Physics and Imaging in Radiation Oncology最新文献

{"title":"On the impact of improved dose calculation accuracy in clinical treatment planning for superficial high-dose-rate brachytherapy of extensive scalp lesions","authors":"Giulio Rossi ,&nbsp;Vasiliki Peppa ,&nbsp;Mark Gainey ,&nbsp;Michael Kollefrath ,&nbsp;Tanja Sprave ,&nbsp;Panagiotis Papagiannis ,&nbsp;Dimos Baltas","doi":"10.1016/j.phro.2024.100673","DOIUrl":"10.1016/j.phro.2024.100673","url":null,"abstract":"<div><div>TG-43-based dose calculations disregard tissue heterogeneities and finite scatter conditions, prompting the introduction of model-based dose calculation algorithms (MBDCAs) to improve accuracy in high-dose-rate (HDR) brachytherapy. This study evaluated the effectiveness of MBDCAs over TG-43 in HDR ¹⁹²Ir brachytherapy of extended scalp lesions. Treatment planning dose calculations were compared with Monte Carlo (MC) data. TG-43 exhibited a dose overestimation ranging from 10% to 23% as the distance from the implant increased, while a better agreement from 2% to 6% was observed between the MBDCA and MC, supporting the adoption of MBDCAs for dose calculations in broad scalp lesions.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"32 ","pages":"Article 100673"},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142700259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact of annotation imperfections and auto-curation for deep learning-based organ-at-risk segmentation","authors":"Victor I.J. Strijbis ,&nbsp;Oliver J. Gurney-Champion ,&nbsp;Berend J. Slotman ,&nbsp;Wilko F.A.R. Verbakel","doi":"10.1016/j.phro.2024.100684","DOIUrl":"10.1016/j.phro.2024.100684","url":null,"abstract":"<div><h3>Background and purpose</h3><div>Segmentation imperfections (noise) in radiotherapy organ-at-risk segmentation naturally arise from specialist experience and image quality. Using clinical contours can result in sub-optimal convolutional neural network (CNN) training and performance, but manual curation is costly. We address the impact of simulated and clinical segmentation noise on CNN parotid gland (PG) segmentation performance and provide proof-of-concept for an easily implemented auto-curation countermeasure.</div></div><div><h3>Methods and Materials</h3><div>The impact of segmentation imperfections was investigated by simulating noise in clean, high-quality segmentations. Curation efficacy was tested by removing lowest-scoring Dice similarity coefficient (DSC) cases early during CNN training, both in simulated (5-fold) and clinical (10-fold) settings, using our full radiotherapy clinical cohort (RTCC; N = 1750 individual PGs). Statistical significance was assessed using Bonferroni-corrected Wilcoxon signed-rank tests. Curation efficacies were evaluated using DSC and mean surface distance (MSD) on in-distribution and out-of-distribution data and visual inspection.</div></div><div><h3>Results</h3><div>The curation step correctly removed median(range) 98(90–100)% of corrupted segmentations and restored the majority (1.2 %/1.3 %) of DSC lost from training with 30 % corrupted segmentations. This effect was masked when using typical (non-curated) validation data. In RTCC, 20 % curation showed improved model generalizability which significantly improved out-of-distribution DSC and MSD (p &lt; 1.0e-12, p &lt; 1.0e-6). Improved consistency was observed in particularly the medial and anterior lobes.</div></div><div><h3>Conclusions</h3><div>Up to 30% case removal, the curation benefit outweighed the training variance lost through curation. Considering the notable ease of implementation, high sensitivity in simulations and performance gains already at lower curation fractions, as a conservative middle ground, we recommend 15% curation of training cases when training CNNs using clinical PG contours.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"32 ","pages":"Article 100684"},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11667007/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142886228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Results of 2023 survey on the use of synthetic computed tomography for magnetic resonance Imaging-only radiotherapy: Current status and future steps","authors":"M. Fusella ,&nbsp;E. Alvarez Andres ,&nbsp;F. Villegas ,&nbsp;L. Milan ,&nbsp;TM. Janssen ,&nbsp;R. Dal Bello ,&nbsp;C. Garibaldi ,&nbsp;L. Placidi ,&nbsp;D. Cusumano","doi":"10.1016/j.phro.2024.100652","DOIUrl":"10.1016/j.phro.2024.100652","url":null,"abstract":"<div><h3>Background and purpose</h3><div>The emergence of synthetic CT (sCT) in MR-guided radiotherapy (MRgRT) represents a significant advancement, supporting MR-only workflows and online treatment adaptation. However, the lack of consensus guidelines has led to varied practices. This study reports results from a 2023 ESTRO survey aimed at defining current practices in sCT development and use.