Radiation Oncology最新文献

{"title":"CHAT-RT study: ChatGPT in radiation oncology-a survey on usage, perception, and impact among DEGRO members.","authors":"Dinah Konnerth, Alev Altay-Langguth, Diana-Coralia Dehelean, Sebastian H Maier, Montserrat Pazos, Paul Rogowski, Stephan Schönecker, Chukwuka Eze, Stefanie Corradini, Claus Belka, Sebastian N Marschner","doi":"10.1186/s13014-025-02721-9","DOIUrl":"10.1186/s13014-025-02721-9","url":null,"abstract":"<p><strong>Background: </strong>Radiation oncology is increasingly turning to Artificial Intelligence (AI) - and in particular Chat Generative pre-trained transformer (ChatGPT) - for decision support, patient education, and workflow efficiency. Despite promising gains, questions about accuracy, General Data Protection Regulation (GDPR)-compliance and ethical use persist, especially in high-stakes cancer care. To clarify real-world attitudes and practices, we surveyed members of the German Society of Radiation Oncology (DEGRO) on their use, perceptions, and concerns regarding ChatGPT across clinical, research, communication, and administrative tasks.</p><p><strong>Methods: </strong>An anonymous online survey was implemented via LimeSurvey platform and distributed to all members of the DEGRO in Germany, Austria, and Switzerland between April and June 2024. The 40-item questionnaire-covering demographics, radiotherapy experience, and ChatGPT's clinical, research, communication, and administrative applications-was developed through a narrative literature review, ChatGPT-assisted drafting, back-translation, expert validation, and pilot testing. Fully completed responses were used for descriptive statistics and analysis.</p><p><strong>Results: </strong>Of 213 respondents, 159 fully completed the survey. Participants were predominantly based in Germany (92.5%), worked in university hospitals (74.2%), and identified as radiation oncologists (54.7%), with a broad range of radiotherapy experience (< 1 year: 7.5%; >15 years: 24.5%). Awareness of ChatGPT was high (94.9%), yet actual use varied: 32.1% never used it, while 35.2% employed it regularly for administrative tasks and 30.2% for manuscript drafting. Mid-career clinicians (6-10 years' experience) showed the greatest enthusiasm-44% agreed it saves time and 72% planned further integration-though all career stages (71.7% overall) expressed strong interest in formal training. Satisfaction was highest for administrative (94.6%) and manuscript support (91.7%) but lower for technical queries (66.7%). Major concerns included misinformation (69.2%), erosion of critical thinking (57.9%), and data-privacy risks (57.2%).</p><p><strong>Conclusion: </strong>Our survey demonstrates high awareness and adoption of ChatGPT for administrative and educational tasks, alongside more cautious use in clinical decision-making. Widespread concerns about misinformation, critical-thinking erosion, and data privacy-especially among early- and mid-career clinicians-underscore the need for targeted AI training, rigorous validation, and transparent governance to ensure safe, effective integration into patient care.</p>","PeriodicalId":49639,"journal":{"name":"Radiation Oncology","volume":"20 1","pages":"140"},"PeriodicalIF":3.3,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12439408/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145070936","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improved local control using higher dose SBRT in metastatic sarcoma patients.","authors":"Mattias Hedman, Elia Rossi, Emmy Dalqvist, Kristin Karlsson, Christina Linder-Stragliotto","doi":"10.1186/s13014-025-02719-3","DOIUrl":"10.1186/s13014-025-02719-3","url":null,"abstract":"<p><strong>Background: </strong>Stereotactic Body Radiotherapy (SBRT) has been proven to be a safe and effective alternative to surgery in patients with metastatic primary sarcoma. However, data describing tumor response in relation to the given radiotherapy dose is lacking. Therefore, this study aims at analyzing efficacy and dose-response relationship in a retrospective cohort.</p><p><strong>Methods: </strong>Patients with metastatic sarcoma treated with ablative SBRT and followed up at the Karolinska University Hospital between 2008 and 2021 were included. SBRT was delivered using an inhomogeneous dose distribution resulting in higher median doses within the planning target volume (PTV) than the dose prescribed. Local control (LC), progression-free survival (PFS), overall survival (OS), adverse events and dose-response relationship were assessed. Statistical analysis was performed to identify variables that correlate to outcome.