Image-Conditioned Diffusion Models for Quality Assurance of Organ-at-Risk Segmentations in Radiotherapy

Clea Dronne; Catharine H Clark; Xavier Loizeau; Elizabeth Miles; Peter Hoskin; Jamie R McClelland

cs.CVAug 24, 2026

Image-Conditioned Diffusion Models for Quality Assurance of Organ-at-Risk Segmentations in Radiotherapy

Authors: Clea Dronne, Catharine H Clark, Xavier Loizeau, Elizabeth Miles, Peter Hoskin, Jamie R McClelland

Organizations: UCL Hawkes Institute, Department of Medical Physics and Biomedical Engineering, University College London, London, United Kingdom · National Physical Laboratory, Teddington, UK · Department of Medical Physics and Biomedical Engineering, University College London, London, United Kingdom · Department of Radiotherapy Physics, University College London Hospital, London, UK ·

Abstract

Accurate organ-at-risk segmentation is essential for radiotherapy planning, but reviewing segmentations is time-consuming and subjective. We investigate normative modelling for segmentation error detection in head-and-neck CT, comparing a VAE framework with an image-conditioned segmentation diffusion model. Models were evaluated on RADCURE brainstem and spinal cord segmentations using simulated boundary and width perturbations. Error detection was assessed using the Dice similarity coefficient and the Distance to Agreement (DTA) between the input and reconstructed segmentations. While both models detected some simulated errors, regional DTA showed that the diffusion model localised subtle boundary errors more consistently. These results support image-conditioned diffusion reconstruction as a promising framework for localised, anatomy-aware segmentation QA.

Figures & tables

Figure 1: Model architectures compared in this work: image-conditioned segmentation diffusion model and VAE baseline.

Figure 2: Examples of reconstructions generated by the VAE and diffusion model for simulated brainstem $-2\uparrow$ and $-3\downarrow$ and spinal cord $+3\uparrow$ boundary errors. Top rows show input and reconstructed segmentations overlaid on CT images; bottom rows show corresponding DTA maps. Cyan contours indicate the simulated error region.

Brainstem
	VAE		Diffusion model
	DSC	DTA	DSC	DTA
$0$	$0.94\pm 0.02$	$0.15\pm 0.05$	$0.92\pm 0.03$	$0.32\pm 0.64$
$-5\uparrow$	$0.94\pm 0.02$	$0.22\pm 0.43$	$0.89\pm 0.04$	$0.94\pm 1.24$
$+5\uparrow$	$0.92\pm 0.02$	$0.24\pm 0.10$	$0.90\pm 0.02$	$0.39\pm 0.33$
$-5\downarrow$	$0.94\pm 0.02$	$0.18\pm 0.12$	$0.91\pm 0.03$	$0.46\pm 0.66$

Table 1: Global DSC and DTA between input and reconstructed segmentations for original and perturbed brainstem and spinal cord cases. The

0

row indicates no error;

\uparrow

denotes superior boundary shifts,

\downarrow

inferior, and

\leftrightarrow

transverse widening. Values are mean

\pm

standard deviation. Bold indicates no significant difference from the no-error condition under a paired one-sided Wilcoxon signed-rank test (

p\geq 0.05

	VAE			Diffusion model
	Original	Error	p-value	Original	Error	p-value
Brainstem
$-2\uparrow$	$0.11\pm 0.12$	$0.17\pm 0.39$	$\mathbf{1.00}$	$0.08\pm 0.09$	$1.11\pm 0.52$	$<0.001$
$-1\uparrow$	$0.16\pm 0.23$	$0.08\pm 0.27$	$\mathbf{1.00}$	$0.10\pm 0.16$	$0.59\pm 0.50$	$<0.001$
$+1\uparrow$	$0.64\pm 0.10$	$0.44\pm 0.20$	$\mathbf{1.00}$	$0.65\pm 0.13$	$0.41\pm 0.20$	$\mathbf{1.00}$
$+2\uparrow$	$0.57\pm 0.13$	$0.41\pm 0.20$	$\mathbf{1.00}$	$0.64\pm 0.21$	$0.41\pm 0.24$	$\mathbf{1.00}$

Table 2: Regional DTA within the simulated-error region, compared between original and perturbed segmentations.

