Technology in Cancer Research & Treatment最新文献

{"title":"Optimizing Helical Tomotherapy for Left-Sided Breast Cancer: A Retrospective Dosimetric Study of a Novel Virtual Organ-Arc Block.","authors":"Yingtao Fang, Wenliang Yu, Jian Qiao, Yanju Yang, Jing Mi, Lei Yu, Ying Guo, Jiazhou Wang, Weigang Hu","doi":"10.1177/15330338251363288","DOIUrl":"10.1177/15330338251363288","url":null,"abstract":"<p><p>IntroductionLeft-sided breast cancer radiotherapy requires precise dose modulation to balance target coverage and organ-at-risk (OAR) sparing. This study evaluates a novel Organ and Arc-based Directional Block (OABD Block) in helical tomotherapy planning to address this challenge.MethodsIn this single-institutional retrospective study, 10 post-mastectomy patients with left-sided breast cancer receiving adjuvant radiotherapy were studied. Target volumes included chest wall, internal mammary, axillary, and supraclavicular lymph nodes, with a dose of 50 Gy over 25 fractions. Using a tomotherapy planning system, an OABD Block was configured to incorporate arc structures and protect organs-at-risk. For each patient, helical tomotherapy plans were prepared with and without the OABD Block, keeping field width, pitch, and modulation factors identical. Additionally, static intensity-modulated radiotherapy (IMRT) plans were created on a United Imaging system. Treatment plans were evaluated by dose-volume parameters, conformity and homogeneity indices, and mean doses to targets and normal tissues.ResultsHelical tomotherapy with the OABD Block provided a mean conformity Index of 0.79 for the Planning Target Volume, higher than plans without the block (0.73) but below IMRT plans (0.88). The homogeneity Index averaged 0.14 with the block, 0.18 without, and 0.11 in IMRT. For the internal mammary lymph node region, D95% reached 5007.7 cGy with the block, compared to 5001.1 cGy without and 4897.9 cGy in IMRT. The OABD Block reduced the mean heart dose to 478.7 cGy, compared to 533.5 cGy without and 638.9 cGy in IMRT. Left lung V5 was 48.0% with the block, 52.7% without, and 53.2% in IMRT; V20 was also lowest with the block (17.5%) versus without (20.3%) and IMRT (24.3%).ConclusionAdding the OABD Block to helical tomotherapy improved internal mammary lymph node dose coverage and reduced exposure to organs at risk.</p>","PeriodicalId":22203,"journal":{"name":"Technology in Cancer Research & Treatment","volume":"24 ","pages":"15330338251363288"},"PeriodicalIF":2.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12304599/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144708772","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and Validation of Predictive Models for Differentiating Resectable Stage III Peripheral SCLC from NSCLC Using Radiomic Features and Clinical Parameters.","authors":"Junjie Zhang, Ligang Hao, Qiuxu Zhang, Lina Zheng, Qian Xu, Fengxiao Gao","doi":"10.1177/15330338251368956","DOIUrl":"https://doi.org/10.1177/15330338251368956","url":null,"abstract":"<p><p>ObjectiveLung cancer is primarily categorized into small cell lung cancer (SCLC) and non-small cell lung cancer (NSCLC), each characterized by distinct therapeutic approaches and prognostic outcomes, particularly in stage III peripheral cases. This study aimed to develop predictive models utilizing clinical and radiomic data to preoperatively differentiate stage III peripheral SCLC from NSCLC.MethodWe conducted a retrospective analysis of 33 stage III peripheral SCLC cases and 99 stage III peripheral NSCLC cases treated at our hospital between January 2016 and July 2024. A total of 1037 radiomic features were extracted from contrast-enhanced CT scans. The cohort was divided into a training set (n = 92) and a test set (n = 40). Radiomic feature selection was performed using the LASSO algorithm, and nine machine learning models were evaluated. The optimal model was employed to compute the radiomics score (Rad-score) and construct a clinical model. A combined model, integrating clinical factors and radiomic features, was assessed for clinical utility through receiver operating characteristic (ROC) curve analysis (area under the curve, AUC), KS statistics and decision curve analysis (DCA). We externally validated the combined model in a group of 84 patients from another hospital.ResultsThe logistic regression-based combined model exhibited superior performance, achieving AUC values of 0.956, 0.775, and 0.841 for the combined, clinical, and radiomics models, respectively, within the training cohort, and 0.905, 0.864, and 0.732 in the test cohort. AUC for the combined model was 0.843 in the external validation cohort. The KS statistics and DCA indicated the clinical utility of the combined model, as evidenced by a Brier score of 0.115.ConclusionThe integration of clinical parameters and radiomics features within the combined model may hold significant potential for the preoperative differentiation of stage III peripheral SCLC from NSCLC.