Radiation Oncology最新文献

{"title":"CT-based auto-segmentation of multiple target volumes for all-in-one radiotherapy in rectal cancer patients.","authors":"Xuemin Li, Luqi Wang, Mengying Yang, Xianan Li, Ting Zhao, Mingqing Wang, Siyi Lu, Yunsong Ji, Wei Zhang, Lecheng Jia, Ran Peng, Junjie Wang, Hao Wang","doi":"10.1186/s13014-025-02694-9","DOIUrl":"10.1186/s13014-025-02694-9","url":null,"abstract":"","PeriodicalId":49639,"journal":{"name":"Radiation Oncology","volume":"20 1","pages":"130"},"PeriodicalIF":3.3,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12366347/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144884181","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":"CBCT-based online adaptive radiotherapy of the bladder - geometrical and dosimetrical considerations compared to conventional IGRT.","authors":"Jann Fischer, Laura Anna Fischer, Jona Bensberg, Natalia Bojko, Mohamed Bouabdallaoui, Jasper Frohn, Petra Hüttenrauch, Mandy Klingebiel, Daniela Schmitt, Katharina Tegeler, Daniela Wagner, Alina Wenzel, Jessica Moldauer, Niklas Christian Scheele, Hanne Elisabeth Ammon, Stephanie Bendrich, Sandra Donath, Leif Hendrik Dröge, Manuel Guhlich, Andrea Hille, Olga Knaus, Martin Leu, Jan Oelmann, Rami El Shafie, Georg Stamm, Arndt F Schilling, Stefan Rieken","doi":"10.1186/s13014-025-02710-y","DOIUrl":"10.1186/s13014-025-02710-y","url":null,"abstract":"<p><strong>Background: </strong>Bladder cancer radiotherapy presents unique challenges due to the dynamic anatomy of the bladder and the surrounding organs. Conventional image-guided radiotherapy (IGRT) relies on fixed treatment margins and daily couch corrections, which can result in suboptimal dose delivery. Cone Beam Computed Tomography (CBCT)-based online adaptive radiotherapy (oART) allows daily re-optimization of treatment plans, potentially improving target dose coverage while minimizing exposure to organs at risk (OAR). This study compares oART with IGRT in bladder cancer patients.</p><p><strong>Methods: </strong>160 oART fractions delivered using the Ethos system (Varian Medical Systems, Palo Alto, CA, USA) were analyzed and compared to conventional IGRT. For each adaptive fraction (fx), three plans were evaluated: the scheduled plan (initial plan recalculated based on daily CBCT), the adapted plan (re-optimized to daily anatomy), and the verification plan (dose distribution recalculated on the verification CBCT - vCBCT). Geometric variations, dose-volume parameters and treatment times were analyzed. Clinical plan acceptability was assessed using predefined dose-volume parameters. Dose coverage on the target's surface was analyzed using a novel method and visualized via Mercator projections.</p><p><strong>Results: </strong>Despite drinking guidelines, bladder volumes varied significantly day-to-day. Dose coverage of the clinical target volume (CTV) improved significantly with adaptation (median D_98% 88.4-97.8%, p < 0.01) and further after vCBCT (median D_98% 98.1%, p < 0.01), with a reduced interquartile range (IQR). Planning target volume (PTV) D_98% also improved with adaptation (median 69.5-92.8%, p < 0.01) and after vCBCT (median 91.8%, p < 0.01), with decreasing IQR. OAR doses showed reduced variability and a measurable dosimetrical benefit. Spatial dose distribution on the surface of the targets improved for adaptation. Plan acceptability in retrospect almost doubled from 11.9% for scheduled plans to 23.1% for adapted plans and 22.5% for verification plans. The scheduled plans were never chosen for treatment. Median oART treatment time was 14 min, compared to 9 min for IGRT.</p><p><strong>Conclusions: </strong>Treatment times were approximately 1.5 times longer than IGRT; however, CBCT-based oART enhanced target dose coverage, reduced OAR doses, and decreased variability in both target and OAR doses compared to IGRT, while also improving plan acceptability, although the results should be interpreted with caution due to the limited sample size and single-center design.</p><p><strong>Trial registration: </strong>Not applicable.