首页 > 最新文献

Cancer Imaging最新文献

英文 中文
Innovative optimization of greater omentum imaging report and data system for enhanced risk stratification of omental lesions. 创新优化大网膜成像报告和数据系统,加强大网膜病变的风险分层。
IF 3.5 2区 医学 Q2 ONCOLOGY Pub Date : 2025-03-10 DOI: 10.1186/s40644-025-00848-2
Zhiguang Chen, Liang Sang, Yuan Cheng, Xuemei Wang, Mutian Lv, Yanjun Liu, ZhiQun Bai

Background: In 2020, we introduced the Greater Omentum Imaging-Reporting and Data System (GOI-RADS), a novel classification system related to peritoneal lesions. However, its clinical application remained unvalidated.

Objective: This study aimed to validate GOI-RADS, optimize its parameters for a new grading system, and explore its clinical usefulness.

Methods: A retrospective-prospective study was conducted to validate and refine the GOI-RADS system. The study consisted of two phases: a retrospective validation phase and a prospective application phase. The first phase included patients with peritoneal lesions from 2019 to 2021, classified by GOI-RADS and verified against pathology. Contrast-enhanced ultrasound (CEUS) and real-time elastography (RTE) data were collected for developing a new grading system. Odds ratios optimized parameters. The second phase (2021-2024) assessed diagnostic consistency among sonographers and performance of grading systems.

Results: Among 215 patients with peritoneal lesions, the actual malignancy rates for GOI-RADS 2 (40.00%) and GOI-RADS 3 (61.22%) were much higher than predicted (5.56% and 37.25%). Combining CEUS and RTE parameters showed varying sensitivity and specificity: RTE + GOI-RADS (95.35%, 55.56%) and CEUS + GOI-RADS (96.51%, 44.44%). However, the grading system based on multiple ultrasound parameters, specifically when incorporating RTE, CEUS parameters, and GOI-RADS (Multi-GOIRADS), exhibited the highest diagnostic sensitivity and specificity of 88.37% and 83.33%, respectively. Its simplified version, sMulti-GOIRADS, had sensitivity of 73.26% and specificity of 94.44%. In the prospective study involving three sonographers of different qualifications, the use of sMulti-GOIRADS was found to be the most time-efficient and showed excellent diagnostic consistency among them. In contrast, Multi-GOIRADS required more time for scoring but offered superior diagnostic performance, particularly among senior sonographers (88.35% and 91.43%).

Conclusions: This study proposes a multiparametric ultrasound-based imaging-reporting and data system for risk stratification of omental malignancy, Multi-GOIRADS, and presents an optimized and simplified version, sMulti-GOIRADS, which demonstrates excellent diagnostic consistency and performance in clinical applications.

{"title":"Innovative optimization of greater omentum imaging report and data system for enhanced risk stratification of omental lesions.","authors":"Zhiguang Chen, Liang Sang, Yuan Cheng, Xuemei Wang, Mutian Lv, Yanjun Liu, ZhiQun Bai","doi":"10.1186/s40644-025-00848-2","DOIUrl":"https://doi.org/10.1186/s40644-025-00848-2","url":null,"abstract":"<p><strong>Background: </strong>In 2020, we introduced the Greater Omentum Imaging-Reporting and Data System (GOI-RADS), a novel classification system related to peritoneal lesions. However, its clinical application remained unvalidated.</p><p><strong>Objective: </strong>This study aimed to validate GOI-RADS, optimize its parameters for a new grading system, and explore its clinical usefulness.</p><p><strong>Methods: </strong>A retrospective-prospective study was conducted to validate and refine the GOI-RADS system. The study consisted of two phases: a retrospective validation phase and a prospective application phase. The first phase included patients with peritoneal lesions from 2019 to 2021, classified by GOI-RADS and verified against pathology. Contrast-enhanced ultrasound (CEUS) and real-time elastography (RTE) data were collected for developing a new grading system. Odds ratios optimized parameters. The second phase (2021-2024) assessed diagnostic consistency among sonographers and performance of grading systems.</p><p><strong>Results: </strong>Among 215 patients with peritoneal lesions, the actual malignancy rates for GOI-RADS 2 (40.00%) and GOI-RADS 3 (61.22%) were much higher than predicted (5.56% and 37.25%). Combining CEUS and RTE parameters showed varying sensitivity and specificity: RTE + GOI-RADS (95.35%, 55.56%) and CEUS + GOI-RADS (96.51%, 44.44%). However, the grading system based on multiple ultrasound parameters, specifically when incorporating RTE, CEUS parameters, and GOI-RADS (Multi-GOIRADS), exhibited the highest diagnostic sensitivity and specificity of 88.37% and 83.33%, respectively. Its simplified version, sMulti-GOIRADS, had sensitivity of 73.26% and specificity of 94.44%. In the prospective study involving three sonographers of different qualifications, the use of sMulti-GOIRADS was found to be the most time-efficient and showed excellent diagnostic consistency among them. In contrast, Multi-GOIRADS required more time for scoring but offered superior diagnostic performance, particularly among senior sonographers (88.35% and 91.43%).</p><p><strong>Conclusions: </strong>This study proposes a multiparametric ultrasound-based imaging-reporting and data system for risk stratification of omental malignancy, Multi-GOIRADS, and presents an optimized and simplified version, sMulti-GOIRADS, which demonstrates excellent diagnostic consistency and performance in clinical applications.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"28"},"PeriodicalIF":3.5,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143595758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A CT-based interpretable deep learning signature for predicting PD-L1 expression in bladder cancer: a two-center study.
IF 3.5 2区 医学 Q2 ONCOLOGY Pub Date : 2025-03-10 DOI: 10.1186/s40644-025-00849-1
Xiaomeng Han, Jing Guan, Li Guo, Qiyan Jiao, Kexin Wang, Feng Hou, Shunli Liu, Shifeng Yang, Chencui Huang, Wenbin Cong, Hexiang Wang

Background: To construct and assess a deep learning (DL) signature that employs computed tomography imaging to predict the expression status of programmed cell death ligand 1 in patients with bladder cancer (BCa).

Methods: This retrospective study included 190 patients from two hospitals who underwent surgical removal of BCa (training set/external validation set, 127/63). We used convolutional neural network and radiomics machine learning technology to generate prediction models. We then compared the performance of the DL signature with the radiomics machine learning signature and selected the optimal signature to build a nomogram with the clinical model. Finally, the internal forecasting process of the DL signature was explained using Shapley additive explanation technology.