</p>","PeriodicalId":22203,"journal":{"name":"Technology in Cancer Research & Treatment","volume":"24 ","pages":"15330338251368956"},"PeriodicalIF":2.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12374101/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144969979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Lightweight Dual-Output Vision Transformer for Enhanced Lung Nodule Classification Using CT Images.","authors":"Menna Allah Mahmoud, Yanhua Wen, Yuling Liufu, Xiaohuan Pan, Ruihua Su, Yubao Guan","doi":"10.1177/15330338251370439","DOIUrl":"https://doi.org/10.1177/15330338251370439","url":null,"abstract":"<p><p>IntroductionThis study evaluates the effectiveness of a lightweight vision transformer (EfficientFormerV2-S2) with a dual-output architecture for lung nodule classification, assessing its performance and generalizability across multiple datasets.MethodsThe study utilized datasets from three sources: Institution 1 (936 images), Institution 2 (280 images), and a public Zenodo dataset (308 images), comprising adenocarcinoma, squamous cell carcinoma, and benign lesions. Model evaluation included holdout validation, five-fold cross-validation, and benchmarking against the PneumoniaMedMNIST dataset. Comprehensive image preprocessing and augmentation techniques were implemented.ResultsThe model demonstrated robust performance across all datasets, achieving test accuracies of 92.62 ± 1.65%, 97.14 ± 1.78%, and 95.74 ± 1.35% for Institutions 1, 2, and Zenodo respectively. Cross-validation results showed consistent performance with minimal variability (standard deviations <2%). On the PneumoniaMedMNIST benchmark, our optimized model achieved superior performance (accuracy: 0.936, AUC: 0.981) compared to ResNet18 and ResNet50 benchmarks.ConclusionThe lightweight transformer-based model demonstrates excellent performance and generalizability across multiple institutional datasets, suggesting its potential for efficient clinical implementation in lung nodule classification tasks.</p>","PeriodicalId":22203,"journal":{"name":"Technology in Cancer Research & Treatment","volume":"24 ","pages":"15330338251370439"},"PeriodicalIF":2.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12374121/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144969994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting the Efficacy of Neoadjuvant Chemotherapy Combined with Immunotherapy for Esophageal Squamous Cell Carcinoma via Enhanced CT Radiomics Combined with Clinical Features.","authors":"Xiang Qin, Fen Wang, Shaohong Wu, Dong Han, Genji Bai, Lili Guo","doi":"10.1177/15330338251370437","DOIUrl":"10.1177/15330338251370437","url":null,"abstract":"<p><p>IntroductionTo evaluate the predictive efficacy of enhanced Computed Tomograph(CT) radiomics combined with clinical features for assessing treatment response to neoadjuvant chemotherapy plus immunotherapy in esophageal squamous cell carcinoma (ESCC) patients.MethodsWe retrospectively analyzed 189 pathologically confirmed esophageal squamous cell carcinoma patients (treated between January 2020 and October 2024) who underwent neoadjuvant chemoimmunotherapy. Patients were stratified into remission and non-remission groups based on pathological response and randomly divided into training (n = 114) and testing (n = 75) sets (6:4 ratio). Clinical predictors were identified using logistic regression to construct a clinical model. Radiomic features were extracted from manually delineated tumor regions on contrast-enhanced CT scans, and a radiomics model was developed. A combined model integrating clinical variables and radiomics probabilities was then built and presented as a nomogram. Model performance was assessed using receiver operating characteristic (ROC) curves (AUC, Area Under the Curve) comparison via Delong test), calibration curves, and decision curve analysis (DCA).ResultsMultivariable analysis identified treatment cycle number as a significant clinical predictor. Ten radiomic features were selected for the final model. In the training set, the clinical model achieved an AUC of 0.705 (95% CI 0.607-0.802), while the radiomics and combined models showed superior performance with AUCs of 0.905 (95% CI 0.843-0.967) and 0.914 (95% CI 0.857-0.970), respectively. Similar trends were observed in the testing set, where the combined model (AUC 0.859, 95% CI 0.768-0.950) outperformed both the radiomics (AUC 0.815) and clinical (AUC 0.644) models.ConclusionThe enhanced CT radiomics model has better predictive efficacy for remission with neoadjuvant chemotherapy combined with immunotherapy in esophageal squamous cell carcinoma patients, and the combined model has greater predictive value.