Cancer Imaging最新文献

{"title":"Differentiating high-grade patterns and predominant subtypes for IASLC grading in invasive pulmonary adenocarcinoma using radiomics and clinical-semantic features.","authors":"Sunyi Zheng, Jiaxin Liu, Jiping Xie, Wenjia Zhang, Keyi Bian, Jing Liang, Jingxiong Li, Jing Wang, Zhaoxiang Ye, Dongsheng Yue, Xiaonan Cui","doi":"10.1186/s40644-025-00864-2","DOIUrl":"10.1186/s40644-025-00864-2","url":null,"abstract":"<p><strong>Objectives: </strong>The International Association for the Study of Lung Cancer (IASLC) grading system for invasive non-mucinous adenocarcinoma (ADC) incorporates high-grade patterns (HGP) and predominant subtypes (PS). Following the system, this study aimed to explore the feasibility of predicting HGP and PS for IASLC grading.</p><p><strong>Materials and methods: </strong>A total of 529 ADCs from patients who underwent radical surgical resection were randomly divided into training and validation datasets in a 7:3 ratio. A two-step model consisting of two submodels was developed for IASLC grading. One submodel assessed whether the HGP exceeded 20% for ADCs, whereas the other distinguished between lepidic and acinar/papillary PS. The predictions from both submodels determined the final IASLC grades. Two variants of this model using either radiomic or clinical-semantic features were created. Additionally, one-step models that directly assessed IASLC grades using clinical-semantic or radiomic features were developed for comparison. The area under the curve (AUC) was used for model evaluation.</p><p><strong>Results: </strong>The two-step radiomic model achieved the highest AUC values of 0.95, 0.85, 0.96 for grades 1, 2, 3 among models. The two-step models outperformed the one-step models in predicting grades 2 and 3, with AUCs of 0.89 and 0.96 vs. 0.53 and 0.81 for radiomics, and 0.68 and 0.77 vs. 0.44 and 0.63 for clinical-semantics (p < 0.001). Radiomics models showed better AUCs than clinical-semantic models for grade 3 regardless of model steps.</p><p><strong>Conclusions: </strong>Predicting HGP and PS using radiomics can achieve accurate IASLC grading in ADCs. Such a two-step radiomics model may provide precise preoperative diagnosis, thereby supporting treatment planning.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"42"},"PeriodicalIF":3.5,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11951669/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143742530","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":"Assessment of intrahepatic cholangiocarcinoma with LI-RADS in the high-risk population: MRI diagnosis and postoperative survival.","authors":"Ruofan Sheng, Beixuan Zheng, Yunfei Zhang, Chun Yang, Dong Wu, Jianjun Zhou, Mengsu Zeng","doi":"10.1186/s40644-025-00860-6","DOIUrl":"10.1186/s40644-025-00860-6","url":null,"abstract":"<p><strong>Background: </strong>The precise impact of LI-RADS-defined risk factors on the diagnosis and prognosis of intrahepatic cholangiocarcinoma (iCCA) remains unclear.</p><p><strong>Objective: </strong>To assess the value of LI-RADS categories and features for iCCA diagnosis, focusing on the diagnostic and prognostic implications of LI-RADS-defined risk factors.</p><p><strong>Methods: </strong>Totally 214 high risk patients, including 107 surgically-confirmed solitary iCCAs and 107 hepatocellular carcinomas (HCC) from two centers were retrospectively enrolled. Clinical and MRI features based on LI-RADS v2018 were compared, and the performance of targetoid features for discriminating iCCA was evaluated. Recurrence-free survival (RFS) was compared across different pathologic diagnoses and LI-RADS categories. Multivariate Cox analysis was performed to identify the independent risk factors for RFS.</p><p><strong>Results: </strong>In the LI-RADS defined high-risk patients, iCCAs differed from HCCs in MRI manifestation. The LR-M category enabled the accurate classification of most iCCAs (89/107, 83.2%), achieving high sensitivity (83.2%), specificity (85.1%), and accuracy (84.1%). The optimal diagnostic performance for iCCA was achieved when at least one targetoid appearance was required for LR-M categorization (AUC = 0.828). Although 26.2% iCCAs presented at least one major feature and 15.0% iCCAs were miscategorized as probably or definitely HCC, only one iCCA case was categorized as LR-5. RFS varied according to both pathologic diagnosis (P = 0.030) and LI-RADS category (P = 0.028), with LI-RADS category demonstrating an independent association with RFS (HR = 1.736, P = 0.033).