Results: On the external validation set, the DL signature had an area under the curve of 0.857 (95% confidence interval: 0.745-0.932), and demonstrated superior prediction performance in comparison with the other models. SHAP expression images revealed that the prediction of PD-L1 expression status is mainly influenced by the tumor edge region, particularly the area close to the bladder wall.

Conclusions: The DL signature performed well in comparison with other models and proved to be a valuable, dependable, and interpretable tool for predicting programmed cell death ligand 1 expression status in patients with BCa.

{"title":"A CT-based interpretable deep learning signature for predicting PD-L1 expression in bladder cancer: a two-center study.","authors":"Xiaomeng Han, Jing Guan, Li Guo, Qiyan Jiao, Kexin Wang, Feng Hou, Shunli Liu, Shifeng Yang, Chencui Huang, Wenbin Cong, Hexiang Wang","doi":"10.1186/s40644-025-00849-1","DOIUrl":"https://doi.org/10.1186/s40644-025-00849-1","url":null,"abstract":"<p><strong>Background: </strong>To construct and assess a deep learning (DL) signature that employs computed tomography imaging to predict the expression status of programmed cell death ligand 1 in patients with bladder cancer (BCa).</p><p><strong>Methods: </strong>This retrospective study included 190 patients from two hospitals who underwent surgical removal of BCa (training set/external validation set, 127/63). We used convolutional neural network and radiomics machine learning technology to generate prediction models. We then compared the performance of the DL signature with the radiomics machine learning signature and selected the optimal signature to build a nomogram with the clinical model. Finally, the internal forecasting process of the DL signature was explained using Shapley additive explanation technology.</p><p><strong>Results: </strong>On the external validation set, the DL signature had an area under the curve of 0.857 (95% confidence interval: 0.745-0.932), and demonstrated superior prediction performance in comparison with the other models. SHAP expression images revealed that the prediction of PD-L1 expression status is mainly influenced by the tumor edge region, particularly the area close to the bladder wall.</p><p><strong>Conclusions: </strong>The DL signature performed well in comparison with other models and proved to be a valuable, dependable, and interpretable tool for predicting programmed cell death ligand 1 expression status in patients with BCa.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"27"},"PeriodicalIF":3.5,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143596400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
DCE-MRI quantitative analysis and MRI-based radiomics for predicting the early efficacy of microwave ablation in lung cancers.
IF 3.5 2区 医学 Q2 ONCOLOGY Pub Date : 2025-03-10 DOI: 10.1186/s40644-025-00851-7
Chen Yang, Fandong Zhu, Jing Yang, Min Wang, Shijun Zhang, Zhenhua Zhao

Objectives: To evaluate the feasibility and value of dynamic contrast-enhanced MRI (DCE-MRI) quantitative analysis and MRI-based radiomics in predicting the efficacy of microwave ablation (MWA) in lung cancers (LCs).

Methods: Forty-three patients with LCs who underwent DCE-MRI within 24 h of receiving MWA were enrolled in the study and divided into two groups according to the modified response evaluation criteria in solid tumors (m-RECIST) criteria: the effective treatment (complete response + partial response + stable disease, n = 28) and the ineffective treatment (progressive disease, n = 15). DCE-MRI datasets were processed by Omni. Kinetics software, using the extended tofts model (ETM) and exchange model (ECM) to yield pharmacokinetic parameters and their histogram features. Changes in quantitative perfusion parameters were compared between the two groups. Scientific research platform ( https://medresearch.shukun.net/ ) was used for radiomics analysis. A total of 1874 radiomic features were extracted for each tumor by manually segmentation of T1WI and Contrast-enhanced of T1WI (Ce-T1WI) fat inhibition sequence. The performances of radiomics models were evaluated by the receiver operating characteristic curve. Based on radiomics features, survival curves were generated by Kaplan-Meier survival analysis to evaluate patient outcomes. P < 0.05 was set for the significance threshold.

Results: The Vp value of ECM was significantly higher in the ineffective group compared to the effective group (p = 0.027). Additionally, the skewness, and kurtosis of Vp (p = 0.020 and 0.013, respectively) derived from ETM and Fp (p = 0.027 and 0.030, respectively) from ECM as well as the quantiles were higher in the ineffective group than in the effective group. Significant statistical differences were observed in the energy and entropy of Ve (p = 0.044 and 0.025, respectively) and Vp (p = 0.025 and 0.026, respectively) between the two groups. In the process of model construction, seven features from T1WI, five features from Ce-T1WI, and ten features from combined sequences were ultimately selected. The area under the curve (AUC) values for the T1WI model, Ce-T1WI model, and combined model were 0.910, 0.890, 0.965 in the training group, and 0.850, 0.700, 0.850 in the test group, respectively.

Conclusions: DCE-MRI quantitative analysis and MRI-based radiomics may be helpful in assessing the early response to MWA in patients with LCs.

