Cancer Imaging最新文献

{"title":"Prognostic value of the pre-treatment SUVmax of ¹⁸F-FDG PET/CT combined with peripheral absolute lymphocyte in patients with newly diagnosed extranodal natural killer/T-cell lymphoma.","authors":"Xingmei Lu, Kate Huang, Peng Li, Yida Li, Xiuhuan Ji, Suidan Chen, Jianmin Li","doi":"10.1186/s40644-025-00882-0","DOIUrl":"10.1186/s40644-025-00882-0","url":null,"abstract":"<p><strong>Background: </strong>Accurate assessment and prediction of patient prognosis, early identification of high-risk patients, and improvement of clinical outcomes for individuals with extranodal natural killer/T-cell lymphoma (ENKTCL) are critical. This study evaluates the prognostic value of a novel model combining maximum standardized uptake value (SUVmax) and absolute lymphocyte count (ALC) in ENKTCL patients.</p><p><strong>Methods: </strong>We conducted a retrospective analysis of clinical data from 57 patients diagnosed with primary ENKTCL. Optimal cut-off values for SUVmax and ALC were determined using receiver operating characteristic (ROC) curves. Clinical characteristics were analyzed by Chi-squared tests or Fisher's exact tests. Survival analysis was performed using the Kaplan-Meier method and log-rank test, while independent prognostic factors were identified through Cox regression analysis.</p><p><strong>Results: </strong>The optimal cut-off values for SUVmax and ALC were established at 11.8 and 0.87 × 10⁹/L, respectively. Univariate and multivariate analyses confirmed that both SUVmax and ALC were independent predictors of prognosis in ENKTCL patients. According to the combined SUVmax-ALC model, the patients were stratified into low-risk, intermediate-risk and high-risk groups. Kaplan-Meier analysis revealed significant differences in overall survival (OS) and progression-free survival (PFS) among these groups (p < 0.001). ROC curve analysis showed that the area under the curve (AUC) for the SUVmax-ALC model was 0.714, superior to individual tests (SUVmax, AUC = 0.674; ALC, AUC = 0.589). In addition, the AUC of the SUVmax-ALC model was higher than the International Prognostic Index (IPI, AUC = 0.632), nomogram-revised risk index (NRI, AUC = 0.566), and prognostic index of natural killer T-cell lymphoma (PINK, AUC = 0.592). Furthermore, the SUVmax-ALC model more effectively identified high-risk patients within low-risk IPI, PINK, or NRI groups, providing additional prognostic information. These findings indicate that the combination of SUVmax and ALC offers enhanced predictive accuracy for ENKTCL prognosis.</p><p><strong>Conclusion: </strong>Pre-treatment SUVmax and ALC can serve as valuable indicators for predicting the prognosis of ENKTCL patients. Compared to IPI, NRI, and PINK scores, the SUVmax-ALC model demonstrates superior performance in risk stratification, suggesting its potential as an effective personalized prognostic tool for ENKTCL patients.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"67"},"PeriodicalIF":3.5,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12139384/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144224394","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":"Characteristics of ¹⁸F-FAPI-04 PET/CT in patients with peritoneal metastasis and to predict treatment efficacy, a head-to-head comparison with ¹⁸F-FDG PET/CT.","authors":"Yafei Zhang, Mimi Xu, Yu Wang, Fang Yu, Xinxin Chen, Guangfa Wang, Kui Zhao, Hong Yang, Xinhui Su","doi":"10.1186/s40644-025-00887-9","DOIUrl":"10.1186/s40644-025-00887-9","url":null,"abstract":"<p><strong>Background: </strong>¹⁸F-FAPI-04 PET/CT shows promise in detecting peritoneal metastases (PM), but its superiority over ¹⁸F-FDG PET/CT for lesion detection and predicting chemotherapy benefit remains unclear.</p><p><strong>Purpose: </strong>To compare ¹⁸F-FAPI-04 and ¹⁸F-FDG PET/CT imaging features in PM and assess predictive value of ¹⁸F-FAPI-04 for chemotherapy efficacy.</p><p><strong>Methods: </strong>39 pathologically confirmed PM patients with digestive malignancies underwent concurrent ¹⁸F-FAPI-04 and ¹⁸F-FDG PET/CT. Semi-quantitative parameters, including SUV_max, tumor/liver ratio (T/L), tumor/mediastinal blood pool ratio (T/B), were analyzed. The tracer uptake was compared via Wilcoxon tests. The relationships between ¹⁸F-FAPI-04 uptake with FAP and α-SMA expression were analyzed using Pearson correlation. Patients were divided into different short-term outcome groups (responders vs. non-responders) according to RECIST criteria (v.1.1) after chemotherapy. Post-chemotherapy outcomes were evaluated using logistic regression.