</p>","PeriodicalId":22203,"journal":{"name":"Technology in Cancer Research & Treatment","volume":"24 ","pages":"15330338251370437"},"PeriodicalIF":2.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12361841/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144875335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Retraction: Inhibition of Mircorna-766-5p Attenuates the Development of Cervical Cancer Through Regulating SCAI.","authors":"","doi":"10.1177/15330338251363342","DOIUrl":"10.1177/15330338251363342","url":null,"abstract":"","PeriodicalId":22203,"journal":{"name":"Technology in Cancer Research & Treatment","volume":"24 ","pages":"15330338251363342"},"PeriodicalIF":2.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12351074/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144837782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Oral Cavity Squamous Cell Carcinoma: Impact of Clear Margin Distance on Locoregional Control in Patients Undergoing Postoperative Radiotherapy.","authors":"Erkan Topkan, Efsun Somay, Ugur Selek","doi":"10.1177/15330338241305823","DOIUrl":"10.1177/15330338241305823","url":null,"abstract":"<p><p>We congratulate Lang and colleagues for their study investigating the impact of resection margin (RM) size on locoregional control (LC) outcomes, overall survival (OS), progression-free survival (PFS), and treatment-related toxicity in 162 patients with oral cavity squamous cell carcinoma (OCSCC) who received postoperative radiotherapy (PORT).1 In this study, 77 (47.5%), 22 (13.6%), and 63 (38.9%) patients had involved (5 mm) RM, respectively. A RM of ≤5 mm was found to be a significant predictor for worse LC (HR 2.6), but not for OS (HR 1.2) or PFS (HR 1.2). The findings of this study provide important insights into how the status of RM affects the local control and survival outcomes of OCSCC patients who undergo PORT. However, we have two concerns that we believe need to be addressed to interpret the results more comprehensively and guide future research on this critical topic.</p>","PeriodicalId":22203,"journal":{"name":"Technology in Cancer Research & Treatment","volume":"24 ","pages":"15330338241305823"},"PeriodicalIF":2.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11795598/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143190710","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"B7-H3 and CD39 Co-Localization in Gastric Cancer: A Potential Prognostic Biomarker and Potential Dual-Target for Immunotherapy.","authors":"Qiange Zhang, Ying Liu, Hanqin Xuan, Shenghua Zhan, Yu Shen, Ruipeng Wang, Siji Chen, Sisi Ding, Cuiping Liu, Lili Huang, Qi Ma, Tingwang Jiang, Lei Cao","doi":"10.1177/15330338251380957","DOIUrl":"10.1177/15330338251380957","url":null,"abstract":"<p><p>IntroductionGastric cancer (GC) is a highly heterogeneous malignancy, necessitating novel therapeutic targets. B7-H3 and CD39, as immune checkpoints, are potential modulators of the tumor microenvironment and may influence the efficacy of immunotherapies.MethodsB7-H3, CD39, and CD8 expression was assessed via immunohistochemistry (IHC) in 268 GC tissues and 80 gastric precancerous lesions. The correlation between B7-H3 and CD39 expression was analyzed using Spearman's correlation. Multiplex immunohistochemistry (m-IHC) was employed to determine the co-localization of B7-H3 and CD39 in GC tissues. Kaplan-Meier survival analysis and Cox regression models were utilized to evaluate clinical outcomes in different patient subgroups.ResultsBoth B7-H3 and CD39 expression showed a stepwise increase during gastric carcinogenesis including chronic superficial gastritis (CSG), chronic atrophic gastritis (CAG), low-grade intraepithelial neoplasia (LGIN), high-grade intraepithelial neoplasia (HGIN) to GC, with significantly higher expression levels in GC tissues compared to all precancerous lesions (<i>P</i> < .05). A significant positive correlation was observed between B7-H3 and CD39 expression (r = 0.2398, <i>P</i> < .001). Co-localization of B7-H3 and CD39 was detected within tumor nests and peritumoral regions and was significantly correlated with tumor volume (<i>P</i> = .017), tumor stage (<i>P</i> = .001), tumor depth (<i>P</i> = .002), lymph node metastasis (<i>P</i> = .005), lymph node involvement (<i>P</i> = .004) and distant metastasis (<i>P</i> = .028). Kaplan-Meier analysis revealed that patients with co-localized B7-H3 and CD39 expression exhibited significantly poorer prognosis (<i>P</i> = .0055). Cox regression analysis confirmed that this co-localization was a significant predictor of survival (<i>P</i> = .007) and an independent prognostic factor in multivariate analysis (<i>P</i> = .027).ConclusionThe co-localized expression of B7-H3 and CD39 in GC patients is strongly associated with poor prognosis. This dual-target expression pattern provides novel insights and a theoretical foundation for the development of dual-target immune checkpoint inhibitors as potential therapeutic strategies.</p>","PeriodicalId":22203,"journal":{"name":"Technology in Cancer Research & Treatment","volume":"24 ","pages":"15330338251380957"},"PeriodicalIF":2.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12461060/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145132055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Differentiation and Localization of Adjacent Murine Tumors Using X-ray and Bioluminescence Tomography.","authors":"Jiahao Chen, Yunwen Huang, Ning Zhao, Yi Ru, Yidong Yang","doi":"10.1177/15330338251382977","DOIUrl":"10.1177/15330338251382977","url":null,"abstract":"<p><p>IntroductionPreviously, a multimodal imaging system including x-ray computed tomography (CT) and bioluminescence tomography (BLT) has been developed on iSMAART and is capable of accurately localizing small tumors on the millimeter scale in three dimensions (3D). Here, a \"2D decomposition + 3D reconstruction\" strategy is proposed to recover multiple tumors that are closely spaced and may have drastically different bioluminescence intensities.MethodsIn the iSMAART system, CT provides the animal anatomy and surface contours required for BLT reconstruction. The BLT and CT are physically registered, rendering superimposed images. For BLT reconstruction, the surface bioluminescence signal is first decomposed using a Gaussian mathematical model into multiple independent signal distributions, before separate reconstruction of individual targets. The final tumor distribution is the summation of the individual reconstruction results. BLT/CT imaging was performed on two types of metastatic tumor models, PC3 prostate tumors and HCT116 colorectal tumors, with 2 mice in each model. A double-blind histopathological analysis was conducted to verify the imaging results.Results and ConclusionBy incorporating the proposed strategy, the iSMAART system accurately differentiated and localized multiple tightly clustered tumors of varying sizes and optical intensities in all mice, and four tumors in a single mouse were simultaneously diagnosed. The tumor sizes measured by BLT closely matched the histopathological results (mean value 2.76 vs 2.41 mm). In this study, we proposed a \"2D decomposition + 3D reconstruction\" strategy, which enables the iSMAART system to accurately localize and quantify multiple tumors in live animals despite significant signal overlap and intensity variations, providing a powerful tool to fulfill and even open up more high-demand research fields.</p>","PeriodicalId":22203,"journal":{"name":"Technology in Cancer Research & Treatment","volume":"24 ","pages":"15330338251382977"},"PeriodicalIF":2.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12480804/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145193071","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Screening of Germline BRCA1 and BRCA2 Variants in Nigerian Breast Cancer Patients.","authors":"Abimbola F Onyia, Paul Jibrin, Temitope Olatunji-Agunbiade, Ademola Oyekan, AbdulRazzaq Lawal, Adewumi Alabi, Anthonia C Sowunmi, Eben A Aje, Oluwabusayo B Ogunniyi, Ebenezer S Nkom, Opeyemi C De Campos, Oluwakemi A Rotimi, Jelili O Oyelade, Solomon O Rotimi","doi":"10.1177/15330338251333012","DOIUrl":"https://doi.org/10.1177/15330338251333012","url":null,"abstract":"<p><p>BackgroundBreast cancer remains a leading cause of mortality among Nigerian women, with triple-negative breast cancer (TNBC) being particularly prevalent. Variations in BRCA1 and BRCA2 genes remain key risk factors for this disease. However, there are gaps in the frequency and spectrum of these variants in Nigerian populations, as well as a dearth in the local capacity to characterize these variations.ObjectiveThis study aimed at identifying and characterizing the germline variations