{"title":"DCE-MRI quantitative analysis and MRI-based radiomics for predicting the early efficacy of microwave ablation in lung cancers.","authors":"Chen Yang, Fandong Zhu, Jing Yang, Min Wang, Shijun Zhang, Zhenhua Zhao","doi":"10.1186/s40644-025-00851-7","DOIUrl":"https://doi.org/10.1186/s40644-025-00851-7","url":null,"abstract":"<p><strong>Objectives: </strong>To evaluate the feasibility and value of dynamic contrast-enhanced MRI (DCE-MRI) quantitative analysis and MRI-based radiomics in predicting the efficacy of microwave ablation (MWA) in lung cancers (LCs).</p><p><strong>Methods: </strong>Forty-three patients with LCs who underwent DCE-MRI within 24 h of receiving MWA were enrolled in the study and divided into two groups according to the modified response evaluation criteria in solid tumors (m-RECIST) criteria: the effective treatment (complete response + partial response + stable disease, n = 28) and the ineffective treatment (progressive disease, n = 15). DCE-MRI datasets were processed by Omni. Kinetics software, using the extended tofts model (ETM) and exchange model (ECM) to yield pharmacokinetic parameters and their histogram features. Changes in quantitative perfusion parameters were compared between the two groups. Scientific research platform ( https://medresearch.shukun.net/ ) was used for radiomics analysis. A total of 1874 radiomic features were extracted for each tumor by manually segmentation of T1WI and Contrast-enhanced of T1WI (Ce-T1WI) fat inhibition sequence. The performances of radiomics models were evaluated by the receiver operating characteristic curve. Based on radiomics features, survival curves were generated by Kaplan-Meier survival analysis to evaluate patient outcomes. P < 0.05 was set for the significance threshold.</p><p><strong>Results: </strong>The V<sub>p</sub> value of ECM was significantly higher in the ineffective group compared to the effective group (p = 0.027). Additionally, the skewness, and kurtosis of V<sub>p</sub> (p = 0.020 and 0.013, respectively) derived from ETM and F<sub>p</sub> (p = 0.027 and 0.030, respectively) from ECM as well as the quantiles were higher in the ineffective group than in the effective group. Significant statistical differences were observed in the energy and entropy of V<sub>e</sub> (p = 0.044 and 0.025, respectively) and V<sub>p</sub> (p = 0.025 and 0.026, respectively) between the two groups. In the process of model construction, seven features from T1WI, five features from Ce-T1WI, and ten features from combined sequences were ultimately selected. The area under the curve (AUC) values for the T1WI model, Ce-T1WI model, and combined model were 0.910, 0.890, 0.965 in the training group, and 0.850, 0.700, 0.850 in the test group, respectively.</p><p><strong>Conclusions: </strong>DCE-MRI quantitative analysis and MRI-based radiomics may be helpful in assessing the early response to MWA in patients with LCs.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"26"},"PeriodicalIF":3.5,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143596404","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Preoperative multiclass classification of thymic mass lesions based on radiomics and machine learning.
IF 3.5 2区 医学 Q2 ONCOLOGY Pub Date : 2025-03-06 DOI: 10.1186/s40644-025-00839-3
Yan Zhu, Li Wang, Aichao Ruan, Zhiyu Peng, Zhenzhong Zhang

Background: Apart from rare cases such as lymphomas, germ cell tumors, neuroendocrine neoplasms, and thymic hyperplasia, thymic mass lesions (TMLs) are typically categorized into cysts, and thymomas. However, the classification results cannot be determined in advance and can only be confirmed through postoperative pathology. Therefore, the objective of this study is to rely on clinical parameters and radiomic features extracted from chest computed tomography (CT) scans to facilitate the preoperative classification of TMLs. The model development specifically focused on thymic cysts and thymomas, as these are the most commonly encountered anterior mediastinal tumors in clinical practice.

Materials and methods: This retrospective study included 400 participants from 3 hospitals between September 2017 and September 2024 due to TMLs. The participants were classified into 7 groups based on the ultimately confirmed etiology: thymic cysts and thymomas, including types A, AB, B1, B2, B3, and C. All participants underwent contrast-enhanced chest CT scans, with senior radiologists delineating regions of interest to extract radiomic features. Additionally, the participants' ages were also collected as clinical parameters for analysis. The participants were randomly allocated into a training set and a validation set at a 7:3 ratio. A classifier models were developed using the data from the training set, and their performances were evaluated on the validation set.

Results: The model exhibited good classification performance with accuracies of 0.8547.

Conclusion: The model can assist in early diagnosis and the development of personalized treatment strategies for patients with TMLs.

{"title":"Preoperative multiclass classification of thymic mass lesions based on radiomics and machine learning.","authors":"Yan Zhu, Li Wang, Aichao Ruan, Zhiyu Peng, Zhenzhong Zhang","doi":"10.1186/s40644-025-00839-3","DOIUrl":"10.1186/s40644-025-00839-3","url":null,"abstract":"<p><strong>Background: </strong>Apart from rare cases such as lymphomas, germ cell tumors, neuroendocrine neoplasms, and thymic hyperplasia, thymic mass lesions (TMLs) are typically categorized into cysts, and thymomas. However, the classification results cannot be determined in advance and can only be confirmed through postoperative pathology. Therefore, the objective of this study is to rely on clinical parameters and radiomic features extracted from chest computed tomography (CT) scans to facilitate the preoperative classification of TMLs. The model development specifically focused on thymic cysts and thymomas, as these are the most commonly encountered anterior mediastinal tumors in clinical practice.</p><p><strong>Materials and methods: </strong>This retrospective study included 400 participants from 3 hospitals between September 2017 and September 2024 due to TMLs. The participants were classified into 7 groups based on the ultimately confirmed etiology: thymic cysts and thymomas, including types A, AB, B1, B2, B3, and C. All participants underwent contrast-enhanced chest CT scans, with senior radiologists delineating regions of interest to extract radiomic features. Additionally, the participants' ages were also collected as clinical parameters for analysis. The participants were randomly allocated into a training set and a validation set at a 7:3 ratio. A classifier models were developed using the data from the training set, and their performances were evaluated on the validation set.</p><p><strong>Results: </strong>The model exhibited good classification performance with accuracies of 0.8547.</p><p><strong>Conclusion: </strong>The model can assist in early diagnosis and the development of personalized treatment strategies for patients with TMLs.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"25"},"PeriodicalIF":3.5,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11884038/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143572288","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}
引用次数: 0
Imaging genomics of cancer: a bibliometric analysis and review.
IF 3.5 2区 医学 Q2 ONCOLOGY Pub Date : 2025-03-04 DOI: 10.1186/s40644-025-00841-9
Xinyi Gou, Aobo Feng, Caizhen Feng, Jin Cheng, Nan Hong

Background: Imaging genomics is a burgeoning field that seeks to connections between medical imaging and genomic features. It has been widely applied to explore heterogeneity and predict responsiveness and disease progression in cancer. This review aims to assess current applications and advancements of imaging genomics in cancer.

Methods: Literature on imaging genomics in cancer was retrieved and selected from PubMed, Web of Science, and Embase before July 2024. Detail information of articles, such as systems and imaging features, were extracted and analyzed. Citation information was extracted from Web of Science and Scopus. Additionally, a bibliometric analysis of the included studies was conducted using the Bibliometrix R package and VOSviewer.

Results: A total of 370 articles were included in the study. The annual growth rate of articles on imaging genomics in cancer is 24.88%. China (133) and the USA (107) were the most productive countries. The top 2 keywords plus were "survival" and "classification". The current research mainly focuses on the central nervous system (121) and the genitourinary system (110, including 44 breast cancer articles). Despite different systems utilizing different imaging modalities, more than half of the studies in each system employed radiomics features.

