Related Experiment Video
Updated: Oct 4, 2025
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
Radiologist-Level Performance by Using Deep Learning for Segmentation of Breast Cancers on MRI Scans
Lukas Hirsch1, Yu Huang1, Shaojun Luo1
1Department of Biomedical Engineering (L.H., Y.H., L.C.P.) and the Benjamin Levich Institute and Department of Physics (S.L., H.A.M.), the City College of the City University of New York, 160 Convent Ave, New York, NY 10031; Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065 (Y.H., C.R.S., R.L.G., I.D.N., A.G.V.B., N.O., E.S.K., D.L., D.A., S.E.W., M.H., D.F.M., K.P., K.J., A.E.E., P.E., E.A.M., E.J.S.); Department of Imaging, A.C. Camargo Cancer Center, São Paulo, Brazil (A.G.V.B.); Department of Radiology, University of California, San Francisco, San Francisco, Calif (N.O.); Department of Radiology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Korea (E.S.K.); and Department of Breast Imaging, Breast Cancer Center TecSalud, ITESM Monterrey, Monterrey, Mexico (D.A.).
Purpose:
To develop a deep network architecture that would achieve fully automated radiologist-level segmentation of cancers at breast MRI.
Materials And Methods:
In this retrospective study, 38 229 examinations (composed of 64 063 individual breast scans from 14 475 patients) were performed in female patients (age range, 12-94 years; mean age, 52 years ± 10 [standard deviation]) who presented between 2002 and 2014 at a single clinical site. A total of 2555 breast cancers were selected that had been segmented on two-dimensional (2D) images by radiologists, as well as 60 108 benign breasts that served as examples of noncancerous tissue; all these were used for model training. For testing, an additional 250 breast cancers were segmented independently on 2D images by four radiologists. Authors selected among several three-dimensional (3D) deep convolutional neural network architectures, input modalities, and harmonization methods. The outcome measure was the Dice score for 2D segmentation, which was compared between the network and radiologists by using the Wilcoxon signed rank test and the two one-sided test procedure.
Results:
The highest-performing network on the training set was a 3D U-Net with dynamic contrast-enhanced MRI as input and with intensity normalized for each examination. In the test set, the median Dice score of this network was 0.77 (interquartile range, 0.26). The performance of the network was equivalent to that of the radiologists (two one-sided test procedures with radiologist performance of 0.69-0.84 as equivalence bounds, P < .001 for both; n = 250).
Conclusion:
When trained on a sufficiently large dataset, the developed 3D U-Net performed as well as fellowship-trained radiologists in detailed 2D segmentation of breast cancers at routine clinical MRI.Keywords: MRI, Breast, Segmentation, Supervised Learning, Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning AlgorithmsPublished under a CC BY 4.0 license. Supplemental material is available for this article.
