Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Assessment of deep learning-based auto-contouring on interobserver consistency in target volume and organs-at-risk delineation for breast cancer: Implications for RTQA program in a multi-institutional studyopen access

Authors
Choi, Min SeoChang, Jee SukKim, KyuboKim, Jin HeeKim, Tae HyungKim, SungminCha, HyejungCho, OyeonChoi, Jin HwaKim, MyungsooKim, JureeKim, Tae GyuYeo, Seung-GuChang, Ah RamAhn, Sung-JaChoi, JinhyunKang, Ki MunKwon, JeannyKoo, TaeryoolKim, Mi YoungChoi, Seo HeeJeong, Bae KwonJang, Bum-SupJo, In YoungLee, HyebinKim, NaleePark, Hae JinIm, Jung HoLee, Sea-WonCho, YeonaLee, Sun YoungChang, Ji HyunChun, JaeheeLee, Eung ManKim, Jin SungShin, Kyung HwanKim, Yong Bae
Issue Date
Feb-2024
Publisher
Churchill Livingstone
Keywords
Auto-contouring; Breast cancer; Deep learning; Inter-observer variation; RTQA
Citation
Breast, v.73
Indexed
SCOPUS
Journal Title
Breast
Volume
73
URI
https://scholarworks.gnu.ac.kr/handle/sw.gnu/68810
DOI
10.1016/j.breast.2023.103599
ISSN
0960-9776
1532-3080
Abstract
Purpose: To quantify interobserver variation (IOV) in target volume and organs-at-risk (OAR) contouring across 31 institutions in breast cancer cases and to explore the clinical utility of deep learning (DL)-based auto-contouring in reducing potential IOV. Methods and materials: In phase 1, two breast cancer cases were randomly selected and distributed to multiple institutions for contouring six clinical target volumes (CTVs) and eight OAR. In Phase 2, auto-contour sets were generated using a previously published DL Breast segmentation model and were made available for all participants. The difference in IOV of submitted contours in phases 1 and 2 was investigated quantitatively using the Dice similarity coefficient (DSC) and Hausdorff distance (HD). The qualitative analysis involved using contour heat maps to visualize the extent and location of these variations and the required modification. Results: Over 800 pairwise comparisons were analysed for each structure in each case. Quantitative phase 2 metrics showed significant improvement in the mean DSC (from 0.69 to 0.77) and HD (from 34.9 to 17.9 mm). Quantitative analysis showed increased interobserver agreement in phase 2, specifically for CTV structures (5–19 %), leading to fewer manual adjustments. Underlying IOV differences causes were reported using a questionnaire and hierarchical clustering analysis based on the volume of CTVs. Conclusion: DL-based auto-contours improved the contour agreement for OARs and CTVs significantly, both qualitatively and quantitatively, suggesting its potential role in minimizing radiation therapy protocol deviation. © 2023
Files in This Item
There are no files associated with this item.
Appears in
Collections
College of Medicine > Department of Medicine > Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Jeong, Bae Kwon photo

Jeong, Bae Kwon
의과대학 (의학과)
Read more

Altmetrics

Total Views & Downloads

BROWSE