Conclusions: Publication databases provide data support for imaging genomics research. The development of artificial intelligence algorithms, especially in feature extraction and model construction, has significantly advanced this field. It is conducive to enhancing the related-models' interpretability. Nonetheless, challenges such as the sample size and the standardization of feature extraction and model construction must overcome. And the research trends revealed in this study will guide the development of imaging genomics in the future and contribute to more accurate cancer diagnosis and treatment in the clinic.

{"title":"Imaging genomics of cancer: a bibliometric analysis and review.","authors":"Xinyi Gou, Aobo Feng, Caizhen Feng, Jin Cheng, Nan Hong","doi":"10.1186/s40644-025-00841-9","DOIUrl":"10.1186/s40644-025-00841-9","url":null,"abstract":"<p><strong>Background: </strong>Imaging genomics is a burgeoning field that seeks to connections between medical imaging and genomic features. It has been widely applied to explore heterogeneity and predict responsiveness and disease progression in cancer. This review aims to assess current applications and advancements of imaging genomics in cancer.</p><p><strong>Methods: </strong>Literature on imaging genomics in cancer was retrieved and selected from PubMed, Web of Science, and Embase before July 2024. Detail information of articles, such as systems and imaging features, were extracted and analyzed. Citation information was extracted from Web of Science and Scopus. Additionally, a bibliometric analysis of the included studies was conducted using the Bibliometrix R package and VOSviewer.</p><p><strong>Results: </strong>A total of 370 articles were included in the study. The annual growth rate of articles on imaging genomics in cancer is 24.88%. China (133) and the USA (107) were the most productive countries. The top 2 keywords plus were \"survival\" and \"classification\". The current research mainly focuses on the central nervous system (121) and the genitourinary system (110, including 44 breast cancer articles). Despite different systems utilizing different imaging modalities, more than half of the studies in each system employed radiomics features.</p><p><strong>Conclusions: </strong>Publication databases provide data support for imaging genomics research. The development of artificial intelligence algorithms, especially in feature extraction and model construction, has significantly advanced this field. It is conducive to enhancing the related-models' interpretability. Nonetheless, challenges such as the sample size and the standardization of feature extraction and model construction must overcome. And the research trends revealed in this study will guide the development of imaging genomics in the future and contribute to more accurate cancer diagnosis and treatment in the clinic.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"24"},"PeriodicalIF":3.5,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11877899/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143555884","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}
引用次数: 0
Head-to-head comparison of 18F-FDG and 68Ga-FAPI PET/CT in common gynecological malignancies.
IF 3.5 2区 医学 Q2 ONCOLOGY Pub Date : 2025-02-28 DOI: 10.1186/s40644-025-00843-7
Tengfei Li, Jintao Zhang, Yuanzhuo Yan, Yue Zhang, Wenjie Pei, Qingchu Hua, Yue Chen

Background: 68Ga-FAPI (fibroblast activation protein inhibitor) is a novel and highly promising radiotracer for PET/CT imaging. It has shown significant tumor uptake and high sensitivity in lesion detection across a range of cancer types. We aimed to compare the diagnostic value of 68Ga-FAPI and 18F-FDG PET/CT in common gynecological malignancies.

Methods: This retrospective study included 35 patients diagnosed with common gynecological tumors, including breast cancer, ovarian cancer, and cervical cancer. Among the 35 patients, 27 underwent PET/CT for the initial assessment of tumors, while 8 were assessed for recurrence detection. The median and range of tumor size and maximum standardized uptake values (SUVmax) were calculated.

Results: Thirty-five patients (median age, 57 years [interquartile range], 51-65 years) were evaluated. In treatment-naive patients (n = 27), 68Ga-FAPI PET/CT led to upstaging of the clinical TNM stage in five (19%) patients compared with 18F-FDG PET/CT. No significant difference in tracer uptake was observed between 18F-FDG and 68Ga-FAPI for primary lesions: breast cancer (7.2 vs. 4.9, P = 0.086), ovarian cancer (16.3 vs. 15.7, P = 0.345), and cervical cancer (18.3 vs. 17.1, P = 0.703). For involved lymph nodes, 68Ga-FAPI PET/CT demonstrated a higher SUVmax for breast cancer (9.9 vs. 6.1, P = 0.007) and cervical cancer (6.3 vs. 4.8, P = 0.048), while no significant difference was noted for ovarian cancer (7.0 vs. 5.9, P = 0.179). Furthermore, 68Ga-FAPI PET/CT demonstrated higher specificity and accuracy compared to 18F-FDG PET/CT for detecting metastatic lymph nodes (100% vs. 66%, P < 0.001; 94% vs. 80%, P < 0.001). In contrast, sensitivity did not differ significantly (97% vs. 86%, P = 0.125). For most distant metastases, 68Ga-FAPI exhibited a higher SUVmax than 18F-FDG in bone metastases (12.9 vs. 4.9, P = 0.036).

Conclusions: 68Ga-FAPI PET/CT demonstrated higher tracer uptake and was superior to 18F-FDG PET/CT in detecting primary and metastatic lesions in patients with common gynecological malignancies.

Trial registration: ChiCTR, ChiCTR2100044131. Registered 10 October 2022, https://www.chictr.org.cn , ChiCTR2100044131.

