CC BY 4.0 · Arch Plast Surg 2024; 51(01): 030-035
DOI: 10.1055/a-2190-5781
Breast/Trunk
Original Article

A Novel, Deep Learning-Based, Automatic Photometric Analysis Software for Breast Aesthetic Scoring

1   Department of Plastic and Reconstructive Surgery, Seoul National University Bundang Hospital, Seoul National University College of Medicine, Seongnamsi, Gyeonggi-do, Republic of Korea
,
1   Department of Plastic and Reconstructive Surgery, Seoul National University Bundang Hospital, Seoul National University College of Medicine, Seongnamsi, Gyeonggi-do, Republic of Korea
,
1   Department of Plastic and Reconstructive Surgery, Seoul National University Bundang Hospital, Seoul National University College of Medicine, Seongnamsi, Gyeonggi-do, Republic of Korea
,
1   Department of Plastic and Reconstructive Surgery, Seoul National University Bundang Hospital, Seoul National University College of Medicine, Seongnamsi, Gyeonggi-do, Republic of Korea
,
1   Department of Plastic and Reconstructive Surgery, Seoul National University Bundang Hospital, Seoul National University College of Medicine, Seongnamsi, Gyeonggi-do, Republic of Korea
› Author Affiliations
Funding None.

Abstract

Background Breast aesthetics evaluation often relies on subjective assessments, leading to the need for objective, automated tools. We developed the Seoul Breast Esthetic Scoring Tool (S-BEST), a photometric analysis software that utilizes a DenseNet-264 deep learning model to automatically evaluate breast landmarks and asymmetry indices.

Methods S-BEST was trained on a dataset of frontal breast photographs annotated with 30 specific landmarks, divided into an 80–20 training–validation split. The software requires the distances of sternal notch to nipple or nipple-to-nipple as input and performs image preprocessing steps, including ratio correction and 8-bit normalization. Breast asymmetry indices and centimeter-based measurements are provided as the output. The accuracy of S-BEST was validated using a paired t-test and Bland–Altman plots, comparing its measurements to those obtained from physical examinations of 100 females diagnosed with breast cancer.

Results S-BEST demonstrated high accuracy in automatic landmark localization, with most distances showing no statistically significant difference compared with physical measurements. However, the nipple to inframammary fold distance showed a significant bias, with a coefficient of determination ranging from 0.3787 to 0.4234 for the left and right sides, respectively.

Conclusion S-BEST provides a fast, reliable, and automated approach for breast aesthetic evaluation based on 2D frontal photographs. While limited by its inability to capture volumetric attributes or multiple viewpoints, it serves as an accessible tool for both clinical and research applications.

Authors' Contributions

Conceptualization: J.K-h.P., C.Y.H., J.H.J., Y.M.


Data curation: S.B.


Formal analysis: J.K-h.P., S.B.


Writing—original draft: J.K-h.P.


Writing—review and editing: S.B., C.Y.H., J.H.J., Y.M.


Ethical Approval

The study was performed in accordance with the principles of the Declaration of Helsinki. The study was approved by the Institutional Review Board of Seoul National University Bundang Hospital (IRB#B-2207-770-101).


Patient Consent

Written informed consent was obtained from the author.




Publication History

Received: 02 May 2023

Accepted: 26 September 2023

Accepted Manuscript online:
12 October 2023

Article published online:
07 February 2024

© 2024. The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution License, permitting unrestricted use, distribution, and reproduction so long as the original work is properly cited. (https://creativecommons.org/licenses/by/4.0/)

Thieme Medical Publishers, Inc.
333 Seventh Avenue, 18th Floor, New York, NY 10001, USA

 
  • References

  • 1 Harris JR, Levene MB, Svensson G, Hellman S. Analysis of cosmetic results following primary radiation therapy for stages I and II carcinoma of the breast. Int J Radiat Oncol Biol Phys 1979; 5 (02) 257-261
  • 2 Patterson MP, Pezner RD, Hill LR, Vora NL, Desai KR, Lipsett JA. Patient self-evaluation of cosmetic outcome of breast-preserving cancer treatment. Int J Radiat Oncol Biol Phys 1985; 11 (10) 1849-1852
  • 3 Westreich M. Anthropomorphic breast measurement: protocol and results in 50 women with aesthetically perfect breasts and clinical application. Plast Reconstr Surg 1997; 100 (02) 468-479
  • 4 Kwon SH, Lao WW, Lee CH. et al. Experiences and attitudes toward aesthetic procedures in East Asia: a cross-sectional survey of five geographical regions. Arch Plast Surg 2021; 48 (06) 660-669
  • 5 Cardoso MJ, Cardoso J, Amaral N. et al. Turning subjective into objective: the BCCT.core software for evaluation of cosmetic results in breast cancer conservative treatment. Breast 2007; 16 (05) 456-461
  • 6 Krois W, Romar AK, Wild T. et al. Objective breast symmetry analysis with the breast analyzing tool (BAT): improved tool for clinical trials. Breast Cancer Res Treat 2017; 164 (02) 421-427
  • 7 Monton J, Kenig N, Chang-Azancot L, Jordan J, Insausti R. A free tool for breast aesthetic scale computation. Ann Plast Surg 2021; 86 (04) 458-462
  • 8 Pezner RD, Patterson MP, Hill LR. et al. Breast retraction assessment: an objective evaluation of cosmetic results of patients treated conservatively for breast cancer. Int J Radiat Oncol Biol Phys 1985; 11 (03) 575-578
  • 9 Cardoso JS, Silva W, Cardoso MJ. Evolution, current challenges, and future possibilities in the objective assessment of aesthetic outcome of breast cancer locoregional treatment. Breast 2020; 49: 123-130
  • 10 Gonçalves T, Silva W, Cardoso MJ. et al. A novel approach to keypoint detection for the aesthetic evaluation of breast cancer surgery outcomes. Health Technol (Berl) 2020; 10 (04) 891-903
  • 11 Najmiddinov B, Park JK, Yoon KH. et al. Conventional versus modified nipple sparing mastectomy in immediate breast reconstruction: complications, aesthetic, and patient-reported outcomes. Front Surg 2022; 9: 1001019
  • 12 Myung Y, Jeon S, Heo C. et al. Validating machine learning approaches for prediction of donor related complication in microsurgical breast reconstruction: a retrospective cohort study. Sci Rep 2021; 11 (01) 5615
  • 13 Park JK, Park S, Heo CY, Jeong JH, Yun B, Myung Y. The safety of operating on breasts with a history of prior reduction mammoplasty: dynamic magnetic resonance imaging analysis of angiogenesis. Aesthet Surg J 2022; 42 (03) NP151-NP158
  • 14 Cardoso MJ, Cardoso JS, Oliveira HP, Gouveia P. The breast cancer conservative treatment. Cosmetic results - BCCT.core - Software for objective assessment of esthetic outcome in breast cancer conservative treatment: a narrative review. Comput Methods Programs Biomed 2016; 126: 154-159
  • 15 Han HH, Choi JM, Eom JS. Objective photographic assessments and comparisons of immediate bilateral breast reconstruction using deep inferior epigastric perforator flaps and implants. Arch Plast Surg 2021; 48 (05) 473-482
  • 16 Kim DY, Lee SJ, Kim EK. et al. Feasibility of anomaly score detected with deep learning in irradiated breast cancer patients with reconstruction. NPJ Digit Med 2022; 5 (01) 125