Impact of artificial intelligence in breast cancer screening with mammography. Dang, L., Chazard, E., Poncelet, E., Serb, T., Rusu, A., Pauwels, X., Parsy, C., Poclet, T., Cauliez, H., Engelaere, C., Ramette, G., Brienne, C., Dujardin, S., & Laurent, N. Breast Cancer (Tokyo, Japan), June, 2022. doi abstract bibtex OBJECTIVES: To demonstrate that radiologists, with the help of artificial intelligence (AI), are able to better classify screening mammograms into the correct breast imaging reporting and data system (BI-RADS) category, and as a secondary objective, to explore the impact of AI on cancer detection and mammogram interpretation time. METHODS: A multi-reader, multi-case study with cross-over design, was performed, including 314 mammograms. Twelve radiologists interpreted the examinations in two sessions delayed by a 4 weeks wash-out period with and without AI support. For each breast of each mammogram, they had to mark the most suspicious lesion (if any) and assign it with a forced BI-RADS category and a level of suspicion or "continuous BI-RADS 100". Cohen's kappa correlation coefficient evaluating the inter-observer agreement for BI-RADS category per breast, and the area under the receiver operating characteristic curve (AUC), were used as metrics and analyzed. RESULTS: On average, the quadratic kappa coefficient increased significantly when using AI for all readers [κ = 0.549, 95% CI (0.528-0.571) without AI and κ = 0.626, 95% CI (0.607-0.6455) with AI]. AUC was significantly improved when using AI (0.74 vs 0.77, p = 0.004). Reading time was not significantly affected for all readers (106 s without AI and vs 102 s with AI; p = 0.754). CONCLUSIONS: When using AI, radiologists were able to better assign mammograms with the correct BI-RADS category without slowing down the interpretation time.
@article{dang_impact_2022,
title = {Impact of artificial intelligence in breast cancer screening with mammography},
issn = {1880-4233},
doi = {10.1007/s12282-022-01375-9},
abstract = {OBJECTIVES: To demonstrate that radiologists, with the help of artificial intelligence (AI), are able to better classify screening mammograms into the correct breast imaging reporting and data system (BI-RADS) category, and as a secondary objective, to explore the impact of AI on cancer detection and mammogram interpretation time.
METHODS: A multi-reader, multi-case study with cross-over design, was performed, including 314 mammograms. Twelve radiologists interpreted the examinations in two sessions delayed by a 4 weeks wash-out period with and without AI support. For each breast of each mammogram, they had to mark the most suspicious lesion (if any) and assign it with a forced BI-RADS category and a level of suspicion or "continuous BI-RADS 100". Cohen's kappa correlation coefficient evaluating the inter-observer agreement for BI-RADS category per breast, and the area under the receiver operating characteristic curve (AUC), were used as metrics and analyzed.
RESULTS: On average, the quadratic kappa coefficient increased significantly when using AI for all readers [κ = 0.549, 95\% CI (0.528-0.571) without AI and κ = 0.626, 95\% CI (0.607-0.6455) with AI]. AUC was significantly improved when using AI (0.74 vs 0.77, p = 0.004). Reading time was not significantly affected for all readers (106 s without AI and vs 102 s with AI; p = 0.754).
CONCLUSIONS: When using AI, radiologists were able to better assign mammograms with the correct BI-RADS category without slowing down the interpretation time.},
language = {eng},
journal = {Breast Cancer (Tokyo, Japan)},
author = {Dang, Lan-Anh and Chazard, Emmanuel and Poncelet, Edouard and Serb, Teodora and Rusu, Aniela and Pauwels, Xavier and Parsy, Clémence and Poclet, Thibault and Cauliez, Hugo and Engelaere, Constance and Ramette, Guillaume and Brienne, Charlotte and Dujardin, Sofiane and Laurent, Nicolas},
month = jun,
year = {2022},
pmid = {35763243},
keywords = {Artificial intelligence, BI-RADS classification, Breast cancer, Mammography},
}
Downloads: 0
{"_id":"H97L38EwEwYHJA2az","bibbaseid":"dang-chazard-poncelet-serb-rusu-pauwels-parsy-poclet-etal-impactofartificialintelligenceinbreastcancerscreeningwithmammography-2022","author_short":["Dang, L.","Chazard, E.","Poncelet, E.","Serb, T.","Rusu, A.","Pauwels, X.","Parsy, C.","Poclet, T.","Cauliez, H.","Engelaere, C.","Ramette, G.","Brienne, C.","Dujardin, S.","Laurent, N."],"bibdata":{"bibtype":"article","type":"article","title":"Impact of artificial intelligence in breast cancer screening with mammography","issn":"1880-4233","doi":"10.1007/s12282-022-01375-9","abstract":"OBJECTIVES: To demonstrate that radiologists, with the help of artificial intelligence (AI), are able to better classify screening mammograms into the correct breast imaging reporting and data system (BI-RADS) category, and as a secondary objective, to explore the impact of AI on cancer detection and mammogram interpretation time. METHODS: A multi-reader, multi-case study with cross-over design, was performed, including 314 mammograms. Twelve radiologists interpreted the examinations in two sessions delayed by a 4 weeks wash-out period with and without AI support. For each breast of each mammogram, they had to mark the most suspicious lesion (if any) and assign it with a forced BI-RADS category and a level of suspicion or \"continuous BI-RADS 100\". Cohen's kappa correlation coefficient evaluating the inter-observer agreement for BI-RADS