{"title":"Head-to-head comparison of <sup>18</sup>F-FDG and <sup>68</sup>Ga-FAPI PET/CT in common gynecological malignancies.","authors":"Tengfei Li, Jintao Zhang, Yuanzhuo Yan, Yue Zhang, Wenjie Pei, Qingchu Hua, Yue Chen","doi":"10.1186/s40644-025-00843-7","DOIUrl":"10.1186/s40644-025-00843-7","url":null,"abstract":"<p><strong>Background: </strong><sup>68</sup>Ga-FAPI (fibroblast activation protein inhibitor) is a novel and highly promising radiotracer for PET/CT imaging. It has shown significant tumor uptake and high sensitivity in lesion detection across a range of cancer types. We aimed to compare the diagnostic value of <sup>68</sup>Ga-FAPI and <sup>18</sup>F-FDG PET/CT in common gynecological malignancies.</p><p><strong>Methods: </strong>This retrospective study included 35 patients diagnosed with common gynecological tumors, including breast cancer, ovarian cancer, and cervical cancer. Among the 35 patients, 27 underwent PET/CT for the initial assessment of tumors, while 8 were assessed for recurrence detection. The median and range of tumor size and maximum standardized uptake values (SUV<sub>max</sub>) were calculated.</p><p><strong>Results: </strong>Thirty-five patients (median age, 57 years [interquartile range], 51-65 years) were evaluated. In treatment-naive patients (n = 27), <sup>68</sup>Ga-FAPI PET/CT led to upstaging of the clinical TNM stage in five (19%) patients compared with <sup>18</sup>F-FDG PET/CT. No significant difference in tracer uptake was observed between <sup>18</sup>F-FDG and <sup>68</sup>Ga-FAPI for primary lesions: breast cancer (7.2 vs. 4.9, P = 0.086), ovarian cancer (16.3 vs. 15.7, P = 0.345), and cervical cancer (18.3 vs. 17.1, P = 0.703). For involved lymph nodes, <sup>68</sup>Ga-FAPI PET/CT demonstrated a higher SUV<sub>max</sub> for breast cancer (9.9 vs. 6.1, P = 0.007) and cervical cancer (6.3 vs. 4.8, P = 0.048), while no significant difference was noted for ovarian cancer (7.0 vs. 5.9, P = 0.179). Furthermore, <sup>68</sup>Ga-FAPI PET/CT demonstrated higher specificity and accuracy compared to <sup>18</sup>F-FDG PET/CT for detecting metastatic lymph nodes (100% vs. 66%, P < 0.001; 94% vs. 80%, P < 0.001). In contrast, sensitivity did not differ significantly (97% vs. 86%, P = 0.125). For most distant metastases, <sup>68</sup>Ga-FAPI exhibited a higher SUV<sub>max</sub> than <sup>18</sup>F-FDG in bone metastases (12.9 vs. 4.9, P = 0.036).</p><p><strong>Conclusions: </strong><sup>68</sup>Ga-FAPI PET/CT demonstrated higher tracer uptake and was superior to <sup>18</sup>F-FDG PET/CT in detecting primary and metastatic lesions in patients with common gynecological malignancies.</p><p><strong>Trial registration: </strong>ChiCTR, ChiCTR2100044131. Registered 10 October 2022, https://www.chictr.org.cn , ChiCTR2100044131.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"21"},"PeriodicalIF":3.5,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11869701/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143531314","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}
引用次数: 0
Preoperative diagnosis of meningioma sinus invasion based on MRI radiomics and deep learning: a multicenter study. 基于磁共振成像放射组学和深度学习的脑膜瘤窦道侵犯术前诊断:一项多中心研究。
IF 3.5 2区 医学 Q2 ONCOLOGY Pub Date : 2025-02-28 DOI: 10.1186/s40644-025-00845-5
Yuan Gui, Wei Hu, Jialiang Ren, Fuqiang Tang, Limei Wang, Fang Zhang, Jing Zhang

Objective: Exploring the construction of a fusion model that combines radiomics and deep learning (DL) features is of great significance for the precise preoperative diagnosis of meningioma sinus invasion.

Materials and methods: This study retrospectively collected data from 601 patients with meningioma confirmed by surgical pathology. For each patient, 3948 radiomics features, 12,288 VGG features, 6144 ResNet features, and 3072 DenseNet features were extracted from MRI images. Thus, univariate logistic regression, correlation analysis, and the Boruta algorithm were applied for further feature dimension reduction, selecting radiomics and DL features highly associated with meningioma sinus invasion. Finally, diagnosis models were constructed using the random forest (RF) algorithm. Additionally, the diagnostic performance of different models was evaluated using receiver operating characteristic (ROC) curves, and AUC values of different models were compared using the DeLong test.

Results: Ultimately, 21 features highly associated with meningioma sinus invasion were selected, including 6 radiomics features, 2 VGG features, 7 ResNet features, and 6 DenseNet features. Based on these features, five models were constructed: the radiomics model, VGG model, ResNet model, DenseNet model, and DL-radiomics (DLR) fusion model. This fusion model demonstrated superior diagnostic performance, with AUC values of 0.818, 0.814, and 0.769 in the training set, internal validation set, and independent external validation set, respectively. Furthermore, the results of the DeLong test indicated that there were significant differences between the fusion model and both the radiomics model and the VGG model (p < 0.05).

Conclusions: The fusion model combining radiomics and DL features exhibits superior diagnostic performance in preoperative diagnosis of meningioma sinus invasion. It is expected to become a powerful tool for clinical surgical plan selection and patient prognosis assessment.

目的探索构建放射组学与深度学习(DL)特征相结合的融合模型,对脑膜瘤窦道侵犯的术前精确诊断具有重要意义:本研究回顾性收集了601例经手术病理证实的脑膜瘤患者的数据。从磁共振图像中为每位患者提取了 3948 个放射组学特征、12288 个 VGG 特征、6144 个 ResNet 特征和 3072 个 DenseNet 特征。然后,应用单变量逻辑回归、相关性分析和 Boruta 算法进一步降低特征维度,筛选出与脑膜瘤窦侵犯高度相关的放射组学特征和 DL 特征。最后,使用随机森林(RF)算法构建诊断模型。此外,还利用接收者操作特征曲线(ROC)评估了不同模型的诊断性能,并利用 DeLong 检验比较了不同模型的 AUC 值:结果:最终选出了与脑膜瘤窦道侵犯高度相关的 21 个特征,包括 6 个放射组学特征、2 个 VGG 特征、7 个 ResNet 特征和 6 个 DenseNet 特征。根据这些特征构建了五个模型:放射组学模型、VGG 模型、ResNet 模型、DenseNet 模型和 DL- 放射组学(DLR)融合模型。该融合模型显示出卓越的诊断性能,其训练集、内部验证集和独立外部验证集的 AUC 值分别为 0.818、0.814 和 0.769。此外,DeLong 检验结果表明,融合模型与放射组学模型和 VGG 模型之间存在显著差异(p 结论:融合模型与 VGG 模型之间存在显著差异:结合放射组学和 DL 特征的融合模型在脑膜瘤窦道侵犯的术前诊断中表现出卓越的诊断性能。它有望成为临床手术方案选择和患者预后评估的有力工具。
{"title":"Preoperative diagnosis of meningioma sinus invasion based on MRI radiomics and deep learning: a multicenter study.","authors":"Yuan Gui, Wei Hu, Jialiang Ren, Fuqiang Tang, Limei Wang, Fang Zhang, Jing Zhang","doi":"10.1186/s40644-025-00845-5","DOIUrl":"10.1186/s40644-025-00845-5","url":null,"abstract":"<p><strong>Objective: </strong>Exploring the construction of a fusion model that combines radiomics and deep learning (DL) features is of great significance for the precise preoperative diagnosis of meningioma sinus invasion.</p><p><strong>Materials and methods: </strong>This study retrospectively collected data from 601 patients with meningioma confirmed by surgical pathology. For each patient, 3948 radiomics features, 12,288 VGG features, 6144 ResNet features, and 3072 DenseNet features were extracted from MRI images. Thus, univariate logistic regression, correlation analysis, and the Boruta algorithm were applied for further feature dimension reduction, selecting radiomics and DL features highly associated with meningioma sinus invasion. Finally, diagnosis models were constructed using the random forest (RF) algorithm. Additionally, the diagnostic performance of different models was evaluated using receiver operating characteristic (ROC) curves, and AUC values of different models were compared using the DeLong test.</p><p><strong>Results: </strong>Ultimately, 21 features highly associated with meningioma sinus invasion were selected, including 6 radiomics features, 2 VGG features, 7 ResNet features, and 6 DenseNet features. Based on these features, five models were constructed: the radiomics model, VGG model, ResNet model, DenseNet model, and DL-radiomics (DLR) fusion model. This fusion model demonstrated superior diagnostic performance, with AUC values of 0.818, 0.814, and 0.769 in the training set, internal validation set, and independent external validation set, respectively. Furthermore, the results of the DeLong test indicated that there were significant differences between the fusion model and both the radiomics model and the VGG model (p < 0.05).</p><p><strong>Conclusions: </strong>The fusion model combining radiomics and DL features exhibits superior diagnostic performance in preoperative diagnosis of meningioma sinus invasion. It is expected to become a powerful tool for clinical surgical plan selection and patient prognosis assessment.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"20"},"PeriodicalIF":3.5,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11869444/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143531316","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}
引用次数: 0
Tumor ADC value predicts outcome and yields refined prognostication in uterine cervical cancer.
IF 3.5 2区 医学 Q2 ONCOLOGY Pub Date : 2025-02-28 DOI: 10.1186/s40644-025-00828-6
Njål Lura, Kari S Wagner-Larsen, Stian Ryste, Kristine Fasmer, David Forsse, Jone Trovik, Mari K Halle, Bjørn I Bertelsen, Frank Riemer, Øyvind Salvesen, Kathrine Woie, Camilla Krakstad, Ingfrid S Haldorsen

