513, 15th International Workshop on Breast Imaging (IWBI2020), 115130C (22 May 2020); doi: 10.1117/12.2564344

Affiliation of Authors: Sweden

Data Source: Sweden

View Publication

The effect of breast density on the performance of deep learning-based breast cancer detection methods for mammography

Conclusion: Transpara risk categorization is not affected by density. Transpara has the potential to improve screening sensitivity even for women with high breast density.

Authors: M. Dustler, V. Dahlblom, A. Tingberg, S. Zackrisson

Publication: Proc. SPIE 11513, 15th International Workshop on Breast Imaging (IWBI2020), 1151324 (22 May 2020); doi: 10.1117/12.2564328

Affiliation of Authors: Sweden

Data Source: Sweden

View Publication

Going from double to single reading for screening exams labeled as likely normal by AI: what is the impact?

Conclusion: Transpara can improve breast cancer screening efficiency by pre-selecting likely normal exams where double-reading can be safely replaced by single reading resulting in 32.6% reading workload reduction.

Authors: C. Balta, A. Rodriguez-Ruiz, C. Mieskes, N. Karssemeijer, S. H. Heywang-Köbrunner

Publication: Proc. SPIE 11513, 15th International Workshop on Breast Imaging (IWBI2020), 115130D (22 May 2020); doi: 10.1117/12.2564179

Affiliation of Authors: the Netherlands, Germany

Data Source: Germany

View Publication

European Congress of Radiology

Evaluation of the performance of artificial intelligence (AI) after one year of use in breast cancer screening practice: is the promise being delivered?

Conclusion: Using Transpara concurrently in clinical practice allows to stratify examinations according to probability of cancer. Transpara increases cancer detection rate and positive predictive value of the recalled women.

Authors: Elías Cabot E, Romero Martin S, Raya Povedano JL, Gubern-Merida A, Álvarez Benítez MAB

Publication: ECR 2022

Affiliation of Authors: Spain, the Netherlands

Data Source: Spain

Reduced workload for breast radiologists: results from a retrospective study using artificial intelligence in mammographic screening

Conclusion: We found in a retrospective analysis that Transpara as a replacement for a second radiologist in a double reading setting would have decreased the radiologist workload without impacting cancer detection. However, prospective studies are needed to identify the optimal combinations of Transpara and radiologists in double reading setting.

Authors: Larsen M, Flåt Aglen C, Lee CI, Roth Hoff S, Lund-Hanssen H, Lang K, Nygård J, Ursin G, Hofvind S

Publication: ECR 2022

Affiliation of Authors: Norway, the Netherlands

Data Source: Norway

AI-based strategy to reduce the recall rate and consensus meeting workload of double reading in breast cancer screening with digital mammography: a retrospective evaluation

Conclusion: Not reading exams with Transpara score 1-6 can reduce radiologists’ RR and workload in screening at the cost of missing some screen-detected cancers. However, recalling the top 1% might compensate this loss in CDR. Transpara-assisted double reading of all exams can potentially lower the RR and increase the CDR, but prospective studies should confirm this.

Authors: Hamm K, Hellingman D, Kotrini L, Vetter B, Jordan T, Entrup C, Engelke M, Janssen N, Schubotz B

Publication: ECR 2022

Affiliation of Authors: Germany, the Netherlands

Data Source: Germany

Implementing AI to predict interval cancers in a national screening program

Conclusion: Transpara has the potential to reduce the stable high rate of interval cancer in case it is applied as a second or third independent reader within a national breast cancer screening program. Moreover, further developments of AI promise increasing performance towards the prediction of interval cancer.

Authors: Celik L, Guner DC, Brehl A-K, Janssen N, Aribal ME

Publication: ECR 2022

Affiliation of Authors: Turkey

Data Source: Turkey

Using an AI system and breast density to quantify the short-term risk of interval cancer in screening: a large retrospective evaluation

Conclusion: Transpara findings combined with breast density significantly improves detection of interval cancers.

Authors: Wanders A J T, Mees W, Janssen N, Dalmis M U, Rodriguez-Ruiz A, Sechopoulos I, van Gils C H, Karssemeijer N, Mann R M, van Rooden J-K

Publication: ECR 2021

Affiliation of Authors: The Netherlands

Data Source: The Netherlands

Using AI with single reading in screening: a simulation of the impact on tumour characteristics of detected cancers

Conclusion: Transpara can replace a radiologist in a double reading screening program, resulting in similar tumor characteristics compared to double reading and potential higher cancer detection rates.

 

Authors: vJanssen N, van Winkel S, Rodríguez-Ruiz A, Karssemeijer N, Sechopoulos I, Mann R M

Publication: ECR 2021

Affiliation of Authors: The Netherlands

Data Source: The Netherlands

Using AI to identify very likely normal cases that may not need a second reader assessment in a French breast cancer screening program (BCSP): a retrospective evaluation

Conclusion: Transpara can be used in the French screening program as an aid to the first reader, to identify 30% of very likely normal mammograms where double reading is not necessary. Combined with breast density, this volume could be increased to 43%.