</p>","PeriodicalId":49639,"journal":{"name":"Radiation Oncology","volume":"20 1","pages":"128"},"PeriodicalIF":3.3,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12351964/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144856897","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":"Integrating peritumor and tumor CT radiomics features in predicting local control after SBRT in patients with pulmonary oligometastases.","authors":"Yao Lu, Yiqi Wang, Yuxi Ding, Danni Chen, Wenguang He, Weixiang Zhong, Jing Yang, Senxiang Yan, Ge Ren, Feng Zhao","doi":"10.1186/s13014-025-02712-w","DOIUrl":"10.1186/s13014-025-02712-w","url":null,"abstract":"<p><strong>Purpose: </strong>Local control prediction for patients with pulmonary oligometastases underwent stereotactic body radiotherapy (SBRT) is crucial for optimizing therapeutic strategies. This study aims to develop and validate a predictive radiomics model integrating both tumor-intrinsic and peritumoral features along with clinical factors to enhance local control prediction using a multi-center dataset.</p><p><strong>Materials and methods: </strong>We analyzed 223 tumors from 146 patients, which was divided into a training set (n = 165) and an external validation set (n = 58). Radiomic features from the gross tumor volume (GTV) and peritumoral regions (pGTV) representing the tumor microenvironment (TME) in CT images were extracted and combined with clinical factors to build a clinical outcome prediction model. Tumor response was classified into Favorable Response Group (FRG) and Unfavorable Response Group (URG) according to the 3-month and 1-year follow-up. Models were built using a Multilayer Perceptron (MLP) approach with SHAP analysis.</p><p><strong>Results: </strong>Model-G (with GTV features) and Model-P (with pGTV features) achieved a validation area under curve (AUC) of 0.806 and 0.708, respectively. Meanwhile, Model-GP (with GTV and pGTV features) demonstrated an improved performance with a validation AUC of 0.851, reflecting the added value of peritumoral features. The Model-GPC, which incorporated GTV, pGTV, and clinical features, achieved a best validation AUC of 0.902, demonstrating the model's ability to robustly integrate clinical and radiomic data for accurate local control prediction.</p><p><strong>Conclusion: </strong>The Model-GPC, integrating clinical and radiomic features, accurately predicts post-SBRT local control in pulmonary oligometastases. Incorporating peritumoral features and SHAP analysis enhances prediction accuracy, offering insights to optimize SBRT strategies.</p>","PeriodicalId":49639,"journal":{"name":"Radiation Oncology","volume":"20 1","pages":"129"},"PeriodicalIF":3.3,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12355760/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144856898","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":"A stacking ensemble framework integrating radiomics and deep learning for prognostic prediction in head and neck cancer.","authors":"Bingzhen Wang, Jinghua Liu, Xiaolei Zhang, Jianpeng Lin, Shuyan Li, Zhongxiao Wang, Zhendong Cao, Dong Wen, Tiange Liu, Hafiz Rashidi Harun Ramli, Hazreen Haizi Harith, Wan Zuha Wan Hasan, Xianling Dong","doi":"10.1186/s13014-025-02695-8","DOIUrl":"10.1186/s13014-025-02695-8","url":null,"abstract":"<p><strong>Background: </strong>Radiomics models frequently face challenges related to reproducibility and robustness. To address these issues, we propose a multimodal, multi-model fusion framework utilizing stacking ensemble learning for prognostic prediction in head and neck cancer (HNC). This approach seeks to improve the accuracy and reliability of survival predictions.</p><p><strong>Methods: </strong>A total of 806 cases from nine centers were collected; 143 cases from two centers were assigned as the external validation cohort, while the remaining 663 were stratified and randomly split into training (n = 530) and internal validation (n = 133) sets. Radiomics features were extracted according to IBSI standards, and deep learning features were obtained using a 3D DenseNet-121 model. Following feature selection, the selected features were input into Cox, SVM, RSF, DeepCox, and DeepSurv models. A stacking fusion strategy was employed to develop the prognostic model. Model performance was evaluated using Kaplan-Meier survival curves and time-dependent ROC curves.</p><p><strong>Results: </strong>On the external validation set, the model using combined PET and CT radiomics features achieved superior performance compared to single-modality models, with the RSF model obtaining the highest concordance index (C-index) of 0.7302. When using deep features extracted by 3D DenseNet-121, the PET + CT-based models demonstrated significantly improved prognostic accuracy, with Deepsurv and DeepCox achieving C-indices of 0.9217 and 0.9208, respectively. In stacking models, the PET + CT model using only radiomics features reached a C-index of 0.7324, while the deep feature-based stacking model achieved 0.9319. The best performance was obtained by the multi-feature fusion model, which integrated both radiomics and deep learning features from PET and CT, yielding a C-index of 0.9345. Kaplan-Meier survival analysis further confirmed the fusion model's ability to distinguish between high-risk and low-risk groups.