</p><p><strong>Results: </strong>Patients (median age 62; 16 females, 23 males) included pancreatic (n = 17), cholangiocarcinoma (n = 8), gastric (n = 6), and colorectal cancers (n = 8). ¹⁸F-FAPI-04 demonstrated significantly higher SUV_max, T/L, and T/B than ¹⁸F-FDG (P < 0.05). Pancreaticobiliary cancers (pancreatic/cholangiocarcinoma) exhibited higher 18F-FAPI-04 uptake than gastroenteric cancers (gastric/colorectal) (P < 0.05), though no differences existed within subgroups. ¹⁸F-FAPI-04 parameters positively correlated with FAP and α-SMA expression. In univariate analysis, ¹⁸F-FAPI-04 uptake differed significantly between responders and non-responders. Multivariate analysis identified SUV_max as an independent predictor (OR = 1.354, 95%CI:1.025-1.788, P = 0.033). Optimal ¹⁸F-FAPI-04 cut-offs for distinguishing outcomes were SUV_max=11.05 (AUC = 0.783; sensitivity = 70.60%, specificity = 80.40%), T/L = 7.53 (AUC = 0.717; 58.82%, 81.82%), and T/B = 8.76 (AUC = 0.751; 64.71%, 86.37%).</p><p><strong>Conclusion: </strong>¹⁸F-FAPI-04 PET/CT outperforms ¹⁸F-FDG in PM detection, with semi-quantitative parameters predicting chemotherapy response.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"66"},"PeriodicalIF":3.5,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12128257/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144207752","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":"Accuracy of cross-sectional imaging in predicting tumor viability using the LI-RADS treatment response algorithm after image-guided percutaneous ablation with radiologic-pathologic explant correlation.","authors":"Anuradha S Shenoy-Bhangle, M Saad Malik, Aamir Ali, Nan Nancy Jiang, Syed Yasir Andrabi, Amit Singal, Michael P Curry, Maria-Andreea Catana, Devin E Eckhoff, Salomao Faintuch, Muneeb Ahmed, Imad Ahmad Nasser, Ammar Sarwar","doi":"10.1186/s40644-025-00884-y","DOIUrl":"10.1186/s40644-025-00884-y","url":null,"abstract":"<p><strong>Background: </strong>Accurate assessment of viable HCC on pre-transplant cross sectional imaging is important for correct organ allocation and overall patient outcome following liver transplantation.</p><p><strong>Purpose: </strong>Determine accuracy of LI-RADS TRA compared to explant pathology in patients treated with thermal ablation, using contrast enhanced multiphase CT and MRI.</p><p><strong>Materials and methods: </strong>Imaging studies for 119 consecutive adult HCC patients treated with thermal ablation and liver transplantation from March 2001 to September 2019 at a single tertiary care hospital were retrospectively studied by three Board-certified radiologists. LI-RADS TRA categories for each tumor were compared with explant pathology. Cohens Kappa test and inter-reader agreement by Fleiss κ test, with 95% confidence intervals obtained with bootstrap technique were used.</p><p><strong>Results: </strong>Of the 119 patients (median age 59 years, 95 [80%] male) with 165 HCCs treated with percutaneous thermal ablation, 68% were completely necrotic and 32% were viable on pathologic analysis. Tumors viable on explant were larger on pre-treatment imaging (median 2.4 vs. 2.1 cm; p = 0.02) with no difference in pre-transplant ablation cavity sizes between groups (4.0 vs. 3.9 cm, respectively; p = 0.58). NPV of LI-RADS TRA for viable tumor was 71% (68-74); PPV of 62.5% (39-81) (p = 0.01) with a sensitivity of 19% (9.4-32), specificity of 95% (89-98), and accuracy of 70% (63-77). On explant, 55 incidental treatment naïve viable tumors, not visible on pre-transplant imaging, were found in 33 patients.</p><p><strong>Conclusion: </strong>The \"non-viable\" category of LI-RADS TRA even when applied to a relatively uniform percutaneous ablation cohort, demonstrated low sensitivity in predicting absence of viable tumor. MRI had more accuracy than CT in predicting tumor viability when compared to explant pathology.