 

Authors: Jarraya H, Damiens Y, Amrane Y, Vendel C, Legros M, Brochart C, Rais J, Medjahdi M, Petit T, Rodríguez-Ruiz A

Publication: ECR 2021

Affiliation of Authors: France, the Netherlands

Data Source: France

The potential for AI to replace a reader in a double reading breast cancer screening program

Conclusion: Transpara can replace a radiologist in a double reading screening program, resulting in reduced workload of 50% and improved sensitivity of 12.5%.

Authors: van Winkel S, Janssen N, Rodriguez-Ruiz A, Karssemeijer N, Sechopoulos I, Mann R M

Publication: ECR 2021

Affiliation of Authors: The Netherlands

Data Source: The Netherlands

Using Artificial Intelligence to transition from digital mammography screening to digital breast tomosynthesis screening: a retrospective evaluation

Conclusion: Screening programs can use Transpara to transition from 2D screening to 3D screening + AI, increasing sensitivity by 25%, reducing recall rate by 27%, and even reducing workload by 30% using 3D+AI in comparison to 2D only.

 

Authors: Raya-Povedano J L , Romero-Martín S , Elías-Cabot E, Gubern-Merida A, Rodríguez-Ruiz A, Alvarez-Benito M. 

Publication: ECR 2021

Affiliation of Authors: Spain, the Netherlands

Data Source: Spain

Replacing double reading in mammography screening with single reading and artificial intelligence: a large retrospective screening evaluation

Conclusion: Transpara can replace one radiologist in a double reading screening program, allowing for workload reduction of 50% and improved sensitivity of 6.7% and reduced recall rate of 8.8%.

 

Authors: Raya-Povedano J L , Romero-Martín S , Elías-Cabot E, Gubern-Merida A, Rodríguez-Ruiz A, Alvarez-Benito M

Publication: ECR 2021

Affiliation of Authors: Spain, the Netherlands

Data Source: Spain

The potential of AI to replace a first reader in a double reading breast cancer screening program: a feasibility study

Conclusion: Replacing a radiologist with Transpara in a double reading screening program could be an effective and safe strategy to reduce workload by 50% without missing cancers

Authors: Janssen N, Rodriguez-Ruiz A, Mieskes C, Karssemeijer N, Heywang-Köbrunner S H. 

Publication: ECR 2021

Affiliation of Authors: Germany, the Netherlands

Data Source: Germany

Measuring short- and long-term breast cancer risk by combining mammographic texture models, an AI-based CAD system, and established risk factors

Conclusion: Transpara can power short and long-term cancer prediction together with breast density, texture and other biomarkers.

 

Authors: Lauritzen A D, Rodriguez-Ruiz A, von Euler-Chelpin M C, Lynge E, Vejborg I, Nielsen M, Karssemeijer N, Lillholm M

Publication: ECR 2021

Affiliation of Authors: Denmark, the Netherlands

Data Source: Denmark

Can artificial intelligence reduce the interval cancer rate in mammography screening?

Findings: Transpara was able to detect a substantial number of interval cancers on prior screening exam. Applying an AI-derived recall rate recommendation for the most suspicious cases to, e.g., a 3rd reader or a consensus discussion, might provide means to help radiologist reduce the interval cancer rate.

Authors: Kristina Lång, Solveig Hofvind, Alejandro Rodriguez Ruiz, Ingvar Andersson

Publication: ECR 2020

Affiliation of Authors: Sweden, the Netherlands

Data Source: Sweden

Reducing Radiologist Workload by Detecting Normal Mammograms with an AI System

Findings: The results show that Transpara can successfully identify normal mammographies with very few missed screen-detected cancers. Furthermore, a substantial amount false positive studies were identified as normal. The results suggest that potentially AI systems could effectively and safely reduce the number of studies that radiologists would have to examine by a considerable amount, and several false positives could be avoided.

Authors: D. Lauritzen, A. Rodriguez-Ruiz, M. C. von Euler-Chelpin, E. Lynge, I. Vejborg, M. Nielsen, N. Karssemeijer, M. Lillholm 

Publication: ECR 2020

Affiliation of Authors: Denmark, the Netherlands

Data Source: Denmark

Reading breast tomosynthesis examinations with an AI decision support system: improving cancer detection accuracy

Findings: Radiologists improved their cancer detection in breast tomosynthesis examinations when using Transpara for support, while simultaneously reading time is reduced.

