Wei Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Wei Chen has a total of 317 co-authors. Here are the top co-authors by number of shared publications:
- Xiaoming Li
T Magnetic Resonance Translational Medicine Research Center, Department of Radiology, Southwest Hospital, Army Medical University (Third Military Medical University), Chongqing, China
8 shared publications Chen Liu
T Magnetic Resonance Imaging Translational Medical Center, Department of Radiology, Southwest Hospital, Army Medical University, Chongqing, China
7 shared publicationsPing Cai
T Magnetic Resonance Translational Medicine Research Center, Department of Radiology, Southwest Hospital, Army Medical University (Third Military Medical University), Chongqing, China
7 shared publicationsYiman Li
T Magnetic Resonance Translational Medicine Research Center Department of Radiology The First Affiliated Hospital of Army Medical University Chongqing China
7 shared publicationsJie Cheng
T Magnetic Resonance Imaging Translational Medical Center, Department of Radiology, Southwest Hospital, Army Medical University, Chongqing, China
6 shared publicationsPinzhen Chen
6 shared publications
Latest Publications
- Open Access
- 18 October 2026
- Published by Wiley in Advanced Science
Foundation Model‐Enabled Pathology‐Informed MRI Model for Preoperative Prediction of Vessels Encapsulating Tumor Clusters in Resectable Hepatocellular Carcinoma: A Multicenter Retrospective Study
Vessels encapsulating tumor clusters (VETC) are an aggressive vascular phenotype of hepatocellular carcinoma that is usually determined after surgery. A foundation model‐enabled framework for pathology‐informed VETC prediction on pretreatment magnetic resonance imaging (MRI), termed PIVOT, uses paired preoperative multiparametric MRI, postoperative hematoxylin and eosin whole‐slide images, and CD34 immunohistochemistry during model development, while inference requires only preoperative MRI. PIVOT‐MRI uses morphologic and vascular embedding alignment, and PIVOT‐Clinical combines the PIVOT‐MRI score with tumor size and alpha‐fetoprotein. The multicenter retrospective study includes 2052 patients in a training cohort, an internal test cohort, and four external validation cohorts. PIVOT‐MRI achieves an area under the receiver operating characteristic curve of 0.887 in the internal test cohort and 0.839‐0.861 across external cohorts. PIVOT‐Clinical increases the internal‐test area under the curve to 0.904 and PIVOT‐Clinical‐defined groups are associated with different two‐year recurrence risks. Removing both histopathologic alignment branches results in the largest ablation‐related performance decrease. Exploratory radiotranscriptomic analyses showed that higher PIVOT‐MRI scores were associated with angiogenesis‐related, endothelial, and proliferative transcriptional programs. PIVOT enables noninvasive preoperative assessment of pathology‐defined vascular aggressiveness in resectable hepatocellular carcinoma while preserving an MRI‐only clinical inference pathway.
- 18 October 2026
- Published by Wiley in Advanced Science
Open AccessFoundation Model‐Enabled Pathology‐Informed MRI Model for Preoperative Prediction of Vessels Encapsulating Tumor Clusters in Resectable Hepatocellular Carcinoma: A Multicenter Retrospective Study
Vessels encapsulating tumor clusters (VETC) are an aggressive vascular phenotype of hepatocellular carcinoma that is usually determined after surgery. A foundation model‐enabled framework for pathology‐informed VETC prediction on pretreatment magnetic resonance imaging (MRI), termed PIVOT, uses paired preoperative multiparametric MRI, postoperative hematoxylin and eosin whole‐slide images, and CD34 immunohistochemistry during model development, while inference requires only preoperative MRI. PIVOT‐MRI uses morphologic and vascular embedding alignment, and PIVOT‐Clinical combines the PIVOT‐MRI score with tumor size and alpha‐fetoprotein. The multicenter retrospective study includes 2052 patients in a training cohort, an internal test cohort, and four external validation cohorts. PIVOT‐MRI achieves an area under the receiver operating characteristic curve of 0.887 in the internal test cohort and 0.839‐0.861 across external cohorts. PIVOT‐Clinical increases the internal‐test area under the curve to 0.904 and PIVOT‐Clinical‐defined groups are associated with different two‐year recurrence risks. Removing both histopathologic alignment branches results in the largest ablation‐related performance decrease. Exploratory radiotranscriptomic analyses showed that higher PIVOT‐MRI scores were associated with angiogenesis‐related, endothelial, and proliferative transcriptional programs. PIVOT enables noninvasive preoperative assessment of pathology‐defined vascular aggressiveness in resectable hepatocellular carcinoma while preserving an MRI‐only clinical inference pathway.