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"65"},"PeriodicalIF":3.5,"publicationDate":"2025-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12103036/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144141072","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":"Multimodal ultrasound-based radiomics and deep learning for differential diagnosis of O-RADS 4-5 adnexal masses.","authors":"Song Zeng, Haoran Jia, Hao Zhang, Xiaoyu Feng, Meng Dong, Lin Lin, XinLu Wang, Hua Yang","doi":"10.1186/s40644-025-00883-z","DOIUrl":"10.1186/s40644-025-00883-z","url":null,"abstract":"<p><strong>Background: </strong>Accurate differentiation between benign and malignant adnexal masses is crucial for patients to avoid unnecessary surgical interventions. Ultrasound (US) is the most widely utilized diagnostic and screening tool for gynecological diseases, with contrast-enhanced US (CEUS) offering enhanced diagnostic precision by clearly delineating blood flow within lesions. According to the Ovarian and Adnexal Reporting and Data System (O-RADS), masses classified as categories 4 and 5 carry the highest risk of malignancy. However, the diagnostic accuracy of US remains heavily reliant on the expertise and subjective interpretation of radiologists. Radiomics has demonstrated significant value in tumor differential diagnosis by extracting microscopic information imperceptible to the human eye. Despite this, no studies to date have explored the application of CEUS-based radiomics for differentiating adnexal masses. This study aims to develop and validate a multimodal US-based nomogram that integrates clinical variables, radiomics, and deep learning (DL) features to effectively distinguish adnexal masses classified as O-RADS 4-5.</p><p><strong>Methods: </strong>From November 2020 to March 2024, we enrolled 340 patients who underwent two-dimensional US (2DUS) and CEUS and had masses categorized as O-RADS 4-5. These patients were randomly divided into a training cohort and a test cohort in a 7:3 ratio. Adnexal masses were manually segmented from 2DUS and CEUS images. Using machine learning (ML) and DL techniques, five models were developed and validated to differentiate adnexal masses. The diagnostic performance of these models was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC), accuracy, sensitivity, specificity, precision, and F1-score. Additionally, a nomogram was constructed to visualize outcome measures.</p><p><strong>Results: </strong>The CEUS-based radiomics model outperformed the 2DUS model (AUC: 0.826 vs. 0.737). Similarly, the CEUS-based DL model surpassed the 2DUS model (AUC: 0.823 vs. 0.793). The ensemble model combining clinical variables, radiomics, and DL features achieved the highest AUC (0.929).</p><p><strong>Conclusions: </strong>Our study confirms the effectiveness of CEUS-based radiomics for distinguishing adnexal masses with high accuracy and specificity using a multimodal US-based radiomics DL nomogram. This approach holds significant promise for improving the diagnostic precision of adnexal masses classified as O-RADS 4-5.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"64"},"PeriodicalIF":3.5,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12100863/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144132205","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":"Morphometric and radiomics analysis toward the prediction of epilepsy associated with supratentorial low-grade glioma in children.","authors":"Min-Lan Tsai, Kevin Li-Chun Hsieh, Yen-Lin Liu, Yi-Shan Yang, Hsi Chang, Tai-Tong Wong, Syu-Jyun Peng","doi":"10.1186/s40644-025-00881-1","DOIUrl":"10.1186/s40644-025-00881-1","url":null,"abstract":"<p><strong>Objectives: </strong>Understanding the impact of epilepsy on pediatric brain tumors is crucial to diagnostic precision and optimal treatment selection. This study investigated MRI radiomics features, tumor location, voxel-based morphometry (VBM) for gray matter density, and tumor volumetry to differentiate between children with low grade glioma (LGG)-associated epilepsies and those without, and further identified key radiomics features for predicting of epilepsy risk in children with supratentorial LGG to construct an epilepsy prediction model.</p><p><strong>Methods: </strong>A total of 206 radiomics features of tumors and voxel-based morphometric analysis of tumor location features were extracted from T2-FLAIR images in a primary cohort of 48 children with LGG with epilepsy (N = 23) or without epilepsy (N = 25), prior to surgery. Feature selection was performed using the minimum redundancy maximum relevance algorithm, and leave-one-out cross-validation was applied to assess the predictive performance of radiomics and tumor location signatures in differentiating epilepsy-associated LGG from non-epilepsy cases.