</div></div><div><h3>Materials and methods</h3><div>An survey was distributed to ESTRO members, including 98 questions across four sections on sCT algorithm generation and usage. By June 2023, 100 centers participated. The survey revealed diverse clinical experiences and roles, with primary sCT use in the pelvis (60%), brain (15%), abdomen (11%), thorax (8%), and head-and-neck (6%). sCT was mostly used for conventional fractionation treatments (68%), photon SBRT (40%), and palliative cases (28%), with limited use in proton therapy (4%).</div></div><div><h3>Results</h3><div>Conditional GANs and GANs were the most used neural network architectures, operating mainly on 1.5 T and 3 T MRI images. Less than half used paired images for training, and only 20% performed image selection. Key MR image quality parameters included magnetic field homogeneity and spatial integrity. Half of the respondents lacked a dedicated sCT-QA program, and many did not apply sanitychecks before calculation. Selection strategies included age, weight, and metal artifacts. A strong consensus (95%) emerged for vendor neutral guidelines.</div></div><div><h3>Conclusion</h3><div>The survey highlights the need for expert-based, vendor-neutral guidelines to standardize sCT tools, metrics, and clinical protocols, ensuring effective sCT use in MR-guided radiotherapy.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"32 ","pages":"Article 100652"},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142357220","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrated framework for quantitative T2-weighted MRI analysis following prostate cancer radiotherapy","authors":"Evangelia I. Zacharaki ,&nbsp;Adrian L. Breto ,&nbsp;Ahmad Algohary ,&nbsp;Veronica Wallaengen ,&nbsp;Sandra M. Gaston ,&nbsp;Sanoj Punnen ,&nbsp;Patricia Castillo ,&nbsp;Pradip M. Pattany ,&nbsp;Oleksandr N. Kryvenko ,&nbsp;Benjamin Spieler ,&nbsp;John C. Ford ,&nbsp;Matthew C. Abramowitz ,&nbsp;Alan Dal Pra ,&nbsp;Alan Pollack ,&nbsp;Radka Stoyanova","doi":"10.1016/j.phro.2024.100660","DOIUrl":"10.1016/j.phro.2024.100660","url":null,"abstract":"<div><h3>Purpose</h3><div>The aim of this study is to develop a framework for quantitative analysis of longitudinal T2-weighted MRIs (T2w) following radiotherapy (RT) for prostate cancer.</div></div><div><h3>Materials and methods</h3><div>The developed methodology includes: <em>(i)</em> deformable image registration of longitudinal series to pre-RT T2w for automated detection of prostate, peripheral zone (PZ), and gross tumor volume (GTV); and <em>(ii)</em> T2w signal-intensity harmonization based on three reference tissues. The <em>RE</em>gistration and <em>HARM</em>onization (<em>REHARM</em>) framework was applied on T2w acquired in a clinical trial consisting of two pre-RT and three post-RT MRI exams. Image registration was assessed by the DICE coefficient between automatic and manual contours, and intensity normalization via inter-patient histogram intersection. Longitudinal consistency was evaluated by the repeatability coefficient and Pearson correlation (<em>r</em>) between the two T2w exams before RT.</div></div><div><h3>Results</h3><div>T2w from 107 MRI exams (23 patients) were utilized. Following <em>REHARM</em>, the histogram intersections for prostate, PZ and GTV increased from median = 0.43/0.16/0.13 to 0.66/0.44/0.46. The repeatability in T2w intensity estimation was better for the automatic than the manual contours for all three regions of interest (<em>r</em> = 0.9, <em>p</em> &lt; 0.0001, for GTV). The changes in the tissues’ T2w values pre- and post-RT became significant, indicating the measurable quantitative signal related to radiation.</div></div><div><h3>Conclusions</h3><div>The developed methodology allows to automate longitudinal analysis reducing data acquisition-related variation and improving consistency. The quantitative characterization of RT-induced changes in T2w will lead to new understanding of radiation effects enabling prediction modeling of RT response.