</p><p><strong>Conclusion: </strong>The stacking-based ensemble model demonstrates superior performance compared to individual machine learning models, markedly improving the robustness of prognostic predictions.</p>","PeriodicalId":49639,"journal":{"name":"Radiation Oncology","volume":"20 1","pages":"127"},"PeriodicalIF":3.3,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12351975/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144849477","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":"Elevated MS4A12 expression is indicative of resistance to concurrent chemoradiotherapy and inferior survival in patients with rectal cancer.","authors":"Chih-I Chen, Yi-Kai Kao, Po-Wen Yang, Pin-Chun Chen, Ching-Chieh Yang, Wan-Shan Li, Hsin-Hwa Tsai, Yu-Jen Wang, Hong-Yue Lai","doi":"10.1186/s13014-025-02709-5","DOIUrl":"10.1186/s13014-025-02709-5","url":null,"abstract":"<p><strong>Introduction: </strong>In individuals presenting with locally advanced rectal cancer, the therapeutic strategy of neoadjuvant concurrent chemoradiotherapy (CCRT) aims to enhance tumor downstaging; however, only a subset of patients exhibit a favorable response. Molecular stratification, combined with the traditional tumor staging system (TNM), is a promising approach for predicting treatment efficacy and patient outcomes. Therefore, we intend to better grasp the molecular basis of CCRT resistance and guide therapeutic strategies with greater precision.</p><p><strong>Methods: </strong>We utilized a public rectal cancer transcriptomic dataset (n = 46) to predict responsiveness to neoadjuvant CCRT by analyzing signal transduction-related genes. In our well-characterized rectal cancer cohort (n = 343), we assessed correlations between membrane-spanning 4-domains A12 (MS4A12) immunostaining and clinicopathological characteristics using Pearson's chi-squared test. To calculate survival rates, we employed the Kaplan-Meier method with a log-rank test. Additionally, we conducted multivariate analyses with the Cox proportional hazards model to identify independent prognostic biomarkers.</p><p><strong>Results: </strong>We identified that the MS4A12 gene is highly expressed in rectal cancer resistant to CCRT. Elevated MS4A12 expression, confirmed by immunohistochemical staining, is significantly associated with advanced tumor status after CCRT (p < 0.001), positive node status both before and after CCRT (p = 0.01 and p = 0.004), the presence of perineural and vascular invasion (p = 0.006 and p = 0.001), and low or no response to CCRT (p < 0.001). Notably, high MS4A12 immunoexpression is strongly correlated with reduced patient survival in rectal cancer. Mechanically, high MS4A12 expression is significantly associated with aberrant glycosylation and B-cell infiltration.</p><p><strong>Conclusion: </strong>MS4A12 expression may offer a helpful predictive and prognostic indicator for identifying patients who could gain advantages from neoadjuvant CCRT.</p>","PeriodicalId":49639,"journal":{"name":"Radiation Oncology","volume":"20 1","pages":"126"},"PeriodicalIF":3.3,"publicationDate":"2025-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12335166/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144812571","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":"From standardized to individualized margins for online adaptive tumor dose escalation in rectal cancer.","authors":"C M Kensen, Lisa Wiersema, Anja Betgen, Doenja M J Lambregts, Corrie A M Marijnen, Uulke A van der Heide, Tomas M Janssen","doi":"10.1186/s13014-025-02706-8","DOIUrl":"10.1186/s13014-025-02706-8","url":null,"abstract":"<p><strong>Purpose: </strong>To determine the impact of tumor characteristics such as tumor volume, circumference and location in the rectum on intrafraction motion during dose-escalated MRI-guided radiotherapy of rectal cancer and to explore the potential of PTV margin individualization.