Authors: Ritse M. Mann, Alejandro Rodriguez-Ruiz, Albert Gubern-Merida, Nico Karssemeijer, I. Sechopoulos 

Publication: ECR 2020

Affiliation of Authors: The Netherlands

Data Source: The Netherlands

Can artificial intelligence identify normal mammograms in screening?

Conclusion: Transpara can reduce the screen-reading workload. With further improvement of the software an even greater exclusion of normal mammograms seems possible since the majority of the cancers with low risk scores were clearly visible.

Authors: K. Lång, M. Dustler, V. Dahlblom, I. Andersson, S. Zackrisson

Publication: ECR 2019

Affiliation of Authors: Sweden

Data Source: Sweden

Artificial intelligence detecting breast cancer on mammography: does breast density play a role?

Conclusion: Transpara Score may be considered as an independent tool to estimate the likelihood of the presence of cancer on mammograms, to stratify screening populations, and to potentially fasten the reading process by reassuring readers on mammograms that are likely normal, irrespective of breast density.

 

Authors: Rodriguez-Ruiz, M. Kallenberg, A. Gubern-Merida, N. Karssemeijer, R. M. Mann

Publication: ECR 2019

Affiliation of Authors: The Netherlands

Data Source: The Netherlands

RSNA

Artificial intelligence (AI) allows safe workload reduction

Replacing one reader in a breast cancer screening workflow with Transpara for the low risk cases could safely reduce the workload by 33.8% with no cancers being missed.

Authors: P. Gialias, A.K. Brehl, H. Gustafsson

Publication: RSNA 2022

Affiliation of Authors: Sweden, the Netherlands

Data Source: Sweden

A prospective study of breast cancer screening with AI as first reader for likely normal mammographies

Initial results of screening with Transpara as first reader, in cases of likely normal FFDMs, reduced the reader workload by 29% and resulted in a lower recall rate, however not significantly so. More time is needed to collect additional data and to detect whether recall rate will safely decrease without sacrificing cancer detection rate. An ongoing study for future publication is currently monitoring rate of consensus conferences, level of reader agreement, interval cancer rate, and cancer detection rate.

Authors: A. D. Lauritzen, N. Janssen, A.K Brehl, I. Vejborg, M. Lillholm

Publication: RSNA 2022

Affiliation of Authors: Denmark, the Netherlands

Data Source: Denmark

Commercially available AI system for breast cancer detection shows promise for risk prediction, including among women with dense breasts

Transpara’s imaging-based measures combined with volumetric density improved discrimination of invasive breast cancer. Including these measures in risk models could better inform tailored screening and supplemental imaging strategies.

Authors: Vachon CM, Scott CG, Winham S, Norman A, Hruska CB, Brandt KR, Kerlikowske K

Publication: RSNA 2021

Affiliation of Authors: USA

Data Source: USA

View Publication

Can artificial intelligence (AI) completely replace human reader in mammography screening program? A retrospective evaluation with digital mammography (DM) and digital breast tomosynthesis (DBT)

Transpara could be used alone in screening programs with DM but with DBT it would be necessary to increase the recall rates to achieve similar sensitivity.

Authors: Romero-Martín S, Raya-Povedano JL, Elías-Cabot E, Gubern-Mérida A, Rodríguez-Ruíz A, Álvarez-Benito M

Publication: RSNA 2021

Affiliation of Authors: Spain, the Netherlands

Data Source: Spain

View Publication

The potential of AI to reduce interval cancer in a middle income country breast cancer screening program

Transpara has the potential to reduce the rate of interval cancers, when applied as a second or third independent reader within a national breast cancer screening program.

Authors: Aribal E, Celik L, Janssen N

Publication: RSNA 2021

Affiliation of Authors: Turkey

Data Source: Turkey

View Publication

Replacing a radiologist by AI in Dutch population based breast cancer screening and the impact of breast density on performance

Transpara provides higher sensitivity than the first reader and is complimentary hence Transpara has potential as second reader but an effective arbitration process is necessary. This effect seems independent of breast density, albeit a remarkable amount of additional cancers detected was in highest and lowest density categories.

Authors: van Winkel S , Janssen N, Karssemeijer N, Mann R

Publication: RSNA 2021

Affiliation of Authors: The Netherlands

Data Source: The Netherlands

View Publication

Artificial Intelligence as a support to the radiologists’ screen reading of mammograms – A retrospective study

Transpara marks a substantial number of the screen-detected and interval cancer and could potentially aid radiologists in their screen-reading and increase the sensitivity of the screening program.

Authors: Larsen M, Aglen CF, Hoff SR, Lund-Hanssen H, Nygard J, Hofvind SS

Publication: RSNA 2021

Affiliation of Authors: Norway

Data Source: Norway

View Publication

Using autonomous AI to reduce the workload of breast cancer screening with breast tomosynthesis: a retrospective validation

Conclusion: Transpara can confidently identify very likely normal 3D exams in screening that could be prevented from double reading, therefore reducing workload up to 70% without reducing sensitivity by 5% or more.