</p><p><strong>Results: </strong>Voxel-based morphometric analysis showed significant positive t-scores within bilateral temporal cortex and negative t-scores in basal ganglia between epilepsy and non-epilepsy groups. Eight radiomics features were identified as significant predictors of epilepsy in LGG, encompassing characteristics of 2 locations, 2 shapes, 1 image gray scale intensity, and 3 textures. The most important predictor was temporal lobe involvement, followed by high dependence high grey level emphasis, elongation, area density, information correlation 1, midbrain and intensity range. The Linear Support Vector Machine (SVM) model yielded the best prediction performance, when implemented with a combination of radiomics features and tumor location features, as evidenced by the following metrics: precision (0.955), recall (0.913), specificity (0.960), accuracy (0.938), F-1 score (0.933), and area under curve (AUC) (0.950).</p><p><strong>Conclusion: </strong>Our findings demonstrated the efficacy of machine learning models based on radiomics features and voxel-based anatomical locations in predicting the risk of epilepsy in supratentorial LGG. This model provides a highly accurate tool for distinguishing epilepsy-associated LGG in children, supporting precise treatment planning.</p><p><strong>Trial registration: </strong>Not applicable.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"63"},"PeriodicalIF":3.5,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12090388/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144101419","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":"Identification of HER2-over-expression, HER2-low-expression, and HER2-zero-expression statuses in breast cancer based on ¹⁸F-FDG PET/CT radiomics.","authors":"Xuefeng Hou, Kun Chen, Huiwen Luo, Wengui Xu, Xiaofeng Li","doi":"10.1186/s40644-025-00880-2","DOIUrl":"10.1186/s40644-025-00880-2","url":null,"abstract":"<p><strong>Purpose: </strong>According to the updated classification system, human epidermal growth factor receptor 2 (HER2) expression statuses are divided into the following three groups: HER2-over-expression, HER2-low-expression, and HER2-zero-expression. HER2-negative expression was reclassified into HER2-low-expression and HER2-zero-expression. This study aimed to identify three different HER2 expression statuses for breast cancer (BC) patients using PET/CT radiomics and clinicopathological characteristics.</p><p><strong>Methods and materials: </strong>A total of 315 BC patients who met the inclusion and exclusion criteria from two institutions were retrospectively included. The patients in institution 1 were divided into the training set and the independent validation set according to the ratio of 7:3, and institution 2 was used as the external validation set. According to the results of pathological examination, all BC patients were divided into HER2-over-expression, HER2-low-expression, and HER2-zero-expression. First, PET/CT radiomic features and clinicopathological features based on each patient were extracted and collected. Second, multiple methods were used to perform feature screening and feature selection. Then, four machine learning classifiers, including logistic regression (LR), k-nearest neighbor (KNN), support vector machine (SVM), and random forest (RF), were constructed to identify HER2-over-expression vs. others, HER2-low-expression vs. others, and HER2-zero-expression vs. others. The receiver operator characteristic (ROC) curve was plotted to measure the model's predictive power.</p><p><strong>Results: </strong>According to the feature screening process, 8, 10, and 2 radiomics features and 2 clinicopathological features were finally selected to construct three prediction models (HER2-over-expression vs. others, HER2-low-expression vs. others, and HER2-zero-expression vs. others). For HER2-over-expression vs. others, the RF model outperformed other models with an AUC value of 0.843 (95%CI: 0.774-0.897), 0.785 (95%CI: 0.665-0.877), and 0.788 (95%CI: 0.708-0.868) in the training set, independent validation set, and external validation set. Concerning HER2-low-expression vs. others, the outperformance of the LR model over other models was identified with an AUC value of 0.783 (95%CI: 0.708-0.846), 0.756 (95%CI: 0.634-0.854), and 0.779 (95%CI: 0.698-0.860) in the training set, independent validation set, and external validation set. Whereas, the KNN model was confirmed as the optimal model to distinguish HER2-zero-expression from others, with an AUC value of 0.929 (95%CI: 0.890-0.958), 0.847 (95%CI: 0.764-0.910), and 0.835 (95%CI: 0.762-0.908) in the training set, independent validation set, and external validation set.