</p><p><strong>Results: </strong>Forty-three patients with a total of 83 lesions were treated. The most frequent histology was leiomyosarcoma (44%). The most common site of metastases was the lung (84%), followed by the liver (11%). The median prescription dose was 45 Gy (range 30-56 Gy) delivered in 3 fractions (range 2-8) with a planned median CTV mean dose of 309 Gy in EQD₂ with α/β = 3 Gy. The local control at 1-year, 2-year and 5-year from SBRT treatment was 97, 93 and 84%, respectively. For tumors with a planned mean CTV dose above EQD₂ 278.8 Gy (corresponding to 60.3 Gy in 3 fractions) the 1, 2 and 5-year local control was 100, 100 and 93%, respectively. Tumors planned with a lower dose than EQD₂ 278.8 Gy (α/β = 3 Gy) had a 1, 2 and 5-year local control of 90, 70 and 52%, respectively. The difference in local control between the high dose and low dose groups was statistically significant (p < 0.001). The median OS for all patients was 43 months. When respecting dose constraints, there were only limited number of mild side effects.</p><p><strong>Conclusion: </strong>In this analysis a strongly significant dose-response relationship with excellent LC rates and limited side effects for patients with metastatic lesions of sarcoma were seen. These results could be related to the inhomogeneous dose distribution of SBRT treatments utilized in this study.</p>","PeriodicalId":49639,"journal":{"name":"Radiation Oncology","volume":"20 1","pages":"139"},"PeriodicalIF":3.3,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12418616/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145024687","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative metabolomic analysis of human lung slices (hu-PCLS) exposed to either standard or FLASH protons: a pilot study.","authors":"Anastasia Velalopoulou, Tytus D Mak, Annabella Deziel, Michele M Kim, Constantinos Koumenis, Melpo Christofidou-Solomidou, Evagelia C Laiakis","doi":"10.1186/s13014-025-02714-8","DOIUrl":"10.1186/s13014-025-02714-8","url":null,"abstract":"","PeriodicalId":49639,"journal":{"name":"Radiation Oncology","volume":"20 1","pages":"138"},"PeriodicalIF":3.3,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12403441/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144976250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Surrogating tumour cell density in head and neck cancer: [¹⁸F]FDG PET- versus ADC (MRI)-based approaches.","authors":"Athanasios Kafkaletos, Ilias Sachpazidis, Michael Mix, Montserrat Carles, Raluca Stoian, Henning Schäfer, Michael Bock, Dimos Baltas, Anca L Grosu","doi":"10.1186/s13014-025-02716-6","DOIUrl":"10.1186/s13014-025-02716-6","url":null,"abstract":"<p><strong>Objective: </strong>In this study we examined the correlation between standardized uptake value (SUV) of [¹⁸F]fluorodeoxyglucose (FDG) and apparent diffusion coefficient (ADC) within the gross tumor volume (GTV) of patients with head and neck squamous cell carcinoma (HNSCC). In addition, we assessed the comparability of cell density (ρ) estimates obtained from FDG PET and MRI data.</p><p><strong>Methods: </strong>Twenty-one HNSCC patients from a prospective FMISO imaging trial underwent pre-treatment PET/CT and MRI. We assessed correlations between FDG SUV (mean, max) and ADC (mean, min) within the GTV using Pearson's correlation coefficient. The tumor cell density within the GTV was calculated from FDG SUV and from ADC maps. For the estimation of ADC-based cell density, we used a published tumor cell volume fraction (v_TC). Agreement between FDG- and ADC-derived cell density estimates was assessed. The best-fitting v_TC* was computed to achieve equal mean ρ_ADC and ρ_FDG for each patient and was compared to the literature.</p><p><strong>Results: </strong>The SUV and ADC metrics showed up to moderate negative correlations, but none of them were statistically significant at p < 0.05. The correlation of SUV_mean vs. ADC_mean with Pearson's correlation coefficient r = -0.426 and p = 0.054 and SUV_max vs. ADC_min with r = -0.414 and p = 0.062 suggested a weak negative trend. The average and standard deviation of mean ρ_FDG and ρ_ADC across our cohort were (1.8 ± 0.6) × 10⁸ cells/ml and (3.3 ± 0.2) × 10⁸ cells/ml. The difference between the mean ρ_FDG and ρ_ADC was statistically significant (p < 0.001). To achieve equal mean ρ_ADC and ρ_FDG for each patient, the mean optimal v_TC* with standard deviation was 0.29 ± 0.09. Although significantly lower than the published mean v_TC​ (0.54), v_TC* lies within the published range of v_TC for HNSCCs (0.28 to 0.75).</p><p><strong>Conclusion: </strong>ADC and SUV metrics exhibited moderate but marginally insignificant correlation in this dataset. Although not directly interchangeable, the two methods provide comparable, clinically relevant cell density estimates, offering flexibility to use the most accessible modality for individualized treatment planning.</p><p><strong>Trial registration: </strong>Registered at German Clinical Trials Register on 20/08/2015 (DRKS00003830).