Physics and Imaging in Radiation Oncology最新文献

{"title":"Necessity of energy layer repainting for proton radiotherapy in breast cancer patients","authors":"Bojan Štrbac,&nbsp;Truls Andersen,&nbsp;Jeffrey Free,&nbsp;Pietro Piscotta,&nbsp;John Maduro,&nbsp;Johannes A. Langendijk","doi":"10.1016/j.phro.2026.100971","DOIUrl":"10.1016/j.phro.2026.100971","url":null,"abstract":"<div><div>This study assessed the necessity of energy layer repainting for free-breathing breast proton therapy using pencil beam scanning (PBS). Ten patients were analyzed via log file-based 4D dose reconstruction across three scenarios: no repainting (1×), 3×, and 5× energy-layer repainting. Median target coverage deviations (D₉₈%) remained within ±4.1% for all strategies, with no statistically significant differences (p &gt; 0.05). Respiratory motion was minimal (mean &lt;2.2 mm)<strong>,</strong> while delivery time increased substantially with repainting. For free-breathing breast PBS with minimal respiratory motion, small target excursions, intra-fraction delivery averaging, and conventional fractionation rendered energy layer repainting unnecessary.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"39 ","pages":"Article 100971"},"PeriodicalIF":3.3,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147805655","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A comparative assessment of deep learning and knowledge-based dose prediction models for advanced radiotherapy planning of prostate cancer with focal boosting","authors":"Maria A. Piliero ,&nbsp;Antonio Angrisani ,&nbsp;Davide G. Bosetti ,&nbsp;Margherita Casiraghi ,&nbsp;Francesco Castronovo ,&nbsp;Nicolas Vial ,&nbsp;Salvatore Cozzi ,&nbsp;Matteo Coppotelli ,&nbsp;Klaudia Krzekotowska ,&nbsp;Lisa Milan ,&nbsp;Francesco Pupillo ,&nbsp;Stefano Presilla ,&nbsp;Thomas Zilli","doi":"10.1016/j.phro.2026.100977","DOIUrl":"10.1016/j.phro.2026.100977","url":null,"abstract":"<div><div>This study compared knowledge-based and deep-learning dose prediction models with clinically approved plans for prostate radiotherapy with focal boosting. The knowledge-based model accurately reproduced clinical plans. Deep-learning predictions showed median variations of 5% (IQR &lt; 5%) for bladder and rectum in high-dose regions and 3.8 Gy higher mean dose (IQR 1.2 Gy) for the femoral heads. However, pudendal artery mean doses were 15 Gy higher (IQR: 10–19 Gy) and urethral V_62.4Gy exceeded 50%, above the 2% constraint, likely reflecting their absence in the training dataset. While deep-learning models provide a consistent spatial framework for plan optimization, expert review remains essential.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"39 ","pages":"Article 100977"},"PeriodicalIF":3.3,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147805793","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The impact of DICOM import/export on radiotherapy structures in commercial systems","authors":"Mark J. Gooding ,&nbsp;Annamieke Koops ,&nbsp;Ciaran Malone ,&nbsp;David Nash ,&nbsp;Maxwell Robinson ,&nbsp;Daniel Rossiter ,&nbsp;Rita Simões ,&nbsp;Christina Skourou ,&nbsp;Georgios Tsekas ,&nbsp;Kieran Venner ,&nbsp;Djamal Boukerroui","doi":"10.1016/j.phro.2026.100981","DOIUrl":"10.1016/j.phro.2026.100981","url":null,"abstract":"<div><div>Background and Purpose: To investigate the impact that loading contours into an internal representation and saving them back to DICOM format has on contour position within commercially available contouring systems.</div><div>Materials and Methods: Two DICOM RT Structure Sets (RTSS) were loaded into 12 different commercial contour editing systems. Small non-editing actions were taken to prompt the systems to convert the structures to their internal representation. Contours were exported again as DICOM RTSS. The exported contours were compared to the original contours. The impact on contour similarity measures was quantified by their calculation against a common reference set for both the original and the re-exported contours.</div><div>Results: Average distances up to 0.23 mm were observed between the original and re-exported contours on thoracic data for some systems, with maximum distances up to 37.7 mm resulting from topological changes. Contour boundary changes impacted contouring similarity measures up to 2.6%, 29%, 35% and 21% for volumetric Dice Similarity Coefficient, 2D Mean Surface Distance, 3D Mean Surface Distance, and Hausdorff Distance, respectively. Notably, Surface Dice Similarity Coefficient and Normalised Added Path Length varied up to 96% and 97% respectively at low tolerances. Other systems preserved the original contours.