\uparrow

denotes superior boundary shifts,

\downarrow

inferior, and

\leftrightarrow

transverse widening. Values are mean

\pm

standard deviation. Bold values indicate no significant DTA increase for the perturbed segmentation under a paired one-sided Wilcoxon signed-rank test (

p\geq 0.05

Medical Image Anomaly Detection

Medical image anomaly detection finds and localizes unusual anatomy or pathology in scans, often when labeled disease examples are scarce.

See all 87 papers

Budget-Aware Uncertainty for Radiotherapy Segmentation QA Using nnU-Net
Apr 13, 2026Ricardo Coimbra Brioso, Lorenzo Mondo, Damiano Dei +4Segmentation Uncertainty Estimation Medical Image Segmentation
Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milan, Italy · Department of Biomedical Sciences, Humanitas University, Pieve Emanuele, Milan, Italy · Radiotherapy and Radiosurgery Department, IRCCS Humanitas Research Hospital, Rozzano, Milan, Italy
Uncertainty as a Proxy for Semantic Correctness in Diffusion-Based Medical Image Synthesis
Oct 2, 2026Yuxuan Ou, Konstantinos Kamnitsas, OxAAA Study +3Medical Image Synthesis Diffusion-Based OOD Detection
Department of Engineering Science, University of Oxford, Oxford, United Kingdom · Nuffield Department of Surgical Sciences, University of Oxford, Oxford, United Kingdom
Bound-Aware Per-Organ Recall Risk Control for Multi-Organ CT Segmentation under Clinical Domain Shift
Aug 18, 2026Souraj Adhikary, Negar Chabi, Andre MastmeyerMulti-Organ Segmentation Medical Image Segmentation
Department of Engineering Sciences, Jade Hochschule Wilhelmshaven, Germany

Apr 13, 2026J/K move · Enter open · S save

Budget-Aware Uncertainty for Radiotherapy Segmentation QA Using nnU-Net

Ricardo Coimbra Brioso, Lorenzo Mondo, Damiano Dei, Nicola Lambri+3

Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milan, Italy · Department of Biomedical Sciences, Humanitas University, Pieve Emanuele, Milan, Italy · Radiotherapy and Radiosurgery Department, IRCCS Humanitas Research Hospital, Rozzano, Milan, Italy

Segmentation Uncertainty Estimation Medical Image Segmentation Uncertainty Calibration Oncology

Open paper AskPDF arXiv

Accurate delineation of the Clinical Target Volume (CTV) is essential for radiotherapy planning, yet remains time-consuming and difficult to assess, especially for complex treatments such as Total Marrow and Lymph Node Irradiation (TMLI). While deep learning-based auto-segmentation can reduce workload, safe clinical deployment requires reliable cues indicating where models may be wrong. In this work, we propose a budget-aware uncertainty-driven quality assurance (QA) framework built on nnU-Net, combining uncertainty quantification and post-hoc calibration to produce voxel-wise uncertainty maps (based on predictive entropy) that can guide targeted manual review. We compare temperature scaling (TS), deep ensembles (DE), checkpoint ensembles (CE), and test-time augmentation (TTA), evaluated both individually and in combination on TMLI as a representative use case. Reliability is assessed through ROI-masked calibration metrics and uncertainty--error alignment under realistic revision constraints, summarized as AUC over the top 0-5% most uncertain voxels. Across configurations, segmentation accuracy remains stable, whereas TS substantially improves calibration. Uncertainty-error alignment improves most with calibrated checkpoint-based inference, leading to uncertainty maps that highlight more consistently regions requiring manual edits. Overall, integrating calibration with efficient ensembling seems a promising strategy to implement a budget-aware QA workflow for radiotherapy segmentation.

Abstract

Medical Image Anomaly Detection

Explore similar work

Budget-Aware Uncertainty for Radiotherapy Segmentation QA Using nnU-Net

Uncertainty as a Proxy for Semantic Correctness in Diffusion-Based Medical Image Synthesis

Bound-Aware Per-Organ Recall Risk Control for Multi-Organ CT Segmentation under Clinical Domain Shift