TY - JOUR
T1 - SCU-Net
T2 - A deep learning method for segmentation and quantification of breast arterial calcifications on mammograms
AU - Guo, Xiaoyuan
AU - O'Neill, W. Charles
AU - Vey, Brianna
AU - Yang, Tianen Christopher
AU - Kim, Thomas J.
AU - Ghassemi, Maryzeh
AU - Pan, Ian
AU - Gichoya, Judy Wawira
AU - Trivedi, Hari
AU - Banerjee, Imon
N1 - Publisher Copyright:
© 2021 American Association of Physicists in Medicine
PY - 2021/10
Y1 - 2021/10
N2 - Purpose: Measurements of breast arterial calcifications (BAC) can offer a personalized, non-invasive approach to risk-stratify women for cardiovascular diseases such as heart attack and stroke. We aim to detect and segment breast arterial calcifications in mammograms accurately and suggest novel measurements to quantify detected BAC for future clinical applications. Methods: To separate BAC in mammograms, we propose a lightweight fine vessel segmentation method Simple Context U-Net (SCU-Net). Due to the large image size of mammograms, we adopt a patch-based way to train SCU-Net and obtain the final whole-image-size results by stitching patchwise results together. To further quantify calcifications, we test five quantitative metrics to inspect the progression of BAC for subjects: sum of mask probability metric ((Formula presented.)), sum of mask area metric ((Formula presented.)), sum of mask intensity metric ((Formula presented.)), sum of mask area with threshold intensity metric (Formula presented.), and sum of mask intensity with threshold X metric (Formula presented.). Finally, we demonstrate the ability of the metrics to longitudinally measure calcifications in a group of 26 subjects and evaluate our quantification metrics compared with calcified voxels and calcium mass on breast CT for 10 subjects. Results: Our segmentation results are compared with state-of-the-art network architectures based on recall, precision, accuracy, F1 score/Dice score, and Jaccard index evaluation metrics and achieve corresponding values of 0.789, 0.708, 0.997, 0.729, and 0.581 for whole-image-size results. The quantification results all show >95% correlation between quantification measures on predicted masks of SCU-Net as compared to the groundtruth and measurement of calcification on breast CT. For the calcification quantification measurement, our calcification volume (voxels) results yield R2-correlation values of 0.834, 0.843, 0.832, 0.798, and 0.800 for the (Formula presented.) metrics, respectively; our calcium mass results yield comparable R2-correlation values of 0.866, 0.873, 0.840, 0.774, and 0.798 for the same metrics. Conclusions: Simple Context U-Net is a simple method to accurately segment arterial calcification retrospectively on routine mammograms. Quantification of the calcifications based on this segmentation in the retrospective cohort study has sufficient sensitivity to detect the normal progression over time and should be useful for future research and clinical applications.
AB - Purpose: Measurements of breast arterial calcifications (BAC) can offer a personalized, non-invasive approach to risk-stratify women for cardiovascular diseases such as heart attack and stroke. We aim to detect and segment breast arterial calcifications in mammograms accurately and suggest novel measurements to quantify detected BAC for future clinical applications. Methods: To separate BAC in mammograms, we propose a lightweight fine vessel segmentation method Simple Context U-Net (SCU-Net). Due to the large image size of mammograms, we adopt a patch-based way to train SCU-Net and obtain the final whole-image-size results by stitching patchwise results together. To further quantify calcifications, we test five quantitative metrics to inspect the progression of BAC for subjects: sum of mask probability metric ((Formula presented.)), sum of mask area metric ((Formula presented.)), sum of mask intensity metric ((Formula presented.)), sum of mask area with threshold intensity metric (Formula presented.), and sum of mask intensity with threshold X metric (Formula presented.). Finally, we demonstrate the ability of the metrics to longitudinally measure calcifications in a group of 26 subjects and evaluate our quantification metrics compared with calcified voxels and calcium mass on breast CT for 10 subjects. Results: Our segmentation results are compared with state-of-the-art network architectures based on recall, precision, accuracy, F1 score/Dice score, and Jaccard index evaluation metrics and achieve corresponding values of 0.789, 0.708, 0.997, 0.729, and 0.581 for whole-image-size results. The quantification results all show >95% correlation between quantification measures on predicted masks of SCU-Net as compared to the groundtruth and measurement of calcification on breast CT. For the calcification quantification measurement, our calcification volume (voxels) results yield R2-correlation values of 0.834, 0.843, 0.832, 0.798, and 0.800 for the (Formula presented.) metrics, respectively; our calcium mass results yield comparable R2-correlation values of 0.866, 0.873, 0.840, 0.774, and 0.798 for the same metrics. Conclusions: Simple Context U-Net is a simple method to accurately segment arterial calcification retrospectively on routine mammograms. Quantification of the calcifications based on this segmentation in the retrospective cohort study has sufficient sensitivity to detect the normal progression over time and should be useful for future research and clinical applications.
KW - U-Net
KW - breast arterial calcification
KW - cardiovascular
KW - deep learning
KW - mammogram
KW - segmentation
UR - http://www.scopus.com/inward/record.url?scp=85113639727&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85113639727&partnerID=8YFLogxK
U2 - 10.1002/mp.15017
DO - 10.1002/mp.15017
M3 - Article
C2 - 34328661
AN - SCOPUS:85113639727
SN - 0094-2405
VL - 48
SP - 5851
EP - 5861
JO - Medical physics
JF - Medical physics
IS - 10
ER -