</div><div>Conclusions: Caution should be employed when comparing contouring accuracy measures between studies or within multi-centre evaluations if different contouring systems have been used. For monitoring auto-contouring in clinical practice, differences between automatic and clinical contours smaller than one quarter of the in-plane voxel size can be disregarded, as possibly reflecting software-related effects rather than intentional editing.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"39 ","pages":"Article 100981"},"PeriodicalIF":3.3,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147860614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An evaluation of uncertainty quantification methods and measures for deep learning outcome prediction models in head and neck cancer radiotherapy","authors":"Daniel C. MacRae ,&nbsp;Luuk van der Hoek ,&nbsp;Joëlle E. van Aalst ,&nbsp;Suzanne P.M de Vette ,&nbsp;Robert van der Wal ,&nbsp;Hendrike Neh ,&nbsp;Baoqiang Ma ,&nbsp;Nanna M. Sijtsema ,&nbsp;Matias A. Valdenegro-Toro ,&nbsp;Peter M.A. van Ooijen ,&nbsp;Lisanne V. van Dijk","doi":"10.1016/j.phro.2026.100978","DOIUrl":"10.1016/j.phro.2026.100978","url":null,"abstract":"<div><h3>Background and Purpose</h3><div>Deep learning (DL) outcome prediction models show promise in radiotherapy but face limited clinical adoption due to concerns about prediction reliability. Although uncertainty quantification (UQ) can provide confidence estimates alongside predictions, there is currently little consensus on appropriate UQ approaches for DL-based outcome prediction. This study therefore evaluates and compares different UQ approaches for normal tissue complication probability (NTCP) and tumour control probability (TCP) models in head and neck cancer.</div></div><div><h3>Materials and Methods</h3><div>Four published DL models were reproduced: two NTCP models predicting xerostomia and dysphagia at six months post-treatment, and two TCP models predicting two-year survival and locoregional control. Three UQ methods—Monte Carlo dropout, deep ensembles, and test-time augmentation—and three uncertainty measures—predictive entropy, variance, and mutual information—were evaluated. Models were retrained on development sets (NTCP: 964 patients, TCP: 255 patients), and assessed on independent validation sets (NTCP: 241 patients, TCP: 85 patients) using discriminative performance, calibration metrics, and sparsification analysis.</div></div><div><h3>Results</h3><div>Incorporating UQ methods maintained comparable discriminative performance to baseline models across all endpoints (mean AUC: 0.72–0.73 vs 0.72). Deep ensembles and Monte Carlo dropout demonstrated strong calibration between uncertainty values and prediction accuracy, while test-time augmentation showed variable reliability. Entropy and variance consistently correlated with prediction accuracy, whereas mutual information proved unstable.</div></div><div><h3>Conclusions</h3><div>Monte Carlo dropout and deep ensembles provide meaningful uncertainty estimates for NTCP and TCP prediction without compromising model performance. These methods show potential for selective prediction workflows where high-confidence predictions guide treatment decisions while uncertain cases are flagged.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"39 ","pages":"Article 100978"},"PeriodicalIF":3.3,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147805656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Benchmarking a new radiochromic film type for photon and proton beam dosimetry","authors":"Peter Kuess ,&nbsp;Barbara Knäusl ,&nbsp;Sarah Helletzgruber ,&nbsp;Dietmar Georg ,&nbsp;Hugo Palmans ,&nbsp;Wolfgang Lechner","doi":"10.1016/j.phro.2026.100985","DOIUrl":"10.1016/j.phro.2026.100985","url":null,"abstract":"<div><h3>Background and Purpose:</h3><div>EBT4 Radiochromic films (RCFs) are replacing the well-described EBT3 type. This study aimed to benchmark the EBT4 type against its predecessor for photon (kV and MV) and proton beam dosimetry.</div></div><div><h3>Materials and Methods:</h3><div>Differences between the film types regarding the signal-to-noise ratio (SNR) were investigated in 6<!