</p><p><strong>Conclusion: </strong>Combined PET/CT radiomic models integrating with clinicopathological characteristics are non-invasively predictive of different HER2 statuses of BC patients.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"62"},"PeriodicalIF":3.5,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12070556/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143983449","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":"Hierarchical diagnosis of breast phyllodes tumors enabled by deep learning of ultrasound images: a retrospective multi-center study.","authors":"Yuqi Yan, Yuanzhen Liu, Yao Wang, Tian Jiang, Jiayu Xie, Yahan Zhou, Xin Liu, Meiying Yan, Qiuqing Zheng, Haifei Xu, Jinxiao Chen, Lin Sui, Chen Chen, RongRong Ru, Kai Wang, Anli Zhao, Shiyan Li, Ying Zhu, Yang Zhang, Vicky Yang Wang, Dong Xu","doi":"10.1186/s40644-025-00879-9","DOIUrl":"10.1186/s40644-025-00879-9","url":null,"abstract":"<p><strong>Objective: </strong>Phyllodes tumors (PTs) are rare breast tumors with high recurrence rates, current methods relying on post-resection pathology often delay detection and require further surgery. We propose a deep-learning-based Phyllodes Tumors Hierarchical Diagnosis Model (PTs-HDM) for preoperative identification and grading.</p><p><strong>Methods: </strong>Ultrasound images from five hospitals were retrospectively collected, with all patients having undergone surgical pathological confirmation of either PTs or fibroadenomas (FAs). PTs-HDM follows a two-stage classification: first distinguishing PTs from FAs, then grading PTs into benign or borderline/malignant. Model performance metrics including AUC and accuracy were quantitatively evaluated. A comparative analysis was conducted between the algorithm's diagnostic capabilities and those of radiologists with varying clinical experience within an external validation cohort. Through the provision of PTs-HDM's automated classification outputs and associated thermal activation mapping guidance, we systematically assessed the enhancement in radiologists' diagnostic concordance and classification accuracy.</p><p><strong>Results: </strong>A total of 712 patients were included. On the external test set, PTs-HDM achieved an AUC of 0.883, accuracy of 87.3% for PT vs. FA classification. Subgroup analysis showed high accuracy for tumors < 2 cm (90.9%). In hierarchical classification, the model obtained an AUC of 0.856 and accuracy of 80.9%. Radiologists' performance improved with PTs-HDM assistance, with binary classification accuracy increasing from 82.7%, 67.7%, and 64.2-87.6%, 76.6%, and 82.1% for senior, attending, and resident radiologists, respectively. Their hierarchical classification AUCs improved from 0.566 to 0.827 to 0.725-0.837. PTs-HDM also enhanced inter-radiologist consistency, increasing Kappa values from - 0.05 to 0.41 to 0.12 to 0.65, and the intraclass correlation coefficient from 0.19 to 0.45.</p><p><strong>Conclusion: </strong>PTs-HDM shows strong diagnostic performance, especially for small lesions, and improves radiologists' accuracy across all experience levels, bridging diagnostic gaps and providing reliable support for PTs' hierarchical diagnosis.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"61"},"PeriodicalIF":3.5,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12063467/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143977356","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":"The impact of a simple positioning aid device on the diagnostic performance of thyroid cancer in CT scans: a randomized controlled trial.","authors":"Wei-Hua Lin, Hui-Juan Huang, Wen-Cong Yang, Qing-Wen Huang, Rui-Gang Huang, Fu-Rong Luo, Dong-Yi Chen, Zheng-Han Yang, Hai-Tao Li, Hui-Huang Zeng, Hui-Jun Xiao","doi":"10.1186/s40644-025-00878-w","DOIUrl":"10.1186/s40644-025-00878-w","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate the effectiveness of a simple positioning aid device in neck CT scans for the diagnosis of thyroid cancer, with a focus on its influence on image quality and diagnostic accuracy.