Unknown

Dataset Information

0

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 study.


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.

SUBMITTER: Choi MS 

PROVIDER: S-EPMC10700624 | biostudies-literature | 2023 Nov

REPOSITORIES: biostudies-literature

altmetric image

Publications

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 study.

Choi Min Seo MS   Chang Jee Suk JS   Kim Kyubo K   Kim Jin Hee JH   Kim Tae Hyung TH   Kim Sungmin S   Cha Hyejung H   Cho Oyeon O   Choi Jin Hwa JH   Kim Myungsoo M   Kim Juree J   Kim Tae Gyu TG   Yeo Seung-Gu SG   Chang Ah Ram AR   Ahn Sung-Ja SJ   Choi Jinhyun J   Kang Ki Mun KM   Kwon Jeanny J   Koo Taeryool T   Kim Mi Young MY   Choi Seo Hee SH   Jeong Bae Kwon BK   Jang Bum-Sup BS   Jo In Young IY   Lee Hyebin H   Kim Nalee N   Park Hae Jin HJ   Im Jung Ho JH   Lee Sea-Won SW   Cho Yeona Y   Lee Sun Young SY   Chang Ji Hyun JH   Chun Jaehee J   Lee Eung Man EM   Kim Jin Sung JS   Shin Kyung Hwan KH   Kim Yong Bae YB  

Breast (Edinburgh, Scotland) 20231115


<h4>Purpose</h4>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.<h4>Methods and materials</h4>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 generat  ...[more]

Similar Datasets

| S-EPMC11408550 | biostudies-literature
| S-EPMC7807634 | biostudies-literature
| S-EPMC9630370 | biostudies-literature
| S-EPMC8691015 | biostudies-literature
| S-EPMC11867573 | biostudies-literature
| S-EPMC11914827 | biostudies-literature
| S-EPMC5364627 | biostudies-literature
| S-EPMC9911775 | biostudies-literature
| S-EPMC9250540 | biostudies-literature
| S-EPMC9576793 | biostudies-literature