--> <!-->MV photon and 148.2<!--> <!-->MeV proton beams in the dose range of 0.2<!--> <!-->Gy to 10<!--> <!-->Gy for all RGB channels. The effect of the dose-averaged linear energy transfer (LET<span><math><msub><mrow></mrow><mrow><mi>d</mi></mrow></msub></math></span>) on the response of both film types was compared within a proton spread-out Bragg peak (SOBP). Furthermore, the relative response in low-kV X-rays was studied and the effect of long-term storage on both film types.</div></div><div><h3>Results:</h3><div>The SNR of EBT4 films was statistically superior for MV-photon irradiations above 1.5<!--> <!-->Gy in the red channel by up to 29<!--> <!-->%. For low-dose proton irradiations, the SNR of EBT3 was higher. The underresponse of both film types in a proton SOBP reached 5 to 7<!--> <!-->%. In low kV X-ray beams, EBT4 deviated from EBT3 on average by 2.5<!--> <!-->%. For irradiations of films with a dose of 2<!--> <!-->Gy or less after 216 days of storage, smaller differences in terms of pixel values were observed for films placed at 10°C.</div></div><div><h3>Conclusions:</h3><div>The presented results are in accordance with recent studies on EBT4 films and extend the knowledge on this film type, especially regarding proton beams and film storage.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"39 ","pages":"Article 100985"},"PeriodicalIF":3.3,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147860611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Structure visibility and online adaptation suitability of a new high-performance ring-gantry cone-beam computed tomography imaging system in thoracic radiotherapy","authors":"Agustinus J.A.J. van de Schoot,&nbsp;Joan J. Penninkhof,&nbsp;Britt Kunnen,&nbsp;Kimm P. Fremeijer,&nbsp;Elise M. Nicolai – Koornneef,&nbsp;Kirsten Offereins - van Harten,&nbsp;Judith H. Sluijter,&nbsp;Nienke D. Sijtsema,&nbsp;Marjan van de Pol,&nbsp;Raymond de Boer,&nbsp;Maarten L.P. Dirkx,&nbsp;Steven F. Petit","doi":"10.1016/j.phro.2026.100984","DOIUrl":"10.1016/j.phro.2026.100984","url":null,"abstract":"<div><h3>Background and purpose</h3><div>A recently introduced high-performance ring-gantry cone-beam computed tomography (CBCT_H) imaging system promises superior image quality compared with conventional ring-gantry CBCT imaging (CBCT_C), however, it incurs additional costs. Our aim was to determine the added value of CBCT_H compared with CBCT_C in thoracic radiotherapy by quantifying structure visibility and online adaptive radiotherapy (oART) suitability.</div></div><div><h3>Materials and methods</h3><div>Twenty lung cancer patients treated in free-breathing and twenty left-sided breast cancer patients treated in deep-inspiration breath-hold were included in this prospective clinical study. Three CBCT imaging pairs per patient, consisting of CBCT_H and CBCT_C acquired on consecutive days, were included. Four observers independently scored all 240 CBCT datasets on structure visibility and oART suitability (1–5 scale). The effect of respiratory motion management on image quality enhancement was determined by comparing cohort-specific score differences.</div></div><div><h3>Results</h3><div>In total, 4440 structure visibility and 960 oART suitability scores were collected. Patient-averaged scores favored CBCT_H in 82% (100%) of the cases in the lung (breast) cohort. Compared with CBCT_C, CBCT_H-based scores increased significantly (p &lt; 0.05) in both cohorts for structure visibility (lung: 2.8 to 3.1; breast: 3.1 to 3.8) and oART suitability (lung: 2.6 to 2.9; breast: 3.1 to 3.9). Structure visibility (oART suitability) score differences increased with deep-inspiration breath-hold (p &lt; 0.001) compared with free-breathing, by on average 0.38 (0.39).</div></div><div><h3>Conclusion</h3><div>In thoracic radiotherapy, CBCT_H yielded statistically significant improvements in structure visibility and oART suitability where the largest improvements were obtained for CBCT_H in deep-inspiration breath-hold. These results can contribute to informed decision-making regarding cost-effectiveness of CBCT_H.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"39 ","pages":"Article 100984"},"PeriodicalIF":3.3,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147805730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Corrigendum to “Clinical target volumes for glioma – Automated delineation to improve neuroanatomic consistency” [Phys. Imaging Radiat. Oncol. 