End-user validation of BRIGHT with custom-developed graphical user interface applied to cervical cancer brachytherapy

Leah R. M. Dickhoff; Ellen M. Kerkhof; Heloisa H. Deuzeman; Laura A. Velema; Stephanie M. de Boer; Lavinia A. L. Verhagen; Danique L. J. Barten; Bradley R. Pieters

cs.NEFeb 18, 2026

End-user validation of BRIGHT with custom-developed graphical user interface applied to cervical cancer brachytherapy

Authors: Leah R. M. Dickhoff, Ellen M. Kerkhof, Heloisa H. Deuzeman, Laura A. Velema, Stephanie M. de Boer, Lavinia A. L. Verhagen, Danique L. J. Barten, Bradley R. Pieters,

Abstract

Multi-objective optimisation using BRIGHT has proven insightful and effective in prostate cancer brachytherapy treatment planning. BRachytherapy via artificially Intelligent GOMEA-Heuristic based Treatment planning (BRIGHT) generates multiple treatment plans, each with a different trade-off between tumour coverage and organs-at-risk sparing. BRIGHT was recently extended to cervical cancer brachytherapy. In this study, we present a novel, custom-developed graphical user interface (GUI) that enables plan navigation, pairwise comparisons, dose distribution visualisation, and possibility for adjustments - essential for efficient clinical use of BRIGHT. End-user validation of BRIGHT with the dedicated GUI was conducted for cervical cancer brachytherapy by emulating clinical practice in ten previously treated patients. A multidisciplinary brachytherapy team used BRIGHT to create new treatment plans. GUI usability was assessed using the System Usability Scale (SUS). BRIGHT plan quality was compared to clinical practice via blinded one-on-one comparisons. The GUI offered helpful features for plan navigation and evaluation, giving users quick insight into whether planning aims are achievable and what treatment options are available. The overall SUS score was 83.3, indicating an 'excellent' system. BRIGHT outperformed clinical practice in five out of ten patients regarding the coverage-sparing trade-off and performed equally well in the remaining five. The BRIGHT plan was preferred over the clinical plan in eight out of ten patients, four of which showed clinically relevant differences. The clinical plan was preferred in two patients, neither with clinically relevant differences. In conclusion, BRIGHT, with its dedicated GUI, is a clinically viable and user-friendly tool for treatment planning in cervical cancer brachytherapy.

Figures & tables

Figure 1: Main window of the BRIGHT GUI. The numbered subparts refer to the subsections in which they are further explained. Subparts 2.1.2 and 2.1.3 are for treatment plan navigation and selection, whereas the other subparts aid in treatment plan evaluation. The three images show the different regions of interest as a delineated colorwash (legend: top right), superposed with isodose lines depicting areas receiving the same radiation dose (legend: mid right, in % of the prescription dose of 7 Gy).

Figure 2: Catheter time chart with distribution of dwell times associated with the separate ovoids, the intrauterine applicator, and the needles.

Figure 3: Tab in the BRIGHT GUI allowing for one-on-one plan comparison with a (retractable) middle view corresponding to the difference in dose between the two plans as a colourwash, with green representing a higher dose from the right plan, and purple a higher dose from the left plan. All dose aims from EMBRACE-II are given side by side in a table, in physical dose, and total EQD2 in brackets. The legend of the ROIs and isodose lines can be found in Figure 1

Figure 4: Re-optimisation settings window.

Figure 5: Workflow for BRIGHT treatment plan selection (and adjustments). Steps shown in grey are optional. See [ 28 ] for explanations of the DICOM standard.

No.	Purpose	End-user(s)	Filled in at time	Full list of questions
1	Patient-specific: BRIGHT plan quality, features used	BT team	After each patient case validation session	Suppl. Table 3
2A	SUS	Every end-user separately	After all validation sessions	Table 4
2B	Software-specific			Table 4
2C	Open questions			Suppl. Table 4
3	Comparison of BRIGHT plan vs. clinical plan	Rad. oncologist	During comparison study	Suppl. Table 5

Table 1: Overview of all questionnaires used in this work.

Panel of Figure 6 — Figure 6: Pareto approximation fronts with the selected plan, possibly adjusted BRIGHT(+Oncentra) plan, and the clinical plan for four representative patient cases. The set of plans that is available after the first optimisation run is plotted in light grey. If re-optimisation was performed and a resulting plan was selected, that set is plotted in dark grey.

Time in BRIGHT	8.5 min (5.0-16.0)
Time in Oncentra	8.0 min (0.0-17.0)
Adjustment in Oncentra explored	7/10 cases
Adjustment considered necessary	3/10 cases
Patient information impacted plan choice	4/10 cases

Table 2: Descriptive statistics on plan choice and manual adjustments in Oncentra. Times given as median (minimum-maximum) in minutes.

Feature	Adjustment type	Number of times used per case
Re-optimisation	Maximum time for specific dwell(s)	1 (0-2)
	Single needle contribution	0 (0-1)
	Total needle contribution	0 (0-1)
	Ovoid contribution	0 (0-0)
	Protocol	0 (0-0)
	Total	1.5 (0-3)

Table 3: Median (minimum-maximum) of number of times specific features have been used over all 10 patient cases.