</p><p><strong>Methods: </strong>A randomized controlled trial was conducted involving 180 patients with suspected thyroid cancer. Participants were randomly assigned to two groups: the device-assisted positioning group (Group A) and the traditional positioning group (Group B). A total of 147 patients who underwent enhanced neck CT scans and subsequent surgical pathological biopsies were included in the final analysis. Image quality and thyroid disease diagnoses were independently assessed by two experienced radiologists, with a unified consensus for the final conclusions. Objective imaging parameters and subjective ratings were used to evaluate image quality. Pathological findings served as the gold standard to compare the diagnostic accuracy of the two groups for thyroid malignancy, capsular invasion, and lymph node metastasis. Additionally, radiation doses in both groups were compared.</p><p><strong>Results: </strong>A total of 147 patients were included in the analysis, with 72 patients in Group A and 75 in Group B. The baseline characteristics of the two groups were similar (P > 0.05). Group A demonstrated significantly superior image quality compared to Group B, with shorter length of artifacts (LA), lower proportion of affected thyroid (PA), and lower artifact index (AI). Subjective assessments also favored Group A, showing better ratings for regional artifacts and overall image quality. In terms of diagnostic accuracy, Group A outperformed Group B in detecting thyroid cancer (AUC: 0.852 vs. 0.676, P = 0.021). For the right thyroid lobe, Group A had significantly better diagnostic performance (AUC: 0.897 vs. 0.746, P = 0.016). Group A also showed superior performance in diagnosing capsular invasion (AUC: 0.861 vs. 0.721, P = 0.037), with similar results observed for both the left and right thyroid lobes. There was no significant difference between the groups in diagnosing lymph node metastasis. Furthermore, thyroid region radiation doses (CTDIvol and SSDE) were significantly lower in Group A compared to Group B.</p><p><strong>Conclusion: </strong>The use of a positioning aid device significantly improves CT image quality, enhancing diagnostic accuracy for malignant thyroid lesions and capsular invasion, while also reducing radiation exposure.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"60"},"PeriodicalIF":3.5,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12063306/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143977372","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":"Preoperative prediction of WHO/ISUP grade of ccRCC using intratumoral and peritumoral habitat imaging: multicenter study.","authors":"Zhihui Chen, Hongqing Zhu, Hongmin Shu, Jianbo Zhang, Kangchen Gu, Wenjun Yao","doi":"10.1186/s40644-025-00875-z","DOIUrl":"https://doi.org/10.1186/s40644-025-00875-z","url":null,"abstract":"<p><strong>Objectives: </strong>The World Health Organization/International Society of Urological Pathology (WHO/ISUP) grading of clear cell renal cell carcinoma (ccRCC) is crucial for prognosis and treatment planning. This study aims to predict the grade using intratumoral and peritumoral subregional CT radiomics analysis for better clinical interventions.</p><p><strong>Methods: </strong>Data from two hospitals included 513 ccRCC patients, who were divided into training (70%), validation (30%), and an external validation set (testing) of 67 patients. Using ITK-SNAP, two radiologists annotated tumor regions of interest (ROI) and extended surrounding areas by 1 mm, 3 mm, and 5 mm. The K-means clustering algorithm divided the tumor region into three sub-regions, and the Least Absolute Shrinkage and Selection Operator (LASSO) regression identified the most predictive features. Various machine learning models were established, including radiomics models, peritumoral radiomics models, models based on intratumoral heterogeneity (ITH) score, clinical models, and comprehensive models. Predictive ability was evaluated using receiver operating characteristic (ROC) curves, area under the curve (AUC) values, DeLong tests, calibration curves, and decision curves.</p><p><strong>Results: </strong>The combined model showed strong predictive power with an AUC of 0.852 (95% CI: 0.725-0.979) on the test data, outperforming individual models. The ITH score model was highly precise, with AUCs of 0.891 (95% CI: 0.854-0.927) in training, 0.877 (95% CI: 0.814-0.941) in validation, and 0.847 (95% CI: 0.725-0.969) in testing, proving its superior predictive ability across datasets.