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"32 ","pages":"Article 100660"},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142660811","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dwell time shaping in inverse treatment planning for cervical brachytherapy","authors":"Frida Dohlmar ,&nbsp;Björn Morén ,&nbsp;Michael Sandborg ,&nbsp;Torbjörn Larsson ,&nbsp;Åsa Carlsson Tedgren","doi":"10.1016/j.phro.2024.100672","DOIUrl":"10.1016/j.phro.2024.100672","url":null,"abstract":"<div><h3>Background and purpose</h3><div>Manual treatment planning for cervical brachytherapy is a challenging task; therefore, we investigated a method for inverse treatment planning using pseudo-structures to control the dwell distribution. Our hypothesis was that this method could produce treatment plans with a pear-shaped dose distribution and a high central dose, that comply with clinical constraints.</div></div><div><h3>Materials and methods</h3><div>Data from 16 previously treated patients were used to compare three treatment planning methods: i) manual, ii) straightforward inverse, and iii) inverse with pseudo-structures. The treatment plans were compared using dose-volume histogram parameters and by analysing the dwell times, and the distribution of total reference air-kerma (TRAK) in the different parts of the applicator. Methods were evaluated in one treatment planning system and verified in a second treatment planning system.</div></div><div><h3>Results</h3><div>The median dose to 90 % of the clinical tumor volume was 7.6 Gy, 7.8 Gy and 8.1 Gy for manual, pseudo-structure and straightforward methods respectively. Distribution of TRAK for the different parts of the applicator for the three methods (manual, pseudo-structures, and straightforward), with combined intracavitary and interstitial treatments, were for vaginal part 39 %, 33 % and 15 %, for intra-uterine part 47 %, 50 % and 47 % and for interstitial part 13 %, 17 % and 38 % respectively. The results were similar in the second treatment planning system.</div></div><div><h3>Conclusion</h3><div>The developed pseudo-structures worked as intended in shaping the dwell time distribution and in meeting the clinical constraints for both investigated treatment planning systems.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"32 ","pages":"Article 100672"},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142660812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"3D gel dosimeter assessment for end-to-end geometric accuracy determination of the online adaptive workflow on the 1.5 T MR-linac","authors":"Stijn Oolbekkink,&nbsp;Jochem W.H. Wolthaus,&nbsp;Bram van Asselen,&nbsp;Bas W. Raaymakers","doi":"10.1016/j.phro.2024.100664","DOIUrl":"10.1016/j.phro.2024.100664","url":null,"abstract":"<div><h3>Background and purpose:</h3><div>During an end-to-end (E2E) test on the online workflow of the MR-linac, the performance of the treatment starting from the acquisition of pre-treatment MRI scans and ending with dose delivery is quantified. In such a test, the geometrical accuracy of the entire workflow is assessed. Ideally, the 3D geometrical accuracy of dose delivery on an MR-linac should be assessed using dosimeters that provide 3D dose distributions. Gel dosimeters, for instance, have proven to be valuable tools for evaluating 3D dose distributions on an MR-linac. In this study, we investigated the use of 3D gel dosimeters for the assessment of the 3D geometrical accuracy and reproducibility of the adaptive procedure on an MR-linac in an E2E verification.</div></div><div><h3>Materials and methods:</h3><div>All measurements were performed on a clinical Unity MR-linac using 3D gel dosimeters in an anthropomorphic head phantom. Film measurements were performed as a reference dosimeter. An online adapt-to-shape procedure was performed for each measurement.</div></div><div><h3>Results:</h3><div>The geometric accuracy and reproducibility of the gel dosimeter measurements were high, and similar to all in-plane film measurements. The largest shift found was 0.3 mm for the gel dosimeter, and 0.6 mm for the in-plane film measurements. The 3D displacement vectors of the gel dosimeter showed similar uncertainties as the in-plane film 2D displacement vectors.