Pelvic MRI is essential for evaluating local and regional tumor extent in uterine cervical cancer (CC). Tumor microstructure captured by diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) markers may be closely linked to prognosis in CC.Purpose To explore whether primary tumor ADC markers predict survival in CC.Material and methods CC patients (n = 179) diagnosed during 2009-2020 with MRI-assessed primary maximum tumorsize ≥ 2 cm were included in this retrospective single-center study. Two radiologists read all MRIs independently, measuring mean tumor ADC values in manually drawn regions of interest (ROIs) and mean tumor ADC (tumorADCmean) from five measurements for the two readers was used. ADC from ROIs in the myometrium (myometriumADC), cervical stroma (cervixADC), and bladder (bladderADC) were used to calculate ADC ratios. ADC markers were explored in relation to the International Federation of Gynecology and Obstetrics (FIGO) (2018) stage, disease-specific survival (DSS), and recurrence/progression-free survival (RPFS).Results Inter-reader agreement for all ADC measurements was high (ICC:0.59-0.79). Low tumorADCmean predicted advanced FIGO stage (P = 0.04) and reduced DSS (hazard ratio (HR): 0.96, P < 0.001; AIC: 441). MyometriumADC/tumorADCmean yielded the best Cox regression fit (AIC = 430) among all tumor ADC markers. Patients with high myometriumADC/tumorADCmean had significantly reduced 5-year DSS for FIGO stage I, II, and III (P = 0.01, 0.004, and 0.02, respectively) and tended to the same for FIGO IV (P = 0.22).Conclusion Low tumorADCmean predicted reduced DSS in CC. High myometriumADC/tumorADCmean was the strongest ADC predictor of poor DSS and a marker of high-risk phenotype independent of FIGO stage.

盆腔磁共振成像对于评估子宫颈癌(CC)的局部和区域肿瘤范围至关重要。通过弥散加权成像(DWI)和表观弥散系数(ADC)标记捕捉到的肿瘤微观结构可能与CC的预后密切相关。材料和方法 在这项回顾性单中心研究中纳入了2009-2020年期间确诊的、经MRI评估原发最大肿瘤大小≥2厘米的CC患者(n = 179)。两名放射科医生独立阅读所有核磁共振成像,测量手动绘制的感兴趣区(ROI)中的平均肿瘤 ADC 值,并使用两名阅读者五次测量的平均肿瘤 ADC(tumorADCmean)。子宫肌层(myometriumADC)、宫颈基质(cervixADC)和膀胱(bladadderADC)ROI 的 ADC 用于计算 ADC 比值。探讨了 ADC 标记与国际妇产科联盟(FIGO)(2018 年)分期、疾病特异性生存期(DSS)和复发/无进展生存期(RPFS)的关系。在所有肿瘤 ADC 标记中,低肿瘤 ADCmean 预测晚期 FIGO 分期(P = 0.04)和降低 DSS(危险比 (HR):0.96,P ADC/肿瘤 ADCmean 的 Cox 回归拟合效果最好(AIC = 430)。子宫肌层 ADC/tumorADCmean 高的患者在 FIGO I、II 和 III 期的 5 年 DSS 显著降低(P = 0.01、0.004 和 0.02,分别为 0.01、0.004 和 0.02),在 FIGO IV 期也趋于相同(P = 0.22)。高子宫肌层ADC/肿瘤ADCmean是预测不良DSS的最强ADC指标,也是独立于FIGO分期的高风险表型标志。
{"title":"Tumor ADC value predicts outcome and yields refined prognostication in uterine cervical cancer.","authors":"Njål Lura, Kari S Wagner-Larsen, Stian Ryste, Kristine Fasmer, David Forsse, Jone Trovik, Mari K Halle, Bjørn I Bertelsen, Frank Riemer, Øyvind Salvesen, Kathrine Woie, Camilla Krakstad, Ingfrid S Haldorsen","doi":"10.1186/s40644-025-00828-6","DOIUrl":"10.1186/s40644-025-00828-6","url":null,"abstract":"<p><p>Pelvic MRI is essential for evaluating local and regional tumor extent in uterine cervical cancer (CC). Tumor microstructure captured by diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) markers may be closely linked to prognosis in CC.Purpose To explore whether primary tumor ADC markers predict survival in CC.Material and methods CC patients (n = 179) diagnosed during 2009-2020 with MRI-assessed primary maximum tumor<sub>size</sub> ≥ 2 cm were included in this retrospective single-center study. Two radiologists read all MRIs independently, measuring mean tumor ADC values in manually drawn regions of interest (ROIs) and mean tumor ADC (tumor<sub>ADCmean</sub>) from five measurements for the two readers was used. ADC from ROIs in the myometrium (myometrium<sub>ADC</sub>), cervical stroma (cervix<sub>ADC</sub>), and bladder (bladder<sub>ADC</sub>) were used to calculate ADC ratios. ADC markers were explored in relation to the International Federation of Gynecology and Obstetrics (FIGO) (2018) stage, disease-specific survival (DSS), and recurrence/progression-free survival (RPFS).Results Inter-reader agreement for all ADC measurements was high (ICC:0.59-0.79). Low tumor<sub>ADCmean</sub> predicted advanced FIGO stage (P = 0.04) and reduced DSS (hazard ratio (HR): 0.96, P < 0.001; AIC: 441). Myometrium<sub>ADC</sub>/tumor<sub>ADCmean</sub> yielded the best Cox regression fit (AIC = 430) among all tumor ADC markers. Patients with high myometrium<sub>ADC</sub>/tumor<sub>ADCmean</sub> had significantly reduced 5-year DSS for FIGO stage I, II, and III (P = 0.01, 0.004, and 0.02, respectively) and tended to the same for FIGO IV (P = 0.22).Conclusion Low tumor<sub>ADCmean</sub> predicted reduced DSS in CC. High myometrium<sub>ADC</sub>/tumor<sub>ADCmean</sub> was the strongest ADC predictor of poor DSS and a marker of high-risk phenotype independent of FIGO stage.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"23"},"PeriodicalIF":3.5,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11871606/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143531318","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}
引用次数: 0
Development of modified multi-parametric CT algorithms for diagnosing clear-cell renal cell carcinoma in small solid renal masses.
IF 3.5 2区 医学 Q2 ONCOLOGY Pub Date : 2025-02-28 DOI: 10.1186/s40644-025-00847-3
Pengfei Jin, Linghui Zhang, Hong Yang, Tingting Jiang, Chenyang Xu, Jiehui Huang, Zhongyu Zhang, Lei Shi, Xu Wang