</p><p><strong>Conclusion: </strong>A comprehensive model combining Habitat, Peri1mm, and salient clinical features was significantly more accurate in predicting ccRCC pathologic grading.</p><p><strong>Key points: </strong>Question: Characterize tumor heterogeneity to non-invasively predict WHO/ISUP pathological grading preoperatively.</p><p><strong>Findings: </strong>An integrated model combining subregion characterization, peritumoral characteristics, and clinical features can predict ccRCC grade preoperatively.</p><p><strong>Clinical relevance: </strong>Subregion tumor characterization outperforms the single-entity approach. The integrated model, compared with the radiomics model, boosts grading and prognostic accuracy for more targeted clinical actions.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"59"},"PeriodicalIF":3.5,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12049773/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143981744","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":"Enhancing ¹⁸F-FDG PET image quality and lesion diagnostic performance across different body mass index using the deep progressive learning reconstruction algorithm.","authors":"Zhihao Chen, Hongxing Yang, Ming Qi, Wen Chen, Fei Liu, Shaoli Song, Jianping Zhang","doi":"10.1186/s40644-025-00877-x","DOIUrl":"https://doi.org/10.1186/s40644-025-00877-x","url":null,"abstract":"<p><strong>Background: </strong>As body mass index (BMI) increases, the quality of 2-deoxy-2-[fluorine-18]fluoro-D-glucose (¹⁸F-FDG) positron emission tomography (PET) images reconstructed with ordered subset expectation maximization (OSEM) declines, negatively impacting lesion diagnostics. It is crucial to identify methods that ensure consistent diagnostic accuracy and maintain image quality. Deep progressive learning (DPL) algorithm, an Artificial Intelligence(AI)-based PET reconstruction technique, offers a promising solution.</p><p><strong>Methods: </strong>150 patients underwent ¹⁸F-FDG PET/CT scans and were categorized by BMI into underweight, normal, and overweight groups. PET images were reconstructed using both OSEM and DPL and their image quality was assessed both visually and quantitatively. Visual assessment employed a 5-point Likert scale to evaluate overall score, image sharpness, image noise, and diagnostic confidence. Quantitative assessment parameters included the background liver image-uniformity-index ([Formula: see text]) and signal-to-noise ratio ([Formula: see text]). Additionally, 466 identifiable lesions were categorized by size: sub-centimeter and larger. We compared maximum standard uptake value ([Formula: see text]), signal-to-background ratio ([Formula: see text]), [Formula: see text], contrast-to-background ratio ([Formula: see text]), and contrast-to-noise ratio ([Formula: see text]) of these lesions to evaluate the diagnostic performance of the DPL and OSEM algorithms across different lesion sizes and BMI categories.</p><p><strong>Results: </strong>DPL produced superior PET image quality compared to OSEM across all BMI groups. The visual quality of DPL showed a slight decline with increasing BMI, while OSEM exhibited a more significant decline. DPL maintained a stable [Formula: see text] across BMI increases, whereas OSEM exhibited increased noise. In the DPL group, quantitative image quality for overweight patients matched that of normal patients with minimal variance from underweight patients. In contrast, OSEM demonstrated significant declines in quantitative image quality with rising BMI. DPL yielded significantly higher contrast ([Formula: see text], [Formula: see text],[Formula: see text]) and [Formula: see text] than OSEM for all lesions across all BMI categories.</p><p><strong>Conclusion: </strong>DPL consistently provided superior image quality and lesion diagnostic performance compared to OSEM across all BMI categories in ¹⁸F-FDG PET/CT scans. Therefore, we recommend using the DPL algorithm for ¹⁸F-FDG PET/CT image reconstruction in all BMI patients.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"58"},"PeriodicalIF":3.5,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12044768/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143981735","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}