</div></div><div><h3>Conclusions:</h3><div>Gel dosimeters can be used for the assessment of the 3D end-to-end geometric accuracy of an MR-linac.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"32 ","pages":"Article 100664"},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142660815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A deep learning model for predicting the modified micro-dosimetric kinetic model-based dose and the dose-averaged linear energy transfer for prostate cancer in carbon ion therapy","authors":"Liwen Zhang ,&nbsp;Weiwei Wang ,&nbsp;Ping Li ,&nbsp;Qing Zhang ,&nbsp;Rongcheng Han","doi":"10.1016/j.phro.2024.100671","DOIUrl":"10.1016/j.phro.2024.100671","url":null,"abstract":"<div><div>Adaptive carbon ion radiotherapy for localized prostate cancer requires accurate evaluation of biological dose and dose-averaged linear energy transfer (LET_d) changes. This study developed a deep learning model to rapidly predict the modified micro-dosimetric kinetic model (mMKM)-based dose and LET_d distributions. Using data from fifty patients for training and testing, the model achieved gamma passing rates exceeding 96% compared to true mMKM-based dose and LET_d recalculated from local effect model I (LEM I) plans. Incorporating computed tomography images, contours, physical dose, and LEM I-based dose as inputs, this model provided a rapid, accurate tool for comprehensive evaluations.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"32 ","pages":"Article 100671"},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142660816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Treatment planning for very high energy electrons: Studies that indicate the potential of the modality","authors":"James L. Bedford,&nbsp;Uwe Oelfke","doi":"10.1016/j.phro.2024.100670","DOIUrl":"10.1016/j.phro.2024.100670","url":null,"abstract":"<div><h3>Background and purpose</h3><div>Radiotherapy using Very High Energy Electrons (VHEE) has the potential to reduce dose to organs at risk compared to photons. This article therefore reviews treatment planning for VHEE, to clarify the potential benefit of the modality.</div></div><div><h3>Materials and methods</h3><div>Articles on VHEE were identified and those which focused on treatment planning were manually selected, particularly those which contained results on patient datasets. Benefits in absorbed dose to organs at risk were converted to percentages of prescription dose so as to provide uniform, clinically relevant reporting.</div></div><div><h3>Results</h3><div>Increased beam energy was found to reduce electron scatter and give rise to a narrower penumbra but lead to a rather constant depth dose curve, which was not as useful for sparing normal tissues as that of protons. The sharp penumbra of VHEE was of benefit in treatment planning for producing treatment plans with conformal dose shaping, with improved dose to critical structures being demonstrated for several treatment sites. Mean dose to critical structures, relative to the prescribed dose, was in the order of 0–10% lower than photons and 0–10% higher than protons. The delivery technology and dose distributions were also promising for radiotherapy with ultra-high dose rate (FLASH).</div></div><div><h3>Conclusion</h3><div>At present, the potential clinical benefit of VHEE relative to photons or protons is small. Further studies are needed to more precisely quantify the relative performance of broad beams versus pencil beam scanning and to investigate treatment sites that might benefit maximally from the use of VHEE beams.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"32 ","pages":"Article 100670"},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142660810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic segmentation for magnetic resonance imaging guided individual elective lymph node irradiation in head and neck cancer patients","authors":"Floris C.J. Reinders ,&nbsp;Mark H.F. Savenije ,&nbsp;Mischa de Ridder ,&nbsp;Matteo Maspero ,&nbsp;Patricia A.H. Doornaert ,&nbsp;Chris H.J. Terhaard ,&nbsp;Cornelis P.J. Raaijmakers ,&nbsp;Kaveh Zakeri ,&nbsp;Nancy Y. Lee ,&nbsp;Eric Aliotta ,&nbsp;Aneesh Rangnekar ,&nbsp;Harini Veeraraghavan ,&nbsp;Marielle E.P. Philippens","doi":"10.1016/j.phro.2024.100655","DOIUrl":"10.1016/j.phro.2024.100655","url":null,"abstract":"<div><h3>Background and purpose</h3><div>In head and neck squamous cell carcinoma (HNSCC) patients, the radiation dose to nearby organs at risk can be reduced by restricting elective neck irradiation from lymph node levels to individual lymph nodes. However, manual delineation of every individual lymph node is time-consuming and error prone. Therefore, automatic magnetic resonance imaging (MRI) segmentation of individual lymph nodes was developed and tested using a convolutional neural network (CNN).