</p><p><strong>Conclusions: </strong>In high-risk patients, iCCAs frequently exhibit HCC major features, leading to miscategorization as probable HCC. However, the LR-5 category remains highly specific for ruling out iCCA. Furthermore, in high-risk patients with solitary resected iCCA or HCC, LI-RADS category enables the prediction of postsurgical prognosis independently from pathological diagnosis.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"40"},"PeriodicalIF":3.5,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11938583/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143718184","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 value of ¹⁸F-FDG PET/CT and ¹⁸F-DOPA PET/CT in determining the initial surgical strategy of patients with medullary thyroid cancer : Preoperative PET/CT imaging for medullary thyroid cancer.","authors":"Eline C Jager, Adrienne H Brouwers, Madelon J H Metman, Dilay Aykan, Lisa H de Vries, Lutske Lodewijk, Menno R Vriens, Schelto Kruijff, Thera P Links","doi":"10.1186/s40644-025-00862-4","DOIUrl":"10.1186/s40644-025-00862-4","url":null,"abstract":"<p><strong>Background: </strong>While total thyroidectomy with central neck dissection (CND) is standard for medullary thyroid cancer (MTC), performing a lateral neck dissection (LND) depends on locoregional metastatic spread and is usually decided per individual. This study evaluated the utility of preoperative PET/CT in staging patients at diagnosis and guiding the initial surgical plan, while also exploring the value of neck ultrasound, MRI, and CT.</p><p><strong>Methods: </strong>All MTC patients from two tertiary hospitals (2000 - 2020) were identified from two retrospective databases. All reports of neck ultrasounds, MRIs, CTs and PET/CTs < 8 months prior to primary surgery or < 4 months after MTC diagnosis were reviewed. The sensitivity and specificity of each imaging modality for locating locoregional lymph node metastases (LNM) was determined.</p><p><strong>Results: </strong>A total of 175 MTC patients were included (91 females and 57 hereditary MTCs). Median age at presentation was 52 years (IQR 38 - 62). Initial treatment included a total thyroidectomy, CND and LND in 155 (89%), 140 (80%) and 59 (33%) patients. Preoperative imaging of the neck included ultrasound (91, 52%), MRI (33, 19%) and CT (31, 18%). PET/CT imaging was performed in 56 (32%) patients (35 ¹⁸F-FDG PET/CTs and 33 ¹⁸F-DOPA PET/CTs). Sensitivity for LNM in the central compartment was 72%, 39%, 6%, 42% and 93% for ¹⁸F-FDG PET/CT, ¹⁸F-DOPA PET/CT, ultrasound, MRI and CT, respectively. Respective specificity rates were 80%, 100%, 100%, 71% and 100%. Sensitivity rates for lateral neck LNM were 89%, 81%, 77%, 76% and 75%, for ¹⁸F-FDG PET/CT, ¹⁸F-DOPA PET/CT, ultrasound, MRI and CT, while specificity rates were 100%, 100%, 75%, 78% and 50%, respectively. Twenty-three patients had distant metastases on imaging. In total, 14 ¹⁸F-FDG PET/CTs and 9 ¹⁸F-DOPA PET/CTs were made in these 23 patients (both in six patients). All but one PET/CT showed distant metastases.</p><p><strong>Conclusions: </strong>PET/CT is a powerful tool to detect locoregional LNM and can particularly help identify cases where LNDs are required, avoiding reoperation later on. For accurate staging of the central neck, PET may be combined with diagnostic CT. Finally, PET/CT's ability to detect distant metastases may support de-escalation of a surgical intervention when cure is unlikely.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"41"},"PeriodicalIF":3.5,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11938770/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143717802","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":"Establishment of a deep-learning-assisted recurrent nasopharyngeal carcinoma detecting simultaneous tactic (DARNDEST) with high cost-effectiveness based on magnetic resonance images: a multicenter study in an endemic area.","authors":"Yishu Deng, Yingying Huang, Haijun Wu, Dongxia He, Wenze Qiu, Bingzhong Jing, Xing Lv, Weixiong Xia, Bin Li, Ying Sun, Chaofeng Li, Chuanmiao Xie, Liangru Ke","doi":"10.1186/s40644-025-00853-5","DOIUrl":"10.1186/s40644-025-00853-5","url":null,"abstract":"<p><strong>Background: </strong>To investigate the feasibility of detecting local recurrent nasopharyngeal carcinoma (rNPC) using unenhanced magnetic resonance images (MRI) and optimize a layered management strategy for follow-up with a deep learning model.