TY - JOUR
T1 - Breast cancer detection with upstream data fusion, machine learning, and automated registration
T2 - initial results
AU - Mullen, Lisa A.
AU - Walton, William C.
AU - Williams, Michael P.
AU - Peyton, Keith S.
AU - Porter, David W.
N1 - Publisher Copyright:
© The Authors.
PY - 2023/2/1
Y1 - 2023/2/1
N2 - Purpose: To develop an artificial intelligence algorithm for the detection of breast cancer by combining upstream data fusion (UDF), machine learning (ML), and automated registration, using digital breast tomosynthesis (DBT) and breast ultrasound (US). Approach: Our retrospective study included examinations from 875 women obtained between April 2013 and January 2019. Included patients had a DBT mammogram, breast US, and biopsy proven breast lesion. Images were annotated by a breast imaging radiologist. An AI algorithm was developed based on ML for image candidate detections and UDF for fused detections. After exclusions, images from 150 patients were evaluated. Ninety-five cases were used for training and validation of ML. Fifty-five cases were included in the UDF test set. UDF performance was evaluated with a free-response receiver operating characteristic (FROC) curve. Results: Forty percent of cases evaluated with UDF (22/55) yielded true ML detections in all three images (craniocaudal DBT, mediolateral oblique DBT, and US). Of these, 20/22 (90.9%) produced a UDF fused detection that contained and classified the lesion correctly. FROC analysis for these cases showed 90% sensitivity at 0.3 false positives per case. In contrast, ML yielded an average of 8.0 false alarms per case. Conclusions: An AI algorithm combining UDF, ML, and automated registration was developed and applied to test cases, showing that UDF can yield fused detections and decrease false alarms when applied to breast cancer detection. Improvement of ML detection is needed to realize the full benefit of UDF.
AB - Purpose: To develop an artificial intelligence algorithm for the detection of breast cancer by combining upstream data fusion (UDF), machine learning (ML), and automated registration, using digital breast tomosynthesis (DBT) and breast ultrasound (US). Approach: Our retrospective study included examinations from 875 women obtained between April 2013 and January 2019. Included patients had a DBT mammogram, breast US, and biopsy proven breast lesion. Images were annotated by a breast imaging radiologist. An AI algorithm was developed based on ML for image candidate detections and UDF for fused detections. After exclusions, images from 150 patients were evaluated. Ninety-five cases were used for training and validation of ML. Fifty-five cases were included in the UDF test set. UDF performance was evaluated with a free-response receiver operating characteristic (FROC) curve. Results: Forty percent of cases evaluated with UDF (22/55) yielded true ML detections in all three images (craniocaudal DBT, mediolateral oblique DBT, and US). Of these, 20/22 (90.9%) produced a UDF fused detection that contained and classified the lesion correctly. FROC analysis for these cases showed 90% sensitivity at 0.3 false positives per case. In contrast, ML yielded an average of 8.0 false alarms per case. Conclusions: An AI algorithm combining UDF, ML, and automated registration was developed and applied to test cases, showing that UDF can yield fused detections and decrease false alarms when applied to breast cancer detection. Improvement of ML detection is needed to realize the full benefit of UDF.
KW - artificial intelligence
KW - breast cancer
KW - fusion
KW - mammography
KW - neural network registration
KW - ultrasound
UR - http://www.scopus.com/inward/record.url?scp=85173260962&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85173260962&partnerID=8YFLogxK
U2 - 10.1117/1.JMI.10.S2.S22409
DO - 10.1117/1.JMI.10.S2.S22409
M3 - Article
C2 - 37287741
AN - SCOPUS:85173260962
SN - 2329-4302
VL - 10
JO - Journal of Medical Imaging
JF - Journal of Medical Imaging
M1 - S22409
ER -