 

Authors: S. Romero Martín, J. Luis Raya Povedano, E. Elías Cabot, A. Gubern-Merida, A. Rodríguez-Ruiz, M. Álvarez Benito

Publication: RSNA 2020

Affiliation of Authors: Spain, the Netherlands

Data Source: Spain

Impact of AI decision support on breast cancer screening interpretation with single-view wide-angle DBT

Conclusion: Radiologists improved their cancer detection performance at DBT when using an AI system for decision support. Furthermore, AI support results in a more optimal distribution of reading time, with readers spending less time in normal cases and more time in suspicious cases.

Authors: M. Pinto, A. Rodriguez-Ruiz, K. Pedersen, S. Hofvind, R. Mann, S. Kappler, J. Wicklein, I. Sechopoulos

Publication: RSNA 2020

Affiliation of Authors: Norway, the Netherlands

Data Source: Norway

Can AI help to increase the PPV of screen-recalled biopsies on calcifications?

Conclusion: When only lesions in exams with an Exam-Score of 10 had been biopsied only one low-grade DCIS would have been missed while the number of benign biopsies would have been reduced by 23.1%.

Authors: C. Balta, N. Janssen, A. Rodriguez-Ruiz, C. Mieskes, N. Karssemeijer, S. H. Heywang-Köbrunner

Publication: RSNA 2020

Affiliation of Authors: Germany, the Netherlands

Data Source: Germany

What impact could AI based computer aided detection have on the number and biological relevance of interval cancers in a population based screening programme?

Conclusion: AI-based CAD localised some cancers on prior screens that were missed by readers, mostly low/intermediate grade ER positive cancers.

Authors: S. J. Vinnicombe, O. Parr, R. Sidebottom, D. Godden, E. Cornford, I. D. Lyburn

Publication: RSNA 2020

Affiliation of Authors: UK, the Netherlands

Data Source: UK

Using AI to triage which screening mammograms benefit from a double reading strategy

Conclusion: AI can be used to triage screening mammograms that would benefit most from double reading, reducing workload and improving screening performance.

Authors: C. Balta, N. Janssen, A. Rodriguez-Ruiz, C. Mieskes, N. Karssemeijer, S. H. Heywang-Köbrunner

Publication: RSNA 2020

Affiliation of Authors: Germany, the Netherlands

Data Source: Germany

The potential of AI for improving early detection in breast cancer screening to reduce interval cancer rates

Conclusion: AI has the potential to reduce interval cancer rates, whether by being used as an independent reader or as a pre-selection tool to determine which cases could benefit from additional screening imaging.

Authors: A.J.T. Wanders, W. Mees, N. Janssen, A. Rodriguez-Ruiz, I. Sechopoulos, J.K. van Rooden, Ritse M. Mann

Publication: RSNA 2020

Affiliation of Authors: The Netherlands

Data Source: The Netherlands

Artificial Intelligence for breast cancer detection in mammographic screening: does it detect the cancers that matter? And can it detect cancers earlier?

Conclusion: Transpara has the highest sensitivity for high grade and invasive cancers. It has potential to detect high grade cancers 3 years earlier. Additionally, It could be used to discriminate 50 of the screening population as being almost certainly normal with less than <1% error.

Authors:  M. Halling Brown, A. Rodriguez-Ruiz, N; Karssemeijer, M. G. Wallis, K. C. Young

Publication: RSNA 2019

Affiliation of Authors: UK, the Netherlands

Data Source: UK

Other

Duty of Candour in Interval Cancer Review: Does AI add transparency?

Conclusion: Transpara could help to reduce the false negative exams in the UK screening program and as an aid in the interval cancer review process.

 

Authors: Dr W Teh

Publication: BSBR 2019

Affiliation of Authors: UK

Data Source: UK

Using AI as a pre-screening tool to replace double with single reading for likely normal mammography cases. A simulation study on the impact on sensitivity, specificity, and workload

Conclusion: In a simulation study, replacing double reading by single reading for mammograms labeled as most likely normal by Transpara shows potential to reduce workload in screening, with minimal effect in sensitivity and a moderate increase in specificity.

Authors: Rodríguez-Ruiz, K. Lång, A. Gubern-Mérida, M. Broeders, G. Gennaro, P. Clauser, T. Helbich, T. Mertelmeier, M. Chevalier, T. Tan, M. G. Wallis, I. Andersson, S. Zackrisson, R. M. Mann, I. Sechopoulos 

Publication: EUSOBI 2019

Affiliation of Authors: the Netherlands, Austria, Sweden, Italy, Germany, Spain, UK, Switzerland

Data Source: the Netherlands, Austria, Sweden, Italy, Germany, Spain, Switzerland, USA