36 (2025) 100865]","authors":"Gregory Buti ,&nbsp;Marcela Giovenco ,&nbsp;Tugba Yilmaz ,&nbsp;Ali Ajdari ,&nbsp;Christopher P. Bridge ,&nbsp;Gregory C. Sharp ,&nbsp;Fredrik Löfman ,&nbsp;Helen A. Shih ,&nbsp;Thomas Bortfeld","doi":"10.1016/j.phro.2026.100975","DOIUrl":"10.1016/j.phro.2026.100975","url":null,"abstract":"","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"39 ","pages":"Article 100975"},"PeriodicalIF":3.3,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147805791","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing the technical capability of a room- and a gantry-mounted kV imaging device for intra-fractional fluoroscopy during stereotactic lung radiotherapy at a C-arm linear accelerator","authors":"Hannah Jungreuthmayer ,&nbsp;Barbara Knäusl ,&nbsp;Julius Arnold ,&nbsp;Martin Buschmann ,&nbsp;Andreas Renner ,&nbsp;Maximilian Schmid ,&nbsp;Dietmar Georg ,&nbsp;Wolfgang Lechner","doi":"10.1016/j.phro.2026.100988","DOIUrl":"10.1016/j.phro.2026.100988","url":null,"abstract":"<div><h3>Background and Purpose:</h3><div>Monitoring lung tumors during stereotactic radiotherapy is important for managing breathing motion, yet the high-performance imaging modules on C-arm linear accelerators are mainly used for patient positioning. This study benchmarked a room-mounted against a gantry-mounted kilovolt (kV) imaging device to assess their potential for lung tumor fluoroscopy.</div></div><div><h3>Materials and Methods:</h3><div>The investigated systems were the ExacTrac Dynamic (ETD, Brainlab, Germany) and the X-ray Volumetric Imaging (XVI, Elekta, Sweden). Contrast-to-Noise Ratio (CNR) and entrance air kerma were measured for different imaging settings — tube voltage (70<!--> <!-->kV to 130<!--> <!-->kV), current (10<!--> <!-->mA to 320<!--> <!-->mA), exposure time (100<!--> <!-->ms and 40<!--> <!-->ms) — using two anthropomorphic thorax phantoms housing three tumors. Additionally, CNR change as a function of time, achievable fluoroscopy imaging duration based on X-ray generator and anode heat and X-ray tube cool-down were evaluated.</div></div><div><h3>Results:</h3><div>CNRs agreed within 15% for the two systems and changed less than 2% over the investigated fluoroscopy durations. Using default imaging settings and considering the average clinical duration of stereotactic lung treatments, entrance air kermas were 44<!--> <!-->mGy (room-mounted) and 41<!--> <!-->mGy (gantry-mounted). Achievable fluoroscopy durations with default settings were 87<!--> <!-->s and 1350<!--> <!-->s, respectively. Anode cool-down times were 125<!--> <!-->min (room-mounted) and 215<!--> <!-->min (gantry-mounted).</div></div><div><h3>Conclusion:</h3><div>The performance metrics of the room-mounted imaging system aligned with those of the gantry-mounted device with regard to CNR and air kerma. The room-mounted system showed a preferable cool-down behavior. However, adaptation of imaging settings is necessary to increase the fluoroscopy duration and avoid overheating.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"39 ","pages":"Article 100988"},"PeriodicalIF":3.3,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147860609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Estimation of accumulated dose to organs at risk in head and neck cancer patients treated with scheduled replanning and dose painting in the ARTFORCE trial","authors":"Anna Liza M.P. de Leeuw ,&nbsp;Simon R. van Kranen ,&nbsp;Jordi Giralt ,&nbsp;Yungan Tao ,&nbsp;Sergi Benavente ,&nbsp;Thanh-Vân F. Nguyen ,&nbsp;Frank J.P. Hoebers ,&nbsp;Ann Hoeben ,&nbsp;Chris H.J. Terhaard ,&nbsp;Lip Wai Lee ,&nbsp;Signe Friesland ,&nbsp;Roel J.H.M. Steenbakkers ,&nbsp;Harry Bartelink ,&nbsp;Coen R.N. Rasch ,&nbsp;Jan-Jakob Sonke ,&nbsp;Olga Hamming-Vrieze","doi":"10.1016/j.phro.2026.100957","DOIUrl":"10.1016/j.phro.2026.100957","url":null,"abstract":"<div><h3>Background and purpose</h3><div>This study investigated whether scheduled adaptive radiotherapy (ART) improved delivered dose to organs at risk (OAR) in patients with locally advanced head and neck cancer treated with dose painting (DP).