</div></div><div><h3>Materials and methods</h3><div>In 50 HNSCC patients (UMC-Utrecht), individual lymph nodes located in lymph node levels Ib-II-III-IV-V were manually segmented on MRI by consensus of two experts, obtaining ground truth segmentations. A 3D CNN (nnU-Net) was trained on 40 patients and tested on 10. Evaluation metrics were Dice Similarity Coefficient (DSC), recall, precision, and F1-score. The segmentations of the CNN was compared to segmentations of two observers. Transfer learning was used with 20 additional patients to re-train and test the CNN in another medical center.</div></div><div><h3>Results</h3><div>nnU-Net produced automatic segmentations of elective lymph nodes with median DSC: 0.72, recall: 0.76, precision: 0.78, and F1-score: 0.78. The CNN had higher recall compared to both observers (p = 0.002). No difference in evaluation scores of the networks in both medical centers was found after re-training with 5 or 10 patients.</div></div><div><h3>Conclusion</h3><div>nnU-Net was able to automatically segment individual lymph nodes on MRI. The detection rate of lymph nodes using nnU-Net was higher than manual segmentations. Re-training nnU-Net was required to successfully transfer the network to the other medical center.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"32 ","pages":"Article 100655"},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of deep learning-based target auto-segmentation for Magnetic Resonance Imaging-guided cervix brachytherapy","authors":"Rita Simões,&nbsp;Eva C. Rijkmans,&nbsp;Eva E. Schaake,&nbsp;Marlies E. Nowee,&nbsp;Sandra van der Velden,&nbsp;Tomas Janssen","doi":"10.1016/j.phro.2024.100669","DOIUrl":"10.1016/j.phro.2024.100669","url":null,"abstract":"<div><h3>Background and purpose</h3><div>The target structures for cervix brachytherapy are segmented by radiation oncologists using imaging and clinical information. At the first fraction, this is performed manually from scratch. For subsequent fractions the first fraction segmentations are rigidly propagated and edited manually. This process is time-consuming while patients wait immobilized. In this work, we evaluate the potential clinical impact of using population-based and patient-specific auto-segmentations as a starting point for target segmentation of the second fraction.</div></div><div><h3>Materials and method</h3><div>For twenty-eight patients with locally advanced cervical cancer, treated with MRI-guided brachytherapy, auto-segmentations were retrospectively generated for the second fraction image using two approaches: 1) population-based model, 2) patient-specific models fine-tuned on first fraction information. A radiation oncologist manually edited the auto-segmentations to assess model-induced bias. Pairwise geometric and dosimetric comparisons were performed for the automatic, edited and clinical structures. The time spent editing the auto-segmentations was compared to the current clinical workflow.</div></div><div><h3>Results</h3><div>The edited structures were more similar to the automatic than to the clinical structures. The geometric and dosimetric differences between the edited and the clinical structures were comparable to the inter-observer variability investigated in literature. Editing the auto-segmentations was faster than the manual segmentation performed during our clinical workflow. Patient-specific auto-segmentations required less edits than population-based structures.</div></div><div><h3>Conclusions</h3><div>Auto-segmentation introduces a bias in the manual delineations but this bias is clinically irrelevant. Auto-segmentation, particularly patient-specific fine-tuning, is a time-saving tool that can improve treatment logistics and therefore reduce patient burden during the second fraction of cervix brachytherapy.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"32 ","pages":"Article 100669"},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}