MRI-based intra-tumoral ecological diversity features and temporal characteristics for predicting microvascular invasion in hepatocellular carcinoma
ObjectiveTo investigate the predictive value of radiomics models based on intra-tumoral ecological diversity (iTED) and temporal characteristics for assessing microvascular invasion (MVI) in patients with hepatocellular carcinoma (HCC).Material and MethodsWe retrospectively analyzed the data of 398...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-03-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2025.1510071/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850179975094730752 |
|---|---|
| author | Yuli Zeng Huiqin Wu Yanqiu Zhu Chao Li Dongyang Du Yang Song Sulian Su Jie Qin Guihua Jiang Guihua Jiang Guihua Jiang |
| author_facet | Yuli Zeng Huiqin Wu Yanqiu Zhu Chao Li Dongyang Du Yang Song Sulian Su Jie Qin Guihua Jiang Guihua Jiang Guihua Jiang |
| author_sort | Yuli Zeng |
| collection | DOAJ |
| description | ObjectiveTo investigate the predictive value of radiomics models based on intra-tumoral ecological diversity (iTED) and temporal characteristics for assessing microvascular invasion (MVI) in patients with hepatocellular carcinoma (HCC).Material and MethodsWe retrospectively analyzed the data of 398 HCC patients who underwent dynamic contrast-enhanced MRI with Gd-EOB-DTPA (training set: 318; testing set: 80). The tumors were segmented into five distinct habitats using case-level clustering and a Gaussian mixture model was used to determine the optimal clusters based on the Bayesian information criterion to produce an iTED feature vector for each patient, which was used to assess intra-tumoral heterogeneity. Radiomics models were developed using iTED features from the arterial phase (AP), portal venous phase (PVP), and hepatobiliary phase (HBP), referred to as MiTED-AP, MiTED-PVP, and MiTED-HBP, respectively. Additionally, temporal features were derived by subtracting the PVP features from the AP features, creating a delta-radiomics model (MDelta). Conventional radiomics features were also extracted from the AP, PVP, and HBP images, resulting in three models: MCVT-AP, MCVT-PVP, and MCVT-HBP. A clinical-radiological model (CR model) was constructed, and two fusion models were generated by combining the radiomics or/and CR models using a stacking algorithm (fusion_R and fusion_CR). Model performance was evaluated using AUC, accuracy, sensitivity, and specificity.ResultsThe MDelta model demonstrated higher sensitivity compared to the MCVT-AP and MCVT-PVP models. No significant differences in performance were observed across different imaging phases for either conventional radiomics (p = 0.096–0.420) or iTED features (p = 0.106–0.744). Similarly, for images from the same phase, we found no significant differences between the performance of conventional radiomics and iTED features (AP: p = 0.158; PVP: p = 0.844; HBP: p = 0.157). The fusion_R and fusion_CR models enhanced MVI discrimination, achieving AUCs of 0.823 (95% CI: 0.816–0.831) and 0.830 (95% CI: 0.824–0.835), respectively.ConclusionDelta radiomics features are temporal and predictive of MVI, providing additional predictive information for MVI beyond conventional AP and PVP features. The iTED features provide an alternative perspective in interpreting tumor characteristics and hold the potential to replace conventional radiomics features to some extent for MVI prediction. |
| format | Article |
| id | doaj-art-9e9cd26c96294dd4b85d3ae135ddbb94 |
| institution | OA Journals |
| issn | 2234-943X |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj-art-9e9cd26c96294dd4b85d3ae135ddbb942025-08-20T02:18:20ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2025-03-011510.3389/fonc.2025.15100711510071MRI-based intra-tumoral ecological diversity features and temporal characteristics for predicting microvascular invasion in hepatocellular carcinomaYuli Zeng0Huiqin Wu1Yanqiu Zhu2Chao Li3Dongyang Du4Yang Song5Sulian Su6Jie Qin7Guihua Jiang8Guihua Jiang9Guihua Jiang10Department of Medical Imaging, The Affiliated Guangdong Second Provincial General Hospital of Jinan University, Guangzhou, Guangdong, ChinaDepartment of Medical Imaging, The Affiliated Guangdong Second Provincial General Hospital of Jinan University, Guangzhou, Guangdong, ChinaDepartment of Radiology, Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, Guangdong, ChinaDepartment of Radiology, Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, Guangdong, ChinaSchool of Computer Science, Inner Mongolia University, Inner Mongolia, ChinaMagnetic Resonance (MR) Scientific Marketing, Siemens Healthineers Ltd., Shanghai, ChinaDepartment of Radiology, Xiamen Humanity Hospital of Fujian Medical University, Xiamen, Fujian, ChinaDepartment of Radiology, Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, Guangdong, ChinaDepartment of Medical Imaging, The Affiliated Guangdong Second Provincial General Hospital of Jinan University, Guangzhou, Guangdong, ChinaDepartment of Radiology, Xiamen Humanity Hospital of Fujian Medical University, Xiamen, Fujian, ChinaGuangzhou Key Laboratory of Molecular Functional Imaging and Artificial Intelligence for Major Brain Diseases, Guangdong Second Provincial General Hospital, Guangzhou, Guangdong, ChinaObjectiveTo investigate the predictive value of radiomics models based on intra-tumoral ecological diversity (iTED) and temporal characteristics for assessing microvascular invasion (MVI) in patients with hepatocellular carcinoma (HCC).Material and MethodsWe retrospectively