</div></div><div><h3>Materials and methods</h3><div>Delivered doses were estimated for 81 patients who were prospectively treated with DP + ART using deformable image registration between CBCT and the planning CT’s. Three simulations were conducted, evaluating (1) a scenario without replanning (Sim_noART), (2) a scenario with ART at fraction 12 (Sim_ART), and (3) the clinical practice with ad hoc replanning (Sim_delivered). It was further evaluated whether selecting patients for ART using accumulated dose in the first 10 fractions (Df10) to the parotid glands and larynx would improve ART efficacy.</div></div><div><h3>Results</h3><div>In Sim_noART, 41% of patients had delivered dose deviations ≥ 3 Gy compared to the planned dose in any OAR, primarily in the parotid glands and larynx. No significant differences were seen between Sim_noART, Sim_ART and Sim_delivered (P ≥ 0.10). Df10 predicted relevant changes upon completing treatment with AUC ≥ 0.95. By selecting patients for ART using Df10, delivered dose significantly improved for the larynx (P ≤ 0.01).</div></div><div><h3>Conclusions</h3><div>Although relevant dose differences between planned and delivered doses were seen in almost half of the patients without ART, minimal improvements in delivered doses were seen introducing ART. Nonetheless, Df10 was prognostic for relevant changes upon completing treatment and selecting patients for ART significantly improved larynx dose. Incorporating accumulated dose into patient selection for ART could help avoid unforeseen increases in delivered dose.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"39 ","pages":"Article 100957"},"PeriodicalIF":3.3,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147860612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative analysis of artificial intelligence-based contouring of cardiac substructures on computed tomography scans for radiation therapy","authors":"Alexandra Moignier ,&nbsp;Tanguy Perennec ,&nbsp;Elise Prangères ,&nbsp;Bastien Bernard ,&nbsp;Angela Botticella ,&nbsp;Xinru Chen ,&nbsp;Robert Finnegan ,&nbsp;Sandrine Huger ,&nbsp;Anna Karlhede ,&nbsp;Thomas Lacornerie ,&nbsp;Fredrik Löfman ,&nbsp;Jérémy Palisson ,&nbsp;Charlotte Robert ,&nbsp;Killian Sambourg ,&nbsp;Jonas Söderberg ,&nbsp;Remus Stoica ,&nbsp;Grégory Delpon ,&nbsp;Elvire Martin-Mervoyer ,&nbsp;François Thillays ,&nbsp;Loïg Vaugier","doi":"10.1016/j.phro.2026.100935","DOIUrl":"10.1016/j.phro.2026.100935","url":null,"abstract":"<div><h3>Background and purpose</h3><div>Artificial intelligence-based contouring tools enable assessment of radiation doses to cardiac substructures beyond mean heart dose. This study examined inter-solution variations in raw contours and the impact of non-contrast enhancement on contours for each solution.</div></div><div><h3>Materials and methods</h3><div>Contrast-enhanced (CE) and non-contrast-enhanced (NCE) breath-hold thoracic computed tomography (CT) scans, sequentially acquired during the same imaging session for twenty lung cancer patients, were used. Seven commercial, three open-source, and one in-house AI solutions were evaluated. On CE-CTs, solutions were compared using Dice Similarity Coefficient (DSC) and 95th percentile of Hausdorff distance (HD95) across each pair of solutions. Then, the effect of non-contrast enhancement on contours was assessed using volume ratios between NCE-CT and CE-CT for each solution.</div></div><div><h3>Results</h3><div>Typically, ten cardiac substructures were contoured by most of the solutions. For the whole heart, cardiac chambers and great vessels, the average median DSC was above 0.8 for 55 of the 123 structure-solution pairs (45%), and the average median HD95 was below 10 mm for 47 of the 123 structure-solution pairs (38%). For the coronary arteries, the average median DSC ranged between 0.03 and 0.50 and the average median HD95 ranged between 19 mm and 70 mm. Non-contrast enhancement influenced results variably; volume differences were below 10% for 84 of the 123 structure-solution pairs (68%).</div></div><div><h3>Conclusions</h3><div>Automatic contouring solutions exhibited inter-solution variability for cardiac substructures that may have clinical impact. Greater transparency and standardisation of models, ideally through international consensus and shared datasets, are essential.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"38 ","pages":"Article 100935"},"PeriodicalIF":3.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147356941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}