</p><p><strong>Methods: </strong>Seventy-seven rectal cancer patients, treated with short course radiotherapy (SCRT) on a 1.5T MR-Linac, were included in the study. For all five treatment fractions per patient, the GTV of the primary tumor was manually delineated on T2-weighted images acquired for online plan adaptation (MRI_adapt). GTV delineations on the MRI acquired for verification after irradiation (MRI_post) were obtained by patient-specific fine-tuning of a population-based GTV autosegmentation model using the delineation on MRI_adapt. The intrafraction motion was calculated as ¾ of the center of gravity (COG) displacement of the GTV between MRI_adapt and MRI_post. PTV margins were calculated using the Van Herk recipe. The effect of tumor volume, circumference and location in the rectum on intrafraction motion was studied using linear mixed effect modeling and individualized margins were calculated for each group.</p><p><strong>Results: </strong>Intrafraction motion was correlated with tumor location with larger displacement in Anterior-Posterior (p = 0.001) and Cranial-Caudal (CC; p = 0.043) direction for caudal tumors compared to proximal tumors (lower border starting > 5 cm from anorectal junction). For tumor volume, a significant (p = 0.049), but small association with Left-Right motion was found, with larger tumors exhibiting larger motion. PTV margins required for the full cohort were 2.8 mm LR, 6.3 mm AP, 2.2 mm cranial and 5.6 mm caudal. Individualizing on tumor location resulted in AP margin of 3.5 mm for proximal rectal tumors and 6.7 mm for distal rectal tumors. Margins in CC direction were 3.2 mm for proximal rectal tumors and asymmetrically 2.0 mm cranial and 6.0 mm caudal for distal rectal tumors.</p><p><strong>Conclusion: </strong>Our study demonstrated that distance to anorectal junction significantly influenced the magnitude and direction of the intrafraction motion of rectal cancer patients receiving SCRT, with distal tumors showing larger motion in the AP and CC directions. For proximal rectal tumors, the margin could be decreased in AP and CC direction.</p>","PeriodicalId":49639,"journal":{"name":"Radiation Oncology","volume":"20 1","pages":"125"},"PeriodicalIF":3.3,"publicationDate":"2025-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12335123/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144805099","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":"A prospective outcomes and cost-effective analysis of surgery compared to stereotactic body radiation therapy for stage I non-small cell lung cancer.","authors":"Andrew Kennedy, Shanna A Arnold Egloff, Casey Martin, Denis Gilmore, Susan Garwood, Tammy Baxter, David Spigel, Melissa Johnson, David Randolph Ii, Casey Chollet-Lipscomb, Laurie Cuttino, Eleanor Osborne, Jenifer Marks, Pratik Doshi, Meredith Mattlin, Richard Geer, Dax Kurbegov, Howard Burris Iii","doi":"10.1186/s13014-025-02699-4","DOIUrl":"10.1186/s13014-025-02699-4","url":null,"abstract":"<p><strong>Background: </strong>To evaluate long-term outcomes, treatment costs, and quality of life associated with curative treatment of newly diagnosed stage I non-small cell lung cancer (NSCLC), by comparing surgery to stereotactic body radiation therapy (SBRT).</p><p><strong>Methods: </strong>Multicenter consecutive prospective study of newly diagnosed stage I NSCLC patients independently assigned surgery or SBRT by a multidisciplinary tumor board, recruited prior to therapy initiation (n = 59). Outcomes included total hospital charges, toxicities, complications, readmissions, and patient satisfaction/ quality of life (FACT-L). Multivariable logistic regression models analyzed the association of treatment type with dichotomous endpoints controlling for age, Charlson Comorbidity Index (CCI), and pre-treatment FACT-L; multiple linear regression was used for delta FACT-L.</p><p><strong>Results: </strong>Of the 55 evaluable patients, 19 (35%) were males and 36 (65%) females. Thirty (55%) patients received SBRT and 25 (45%) received surgery with a mean age of 73 (57-85) and 67 (55-84) years, respectively. Median follow-up time was 514 days after SBRT and 648 days after surgery. The mean CCI for SBRT and surgery patients was 3.87 and 2.36, respectively. SBRT patients experienced significantly greater improvement in quality of life compared to surgery (delta FACT-L, 14, 95%CI, 2 to 26, p = 0.0232) after adjusting for baseline FACT-L. CCI but not age, treatment type, or baseline FACT-L was significantly associated with readmissions (OR, 1.42, 95%CI, 1.08 to 2.00, p = 0.0226). Interestingly, CCI was significantly lower (2.36 ± 1.66, 3.87 ± 2.84, p = 0.0418) yet total hospital charges were significantly greater ($251,759±$215,643, $129,238±$86,588, p = 0.0009) for patients receiving surgery verses SBRT.