- Open Access
- 9 October 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (20) , 3270
Non-Invasive Assessment of SMAD4 Expression Status in Pancreatic Ductal Adenocarcinoma: Diagnostic Value of T1ρ-Weighted Imaging Combined with Clinical Parameters
Background/Objectives: Pancreatic ductal adenocarcinoma (PDAC) is a malignancy with poor prognosis, where SMAD4 protein loss is closely associated with increased tumor aggressiveness and metastatic potential. Current assessment of SMAD4 expression relies on IHC of tumor tissue obtained by biopsy or resection, in which limited sampling may not represent intratumoral heterogeneity. T1ρ-weighted imaging, an emerging functional MRI technique, shows promise in characterizing tumor microstructural properties. This study aimed to evaluate the value of T1ρ imaging combined with conventional MRI sequences and clinical parameters for non-invasive prediction of SMAD4 protein expression status in PDAC. Methods: This retrospective single-center study included 57 patients with histologically confirmed PDAC who underwent pretreatment MRI with T1ρ imaging between September 2024 and May 2025. Immunohistochemical analysis revealed SMAD4 intact in 28 tumors (49.1%) and SMAD4 loss in 29 tumors (50.9%). T1ρ values were measured and compared between SMAD4 intact and SMAD4 loss tumors. A multiparametric predictive model incorporating T1ρ values, lymph node metastasis status, and carbohydrate antigen 19-9 (CA19-9) levels was developed. Results: SMAD4 intact tumors demonstrated significantly higher T1ρ values compared to SMAD4 loss tumors (96.34 ± 14.12 vs. 71.93 ± 10.24 ms, p < 0.001). T1ρ achieved an AUC of 0.901 (95% CI: 0.817–0.986), with 82.14% sensitivity and 89.66% specificity, for predicting SMAD4 expression status. A multiparametric model combining T1ρ values, lymph node metastasis status, and CA19-9 levels yielded a numerically higher AUC of 0.932 (95% CI: 0.862–1.000), although the difference from T1ρ alone was not statistically significant (DeLong test, p > 0.05). Conclusions: T1ρ imaging showed potential for predicting SMAD4 status in PDAC.
- 9 October 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (20) , 3270
Open AccessNon-Invasive Assessment of SMAD4 Expression Status in Pancreatic Ductal Adenocarcinoma: Diagnostic Value of T1ρ-Weighted Imaging Combined with Clinical Parameters
Background/Objectives: Pancreatic ductal adenocarcinoma (PDAC) is a malignancy with poor prognosis, where SMAD4 protein loss is closely associated with increased tumor aggressiveness and metastatic potential. Current assessment of SMAD4 expression relies on IHC of tumor tissue obtained by biopsy or resection, in which limited sampling may not represent intratumoral heterogeneity. T1ρ-weighted imaging, an emerging functional MRI technique, shows promise in characterizing tumor microstructural properties. This study aimed to evaluate the value of T1ρ imaging combined with conventional MRI sequences and clinical parameters for non-invasive prediction of SMAD4 protein expression status in PDAC. Methods: This retrospective single-center study included 57 patients with histologically confirmed PDAC who underwent pretreatment MRI with T1ρ imaging between September 2024 and May 2025. Immunohistochemical analysis revealed SMAD4 intact in 28 tumors (49.1%) and SMAD4 loss in 29 tumors (50.9%). T1ρ values were measured and compared between SMAD4 intact and SMAD4 loss tumors. A multiparametric predictive model incorporating T1ρ values, lymph node metastasis status, and carbohydrate antigen 19-9 (CA19-9) levels was developed. Results: SMAD4 intact tumors demonstrated significantly higher T1ρ values compared to SMAD4 loss tumors (96.34 ± 14.12 vs. 71.93 ± 10.24 ms, p < 0.001). T1ρ achieved an AUC of 0.901 (95% CI: 0.817–0.986), with 82.14% sensitivity and 89.66% specificity, for predicting SMAD4 expression status. A multiparametric model combining T1ρ values, lymph node metastasis status, and CA19-9 levels yielded a numerically higher AUC of 0.932 (95% CI: 0.862–1.000), although the difference from T1ρ alone was not statistically significant (DeLong test, p > 0.05). Conclusions: T1ρ imaging showed potential for predicting SMAD4 status in PDAC.