</p><p><strong>Methods: </strong>Deep learning models based on 3D DenseNet or ResNet frames using unique sequence (T1WI, T2WI, or T1WIC) or a combination of T1WI and T2WI sequences (T1_T2) were developed to detect local rNPC. A deep-learning-assisted recurrent NPC detecting simultaneous tactic (DARNDEST) utilized DenseNet was optimized by superimposing the T1WIC model over the T1_T2 model in a specific population. Diagnostic efficacy (accuracy, sensitivity, specificity) and examination cost of a single MR scan were compared among the conventional method, T1_T2 model, and DARNDEST using McNemar's Z test.</p><p><strong>Results: </strong>No significant differences in overall accuracy, sensitivity, and specificity were found between the T1WIC model and T1WI, T2WI, or T1_T2 models in both test sets (all P > 0.0167). The DARNDEST had higher accuracy and sensitivity but lower specificity than the T1_T2 model in both the internal (accuracy, 85.91% vs. 84.99%; sensitivity, 90.36% vs. 84.26%; specificity, 82.20% vs. 85.59%) and external (accuracy, 86.14% vs. 84.16%; sensitivity, 90.32% vs. 84.95%; specificity, 82.57% vs. 83.49%) test sets. The cost of a single MR examination using DARNDEST was $330,724 (internal) and $328,971 (external) with a hypothetical cohort of 1,000 patients, relative to $313,250 of the T1_T2 model and $340,865 of the conventional method.</p><p><strong>Conclusions: </strong>Detecting local rNPC using unenhanced MRI with deep learning is feasible and DARNDEST-driven follow-up management is efficient and economic.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"39"},"PeriodicalIF":3.5,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11931764/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143699496","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":"Acinar cell carcinoma of the pancreas: can CT and MR features predict survival?","authors":"Monica Cheng, Nikita Consul, Ryan Chung, Carlos Fernandez- Del Castillo, Yasmin Hernandez-Barco, Avinash Kambadakone","doi":"10.1186/s40644-025-00859-z","DOIUrl":"10.1186/s40644-025-00859-z","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate the CT and MRI features of pancreatic acinar cell carcinoma (pACC) and their association with patient outcome and survival.</p><p><strong>Methods: </strong>This retrospective single-center study included 49 patients with pathology-proven pancreatic acinar cell carcinoma who underwent diagnostic imaging between August 1998 - September 2019. Two radiologists reviewed CT and MRI features independently. Survival was estimated using the Kaplan-Meier method, and Cox proportional-hazards regression model was used to identify factors associated with survival.</p><p><strong>Results: </strong>pACC tended to present as a solid (31/49, 63.3%) pancreatic head mass (26/49, 53.1%) with ill-defined margins (32/49, 65.3%) and median maximal diameter of 4.1 cm (IQR, 2.9-6.2). Majority of lesions were hypo- or isodense (38/49, 77.6%) compared to normal pancreatic parenchyma, with heterogenous (39/49, 79.6%) enhancement pattern. Biliary ductal dilatation was uncommon, with pancreatic ductal dilatation in 22.4% (11/49) and common bile duct dilatation in 14.3% (7/49). Intralesional calcifications were seen in 6.1% (3/49). Metastasis was present in 71.4% (35/49) of patients at the time of diagnosis. On MRI, 88.9% (16/18) demonstrated diffusion restriction and 59.1% (13/22) with heterogenous enhancement. On multivariate analysis, the imaging presence of T1 hyperintensity (p = 0.02), hypoattenuating necrotic components (p = 0.02), and splenic vein invasion (p = 0.04) were associated with worse survival.</p><p><strong>Conclusion: </strong>Pancreatic acinar cell carcinoma is a rare pancreatic neoplasm that often presents as a large ill-defined heterogeneously enhancing mass without biliary ductal dilation. T1 hyperintensity, presence of hypoattenuating necrotic components, and splenic vein invasion were independent predictors of survival.