category per breast, and the area under the receiver operating characteristic curve (AUC), were used as metrics and analyzed. RESULTS: On average, the quadratic kappa coefficient increased significantly when using AI for all readers [κ = 0.549, 95% CI (0.528-0.571) without AI and κ = 0.626, 95% CI (0.607-0.6455) with AI]. AUC was significantly improved when using AI (0.74 vs 0.77, p = 0.004). Reading time was not significantly affected for all readers (106 s without AI and vs 102 s with AI; p = 0.754). CONCLUSIONS: When using AI, radiologists were able to better assign mammograms with the correct BI-RADS category without slowing down the interpretation time.","language":"eng","journal":"Breast Cancer (Tokyo, Japan)","author":[{"propositions":[],"lastnames":["Dang"],"firstnames":["Lan-Anh"],"suffixes":[]},{"propositions":[],"lastnames":["Chazard"],"firstnames":["Emmanuel"],"suffixes":[]},{"propositions":[],"lastnames":["Poncelet"],"firstnames":["Edouard"],"suffixes":[]},{"propositions":[],"lastnames":["Serb"],"firstnames":["Teodora"],"suffixes":[]},{"propositions":[],"lastnames":["Rusu"],"firstnames":["Aniela"],"suffixes":[]},{"propositions":[],"lastnames":["Pauwels"],"firstnames":["Xavier"],"suffixes":[]},{"propositions":[],"lastnames":["Parsy"],"firstnames":["Clémence"],"suffixes":[]},{"propositions":[],"lastnames":["Poclet"],"firstnames":["Thibault"],"suffixes":[]},{"propositions":[],"lastnames":["Cauliez"],"firstnames":["Hugo"],"suffixes":[]},{"propositions":[],"lastnames":["Engelaere"],"firstnames":["Constance"],"suffixes":[]},{"propositions":[],"lastnames":["Ramette"],"firstnames":["Guillaume"],"suffixes":[]},{"propositions":[],"lastnames":["Brienne"],"firstnames":["Charlotte"],"suffixes":[]},{"propositions":[],"lastnames":["Dujardin"],"firstnames":["Sofiane"],"suffixes":[]},{"propositions":[],"lastnames":["Laurent"],"firstnames":["Nicolas"],"suffixes":[]}],"month":"June","year":"2022","pmid":"35763243","keywords":"Artificial intelligence, BI-RADS classification, Breast cancer, Mammography","bibtex":"@article{dang_impact_2022,\n\ttitle = {Impact of artificial intelligence in breast cancer screening with mammography},\n\tissn = {1880-4233},\n\tdoi = {10.1007/s12282-022-01375-9},\n\tabstract = {OBJECTIVES: To demonstrate that radiologists, with the help of artificial intelligence (AI), are able to better classify screening mammograms into the correct breast imaging reporting and data system (BI-RADS) category, and as a secondary objective, to explore the impact of AI on cancer detection and mammogram interpretation time.\nMETHODS: A multi-reader, multi-case study with cross-over design, was performed, including 314 mammograms. Twelve radiologists interpreted the examinations in two sessions delayed by a 4 weeks wash-out period with and without AI support. For each breast of each mammogram, they had to mark the most suspicious lesion (if any) and assign it with a forced BI-RADS category and a level of suspicion or \"continuous BI-RADS 100\". Cohen's kappa correlation coefficient evaluating the inter-observer agreement for BI-RADS category per breast, and the area under the receiver operating characteristic curve (AUC), were used as metrics and analyzed.\nRESULTS: On average, the quadratic kappa coefficient increased significantly when using AI for all readers [κ = 0.549, 95\\% CI (0.528-0.571) without AI and κ = 0.626, 95\\% CI (0.607-0.6455) with AI]. AUC was significantly improved when using AI (0.74 vs 0.77, p = 0.004). Reading time was not significantly affected for all readers (106 s without AI and vs 102 s with AI; p = 0.754).\nCONCLUSIONS: When using AI, radiologists were able to better assign mammograms with the correct BI-RADS category without slowing down the interpretation time.},\n\tlanguage = {eng},\n\tjournal = {Breast Cancer (Tokyo, Japan)},\n\tauthor = {Dang, Lan-Anh and Chazard, Emmanuel and Poncelet, Edouard and Serb, Teodora and Rusu, Aniela and Pauwels, Xavier and Parsy, Clémence and Poclet, Thibault and Cauliez, Hugo and Engelaere, Constance and Ramette, Guillaume and Brienne, Charlotte and Dujardin, Sofiane and Laurent, Nicolas},\n\tmonth = jun,\n\tyear = {2022},\n\tpmid = {35763243},\n\tkeywords = {Artificial intelligence, BI-RADS classification, Breast cancer, Mammography},\n}\n\n","author_short":["Dang, L.","Chazard, E.","Poncelet, E.","Serb, T.","Rusu, A.","Pauwels, X.","Parsy, C.","Poclet, T.","Cauliez, H.","Engelaere, C.","Ramette, G.","Brienne, C.","Dujardin, S.","Laurent, N."],"key":"dang_impact_2022","id":"dang_impact_2022","bibbaseid":"dang-chazard-poncelet-serb-rusu-pauwels-parsy-poclet-etal-impactofartificialintelligenceinbreastcancerscreeningwithmammography-2022","role":"author","urls":{},"keyword":["Artificial intelligence","BI-RADS classification","Breast cancer","Mammography"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://api.zotero.org/users/1597782/collections/MSB7W4UM/items?key=gxIPM4PJtMVcB8OpssCWodtP&format=bibtex&limit=100&start=0&sort=date","dataSources":["PSBFFbnPhFKwYx7yq","doevpoZ8x7wJceFTM"],"keywords":["artificial intelligence","bi-rads classification","breast cancer","mammography"],"search_terms":["impact","artificial","intelligence","breast","cancer","screening","mammography","dang","chazard","poncelet","serb","rusu","pauwels","parsy","poclet","cauliez","engelaere","ramette","brienne","dujardin","laurent"],"title":"Impact of artificial intelligence in breast cancer screening with mammography","year":2022}