- Open Access
- 6 September 2026
- Published by Wiley in CNS Neuroscience & Therapeutics
- Vol. 32 (9) , e71039
Choroid Plexus Microstructural Alterations Link Glymphatic Dysfunction and White Matter Degeneration in Parkinson's Disease
Objectives: Glymphatic dysfunction is increasingly recognized as a key contributor to the progression of Parkinson's disease (PD). In PD, both choroid plexus (CP) alterations and white matter abnormalities have been linked to glymphatic dysfunction. However, how CP microstructural abnormalities relate to glymphatic function, corpus callosum (CC) degeneration, and clinical impairment remains unclear. This study aimed to investigate these associations in PD. Methods: Eighty‐one patients with idiopathic PD and eighty age‐ and sex‐matched healthy controls (HC) underwent MRI scanning. CP microstructural metrics (free water [FW], FW‐corrected fractional anisotropy [FA FWcorr ] and FW‐corrected mean diffusivity [MD FWcorr ]) were extracted, along with the diffusion tensor image analysis along the perivascular space (DTI‐ALPS) index and CC subregional volumes. Group comparisons, partial correlation, multiple linear regression, and mediation analyses were performed. Results: Patients with PD showed significantly higher CP FW and MD FWcorr values and a lower DTI‐ALPS index than HC. Higher CP MD FWcorr was associated with worse motor symptoms and poorer cognitive performance after covariate adjustment. Mediation analysis suggested that the ALPS index mediated the associations between CP microstructural alterations and CC subregional volumes. Conclusions: CP microstructural abnormalities were associated with DTI‐ALPS alterations, CC degeneration, and clinical impairment in PD. FW‐DTI metrics of the CP may provide useful imaging markers for characterizing CP‐related changes in PD.
- 6 September 2026
- Published by Wiley in CNS Neuroscience & Therapeutics
- Vol. 32 (9) , e71039
Open AccessChoroid Plexus Microstructural Alterations Link Glymphatic Dysfunction and White Matter Degeneration in Parkinson's Disease
Objectives: Glymphatic dysfunction is increasingly recognized as a key contributor to the progression of Parkinson's disease (PD). In PD, both choroid plexus (CP) alterations and white matter abnormalities have been linked to glymphatic dysfunction. However, how CP microstructural abnormalities relate to glymphatic function, corpus callosum (CC) degeneration, and clinical impairment remains unclear. This study aimed to investigate these associations in PD. Methods: Eighty‐one patients with idiopathic PD and eighty age‐ and sex‐matched healthy controls (HC) underwent MRI scanning. CP microstructural metrics (free water [FW], FW‐corrected fractional anisotropy [FA FWcorr ] and FW‐corrected mean diffusivity [MD FWcorr ]) were extracted, along with the diffusion tensor image analysis along the perivascular space (DTI‐ALPS) index and CC subregional volumes. Group comparisons, partial correlation, multiple linear regression, and mediation analyses were performed. Results: Patients with PD showed significantly higher CP FW and MD FWcorr values and a lower DTI‐ALPS index than HC. Higher CP MD FWcorr was associated with worse motor symptoms and poorer cognitive performance after covariate adjustment. Mediation analysis suggested that the ALPS index mediated the associations between CP microstructural alterations and CC subregional volumes. Conclusions: CP microstructural abnormalities were associated with DTI‐ALPS alterations, CC degeneration, and clinical impairment in PD. FW‐DTI metrics of the CP may provide useful imaging markers for characterizing CP‐related changes in PD.