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"38"},"PeriodicalIF":3.5,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11929164/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143676920","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":"LI-RADS-based hepatocellular carcinoma risk mapping using contrast-enhanced MRI and self-configuring deep learning.","authors":"Róbert Stollmayer, Selda Güven, Christian Marcel Heidt, Kai Schlamp, Pál Novák Kaposi, Oyunbileg von Stackelberg, Hans-Ulrich Kauczor, Miriam Klauss, Philipp Mayer","doi":"10.1186/s40644-025-00844-6","DOIUrl":"10.1186/s40644-025-00844-6","url":null,"abstract":"<p><strong>Background: </strong>Hepatocellular carcinoma (HCC) is often diagnosed using gadoxetate disodium-enhanced magnetic resonance imaging (EOB-MRI). Standardized reporting according to the Liver Imaging Reporting and Data System (LI-RADS) can improve Gd-MRI interpretation but is rather complex and time-consuming. These limitations could potentially be alleviated using recent deep learning-based segmentation and classification methods such as nnU-Net. The study aims to create and evaluate an automatic segmentation model for HCC risk assessment, according to LI-RADS v2018 using nnU-Net.</p><p><strong>Methods: </strong>For this single-center retrospective study, 602 patients at risk for HCC were included, who had dynamic EOB-MRI examinations between 05/2005 and 09/2022, containing ≥ LR-3 lesion(s). Manual lesion segmentations in semantic segmentation masks as LR-3, LR-4, LR-5 or LR-M served as ground truth. A set of U-Net models with 14 input channels was trained using the nnU-Net framework for automatic segmentation. Lesion detection, LI-RADS classification, and instance segmentation metrics were calculated by post-processing the semantic segmentation outputs of the final model ensemble. For the external evaluation, a modified version of the LiverHccSeg dataset was used.</p><p><strong>Results: </strong>The final training/internal test/external test cohorts included 383/219/16 patients. In the three cohorts, LI-RADS lesions (≥ LR-3 and LR-M) ≥ 10 mm were detected with sensitivities of 0.41-0.85/0.40-0.90/0.83 (LR-5: 0.85/0.90/0.83) and positive predictive values of 0.70-0.94/0.67-0.88/0.90 (LR-5: 0.94/0.88/0.90). F1 scores for LI-RADS classification of detected lesions ranged between 0.48-0.69/0.47-0.74/0.84 (LR-5: 0.69/0.74/0.84). Median per lesion Sørensen-Dice coefficients were between 0.61-0.74/0.52-0.77/0.84 (LR-5: 0.74/0.77/0.84).</p><p><strong>Conclusion: </strong>Deep learning-based HCC risk assessment according to LI-RADS can be implemented as automatically generated tumor risk maps using out-of-the-box image segmentation tools with high detection performance for LR-5 lesions. Before translation into clinical practice, further improvements in automatic LI-RADS classification, for example through large multi-center studies, would be desirable.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"36"},"PeriodicalIF":3.5,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11912691/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143646901","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":"Deep learning-based fully automated detection and segmentation of pelvic lymph nodes on diffusion-weighted images for prostate cancer: a multicenter study.","authors":"Zhaonan Sun, Pengsheng Wu, Tongtong Zhao, Ge Gao, Huihui Wang, Xiaodong Zhang, Xiaoying Wang","doi":"10.1186/s40644-025-00840-w","DOIUrl":"10.1186/s40644-025-00840-w","url":null,"abstract":"<p><strong>Background: </strong>Accurate identification and evaluation of lymph nodes (LNs) in prostate cancer (PCa) patients is crucial for effective staging but can be time-consuming. We utilized a 3D V-Net model to improve the efficiency and accuracy of LN detection and segmentation.</p><p><strong>Methods: </strong>Utilizing pelvic diffusion-weighted imaging (DWI) scans, the 3D V-Net framework underwent training on a dataset comprising data from a hospital with 1,151 patients, encompassing 32,507 annotated LNs, following data augmentation procedures. Subsequently, external validation was conducted on data from 401 patients across three additional hospitals, encompassing 7,707 LNs. The segmentation performance was evaluated using the Dice similarity coefficient (DSC). The comparison between automated and manual segmentation regarding the short diameter and volume of LNs was conducted using Bland-Altman plots and correlation analysis. The performance for suspicious metastatic LN detection (short diameter > 8 mm) was evaluated using sensitivity, positive predictive value (PPV), and per-patient false-positive rate (FP/vol) at the LN level and sensitivity, specificity, and PPV at the patient level.