</p>","PeriodicalId":49639,"journal":{"name":"Radiation Oncology","volume":"20 1","pages":"137"},"PeriodicalIF":3.3,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12403412/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144976272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Technical aspects of SBRT for therapy-refractory ventricular tachycardia: a systematic review for radiation oncologists.","authors":"Alicia Greiner, Lukas Grajewski, Maximilian Römer, Klaus Pietschmann, Georg Wurschi","doi":"10.1186/s13014-025-02704-w","DOIUrl":"https://doi.org/10.1186/s13014-025-02704-w","url":null,"abstract":"","PeriodicalId":49639,"journal":{"name":"Radiation Oncology","volume":"20 1","pages":"136"},"PeriodicalIF":3.3,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12395866/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144976293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Nasopharyngeal cancer adaptive radiotherapy with CBCT-derived synthetic CT: deep learning-based auto-segmentation precision and dose calculation consistency on a C-Arm linac.","authors":"Weijie Lei, Lixiang Han, Zhenmei Cao, Tingting Duan, Bin Wang, Caihong Li, Xi Pei","doi":"10.1186/s13014-025-02715-7","DOIUrl":"https://doi.org/10.1186/s13014-025-02715-7","url":null,"abstract":"<p><strong>Background: </strong>To evaluate the precision of automated segmentation facilitated by deep learning (DL) and dose calculation in adaptive radiotherapy (ART) for nasopharyngeal cancer (NPC), leveraging synthetic CT (sCT) images derived from cone-beam CT (CBCT) scans on a conventional C-arm linac.</p><p><strong>Materials and methods: </strong>Sixteen NPC patients undergoing a two-phase offline ART were analyzed retrospectively. The initial (pCT₁) and adaptive (pCT₂) CT scans served as gold standard alongside weekly acquired CBCT scans. Patient data, including manually delineated contours and dose information, were imported into ArcherQA. Using a cycle-consistent generative adversarial network (cycle-GAN) trained on an independent dataset, sCT images (sCT₁, sCT₄, sCT₄^*) were generated from weekly CBCT scans (CBCT₁, CBCT₄, CBCT₄) paired with corresponding planning CTs (pCT₁, pCT₁, pCT₂). Auto-segmentation was performed on sCTs, followed by GPU-accelerated Monte Carlo dose recalculation. Auto-segmentation accuracy was assessed via Dice similarity coefficient (DSC) and 95th percentile Hausdorff distance (HD₉₅). Dose calculation fidelity on sCTs was evaluated using dose-volume parameters. Dosimetric consistency between recalculated sCT and pCT plans was analyzed via Spearman's correlation, while volumetric changes were concurrently evaluated to quantify anatomical variations.</p><p><strong>Results: </strong>Most anatomical structures demonstrated high pCT-sCT agreement, with mean values of DSC > 0.85 and HD₉₅ < 5.10 mm. Notable exceptions included the primary Gross Tumor Volume (GTVp) in the pCT₂-sCT₄ comparison (DSC: 0.75, HD₉₅: 6.03 mm), involved lymph node (GTVn) showing lower agreement (DSC: 0.43, HD₉₅: 16.42 mm), and submandibular glands with moderate agreement (DSC: 0.64-0.73, HD₉₅: 4.45-5.66 mm). Dosimetric analysis revealed the largest mean differences in GTVn D₉₉: -1.44 Gy (95% CI: [-3.01, 0.13] Gy) and right parotid mean dose: -1.94 Gy (95% CI: [-3.33, -0.55] Gy, p < 0.05). Anatomical variations, quantified via sCTs measurements, correlated significantly with offline adaptive plan adjustments in ART. This correlation was strong for parotid glands (ρ > 0.72, p < 0.001), a result that aligned with sCT-derived dose discrepancy analysis (ρ > 0.57, p < 0.05).</p><p><strong>Conclusion: </strong>The proposed method exhibited minor variations in volumetric and dosimetric parameters compared to prior treatment data, suggesting potential efficiency improvements for ART in NPC through reduced human dependency.</p>","PeriodicalId":49639,"journal":{"name":"Radiation Oncology","volume":"20 1","pages":"135"},"PeriodicalIF":3.3,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12395649/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144976292","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comprehensive one-day management of prostate cancer patients: PRO-FAST single-fraction ablative, urethral-sparing, HDR-like, robotic SBRT.","authors":"Andrei Fodor, Laura Giannini, Miriam Torrisi, Chiara Brombin, Sara Broggi, Andrea Losa, Tommaso Maga, Renata Mellone, Carlo Martinenghi, Roberta Tummineri, Paola Mangili, Chiara Lucrezia Deantoni, Alessia Tudda, Roberta Castriconi, Paola Maria Vittoria Rancoita, Mariaclelia Stefania Di Serio, Franco Gaboardi, Claudio Fiorino, Antonella Del Vecchio, Arturo Chiti, Francesco De Cobelli, Nadia Di Muzio","doi":"10.1186/s13014-025-02713-9","DOIUrl":"10.1186/s13014-025-02713-9","url":null,"abstract":"<p><strong>Background: </strong>Radiotherapy (RT) is a standard curative treatment for prostate cancer (PCa) and there is growing evidence of the high efficacy of moderate and ultra-hypofractionated RT. Reducing treatment duration to one week or less is a major advance, but very few studies have explored single-fraction therapy. This study evaluates the feasibility, safety, and efficacy of single-fraction stereotactic body RT (SBRT) while delivering the entire procedure in one day, with a potentially high benefit in terms of patient comfort and therapy cost and logistics.