in BRCA1/2 in Nigerian breast cancer patients and healthy age-matched controls to understand the genetic risk profile of breast cancer in this population.MethodsA prospective case-control study was conducted involving 45 breast cancer patients and 51 controls recruited from four major hospitals. DNA was extracted from blood samples, followed by targeted sequencing of BRCA1/2 exonic and intronic regions using the Ampliseq BRCA panel and Illumina MiSeq platform. Variant calling was performed, clinical significance was evaluated on ClinVar and BRCA Exchange databases, and haplotype analysis was performed using NIH LDlink and Haploview 4.2 software.ResultsPathogenic BRCA1/2 variants were identified in 6.7% of breast cancer patients, all with TNBC and a family history of cancer. Two pathogenic BRCA1 variants were detected: a frameshift deletion BRCA1 c.133_134delAA (p.Lys45 fs) (rs397508857) and a missense variant BRCA1 c.5324T > A (p.Met1775Arg) (rs41293463). A BRCA2 frameshift deletion BRCA2 c.8817_8820del (p.Lys2939 fs) (rs397508010) was also identified. These variants were absent in controls. Haplotype analysis revealed distinct BRCA1 and BRCA2 haplotypes in the breast cancer group.ConclusionThis study identifies key BRCA1/2 pathogenic variants and unique haplotypes in Nigerian breast cancer patients, highlighting the need for population-specific genetic screening. Integrating genetic testing into breast cancer management strategies could facilitate early detection, personalized treatment planning, and genetic counseling in Nigeria.</p>","PeriodicalId":22203,"journal":{"name":"Technology in Cancer Research & Treatment","volume":"24 ","pages":"15330338251333012"},"PeriodicalIF":2.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12033648/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143987012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparison of Deep Learning-Based Auto-Segmentation Results on Daily Kilovoltage, Megavoltage, and Cone Beam CT Images in Image-Guided Radiotherapy.","authors":"Zhixing Wang, Chengyu Shi, Carson Wong, Seyi M Oderinde, William T Watkins, Kun Qing, Bo Liu, Terence M Williams, An Liu, Chunhui Han","doi":"10.1177/15330338251344198","DOIUrl":"10.1177/15330338251344198","url":null,"abstract":"<p><p>IntroductionThis study aims to evaluate auto-segmentation results using deep learning-based auto-segmentation models on different online CT imaging modalities in image-guided radiotherapy.MethodsPhantom studies were first performed to benchmark image quality. Daily CT images for sixty patients were retrospectively retrieved from fan-beam kilovoltage CT (kVCT), kV cone-beam CT (kV-CBCT), and megavoltage CT (MVCT) scans. For each imaging modality, half of the patients received CT scans in the pelvic region, while the other half in the thoracic region. Deep learning auto-segmentation models using a convolutional neural network algorithm were used to generate organs-at-risk contours. Quantitative metrics were calculated to compare auto-segmentation results with manual contours.ResultsThe auto-segmentation contours on kVCT images showed statistically significant difference in Dice similarity coefficient (DSC), Jaccard similarity coefficient, sensitivity index, inclusiveness index, and the 95^th percentile Hausdorff distance, compared to those on kV-CBCT and MVCT images for most major organs. In the pelvic region, the largest difference in DSC was observed for the bowel volume with an average DSC of 0.84 ± 0.05, 0.35 ± 0.23, and 0.48 ± 0.27 for kVCT, kV-CBCT, and MVCT images, respectively (<i>p</i>-value < 0.05); in the thoracic region, the largest difference in DSC was found for the esophagus with an average DSC of 0.63 ± 0.16, 0.18 ± 0.13, and 0.22 ± 0.08 for kVCT, kV-CBCT, and MVCT images, respectively (<i>p</i>-value < 0.05).ConclusionDeep learning-based auto-segmentation models showed better agreement with manual contouring when using kVCT images compared to kV-CBCT or MVCT images. However, manual correction remains necessary after auto-segmentation with all imaging modalities, particularly for organs with limited contrast from surrounding tissues. These findings underscore the potential and limits in applying deep learning-based auto-segmentation models for adaptive radiotherapy.</p>","PeriodicalId":22203,"journal":{"name":"Technology in Cancer Research & Treatment","volume":"24 ","pages":"15330338251344198"},"PeriodicalIF":2.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12099101/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144111982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}