</p><p><strong>Results: </strong>In the external validation test dataset, the model achieved a DSC of 0.77-0.82 for all, suspicious, and largest LNs. The model achieved a sensitivity, PPV, and FP/vol of 60.1% (95% confidence interval (CI), 57.6-62.6%), 79.2% (95% CI, 76.6-81.5%), and 0.56 at the LN level, respectively. At the patient level, the model achieved a sensitivity, specificity, and PPV of 81.1% (95% CI, 76.5-85.0%), 75.6% (95% CI, 65.1-83.8%), and 93.2% (95% CI, 89.7-95.6%), respectively. The model achieved a strong correlation and good consistency between the short diameter and volume of the automatically segmented and manually annotated LNs.</p><p><strong>Conclusion: </strong>This 3D V-Net model can segment LNs effectively based on pelvic DWI images for PCa and holds great potential for facilitating N-staging in clinical practice.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"37"},"PeriodicalIF":3.5,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11912796/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143646900","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":"Development and evaluation of a deep learning framework for pelvic and sacral tumor segmentation from multi-sequence MRI: a retrospective study.","authors":"Ping Yin, Weidao Chen, Qianrui Fan, Ruize Yu, Xia Liu, Tao Liu, Dawei Wang, Nan Hong","doi":"10.1186/s40644-025-00850-8","DOIUrl":"10.1186/s40644-025-00850-8","url":null,"abstract":"<p><strong>Background: </strong>Accurate segmentation of pelvic and sacral tumors (PSTs) in multi-sequence magnetic resonance imaging (MRI) is essential for effective treatment and surgical planning.</p><p><strong>Purpose: </strong>To develop a deep learning (DL) framework for efficient segmentation of PSTs from multi-sequence MRI.</p><p><strong>Materials and methods: </strong>This study included a total of 616 patients with pathologically confirmed PSTs between April 2011 to May 2022. We proposed a practical DL framework that integrates a 2.5D U-net and MobileNetV2 for automatic PST segmentation with a fast annotation strategy across multiple MRI sequences, including T1-weighted (T1-w), T2-weighted (T2-w), diffusion-weighted imaging (DWI), and contrast-enhanced T1-weighted (CET1-w). Two distinct models, the All-sequence segmentation model and the T2-fusion segmentation model, were developed. During the implementation of our DL models, all regions of interest (ROIs) in the training set were coarse labeled, and ROIs in the test set were fine labeled. Dice score and intersection over union (IoU) were used to evaluate model performance.</p><p><strong>Results: </strong>The 2.5D MobileNetV2 architecture demonstrated improved segmentation performance compared to 2D and 3D U-Net models, with a Dice score of 0.741 and an IoU of 0.615. The All-sequence model, which was trained using a fusion of four MRI sequences (T1-w, CET1-w, T2-w, and DWI), exhibited superior performance with Dice scores of 0.659 for T1-w, 0.763 for CET1-w, 0.819 for T2-w, and 0.723 for DWI as inputs. In contrast, the T2-fusion segmentation model, which used T2-w and CET1-w sequences as inputs, achieved a Dice score of 0.833 and an IoU value of 0.719.</p><p><strong>Conclusions: </strong>In this study, we developed a practical DL framework for PST segmentation via multi-sequence MRI, which reduces the dependence on data annotation. These models offer solutions for various clinical scenarios and have significant potential for wide-ranging applications.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"34"},"PeriodicalIF":3.5,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11907785/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143623810","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":"Intratumoral and peritumoral CT radiomics in predicting anaplastic lymphoma kinase mutations and survival in patients with lung adenocarcinoma: a multicenter study.","authors":"Weiyue Chen, Guihan Lin, Ye Feng, Yongjun Chen, Yanjun Li, Jianbin Li, Weibo Mao, Yang Jing, Chunli Kong, Yumin Hu, Minjiang Chen, Shuiwei Xia, Chenying Lu, Jianfei Tu, Jiansong Ji","doi":"10.1186/s40644-025-00856-2","DOIUrl":"10.1186/s40644-025-00856-2","url":null,"abstract":"<p><strong>Background: </strong>To explore the value of intratumoral and peritumoral radiomics in preoperative prediction of anaplastic lymphoma kinase (ALK) mutation status and survival in patients with lung adenocarcinoma.