Objective: To refine the existing CT algorithm to enhance inter-reader agreement and improve the diagnostic performance for clear-cell renal cell carcinoma (ccRCC) in solid renal masses less than 4 cm.

Methods: A retrospective collection of 331 patients with pathologically confirmed renal masses were enrolled in this study. Two radiologists independently assessed the CT images: in addition to heterogeneity score (HS) and mass-to-cortex corticomedullary attenuation ratio (MCAR), measured parameters included ratio of major diameter to minor diameter at the maximum axial section (Major axis / Minor axis), tumor-renal interface, standardized heterogeneity ratio (SHR), and standardized nephrographic reduction rate (SNRR). Spearman's correlation analysis was performed to evaluate the relationship between SHR and HS. Univariate and multivariate logistic regression analyses were employed to identify independent risk factors and then CT-score was adjusted by those indicators. The diagnostic efficacy of the modified CT-scores was evaluated using ROC curve analysis.

Results: The SHR and heterogeneity grade (HG) of mass were correlated positively with the HS (R = 0.749, 0.730, all P < 0.001). Logistic regression analysis determined that the Major axis / Minor axis (> 1.16), the tumor-renal interface (> 22.3 mm), and the SNRR (> 0.16) as additional independent risk factors to combine with HS and MCAR. Compared to the original CT-score, the two CT algorithms combined tumor-renal interface and SNRR showed significantly improved diagnostic efficacy for ccRCC (AUC: 0.770 vs. 0.861 and 0.862, all P < 0.001). The inter-observer agreement for HG was higher than that for HS (weighted Kappa coefficient: 0.797 vs. 0.722). The consistency of modified CT-score was also superior to original CT-score (weighted Kappa coefficient: 0.935 vs. 0.878).

Conclusion: The modified CT algorithms not only enhanced inter-reader consistency but also improved the diagnostic capability for ccRCC in small renal masses.

