Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jun;59(6):2252-2262.
doi: 10.1002/jmri.28960. Epub 2023 Aug 19.

3D Breast Cancer Segmentation in DCE-MRI Using Deep Learning With Weak Annotation

Ga Eun Park  1 , Sung Hun Kim  1 , Yoonho Nam  2 , Junghwa Kang  2 , Minjeong Park  2 , Bong Joo Kang  1
Affiliations

3D Breast Cancer Segmentation in DCE-MRI Using Deep Learning With Weak Annotation

Ga Eun Park et al. J Magn Reson Imaging. 2024 Jun.

Abstract

Background: Deep learning models require large-scale training to perform confidently, but obtaining annotated datasets in medical imaging is challenging. Weak annotation has emerged as a way to save time and effort.

Purpose: To develop a deep learning model for 3D breast cancer segmentation in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) using weak annotation with reliable performance.

Study type: Retrospective.

Population: Seven hundred and thirty-six women with breast cancer from a single institution, divided into the development (N = 544) and test dataset (N = 192).

Field strength/sequence: 3.0-T, 3D fat-saturated gradient-echo axial T1-weighted flash 3D volumetric interpolated brain examination (VIBE) sequences.

Assessment: Two radiologists performed a weak annotation of the ground truth using bounding boxes. Based on this, the ground truth annotation was completed through autonomic and manual correction. The deep learning model using 3D U-Net transformer (UNETR) was trained with this annotated dataset. The segmentation results of the test set were analyzed by quantitative and qualitative methods, and the regions were divided into whole breast and region of interest (ROI) within the bounding box.

Statistical tests: As a quantitative method, we used the Dice similarity coefficient to evaluate the segmentation result. The volume correlation with the ground truth was evaluated with the Spearman correlation coefficient. Qualitatively, three readers independently evaluated the visual score in four scales. A P-value <0.05 was considered statistically significant.

Results: The deep learning model we developed achieved a median Dice similarity score of 0.75 and 0.89 for the whole breast and ROI, respectively. The volume correlation coefficient with respect to the ground truth volume was 0.82 and 0.86 for the whole breast and ROI, respectively. The mean visual score, as evaluated by three readers, was 3.4.

Data conclusion: The proposed deep learning model with weak annotation may show good performance for 3D segmentations of breast cancer using DCE-MRI.

Level of evidence: 3 TECHNICAL EFFICACY: Stage 2.

Keywords: breast cancer; deep learning; segmentation.

PubMed Disclaimer

Comment in

References

    1. Mann RM, Cho N, Moy L. Breast MRI: State of the art. Radiology 2019;292(3):520‐536.
    1. Yang P‐T, Wu W‐S, Wu C‐C, Shih Y‐N, Hsieh C‐H, Hsu J‐L. Breast cancer recurrence prediction with ensemble methods and cost‐sensitive learning. Open Med (Wars) 2021;16(1):754‐768.
    1. Kim JY, Lee YS, Yu J, et al. Deep learning‐based prediction model for breast cancer recurrence using adjuvant breast cancer cohort in tertiary cancer center registry. Front Oncol 2021;11:596364.
    1. Avanzo M, Porzio M, Lorenzon L, et al. Artificial intelligence applications in medical imaging: A review of the medical physics research in Italy. Phys Med 2021;83:221‐241.
    1. Parekh VS, Macura KJ, Harvey SC, et al. Multiparametric deep learning tissue signatures for a radiological biomarker of breast cancer: Preliminary results. Med Phys 2020;47(1):75‐88.

Publication types

LinkOut - more resources