Abstract
Purpose: To compare breast cancer detection performance of radiologists reading mammographic examinations unaided versus supported by an artificial intelligence (AI) system. Materials and Methods: An enriched retrospective, fully crossed, multireader, multicase, HIPAA-compliant study was performed. Screening digital mammographic examinations from 240 women (median age, 62 years; range, 39–89 years) performed between 2013 and 2017 were included. The 240 examinations (100 showing cancers, 40 leading to false-positive recalls, 100 normal) were interpreted by 14 Mammography Quality Standards Act–qualified radiologists, once with and once without AI support. The readers provided a Breast Imaging Reporting and Data System score and probability of malignancy. AI support provided radiologists with interactive decision support (clicking on a breast region yields a local cancer likelihood score), traditional lesion markers for computer-detected abnormalities, and an examination-based cancer likelihood score. The area under the receiver operating characteristic curve (AUC), specificity and sensitivity, and reading time were compared between conditions by using mixed-models analysis dof variance and generalized linear models for multiple repeated measurements. Results: On average, the AUC was higher with AI support than with unaided reading (0.89 vs 0.87, respectively; P = .002). Sensitivity increased with AI support (86% [86 of 100] vs 83% [83 of 100]; P = .046), whereas specificity trended toward improvement (79% [111 of 140]) vs 77% [108 of 140]; P = .06). Reading time per case was similar (unaided, 146 seconds; supported by AI, 149 seconds; P = .15). The AUC with the AI system alone was similar to the average AUC of the radiologists (0.89 vs 0.87). Conclusion: Radiologists improved their cancer detection at mammography when using an artificial intelligence system for support, without requiring additional reading time.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 1-10 |
| Number of pages | 10 |
| Journal | Radiology |
| Volume | 290 |
| Issue number | 3 |
| DOIs | |
| State | Published - Mar 1 2019 |
| Externally published | Yes |
Fingerprint
ASJC Scopus subject areas
- Radiology Nuclear Medicine and imaging
Cite this
Detection of breast cancer with mammography : Effect of an artificial intelligence support system. / Rodríguez-Ruiz, Alejandro; Krupinski, Elizabeth A; Mordang, Jan Jurre; Schilling, Kathy; Heywang-Köbrunner, Sylvia H.; Sechopoulos, Ioannis; Mann, Ritse M.
In: Radiology, Vol. 290, No. 3, 01.03.2019, p. 1-10.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Detection of breast cancer with mammography
T2 - Effect of an artificial intelligence support system
AU - Rodríguez-Ruiz, Alejandro
AU - Krupinski, Elizabeth A
AU - Mordang, Jan Jurre
AU - Schilling, Kathy
AU - Heywang-Köbrunner, Sylvia H.
AU - Sechopoulos, Ioannis
AU - Mann, Ritse M.
PY - 2019/3/1
Y1 - 2019/3/1
N2 - Purpose: To compare breast cancer detection performance of radiologists reading mammographic examinations unaided versus supported by an artificial intelligence (AI) system. Materials and Methods: An enriched retrospective, fully crossed, multireader, multicase, HIPAA-compliant study was performed. Screening digital mammographic examinations from 240 women (median age, 62 years; range, 39–89 years) performed between 2013 and 2017 were included. The 240 examinations (100 showing cancers, 40 leading to false-positive recalls, 100 normal) were interpreted by 14 Mammography Quality Standards Act–qualified radiologists, once with and once without AI support. The readers provided a Breast Imaging Reporting and Data System score and probability of malignancy. AI support provided radiologists with interactive decision support (clicking on a breast region yields a local cancer likelihood score), traditional lesion markers for computer-detected abnormalities, and an examination-based cancer likelihood score. The area under the receiver operating characteristic curve (AUC), specificity and sensitivity, and reading time were compared between conditions by using mixed-models analysis dof variance and generalized linear models for multiple repeated measurements. Results: On average, the AUC was higher with AI support than with unaided reading (0.89 vs 0.87, respectively; P = .002). Sensitivity increased with AI support (86% [86 of 100] vs 83% [83 of 100]; P = .046), whereas specificity trended toward improvement (79% [111 of 140]) vs 77% [108 of 140]; P = .06). Reading time per case was similar (unaided, 146 seconds; supported by AI, 149 seconds; P = .15). The AUC with the AI system alone was similar to the average AUC of the radiologists (0.89 vs 0.87). Conclusion: Radiologists improved their cancer detection at mammography when using an artificial intelligence system for support, without requiring additional reading time.
AB - Purpose: To compare breast cancer detection performance of radiologists reading mammographic examinations unaided versus supported by an artificial intelligence (AI) system. Materials and Methods: An enriched retrospective, fully crossed, multireader, multicase, HIPAA-compliant study was performed. Screening digital mammographic examinations from 240 women (median age, 62 years; range, 39–89 years) performed between 2013 and 2017 were included. The 240 examinations (100 showing cancers, 40 leading to false-positive recalls, 100 normal) were interpreted by 14 Mammography Quality Standards Act–qualified radiologists, once with and once without AI support. The readers provided a Breast Imaging Reporting and Data System score and probability of malignancy. AI support provided radiologists with interactive decision support (clicking on a breast region yields a local cancer likelihood score), traditional lesion markers for computer-detected abnormalities, and an examination-based cancer likelihood score. The area under the receiver operating characteristic curve (AUC), specificity and sensitivity, and reading time were compared between conditions by using mixed-models analysis dof variance and generalized linear models for multiple repeated measurements. Results: On average, the AUC was higher with AI support than with unaided reading (0.89 vs 0.87, respectively; P = .002). Sensitivity increased with AI support (86% [86 of 100] vs 83% [83 of 100]; P = .046), whereas specificity trended toward improvement (79% [111 of 140]) vs 77% [108 of 140]; P = .06). Reading time per case was similar (unaided, 146 seconds; supported by AI, 149 seconds; P = .15). The AUC with the AI system alone was similar to the average AUC of the radiologists (0.89 vs 0.87). Conclusion: Radiologists improved their cancer detection at mammography when using an artificial intelligence system for support, without requiring additional reading time.
UR - http://www.scopus.com/inward/record.url?scp=85060384196&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85060384196&partnerID=8YFLogxK
U2 - 10.1148/radiol.2018181371
DO - 10.1148/radiol.2018181371
M3 - Article
C2 - 30457482
AN - SCOPUS:85060384196
VL - 290
SP - 1
EP - 10
JO - Radiology
JF - Radiology
SN - 0033-8419
IS - 3
ER -