</p><p><strong>Conclusions: </strong>Although limitations include small sample size and absence of recurrence data, these analyses justify further evaluation of long-term outcomes, including cost and quality of life, to optimize treatment assignment of early stage NSCLC patients. These observations reveal that, despite targeting patients with higher CCI, SBRT is more cost-effective, with a greater improvement in quality of life than surgery.</p><p><strong>Trial registration: </strong>Central Institutional Review Board (IRB) approval was obtained under expedited review and deemed minimal risk to patients (WCG Clinical IRB00000533 Study 1171593). All participating sites obtained local IRB approval before study initiation. Informed consent was obtained from all patients prior to study entry.</p>","PeriodicalId":49639,"journal":{"name":"Radiation Oncology","volume":"20 1","pages":"123"},"PeriodicalIF":3.3,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12326780/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144790543","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":"Proton therapy for adult type IDH-mutated glioma: Proglio-1, a multicenter retrospective study.","authors":"Nicolas Goliot, Emmanuel Jouglar, Julian Jacob, François Christy, Eva Seutin, Renaud Schiappa, Sarah Dumont, Selim Mohssine, Dinu Stefan, Arthur Leclerc, Evelyne Emery, Cyril Moignier, Jeanne Riverain, Fernand Missohou, Maxime Fontanilles, Samuel Valable, Jacques Balosso, Jérôme Doyen, Paul Lesueur","doi":"10.1186/s13014-025-02702-y","DOIUrl":"10.1186/s13014-025-02702-y","url":null,"abstract":"<p><strong>Background: </strong>Gliomas with isocitrate dehydrogenase (IDH) mutation affect young adults with a long-life expectancy. While radiotherapy is effective, studies have shown its detrimental effects on cognition and quality of life. Unlike photon radiotherapy, proton therapy better spares healthy tissue. This study aimed to report mid-term survival and toxicities of proton therapy in a multicentric cohort of adults with IDH-mutant gliomas.</p><p><strong>Methods: </strong>We retrospectively analyzed 90 patients treated with proton therapy in France since 2016, including 60 with IDH-mutated astrocytomas and 30 with oligodendrogliomas. Overall survival (OS) and progression-free survival (PFS) were estimated by Kaplan-Meier and compared with the log-rank test. Prognostic factors were assessed using univariate Cox models. Toxicities, radiation-induced-contrast-enhancement (RICE) and patterns of recurrence were evaluated.</p><p><strong>Results: </strong>At the time of proton therapy, World Health Organization (WHO) pathology grades 2, 3, and 4 were observed in 42%, 54%, and 3% of patients, respectively. Protons were delivered as upfront therapy in 41 patients and after recurrence in 49. After a median follow-up of 27.3 months, median OS was not reached, and median PFS was 42.5 months for the whole cohort. WHO grades 3-4 had lower PFS than WHO grade 2 (p = 0.044). Patterns of recurrence were in-field (79%), out-of-field (7%), borderline (4%), and mixed (11%). Proton therapy was well tolerated, with only three grade > 2 toxicities. RICE occurred in 23 patients, but 74% of them did not require any treatment.</p><p><strong>Conclusions: </strong>Proton therapy in IDH-mutated gliomas shows a favorable mid-term tolerance and efficacy profile.</p>","PeriodicalId":49639,"journal":{"name":"Radiation Oncology","volume":"20 1","pages":"124"},"PeriodicalIF":3.3,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12326604/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144790544","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":"Early prediction of proton therapy dose distributions and DVHs for hepatocellular carcinoma using contour-based CNN models from diagnostic CT and MRI.","authors":"Toshiya Rachi, Taku Tochinai","doi":"10.1186/s13014-025-02708-6","DOIUrl":"10.1186/s13014-025-02708-6","url":null,"abstract":"<p><strong>Background: </strong>Proton therapy is commonly used for treating hepatocellular carcinoma (HCC); however, its feasibility can be challenging to assess in large tumors or those adjacent to critical organs at risk (OARs), which are typically assessed only after planning computed tomography (CT) acquisition. This study aimed to predict proton dose distributions using diagnostic CT (dCT) and diagnostic MRI (dMRI) with a convolutional neural network (CNN), enabling early treatment feasibility assessments.