Towards robust deep learning-based autosegmentation in MRI-planned gynecological brachytherapy: Importance of scalable development and comprehensive evaluation

Document Type

Article

Publication Date

1-1-2026

Publication Title

Brachytherapy

Keywords

Deep Learning, Humans, Brachytherapy, Female, Magnetic Resonance Imaging, Organs at Risk, Uterine Cervical Neoplasms, Radiotherapy Planning, Computer-Assisted, Radiotherapy Dosage, Urinary Bladder

Abstract

PURPOSE: To present comprehensive development and evaluation methodologies for a generalizable deep learning (DL)-driven autocontouring model of standard pelvic organs-at-risk (OARs) in MRI-planned cervical brachytherapy.

MATERIALS AND METHODS: A curated dataset of 200 3D-MRIs (85% training/validation, 15% testing) including multiple applicator types, varying treated anatomies, and manual contours of OARs (bladder, rectum, sigmoid, small bowel) by 3 physicians was utilized to develop an nnU-Net-based autocontouring model. Iterative tuning was conducted to determine the optimal hyperparameters and enhance evaluation metrics. Model performance was assessed using quantitative metrics, like geometric (e.g., Dice Coefficient (DC) and Hausdorff Distance 95th Percentile (HD95)) and dosimetric (dose-volume histograms (DVHs), dose differences (ΔD2cc)), and then correlated with qualitative physician-review (modified Turing and Likert tests).

RESULTS: Geometric metrics were best for bladder (e.g., mean ± SD DC|HD95(mm) 0.93 ± 0.02|2.26 ± 1.07) with greater variability exhibited for small bowel (0.62 ± 0.16|24.90 ± 14.36). Dosimetric comparisons of manual vs predicted contours showed high agreement in DVHs, with mean ΔD2cc < 0.60 Gy EQD2(3) across all OARs. Model performance was consistent, irrespective of applicator type, OAR volume, or contourer. Quantitative scores in support of DLM were not always associated with as favorable qualitative results, yet physician-review showed clinical acceptability (80% for bladder and rectum).

CONCLUSION: The DL-based autocontouring model, trained on a heterogeneous in-house dataset, demonstrates clinical acceptability for OARs as determined by comprehensive evaluation. It also shows promise for translatability to target contouring, and adaptability to other gynecological (noncervix) brachytherapy applications. Differences in qualitative and quantitative results exist; directionality and magnitude should be considered in clinical usability assessments of brachytherapy autocontouring models.

Medical Subject Headings

Deep Learning; Humans; Brachytherapy; Female; Magnetic Resonance Imaging; Organs at Risk; Uterine Cervical Neoplasms; Radiotherapy Planning, Computer-Assisted; Radiotherapy Dosage; Urinary Bladder

PubMed ID

41571559

ePublication

ePub ahead of print

Volume

25

Issue

2

First Page

361

Last Page

372

Share

COinS