Mammography screening currently relies on subjective human interpretation. Artificial intelligence (AI) advances could be used to increase mammography screening accuracy by reducing missed cancers and false positives.
To evaluate whether AI can overcome human mammography interpretation limitations with a rigorous, unbiased evaluation of machine learning algorithms.
In this diagnostic accuracy study conducted between September 2016 and November 2017, an international, crowdsourced challenge was hosted to foster AI algorithm development focused on interpreting screening mammography. More than 1100 participants comprising 126 teams from 44 countries participated. Analysis began November 18, 2016.
Algorithms used images alone (challenge 1) or combined images, previous examinations (if available), and clinical and demographic risk factor data (challenge 2) and output a score that translated to cancer yes/no within 12 months. Algorithm accuracy for breast cancer detection was evaluated using area under the curve and algorithm specificity compared with radiologists’ specificity with radiologists’ sensitivity set at 85.9% (United States) and 83.9% (Sweden). An ensemble method aggregating top-performing AI algorithms and radiologists’ recall assessment was developed and evaluated.
Overall, 144 231 screening mammograms from 85 580 US women (952 cancer positive ≤12 months from screening) were used for algorithm training and validation. A second independent validation cohort included 166 578 examinations from 68 008 Swedish women (780 cancer positive). The top-performing algorithm achieved an area under the curve of 0.858 (United States) and 0.903 (Sweden) and 66.2% (United States) and 81.2% (Sweden) specificity at the radiologists’ sensitivity, lower than community-practice radiologists’ specificity of 90.5% (United States) and 98.5% (Sweden). Combining top-performing algorithms and US radiologist assessments resulted in a higher area under the curve of 0.942 and achieved a significantly improved specificity (92.0%) at the same sensitivity.
While no single AI algorithm outperformed radiologists, an ensemble of AI algorithms combined with radiologist assessment in a single-reader screening environment improved overall accuracy. This study underscores the potential of using machine learning methods for enhancing mammography screening interpretation.
Thomas Schaffter, PhD; Diana S. M. Buist, PhD, MPH; Christoph I. Lee, MD, MS; Yaroslav Nikulin, MS; Dezső Ribli, MSc; Yuanfang Guan, PhD; William Lotter, PhD; Zequn Jie, PhD; Hao Du, BEng; Sijia Wang, MSc; Jiashi Feng, PhD; Mengling Feng, PhD; Hyo-Eun Kim, PhD; Francisco Albiol, PhD; Alberto Albiol, PhD; Stephen Morrell, B Bus Sc, MiF, M Res; Zbigniew Wojna, MSI; Mehmet Eren Ahsen, PhD; Umar Asif, PhD; Antonio Jimeno Yepes, PhD; Shivanthan Yohanandan, PhD; Simona Rabinovici-Cohen, MSc; Darvin Yi, MSc; Bruce Hoff, PhD; Thomas Yu, BS; Elias Chaibub Neto, PhD; Daniel L. Rubin, MD, MS; Peter Lindholm, MD, PhD; Laurie R. Margolies, MD; Russell Bailey McBride, PhD, MPH; Joseph H. Rothstein, MSc; Weiva Sieh, MD, PhD; Rami Ben-Ari, PhD; Stefan Harrer, PhD; Andrew Trister, MD, PhD; Stephen Friend, MD, PhD; Thea Norman, PhD; Berkman Sahiner, PhD; Fredrik Strand, MD, PhD; Justin Guinney, PhD; Gustavo Stolovitzky, PhD; and the DM DREAM Consortium
Photometric Transformer Networks and Label Adjustment for Breast Density Prediction
External Evaluation of 3 Commercial Artificial Intelligence Algorithms for Independent Assessment of Screening Mammograms
A Robust and Effective Approach Towards Accurate Metastasis Detection and pN-stage Classification in Breast Cancer
A Unified Framework for Tumor Proliferation Score Prediction in Breast Histopathology
Changes in cancer detection and false-positive recall in mammography using artificial intelligence: a retrospective, multireader study
Effect of artificial intelligence-based triaging of breast cancer screening mammograms on cancer detection and radiologist workload: a retrospective simulation study
Applying Data-driven Imaging Biomarker in Mammography for Breast Cancer Screening: Preliminary Study
Application of artificial intelligence–based computer-assisted diagnosis on synthetic mammograms from breast tomosynthesis: comparison with digital mammograms
Reducing Domain Gap by Reducing Style Bias
유방촬영의 위양성 판정에 관한 전통적 진단보조프로그램과 인공지능 기반 진단보조프로그램의 비교
인공지능 기반 컴퓨터 보조진단을 이용한 선별 유방촬영술에서의 간격암에 대한 후향 분석
Mammographic Surveillance After Breast Conserving Therapy: Impact of Digital Breast Tomosynthesis and Artificial Intelligence-Based Computer-Aided Detection
Diagnostic Performance of Artificial Intelligence-Based Computer-Aided Diagnosis for Breast Microcalcification on Mammography
Can artificial intelligence replace ultrasound as a complementary tool to mammogram for the diagnosis of the breast cancer?
Retrospective Review of Missed Cancer Detection and Its Mammography Findings with Artificial-Intelligence-Based, Computer-Aided Diagnosis
Mammographically occult breast cancers detected with AI-based diagnosis supporting software: clinical and histopathologic characteristics
Mammographic Density Assessment by Artificial Intelligence-Based Computer-Assisted Diagnosis: A Comparison with Automated Volumetric Assessment
Artificial Intelligence for Breast Cancer Screening in Mammography (AI-STREAM): A Prospective Multicenter Study Design in Korea Using AI-Based CADe/x
Need of pretreatment support of breast cancer patient caregivers compared to patients.