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

Forskningsoutput: TidskriftsbidragArtikel i vetenskaplig tidskrift

Standard

Can we reduce the workload of mammographic screening by automatic identification of normal exams with artificial intelligence? A feasibility study. / Rodriguez-Ruiz, Alejandro; Lång, Kristina; Gubern-Merida, Albert; Teuwen, Jonas; Broeders, Mireille; Gennaro, Gisella; Clauser, Paola; Helbich, Thomas H.; Chevalier, Margarita; Mertelmeier, Thomas; Wallis, Matthew G.; Andersson, Ingvar; Zackrisson, Sophia; Sechopoulos, Ioannis; Mann, Ritse M.

I: European Radiology, Vol. 29, Nr. 9, 2019, s. 4825-4832.

Forskningsoutput: TidskriftsbidragArtikel i vetenskaplig tidskrift

Harvard

Rodriguez-Ruiz, A, Lång, K, Gubern-Merida, A, Teuwen, J, Broeders, M, Gennaro, G, Clauser, P, Helbich, TH, Chevalier, M, Mertelmeier, T, Wallis, MG, Andersson, I, Zackrisson, S, Sechopoulos, I & Mann, RM 2019, 'Can we reduce the workload of mammographic screening by automatic identification of normal exams with artificial intelligence? A feasibility study', European Radiology, vol. 29, nr. 9, s. 4825-4832. https://doi.org/10.1007/s00330-019-06186-9

APA

Rodriguez-Ruiz, A., Lång, K., Gubern-Merida, A., Teuwen, J., Broeders, M., Gennaro, G., Clauser, P., Helbich, T. H., Chevalier, M., Mertelmeier, T., Wallis, M. G., Andersson, I., Zackrisson, S., Sechopoulos, I., & Mann, R. M. (2019). Can we reduce the workload of mammographic screening by automatic identification of normal exams with artificial intelligence? A feasibility study. European Radiology, 29(9), 4825-4832. https://doi.org/10.1007/s00330-019-06186-9

CBE

Rodriguez-Ruiz A, Lång K, Gubern-Merida A, Teuwen J, Broeders M, Gennaro G, Clauser P, Helbich TH, Chevalier M, Mertelmeier T, Wallis MG, Andersson I, Zackrisson S, Sechopoulos I, Mann RM. 2019. Can we reduce the workload of mammographic screening by automatic identification of normal exams with artificial intelligence? A feasibility study. European Radiology. 29(9):4825-4832. https://doi.org/10.1007/s00330-019-06186-9

MLA

Vancouver

Author

Rodriguez-Ruiz, Alejandro ; Lång, Kristina ; Gubern-Merida, Albert ; Teuwen, Jonas ; Broeders, Mireille ; Gennaro, Gisella ; Clauser, Paola ; Helbich, Thomas H. ; Chevalier, Margarita ; Mertelmeier, Thomas ; Wallis, Matthew G. ; Andersson, Ingvar ; Zackrisson, Sophia ; Sechopoulos, Ioannis ; Mann, Ritse M. / Can we reduce the workload of mammographic screening by automatic identification of normal exams with artificial intelligence? A feasibility study. I: European Radiology. 2019 ; Vol. 29, Nr. 9. s. 4825-4832.

RIS

TY - JOUR

T1 - Can we reduce the workload of mammographic screening by automatic identification of normal exams with artificial intelligence? A feasibility study

AU - Rodriguez-Ruiz, Alejandro

AU - Lång, Kristina

AU - Gubern-Merida, Albert

AU - Teuwen, Jonas

AU - Broeders, Mireille

AU - Gennaro, Gisella

AU - Clauser, Paola

AU - Helbich, Thomas H.

AU - Chevalier, Margarita

AU - Mertelmeier, Thomas

AU - Wallis, Matthew G.

AU - Andersson, Ingvar

AU - Zackrisson, Sophia

AU - Sechopoulos, Ioannis

AU - Mann, Ritse M.

