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
. 2021 Oct 14;16(1):203.
doi: 10.1186/s13014-021-01923-1.

Evaluation of deep learning-based autosegmentation in breast cancer radiotherapy

Hwa Kyung Byun  1 , Jee Suk Chang  2 , Min Seo Choi  1 , Jaehee Chun  1 , Jinhong Jung  3 , Chiyoung Jeong  4 , Jin Sung Kim  1 , Yongjin Chang  5 , Seung Yeun Chung  1   6 , Seungryul Lee  7 , Yong Bae Kim  1
Affiliations

Evaluation of deep learning-based autosegmentation in breast cancer radiotherapy

Hwa Kyung Byun et al. Radiat Oncol. .

Abstract

Purpose: To study the performance of a proposed deep learning-based autocontouring system in delineating organs at risk (OARs) in breast radiotherapy with a group of experts.

Methods: Eleven experts from two institutions delineated nine OARs in 10 cases of adjuvant radiotherapy after breast-conserving surgery. Autocontours were then provided to the experts for correction. Overall, 110 manual contours, 110 corrected autocontours, and 10 autocontours of each type of OAR were analyzed. The Dice similarity coefficient (DSC) and Hausdorff distance (HD) were used to compare the degree of agreement between the best manual contour (chosen by an independent expert committee) and each autocontour, corrected autocontour, and manual contour. Higher DSCs and lower HDs indicated a better geometric overlap. The amount of time reduction using the autocontouring system was examined. User satisfaction was evaluated using a survey.

Results: Manual contours, corrected autocontours, and autocontours had a similar accuracy in the average DSC value (0.88 vs. 0.90 vs. 0.90). The accuracy of autocontours ranked the second place, based on DSCs, and the first place, based on HDs among the manual contours. Interphysician variations among the experts were reduced in corrected autocontours, compared to variations in manual contours (DSC: 0.89-0.90 vs. 0.87-0.90; HD: 4.3-5.8 mm vs. 5.3-7.6 mm). Among the manual delineations, the breast contours had the largest variations, which improved most significantly with the autocontouring system. The total mean times for nine OARs were 37 min for manual contours and 6 min for corrected autocontours. The results of the survey revealed good user satisfaction.

Conclusions: The autocontouring system had a similar performance in OARs as that of the experts' manual contouring. This system can be valuable in improving the quality of breast radiotherapy and reducing interphysician variability in clinical practice.

Keywords: Autocontouring; Breast; Organs at risk; Radiotherapy.

PubMed Disclaimer

Conflict of interest statement

None.

Figures

Fig. 1
Fig. 1
A Dice similarity coefficient and B Hausdorff distance values, based on the organs at risk. The manual contours, corrected autocontours, and autocontours are compared. Data are presented as the mean ± standard error
Fig. 2
Fig. 2
Radar graphs showing the mean Dice similarity coefficient value of each participant, based on the organ at risk. A Manual contours. B Corrected autocontours. The Dice similarity coefficient values of the corrected-autocontours are more homogeneous than those of the manual contours, which indicate reduced interphysician variability
Fig. 3
Fig. 3
Examples of manual and corrected autocontours of all experts. A The breast contours show that interphysician variability in manual contours occurs mostly at the lateral and anterior borders of the breasts, and that this variability is reduced in corrected autocontours. B The heart contours show that interphysician variability in manual contours occurs mostly for the superior borders of the hearts, and that this variability is reduced in corrected autocontours
Fig. 4
Fig. 4
A comparison of the contouring time for manual contouring and corrected autocontouring. A The total contouring time of all nine organs at risk of each expert. B The contouring time of each organ at risk. Data are presented as the mean ± standard error
See this image and copyright information in PMC

References

    1. Fogliata A, Nicolini G, Alber M, Asell M, Dobler B, El-Haddad M, et al. IMRT for breast. A planning study. Radiother Oncol. 2005;76(3):300–310. doi: 10.1016/j.radonc.2005.08.004. - DOI - PubMed
    1. Bi WL, Hosny A, Schabath MB, Giger ML, Birkbak NJ, Mehrtash A, et al. Artificial intelligence in cancer imaging: clinical challenges and applications. CA Cancer J Clin. 2019;69(2):127–157. - PMC - PubMed
    1. Jiang F, Grigorev A, Rho S, Tian Z, Fu Y, Jifara W, et al. Medical image semantic segmentation based on deep learning. Neural Comput Appl. 2018;29(5):1257–1265. doi: 10.1007/s00521-017-3158-6. - DOI
    1. Wright JL, Yom SS, Awan MJ, Dawes S, Fischer-Valuck B, Kudner R, et al. Standardizing normal tissue contouring for radiation therapy treatment planning: an ASTRO consensus paper. Pract Radiat Oncol. 2019;9(2):65–72. doi: 10.1016/j.prro.2018.12.003. - DOI - PubMed
    1. Men K, Zhang T, Chen X, Chen B, Tang Y, Wang S, et al. Fully automatic and robust segmentation of the clinical target volume for radiotherapy of breast cancer using big data and deep learning. Phys Med. 2018;50:13–19. doi: 10.1016/j.ejmp.2018.05.006. - DOI - PubMed

Publication types

MeSH terms