</p><p><strong>Methods: </strong>We retrospectively collected data from 505 eligible patients with lung adenocarcinoma from four hospitals (training and external validation sets 1-3). The CT-based radiomics features were extracted separately from the gross tumor volume (GTV) and GTV incorporating peritumoral 3-, 6-, 9-, 12-, and 15-mm regions (GPTV₃, GPTV₆, GPTV₉, GPTV₁₂, and GPTV₁₅), and screened the most relevant features to construct radiomics models to predict ALK (+). The combined model incorporated radiomics scores (Rad-scores) of the best radiomics model and clinical predictors was constructed. Performance was evaluated using receiver operating characteristic (ROC) analysis. Progression-free survival (PFS) outcomes were examined using the Cox proportional hazards model.</p><p><strong>Results: </strong>In the four sets, 21.19% (107/505) patients were ALK (+). The GPTV₃ radiomics model using a support vector machine algorithm achieved the best predictive performance, with the highest average AUC of 0.811 in the validation sets. Clinical TNM stage and pleural indentation were independent predictors. The combined model incorporating the GPTV₃-Rad-score and clinical predictors achieved higher performance than the clinical model alone in predicting ALK (+) in three validation sets [AUC: 0.855 (95% CI: 0.766-0.919) vs. 0.648 (95% CI: 0.543-0.745), P = 0.001; 0.882 (95% CI: 0.801-0.962) vs. 0.634 (95% CI: 0.548-0.714), P < 0.001; 0.810 (95% CI: 0.727-0.877) vs. 0.663 (95% CI: 0.570-0.748), P = 0.006]. The prediction score of the combined model could stratify PFS outcomes in patients receiving ALK-TKI therapy (HR: 0.37; 95% CI: 0.15-0.89; P = 0.026) and immunotherapy (HR: 2.49; 95% CI: 1.22-5.08; P = 0.012).</p><p><strong>Conclusion: </strong>The presented combined model based on GPTV₃ effectively mined tumor features to predict ALK mutation status and stratify PFS outcomes in patients with lung adenocarcinoma.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"35"},"PeriodicalIF":3.5,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11907895/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143622991","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":"Change in diffusion weighted imaging after induction chemotherapy outperforms RECIST guideline for long-term outcome prediction in advanced nasopharyngeal carcinoma.","authors":"Qi Yong H Ai, Ho Sang Leung, Frankie K F Mo, Kaijing Mao, Lun M Wong, Yannis Yan Liang, Edwin P Hui, Brigette B Y Ma, Ann D King","doi":"10.1186/s40644-025-00854-4","DOIUrl":"10.1186/s40644-025-00854-4","url":null,"abstract":"<p><strong>Purpose: </strong>To investigate change in diffusion weighted imaging (DWI) between pre-treatment (pre-) and after induction chemotherapy (post-IC) for long-term outcome prediction in advanced nasopharyngeal carcinoma (adNPC).</p><p><strong>Materials and methods: </strong>Mean apparent diffusion coefficients (ADCs) of two DWIs (ADC_pre and ADC_post-IC) and changes in ADC between two scans (ΔADC%) were calculated from 64 eligible patients with adNPC and correlated with disease free survival (DFS), locoregional recurrence free survival (LRRFS), distant metastases free survival (DMFS), and overall survival (OS) using Cox regression analysis. C-indexes of the independent parameters for outcome were compared with that of RECIST response groups. Survival rates between two patient groups were evaluated and compared.</p><p><strong>Results: </strong>Univariable analysis showed that high ΔADC% predicted good DFS, LRRFS, and DMFS p < 0.05), but did not predict OS (p = 0.40). Neither ADC_pre nor ADC_post-IC (p = 0.07 to 0.97) predicted outcome. Multivariate analysis showed that ΔADC% independently predicted DFS, LRRFS, and DMFS (p < 0.01 to 0.03). Compared with the RECIST groups, the ΔADC% groups (threshold of 34.2%) showed a higher c-index for 3-year (0.47 vs. 0.71, p < 0.01) and 5-year DFS (0.51 vs. 0.72, p < 0.01). Compared with patients with ΔADC%<34.2%, patients with ΔADC%≥34.2% had higher 3-year DFS, LRRFS and DMFS of 100%, 100% and 100%, respectively (p < 0.05).</p><p><strong>Conclusion: </strong>Results suggest that ΔADC% was an independent predictor for long-term outcome and was superior to RECIST guideline for outcome prediction in adNPC. A ΔADC% threshold of ≥ 34.2% may be valuable for selecting patients who respond to treatment for de-escalation of treatment or post-treatment surveillance.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"32"},"PeriodicalIF":3.5,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11905565/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143613243","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}