Cora Warda , Cihan Gani , Simon Boeke , David Mönnich , Moritz Schneider , Maximilian Niyazi , Daniela Thorwarth
{"title":"Simulation-free magnetic resonance-guided radiation therapy of prostate cancer","authors":"Cora Warda , Cihan Gani , Simon Boeke , David Mönnich , Moritz Schneider , Maximilian Niyazi , Daniela Thorwarth","doi":"10.1016/j.phro.2024.100667","DOIUrl":"10.1016/j.phro.2024.100667","url":null,"abstract":"<div><h3>Background and purpose</h3><div>Despite recent advances of online image-guided high-precision patient positioning and adaptation using magnetic resonance imaging (MRI) or cone-beam computed tomography (CT), standard radiation therapy pathway still involves a dedicated simulation scan. The aim of this study was to evaluate the feasibility and planning quality of integrating a simulation-free treatment planning workflow for adaptive online MRI-guided radiation therapy on a 1.5 T MRI linear accelerator (MRI-Linac) in prostate cancer using diagnostic CT (dCT) scans.</div></div><div><h3>Materials and methods</h3><div>For ten patients with prostate cancer previously treated at the MRI-Linac with adaptive radiation therapy (42.7 Gy in 7 fractions), simulation-free reference plans based on dCT were retrospectively created, and adaptive plans were simulated for the first treatment fraction. Reference and adapted plans derived from both standard and simulation-free workflows were compared with regard to institutional dose/volume criteria, followed by statistical assessment using the paired Wilcoxon signed-rank test with a Bonferroni-corrected significance level of α = 0.025.</div></div><div><h3>Results</h3><div>Simulation-free reference and adapted plans consistently met dose/volume criteria. Statistical analysis revealed no significant differences between both workflows, except median values for near-maximum dose (D2%) in the planning target volume: 44.2 Gy (standard) vs. 44.5 Gy (simulation-free) in reference plans (p = 0.01), and 44.5 Gy vs. 44.6 Gy in adapted plans (p = 0.01).</div></div><div><h3>Conclusion</h3><div>This study demonstrated the feasibility of simulation-free radiation therapy planning using dCT. Comparable treatment plan quality was observed for both reference and adapted radiation therapy plans in a curative setting for patients with prostate cancer.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"32 ","pages":"Article 100667"},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142660817","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}
Martina Murr , Daniel Wegener , Simon Böke , Cihan Gani , David Mönnich , Maximilian Niyazi , Moritz Schneider , Daniel Zips , Arndt-Christian Müller , Daniela Thorwarth
{"title":"Comparison of online adaptive and non-adaptive magnetic resonance image-guided radiation therapy in prostate cancer using dose accumulation","authors":"Martina Murr , Daniel Wegener , Simon Böke , Cihan Gani , David Mönnich , Maximilian Niyazi , Moritz Schneider , Daniel Zips , Arndt-Christian Müller , Daniela Thorwarth","doi":"10.1016/j.phro.2024.100662","DOIUrl":"10.1016/j.phro.2024.100662","url":null,"abstract":"<div><h3>Background and purpose</h3><div>Conventional image-guided radiotherapy (conv-IGRT) is standard in prostate cancer (PC) but does not account for inter-fraction anatomical changes. Online-adaptive magnetic resonance-guided RT (OA-MRgRT) may improve organ-at-risk (OARs) sparing and clinical target volume (CTV) coverage. The aim of this study was to analyze accumulated OAR and target doses in PC after OA-MRgRT and conv-IGRT in comparison to pre-treatment reference planning (refPlan).</div></div><div><h3>Material and methods</h3><div>Ten patients with PC, previously treated with OA-MRgRT at the 1.5 T MR-Linac (20x3Gy), were included. Accumulated OA-MRgRT doses were determined by deformably registering all fraction’s MR-images. Conv-IGRT was simulated through rigid registration of the planning computed tomography with each fraction’s MR-image for dose mapping/accumulation. Dose-volume parameters (DVPs), including CTV D50% and D98%, rectum, bladder, urethra, Dmax and V56Gy for OA-MRgRT, conv-IGRT and refPlan were compared using the Wilcoxon signed-rank test. Clinical relevance of accumulated dose differences was analyzed using a normal-tissue complication-probability model.