	Statement	Best possible score	RO	MP	RTT
SUS	1. I think I would like to use this system frequently	5	5	4	5
	2. I found the system unnecessarily complex	1	2	1	2
	3. I thought the system was easy to use	5	4	4	4
	4. I think that I would need the support of a technical person to be able to use this system	1	2	1	2
	5. I found the various functions in this system were well integrated	5	5	4	4
	6. I thought there was too much inconsistency in this system	1	1	2	2

Table 4: Responses to Questionnaire 2A (SUS) and Questionnaire 2B (software-specific) by the radiation oncologist (RO), medical physicist (MP), and radiation therapy technologist (RTT). Response options range from 1 = strongly disagree, 2 = disagree, 3 = neither agree or disagree, 4 = agree, to 5 = strongly agree. As some statements are worded negatively, the best possible score column indicates whether high or low values are desirable for each statement.

	SUS score
Radiation oncologist	87.5
Medical physicist	85.0
Radiation therapy technologist	77.5
Mean	83.3

Table 5: SUS score (Questionnaire 2A) per discipline, as well as the overall mean.

Panel of Figure 7 — Figure 7: a. Preferred plan (right for BRIGHT, left for clinical) based on EMBRACE-II DV metric values, 3D dose distribution, and overall plan choice for all 10 patient cases. Each colour represents a different end-user, with differences judged as clinically irrelevant shown in transparent. b. Overall plan choice preferences after the consensus meeting, with results plotted as black boxes.

Oncology

Oncology studies cancer biology, prevention, diagnosis, treatment, and data-driven ways to improve patient care.

See all 259 papers

BAT-RM: A Boundary-Aware Transformer with Region-Aware Multi-Directional Mamba for Clinically Deployed Cervical Cancer Radiotherapy Auto-Contouring
Jul 11, 2026Istiak Ahmed, Kazi Shahriar Sanjid, Galib Ahmed +16Visual SSMs Medical Image Segmentation
Department of Electrical and Computer Engineering, North South University, Dhaka, 1229, Bangladesh · Big-Matrix Lab, Department of Mathematics and Physics, North South University, Dhaka, 1229, Bangladesh · Department of Data Science, Erlangen, Friedrich-Alexander University, 91054, Germany +8
Clinical Reasoning AI for Oncology Treatment Planning: A Multi-Specialty Case-Based Evaluation
Mar 27, 2026Philippe E. Spiess, Md Muntasir Zitu, Alison Walker +33Clinical Decision Support Oncology
Moffitt Cancer Center and Research Institute, 12902 Magnolia Drive, Tampa, FL 33612, USA. · Innova Montréal Inc., IT Services and Consulting, Montréal, QC, Canada. · Oncobrain, Inc., Tampa, FL, USA. +1
A Breast Vision Pathology Foundation Model for Real-world Clinical Utility
May 6, 2026Yingxue Xu, Zhengyu Zhang, Xiuming Zhang +32Healthcare Clinical Decision Support
Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong SAR, China · Department of Pathology, Nanfang Hospital, School of Basic Medical Sciences, Southern Medical University, Guangzhou, China · Department of Pathology, The First Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, China +18

Jul 11, 2026J/K move · Enter open · S save

BAT-RM: A Boundary-Aware Transformer with Region-Aware Multi-Directional Mamba for Clinically Deployed Cervical Cancer Radiotherapy Auto-Contouring

Istiak Ahmed, Kazi Shahriar Sanjid, Galib Ahmed, Md. Tanzim Hossain+15

Department of Electrical and Computer Engineering, North South University, Dhaka, 1229, Bangladesh · Big-Matrix Lab, Department of Mathematics and Physics, North South University, Dhaka, 1229, Bangladesh · Department of Data Science, Erlangen, Friedrich-Alexander University, 91054, Germany+8

Visual SSMs Medical Image Segmentation Oncology Boundary-Aware Segmentation

Open paper AskPDF arXiv

We present a clinically deployed end-to-end auto-contouring system for cervical cancer radiotherapy planning, anchored by the Boundary-Aware Transformer with Region-Aware Mamba (BAT-RM), a hybrid architecture that integrates Sobel-gated boundary attention, a linear-time, multi-directional Mamba module for long-range context, and a boundary-skeleton-guided fusion gate. This design achieves linear-time complexity for long-range context modeling, avoiding the quadratic cost of full spatial self-attention. The full pipeline spans multi-institutional data collection, rigorous inter-rater quality assurance, external validation in an independent cohort, and a web-based clinical interface natively compatible with Varian, RayStation, and Monaco. Against four baselines, BAT-RM achieves superior performance across seven anatomical classes, with statistically significant improvements in target volumes, including GTV and CTV, and in organs at risk such as the rectum and bladder. A prospective multi-center reader study involving 13 radiation oncologists demonstrated that AI assistance elevates junior oncologists' IoU from 0.899 to 0.965, approaching senior-level accuracy, while reducing contouring time by more than 80%. The system also reduced expert consultation rates and improved inter-reader consistency, reflecting gains in both efficiency and quality assurance. Following clinical deployment at a partner hospital, the system reduced patient wait times from days to hours without additional staffing, enabling same-day or next-day initiation of treatment for routine cases. BAT-RM demonstrates that a rigorous research pipeline, from data curation to clinical deployment, can translate directly into measurable patient benefit in resource-constrained settings where the demand for radiotherapy far exceeds specialist capacity.

Abstract

Oncology

Explore similar work

BAT-RM: A Boundary-Aware Transformer with Region-Aware Multi-Directional Mamba for Clinically Deployed Cervical Cancer Radiotherapy Auto-Contouring

Clinical Reasoning AI for Oncology Treatment Planning: A Multi-Specialty Case-Based Evaluation

A Breast Vision Pathology Foundation Model for Real-world Clinical Utility