</p><p><strong>Methods: </strong>This prospective, non-randomized monocentric trial uses Robotic Radiosurgery (CyberKnife v.7 system) to deliver a single 24 Gy fraction to the prostate (± seminal vesicles) with a \"urethral sparing HDR-like\" technique, and target tracking. The first phase will enroll 13 PCa patients following Simon's optimal design. Treatment is to be stopped if ≥ 2 patients develop ≥ G3 toxicity (CTCAE v5.0) within a month from RT end; otherwise, 52 more patients will be added, totaling 65. To account for minimal drop-out, 5 extra patients will be enrolled, reaching 70. All procedures are performed in a single day, including fiducial implantation, imaging acquisition, contouring, planning, dosimetry quality control, and treatment. Apart from treatment feasibility in terms of one-month acute toxicity, secondary endpoints include late toxicity, biochemical and clinical control.</p><p><strong>Discussion: </strong>Few others have investigated the 24 Gy single-fraction schedule using different delivery modalities (not including tracking), which has proved to be non-inferior to 5 fraction SBRT. Our approach aims to maintain (and possibly improve) the previously reported acute, subacute and late toxicity as well as disease control, adding evidence in favor of single-fraction delivery. Another significant goal of the study is the demonstration that all the complex treatment procedures can be safely delivered in a single day. This would be especially appealing for patients far from radiotherapy centers and those with work commitments not allowing daily hospital visits. The study of response to RT can also provide useful information about PCa radiobiology. Planned additional analyses may help in better assessing the clinical value of PSMA PET/CT in the selection of high-risk patients with true limited disease, and in identifying radiomic features associated to outcome.</p><p><strong>Trial registration: </strong>The study was prospectively registered at clinicaltrials.gov (NCT05936736).</p>","PeriodicalId":49639,"journal":{"name":"Radiation Oncology","volume":"20 1","pages":"134"},"PeriodicalIF":3.3,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12392665/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144976303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Use of PULSAR (personalized ultra-fractionated stereotactic adaptive radiotherapy) as consolidation with immune checkpoint inhibition in the treatment of pediatric metastatic melanoma.","authors":"Kyra L McCarty, Tanya Watt, Tu D Dan, Robert D Timmerman, Kiran A Kumar","doi":"10.1186/s13014-025-02691-y","DOIUrl":"https://doi.org/10.1186/s13014-025-02691-y","url":null,"abstract":"<p><p>We present a case of extensive and bulky pediatric metastatic melanoma originating in the head and neck which markedly responded to combination therapy with anti-programmed cell death (PD-1) inhibition and consolidative personalized ultra-fractionated stereotactic adaptive radiotherapy (PULSAR). After surgical debulking with neck dissection, the patient was initially treated with anti-PD-1 and anti-cytotoxic T-lymphocyte associated protein 4 (CTLA-4) dual checkpoint blockade immunotherapy, but quickly had disease progression. He was transitioned to a different anti-PD-1 immunotherapy in combination with tyrosine kinase inhibitors in conjunction with consolidative local therapy using PULSAR. This combination therapy achieved tumor response and progression-free status for one year before further disease progression at a separate site in the mediastinum. Due to otherwise good disease control, single agent anti-PD-1 immunotherapy was continued and salvage PULSAR was administered to the progressive site, again resulting in tumor response and progression-free status for 6 months. None of the bulkier sites of gross disease had local progression after combination therapy. This case suggests that the synergistic effect of PULSAR and anti-PD-1 immunotherapy is efficacious for relapsed or refractory metastatic melanoma in pediatric patients. Clinical trial number: not applicable.