PY - 2019

Y1 - 2019

N2 - Purpose: To study the feasibility of automatically identifying normal digital mammography (DM) exams with artificial intelligence (AI) to reduce the breast cancer screening reading workload. Methods and materials: A total of 2652 DM exams (653 cancer) and interpretations by 101 radiologists were gathered from nine previously performed multi-reader multi-case receiver operating characteristic (MRMC ROC) studies. An AI system was used to obtain a score between 1 and 10 for each exam, representing the likelihood of cancer present. Using all AI scores between 1 and 9 as possible thresholds, the exams were divided into groups of low- and high likelihood of cancer present. It was assumed that, under the pre-selection scenario, only the high-likelihood group would be read by radiologists, while all low-likelihood exams would be reported as normal. The area under the reader-averaged ROC curve (AUC) was calculated for the original evaluations and for the pre-selection scenarios and compared using a non-inferiority hypothesis. Results: Setting the low/high-likelihood threshold at an AI score of 5 (high likelihood > 5) results in a trade-off of approximately halving (− 47%) the workload to be read by radiologists while excluding 7% of true-positive exams. Using an AI score of 2 as threshold yields a workload reduction of 17% while only excluding 1% of true-positive exams. Pre-selection did not change the average AUC of radiologists (inferior 95% CI > − 0.05) for any threshold except at the extreme AI score of 9. Conclusion: It is possible to automatically pre-select exams using AI to significantly reduce the breast cancer screening reading workload. Key Points: • There is potential to use artificial intelligence to automatically reduce the breast cancer screening reading workload by excluding exams with a low likelihood of cancer. • The exclusion of exams with the lowest likelihood of cancer in screening might not change radiologists’ breast cancer detection performance. • When excluding exams with the lowest likelihood of cancer, the decrease in true-positive recalls would be balanced by a simultaneous reduction in false-positive recalls.

AB - Purpose: To study the feasibility of automatically identifying normal digital mammography (DM) exams with artificial intelligence (AI) to reduce the breast cancer screening reading workload. Methods and materials: A total of 2652 DM exams (653 cancer) and interpretations by 101 radiologists were gathered from nine previously performed multi-reader multi-case receiver operating characteristic (MRMC ROC) studies. An AI system was used to obtain a score between 1 and 10 for each exam, representing the likelihood of cancer present. Using all AI scores between 1 and 9 as possible thresholds, the exams were divided into groups of low- and high likelihood of cancer present. It was assumed that, under the pre-selection scenario, only the high-likelihood group would be read by radiologists, while all low-likelihood exams would be reported as normal. The area under the reader-averaged ROC curve (AUC) was calculated for the original evaluations and for the pre-selection scenarios and compared using a non-inferiority hypothesis. Results: Setting the low/high-likelihood threshold at an AI score of 5 (high likelihood > 5) results in a trade-off of approximately halving (− 47%) the workload to be read by radiologists while excluding 7% of true-positive exams. Using an AI score of 2 as threshold yields a workload reduction of 17% while only excluding 1% of true-positive exams. Pre-selection did not change the average AUC of radiologists (inferior 95% CI > − 0.05) for any threshold except at the extreme AI score of 9. Conclusion: It is possible to automatically pre-select exams using AI to significantly reduce the breast cancer screening reading workload. Key Points: • There is potential to use artificial intelligence to automatically reduce the breast cancer screening reading workload by excluding exams with a low likelihood of cancer. • The exclusion of exams with the lowest likelihood of cancer in screening might not change radiologists’ breast cancer detection performance. • When excluding exams with the lowest likelihood of cancer, the decrease in true-positive recalls would be balanced by a simultaneous reduction in false-positive recalls.

KW - Artificial intelligence

KW - Breast cancer

KW - Deep learning

KW - Mammography

KW - Screening

U2 - 10.1007/s00330-019-06186-9

DO - 10.1007/s00330-019-06186-9

M3 - Article

C2 - 30993432

AN - SCOPUS:85064708076

VL - 29

SP - 4825

EP - 4832

JO - European Radiology

JF - European Radiology

SN - 0938-7994

IS - 9

ER -