目的改进现有的 CT 算法,以提高阅片员之间的一致性,并改善对小于 4 厘米的实性肾肿块中透明细胞肾细胞癌(ccRCC)的诊断性能:本研究回顾性收集了331例经病理证实的肾肿块患者。两名放射科医生独立评估 CT 图像:除异质性评分(HS)和肿块与皮质髓质衰减比(MCAR)外,测量参数还包括最大轴切面上大直径与小直径之比(大轴/小轴)、肿瘤与肾脏界面、标准化异质性比(SHR)和标准化肾图减影率(SNRR)。斯皮尔曼相关分析用于评估 SHR 与 HS 之间的关系。采用单变量和多变量逻辑回归分析确定独立的风险因素,然后根据这些指标调整 CT 评分。采用 ROC 曲线分析评估了修正 CT 评分的诊断效果:结果:肿块的SHR和异质性分级(HG)与HS呈正相关(R=0.749,0.730,P均为1.16),肿瘤肾界面(> 22.3 mm)和SNRR(> 0.16)是与HS和MCAR相结合的额外独立危险因素。与原始的 CT 评分相比,两种 CT 算法结合肿瘤肾界面和 SNRR 对 ccRCC 的诊断效果显著提高(AUC:AUC: 0.770 vs. 0.861 and 0.862, all P Conclusion:修改后的 CT 算法不仅增强了阅片者之间的一致性,还提高了对肾脏小肿块中 ccRCC 的诊断能力。
{"title":"Development of modified multi-parametric CT algorithms for diagnosing clear-cell renal cell carcinoma in small solid renal masses.","authors":"Pengfei Jin, Linghui Zhang, Hong Yang, Tingting Jiang, Chenyang Xu, Jiehui Huang, Zhongyu Zhang, Lei Shi, Xu Wang","doi":"10.1186/s40644-025-00847-3","DOIUrl":"10.1186/s40644-025-00847-3","url":null,"abstract":"<p><strong>Objective: </strong>To refine the existing CT algorithm to enhance inter-reader agreement and improve the diagnostic performance for clear-cell renal cell carcinoma (ccRCC) in solid renal masses less than 4 cm.</p><p><strong>Methods: </strong>A retrospective collection of 331 patients with pathologically confirmed renal masses were enrolled in this study. Two radiologists independently assessed the CT images: in addition to heterogeneity score (HS) and mass-to-cortex corticomedullary attenuation ratio (MCAR), measured parameters included ratio of major diameter to minor diameter at the maximum axial section (Major axis / Minor axis), tumor-renal interface, standardized heterogeneity ratio (SHR), and standardized nephrographic reduction rate (SNRR). Spearman's correlation analysis was performed to evaluate the relationship between SHR and HS. Univariate and multivariate logistic regression analyses were employed to identify independent risk factors and then CT-score was adjusted by those indicators. The diagnostic efficacy of the modified CT-scores was evaluated using ROC curve analysis.</p><p><strong>Results: </strong>The SHR and heterogeneity grade (HG) of mass were correlated positively with the HS (R = 0.749, 0.730, all P < 0.001). Logistic regression analysis determined that the Major axis / Minor axis (> 1.16), the tumor-renal interface (> 22.3 mm), and the SNRR (> 0.16) as additional independent risk factors to combine with HS and MCAR. Compared to the original CT-score, the two CT algorithms combined tumor-renal interface and SNRR showed significantly improved diagnostic efficacy for ccRCC (AUC: 0.770 vs. 0.861 and 0.862, all P < 0.001). The inter-observer agreement for HG was higher than that for HS (weighted Kappa coefficient: 0.797 vs. 0.722). The consistency of modified CT-score was also superior to original CT-score (weighted Kappa coefficient: 0.935 vs. 0.878).</p><p><strong>Conclusion: </strong>The modified CT algorithms not only enhanced inter-reader consistency but also improved the diagnostic capability for ccRCC in small renal masses.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"22"},"PeriodicalIF":3.5,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11869432/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143531312","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}
引用次数: 0
To accurately predict lymph node metastasis in patients with mass-forming intrahepatic cholangiocarcinoma by using CT radiomics features of tumor habitat subregions.
IF 3.5 2区 医学 Q2 ONCOLOGY Pub Date : 2025-02-26 DOI: 10.1186/s40644-025-00842-8
Pengyu Chen, Zhenwei Yang, Peigang Ning, Hao Yuan, Zuochao Qi, Qingshan Li, Bo Meng, Xianzhou Zhang, Haibo Yu

Background: This study aims to introduce the concept of habitat subregions and construct an accurate prediction model by analyzing refined medical images, to predict lymph node metastasis (LNM) in patients with intrahepatic cholangiocarcinoma (ICC) before surgery, and to provide personalized support for clinical decision-making.

Methods: Clinical, radiological, and pathological data from ICC patients were retrospectively collected. Using information from the arterial and venous phases of multisequence CT images, tumor habitat subregions were delineated through the K-means clustering algorithm. Radiomic features were extracted and screened, and prediction models based on different subregions were constructed and compared with traditional intratumoral models. Finally, a lymph node metastasis prediction model was established by integrating the features of several subregional models, and its performance was evaluated.

Results: A total of 164 ICC patients were included in this study, 103 of whom underwent lymph node dissection. The patients were divided into LNM- and LNM + groups on the basis of lymph node status, and significant differences in white blood cell indicators were found between the two groups. Survival analysis revealed that patients with positive lymph nodes had significantly worse prognoses. Through cluster analysis, the optimal number of habitat subregions was determined to be 5, and prediction models based on different subregions were constructed. A comparison of the performance of each model revealed that the Habitat1 and Habitat5 models had excellent performance. The optimal model obtained by fusing the features of the Habitat1 and Habitat5 models had AUC values of 0.923 and 0.913 in the training set and validation set, respectively, demonstrating good predictive ability. Calibration curves and decision curve analysis further validated the superiority and clinical application value of the model.

Conclusions: This study successfully constructed an accurate prediction model based on habitat subregions that can effectively predict the lymph node metastasis of ICC patients preoperatively. This model is expected to provide personalized decision support to clinicians and help to optimize treatment plans and improve patient outcomes.

{"title":"To accurately predict lymph node metastasis in patients with mass-forming intrahepatic cholangiocarcinoma by using CT radiomics features of tumor habitat subregions.","authors":"Pengyu Chen, Zhenwei Yang, Peigang Ning, Hao Yuan, Zuochao Qi, Qingshan Li, Bo Meng, Xianzhou Zhang, Haibo Yu","doi":"10.1186/s40644-025-00842-8","DOIUrl":"10.1186/s40644-025-00842-8","url":null,"abstract":"<p><strong>Background: </strong>This study aims to introduce the concept of habitat subregions and construct an accurate prediction model by analyzing refined medical images, to predict lymph node metastasis (LNM) in patients with intrahepatic cholangiocarcinoma (ICC) before surgery, and to provide personalized support for clinical decision-making.</p><p><strong>Methods: </strong>Clinical, radiological, and pathological data from ICC patients were retrospectively collected. Using information from the arterial and venous phases of multisequence CT images, tumor habitat subregions were delineated through the K-means clustering algorithm. Radiomic features were extracted and screened, and prediction models based on different subregions were constructed and compared with traditional intratumoral models. Finally, a lymph node metastasis prediction model was established by integrating the features of several subregional models, and its performance was evaluated.</p><p><strong>Results: </strong>A total of 164 ICC patients were included in this study, 103 of whom underwent lymph node dissection. The patients were divided into LNM- and LNM + groups on the basis of lymph node status, and significant differences in white blood cell indicators were found between the two groups. Survival analysis revealed that patients with positive lymph nodes had significantly worse prognoses. Through cluster analysis, the optimal number of habitat subregions was determined to be 5, and prediction models based on different subregions were constructed. A comparison of the performance of each model revealed that the Habitat1 and Habitat5 models had excellent performance. The optimal model obtained by fusing the features of the Habitat1 and Habitat5 models had AUC values of 0.923 and 0.913 in the training set and validation set, respectively, demonstrating good predictive ability. Calibration curves and decision curve analysis further validated the superiority and clinical application value of the model.</p><p><strong>Conclusions: </strong>This study successfully constructed an accurate prediction model based on habitat subregions that can effectively predict the lymph node metastasis of ICC patients preoperatively. This model is expected to provide personalized decision support to clinicians and help to optimize treatment plans and improve patient outcomes.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"19"},"PeriodicalIF":3.5,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11863903/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143514775","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}
引用次数: 0
期刊
Cancer Imaging
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1