</p>","PeriodicalId":49639,"journal":{"name":"Radiation Oncology","volume":"20 1","pages":"132"},"PeriodicalIF":3.3,"publicationDate":"2025-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12369228/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144976429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Tumor irradiation induced immunogenic response: the impact of DNA damage induction and misrepair.","authors":"Qi Liu, Xiaoran Shi, Nilupaier Tayier, Lin Ma","doi":"10.1186/s13014-025-02711-x","DOIUrl":"https://doi.org/10.1186/s13014-025-02711-x","url":null,"abstract":"<p><p>Focal tumor irradiation, a cornerstone of cancer therapy, has been increasingly recognized for its capacity to provoke systemic immunogenic responses that extend beyond localized tumor control. Recent advances highlight DNA damage, especially DNA double-strand breaks (DSBs), as a central mediator linking radiotherapy to anti-tumor immune activation. Importantly, DNA misrepair, prevalent in cancer cells with deficient or dysregulated repair machinery, serves as a double-edged sword: while fostering tumor adaptation and genomic instability, it also fuels immune recognition through the accumulation of neoantigens, extracellular DNA release, immunogenic cell death, and the modulation of immune-related cytokines and chemokines. This review critically synthesizes the latest clinical and preclinical insights into the dynamic interplay between DNA damage, repair fidelity, and the immunogenic consequences of tumor irradiation. By focusing on the impact of DSB induction and misrepair processes, we underscore the emerging therapeutic opportunities of modulating DNA repair pathways during radiotherapy to potentiate anti-tumor immunity, particularly in synergy with immune checkpoint blockade. This article provides a comprehensive perspective on the molecular underpinnings and translational potential of harnessing irradiation-induced immunogenicity, offering a roadmap for future therapeutic strategies in radiation oncology and cancer immunotherapy. CLINICAL TRIAL NUMBER: Not applicable.</p>","PeriodicalId":49639,"journal":{"name":"Radiation Oncology","volume":"20 1","pages":"133"},"PeriodicalIF":3.3,"publicationDate":"2025-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12372257/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144976335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Criteria-calibration approaches to deep learning-based cervical cancer radiation treatment auto-planning.","authors":"Yongguang Liang, Jingru Yang, Shuoyang Wei, Yanfei Liu, Shumeng He, Kang Zhang, Jie Qiu, Bo Yang","doi":"10.1186/s13014-025-02684-x","DOIUrl":"https://doi.org/10.1186/s13014-025-02684-x","url":null,"abstract":"<p><strong>Background: </strong>Knowledge-Based Planning (KBP) pipelines, which integrate machine learning-based models to predict dose distribution, have gained popularity in clinical radiation therapy. However, for patients with specific requirements, the trained models may struggle to rapidly adjust to guide the automatic planning process. Therefore, the aim of this study was to calibrate the dose prediction model to improve the quality and accuracy of automatic planning for cervical cancer radiation therapy.</p><p><strong>Materials and methods: </strong>We retrospectively collected a routine cervical cancer dataset (200 cases) to conduct the KBP pipelines for automatically generating radiation planning, and a small number of ovarian-protection and myelosuppressive datasets (21 cases) to calibrate and evaluate the dose prediction model. A total of three criteria-calibration approaches to solve the data imbalance problem in dose prediction were introduced and compared, including Prediction Tolerance function on uTPS (United Imaging Healthcare Co., Ltd., Shanghai), transfer learning, and mixture density network.</p><p><strong>Results: </strong>The Prediction Tolerance function allowed for rapid optimization adjustments without model modification, which is suitable for patients with strong desires for ovary protection. The transfer learning approach required minimal training time and data to generate acceptable automatic planning results. The Mixture Density Network (MDN) approach, although the most time-consuming to train, achieved robust prediction results and facilitated dataset analysis. The MDN method showed the greatest consistency between predicted dose distribution and actual optimization outcomes, highlighting its potential as a reliable calibration method for dose prediction.</p><p><strong>Conclusion: </strong>This study demonstrated an automatic KBP workflow and compared three criteria-calibration approaches to address the data imbalance problem in dose prediction. These approaches can partially calibrate pre-existing models to accommodate newly added criteria and could be implemented according to specific requirements in different scenarios. Although there are trade-offs in various aspects, they all can generate feasible radiation treatment plans.</p>","PeriodicalId":49639,"journal":{"name":"Radiation Oncology","volume":"20 1","pages":"131"},"PeriodicalIF":3.3,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12369083/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144976345","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}