analyzed the data of 398 HCC patients who underwent dynamic contrast-enhanced MRI with Gd-EOB-DTPA (training set: 318; testing set: 80). The tumors were segmented into five distinct habitats using case-level clustering and a Gaussian mixture model was used to determine the optimal clusters based on the Bayesian information criterion to produce an iTED feature vector for each patient, which was used to assess intra-tumoral heterogeneity. Radiomics models were developed using iTED features from the arterial phase (AP), portal venous phase (PVP), and hepatobiliary phase (HBP), referred to as MiTED-AP, MiTED-PVP, and MiTED-HBP, respectively. Additionally, temporal features were derived by subtracting the PVP features from the AP features, creating a delta-radiomics model (MDelta). Conventional radiomics features were also extracted from the AP, PVP, and HBP images, resulting in three models: MCVT-AP, MCVT-PVP, and MCVT-HBP. A clinical-radiological model (CR model) was constructed, and two fusion models were generated by combining the radiomics or/and CR models using a stacking algorithm (fusion_R and fusion_CR). Model performance was evaluated using AUC, accuracy, sensitivity, and specificity.ResultsThe MDelta model demonstrated higher sensitivity compared to the MCVT-AP and MCVT-PVP models. No significant differences in performance were observed across different imaging phases for either conventional radiomics (p = 0.096–0.420) or iTED features (p = 0.106–0.744). Similarly, for images from the same phase, we found no significant differences between the performance of conventional radiomics and iTED features (AP: p = 0.158; PVP: p = 0.844; HBP: p = 0.157). The fusion_R and fusion_CR models enhanced MVI discrimination, achieving AUCs of 0.823 (95% CI: 0.816–0.831) and 0.830 (95% CI: 0.824–0.835), respectively.ConclusionDelta radiomics features are temporal and predictive of MVI, providing additional predictive information for MVI beyond conventional AP and PVP features. The iTED features provide an alternative perspective in interpreting tumor characteristics and hold the potential to replace conventional radiomics features to some extent for MVI prediction.https://www.frontiersin.org/articles/10.3389/fonc.2025.1510071/fullintra-tumoral heterogeneitytemporal featuresmicrovascular invasionradiomicsensemble learning |
| spellingShingle | Yuli Zeng Huiqin Wu Yanqiu Zhu Chao Li Dongyang Du Yang Song Sulian Su Jie Qin Guihua Jiang Guihua Jiang Guihua Jiang MRI-based intra-tumoral ecological diversity features and temporal characteristics for predicting microvascular invasion in hepatocellular carcinoma Frontiers in Oncology intra-tumoral heterogeneity temporal features microvascular invasion radiomics ensemble learning |
| title | MRI-based intra-tumoral ecological diversity features and temporal characteristics for predicting microvascular invasion in hepatocellular carcinoma |
| title_full | MRI-based intra-tumoral ecological diversity features and temporal characteristics for predicting microvascular invasion in hepatocellular carcinoma |
| title_fullStr | MRI-based intra-tumoral ecological diversity features and temporal characteristics for predicting microvascular invasion in hepatocellular carcinoma |
| title_full_unstemmed | MRI-based intra-tumoral ecological diversity features and temporal characteristics for predicting microvascular invasion in hepatocellular carcinoma |
| title_short | MRI-based intra-tumoral ecological diversity features and temporal characteristics for predicting microvascular invasion in hepatocellular carcinoma |
| title_sort | mri based intra tumoral ecological diversity features and temporal characteristics for predicting microvascular invasion in hepatocellular carcinoma |
| topic | intra-tumoral heterogeneity temporal features microvascular invasion radiomics ensemble learning |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2025.1510071/full |
| work_keys_str_mv | AT yulizeng mribasedintratumoralecologicaldiversityfeaturesandtemporalcharacteristicsforpredictingmicrovascularinvasioninhepatocellularcarcinoma AT huiqinwu mribasedintratumoralecologicaldiversityfeaturesandtemporalcharacteristicsforpredictingmicrovascularinvasioninhepatocellularcarcinoma AT yanqiuzhu mribasedintratumoralecologicaldiversityfeaturesandtemporalcharacteristicsforpredictingmicrovascularinvasioninhepatocellularcarcinoma AT chaoli mribasedintratumoralecologicaldiversityfeaturesandtemporalcharacteristicsforpredictingmicrovascularinvasioninhepatocellularcarcinoma AT dongyangdu mribasedintratumoralecologicaldiversityfeaturesandtemporalcharacteristicsforpredictingmicrovascularinvasioninhepatocellularcarcinoma AT yangsong mribasedintratumoralecologicaldiversityfeaturesandtemporalcharacteristicsforpredictingmicrovascularinvasioninhepatocellularcarcinoma AT suliansu mribasedintratumoralecologicaldiversityfeaturesandtemporalcharacteristicsforpredictingmicrovascularinvasioninhepatocellularcarcinoma AT jieqin mribasedintratumoralecologicaldiversityfeaturesandtemporalcharacteristicsforpredictingmicrovascularinvasioninhepatocellularcarcinoma AT guihuajiang mribasedintratumoralecologicaldiversityfeaturesandtemporalcharacteristicsforpredictingmicrovascularinvasioninhepatocellularcarcinoma AT guihuajiang mribasedintratumoralecologicaldiversityfeaturesandtemporalcharacteristicsforpredictingmicrovascularinvasioninhepatocellularcarcinoma AT guihuajiang mribasedintratumoralecologicaldiversityfeaturesandtemporalcharacteristicsforpredictingmicrovascularinvasioninhepatocellularcarcinoma |