</p><p><strong>Methods: </strong>Dose distributions and dose-volume histograms (DVHs) were calculated for 118 patients with HCC using intensity-modulated proton therapy (IMPT) and passive proton therapy. A CPU-based CNN model was used to predict DVHs and 3D dose distributions from diagnostic images. Prediction accuracy was evaluated using mean absolute error (MAE), mean squared error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and gamma passing rate with a 3 mm/3% criterion.</p><p><strong>Results: </strong>The predicted DVHs and dose distributions showed high agreement with actual values. MAE remained below 3.0%, with passive techniques achieving 1.2-1.8%. MSE was below 0.004 in all cases. PSNR ranged from 24 to 28 dB, and SSIM exceeded 0.94 in most conditions. Gamma passing rates averaged 82-83% for IMPT and 92-93% for passive techniques. The model achieved comparable accuracy when using dMRI and dCT.</p><p><strong>Conclusions: </strong>This study demonstrates that early dose distribution prediction from diagnostic imaging is feasible and accurate using a lightweight CNN model. Despite anatomical variability between diagnostic and planning images, this approach provides timely insights into treatment feasibility, potentially supporting insurance pre-authorization, reducing unnecessary imaging, and optimizing clinical workflows for HCC proton therapy.</p>","PeriodicalId":49639,"journal":{"name":"Radiation Oncology","volume":"20 1","pages":"122"},"PeriodicalIF":3.3,"publicationDate":"2025-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12323130/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144785799","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":"Early prediction of histopathological response of locally advanced rectal cancer after 1 week of preoperative radiochemotherapy using ¹⁸FDG PET-CT imaging: a prospective clinical validation study.","authors":"Yulia Kundel, Zoya Cohen, Noa Gordon, Aaron Sulkes, Sara Morgenstern, Gali Perl, Nir Wasserberg, David Groshar, Hanna Bernstine, Baruch Brenner","doi":"10.1186/s13014-025-02703-x","DOIUrl":"10.1186/s13014-025-02703-x","url":null,"abstract":"<p><strong>Background: </strong>Neoadjuvant (preoperative) radiochemotherapy (nRCT) is a standard of care in locally advanced rectal cancer (LARC). Several studies have shown that the decline in ¹⁸FDG uptake after 2 weeks of nRCT compared with the baseline, i.e. the tumor's metabolic response, may correlate with histopathological response. However, our previous prospective study suggested that the tumor's histopathological response could be predicted by the metabolic response already observed after 1 week of nRCT. The current study was undertaken to validate these findings.</p><p><strong>Methods: </strong>Thirty-eight patients with LARC who received standard nRCT followed by radical surgery were enrolled. Metabolic response, evaluated by the percent of change in maximum standardized uptake value (ΔSUVmax%), measured by PET-CT imaging at baseline and on day 8 of nRCT, was compared with the histopathological response at surgery. Histopathological response was assessed by pathological complete response (pCR) and, when possible, by tumor regression grade (TRG). We also examined the association of baseline and second PET-CT parameters with pCR and TRG at surgery.</p><p><strong>Trial registration: </strong>0239-07-RMC, registration date: 21/08/2007.</p><p><strong>Results: </strong>Neither pCR nor TRG were associated with any change in PET-CT parameters after 1 week of treatment. Baseline metabolic tumor volume (MTV) was the only PET-CT parameter with a statistically significant association with pCR (p = 0.002), but not with TRG (p = 0.08).</p><p><strong>Conclusions: </strong>A decrease in SUVmax after 1 week of nRCT for LARC failed to predict the achievement of pCR or TRG in the post-nRCT surgical specimen, underlining the importance of validation clinical trials. Nonetheless, our findings on the correlation between baseline MTV and histopathological response can, if confirmed, be a useful tool for treatment selection. Validation in a larger independent cohort is planned.</p>","PeriodicalId":49639,"journal":{"name":"Radiation Oncology","volume":"20 1","pages":"121"},"PeriodicalIF":3.3,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12317454/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144765731","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}