</div></div><div><h3>Results</h3><div>CTV-DVPs were comparable, whereas OA-MRgRT yielded decreased median OAR-DVPs compared to conv-IGRT, except for bladder V56Gy. OA-MRgRT demonstrated significantly lower median rectum Dmax over conv-IGRT (59.1/59.9 Gy, p = 0.006) and refPlan (60.1 Gy, p = 0.012). Similarly, OA-MRgRT yielded reduced median bladder Dmax compared to conv-IGRT (60.0/60.4 Gy, p = 0.006), and refPlan (61.2 Gy, p = 0.002). Overall, accumulated dose differences were small and did not translate into clinically relevant effects.</div></div><div><h3>Conclusion</h3><div>Deformably accumulated OA-MRgRT using 20x3Gy in PC showed significant but small dosimetric differences comparted to conv-IGRT. Feasibility of a dose accumulation methodology was demonstrated, which may be relevant for evaluating future hypo-fractionated OA-MRgRT approaches.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"32 ","pages":"Article 100662"},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142552813","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}
M. Fusella , E. Alvarez Andres , F. Villegas , L. Milan , TM. Janssen , R. Dal Bello , C. Garibaldi , L. Placidi , D. Cusumano
{"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 , E. Alvarez Andres , F. Villegas , L. Milan , TM. Janssen , R. Dal Bello , C. Garibaldi , L. Placidi , 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}
Evangelia I. Zacharaki , Adrian L. Breto , Ahmad Algohary , Veronica Wallaengen , Sandra M. Gaston , Sanoj Punnen , Patricia Castillo , Pradip M. Pattany , Oleksandr N. Kryvenko , Benjamin Spieler , John C. Ford , Matthew C. Abramowitz , Alan Dal Pra , Alan Pollack , Radka Stoyanova
{"title":"Integrated framework for quantitative T2-weighted MRI analysis following prostate cancer radiotherapy","authors":"Evangelia I. Zacharaki , Adrian L. Breto , Ahmad Algohary , Veronica Wallaengen , Sandra M. Gaston , Sanoj Punnen , Patricia Castillo , Pradip M. Pattany , Oleksandr N. Kryvenko , Benjamin Spieler , John C. Ford , Matthew C. Abramowitz , Alan Dal Pra , Alan Pollack , 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> < 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}
Frida Dohlmar , Björn Morén , Michael Sandborg , Torbjörn Larsson , Åsa Carlsson Tedgren
{"title":"Dwell time shaping in inverse treatment planning for cervical brachytherapy","authors":"Frida Dohlmar , Björn Morén , Michael Sandborg , Torbjörn Larsson , 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}
Stijn Oolbekkink, Jochem W.H. Wolthaus, Bram van Asselen, Bas W. Raaymakers
{"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, Jochem W.H. Wolthaus, Bram van Asselen, 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}
Liwen Zhang , Weiwei Wang , Ping Li , Qing Zhang , Rongcheng Han
{"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 , Weiwei Wang , Ping Li , Qing Zhang , 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<sub>d</sub>) changes. This study developed a deep learning model to rapidly predict the modified micro-dosimetric kinetic model (mMKM)-based dose and LET<sub>d</sub> 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<sub>d</sub> 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, 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}
Floris C.J. Reinders , Mark H.F. Savenije , Mischa de Ridder , Matteo Maspero , Patricia A.H. Doornaert , Chris H.J. Terhaard , Cornelis P.J. Raaijmakers , Kaveh Zakeri , Nancy Y. Lee , Eric Aliotta , Aneesh Rangnekar , Harini Veeraraghavan , Marielle E.P. Philippens
{"title":"Automatic segmentation for magnetic resonance imaging guided individual elective lymph node irradiation in head and neck cancer patients","authors":"Floris C.J. Reinders , Mark H.F. Savenije , Mischa de Ridder , Matteo Maspero , Patricia A.H. Doornaert , Chris H.J. Terhaard , Cornelis P.J. Raaijmakers , Kaveh Zakeri , Nancy Y. Lee , Eric Aliotta , Aneesh Rangnekar , Harini Veeraraghavan , 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}
Rita Simões, Eva C. Rijkmans, Eva E. Schaake, Marlies E. Nowee, Sandra van der Velden, Tomas Janssen
{"title":"Evaluation of deep learning-based target auto-segmentation for Magnetic Resonance Imaging-guided cervix brachytherapy","authors":"Rita Simões, Eva C. Rijkmans, Eva E. Schaake, Marlies E. Nowee, Sandra van der Velden, 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}