- Open Access
- 23 July 2026
- Published by Springer Nature in BMC Medical Imaging
- Vol. 26 (1)
Prenatal MRI quantitative analysis of the nonlinear morphological changes of the choroid plexus during the progression of fetal ventriculomegaly
To quantify fetal choroid plexus (CP) morphological changes across ventriculomegaly (VM) grades using routine 1.5-T MRI and assess their association with l
- 23 July 2026
- Published by Springer Nature in BMC Medical Imaging
- Vol. 26 (1)
Open AccessPrenatal MRI quantitative analysis of the nonlinear morphological changes of the choroid plexus during the progression of fetal ventriculomegaly
To quantify fetal choroid plexus (CP) morphological changes across ventriculomegaly (VM) grades using routine 1.5-T MRI and assess their association with l
- Open Access
- 6 July 2026
- Published by Wiley in CNS Neuroscience & Therapeutics
- Vol. 32 (7) , e71016
Mapping the Disrupted Connectome in Spinocerebellar Ataxia Type 3: A Network‐Based Statistics Study Identifying Novel Therapeutic Targets for Neuromodulation
Aims: Spinocerebellar ataxia type 3 (SCA3) is characterized by progressive neurodegeneration. This study aimed to map alterations in structural and functional connectivity (SC and FC) in SCA3 using network‐based statistics (NBS) and to explore the potential of transcranial magnetic stimulation (TMS) for modulating these aberrant networks and identifying novel therapeutic targets. Methods: NBS was used to compare SC and FC between a large cohort of 117 SCA3 patients and 163 healthy controls (HCs). Partial correlation analysis examined the associations between altered connectivity and clinical variables (CAG repeat length, disease duration, and clinical scale scores). Additionally, paired t ‐tests were used to evaluate longitudinal brain connectivity changes in 58 patients before and after TMS intervention to assess therapeutic effects. Results: SCA3 patients exhibited a distinct disconnection–compensation pattern, characterized by significantly reduced SC and elevated FC within the subcortical (SUB), sensorimotor (SMN), and dorsal attention (DAN) networks. SC between the frontoparietal network (FPN) and SUB was abnormally increased and positively correlated with both disease duration and CAG repeat length, whereas intra‐SUB SC was negatively correlated with disease duration. Following TMS intervention, SC strength in two pathways that were abnormally enhanced at baseline was significantly attenuated. Conclusion: Our findings reveal extensive connectome reorganization in SCA3. The correlations between SC abnormalities and clinical metrics, coupled with the modulatory effects of TMS, suggest that network‐based metrics can serve as biomarkers and guide the development of personalized neuromodulation strategies for SCA3. Trial Registration: (ChiCTR) 1800019901, 2000039434, 2500095738.
- 6 July 2026
- Published by Wiley in CNS Neuroscience & Therapeutics
- Vol. 32 (7) , e71016
Open AccessMapping the Disrupted Connectome in Spinocerebellar Ataxia Type 3: A Network‐Based Statistics Study Identifying Novel Therapeutic Targets for Neuromodulation
Aims: Spinocerebellar ataxia type 3 (SCA3) is characterized by progressive neurodegeneration. This study aimed to map alterations in structural and functional connectivity (SC and FC) in SCA3 using network‐based statistics (NBS) and to explore the potential of transcranial magnetic stimulation (TMS) for modulating these aberrant networks and identifying novel therapeutic targets. Methods: NBS was used to compare SC and FC between a large cohort of 117 SCA3 patients and 163 healthy controls (HCs). Partial correlation analysis examined the associations between altered connectivity and clinical variables (CAG repeat length, disease duration, and clinical scale scores). Additionally, paired t ‐tests were used to evaluate longitudinal brain connectivity changes in 58 patients before and after TMS intervention to assess therapeutic effects. Results: SCA3 patients exhibited a distinct disconnection–compensation pattern, characterized by significantly reduced SC and elevated FC within the subcortical (SUB), sensorimotor (SMN), and dorsal attention (DAN) networks. SC between the frontoparietal network (FPN) and SUB was abnormally increased and positively correlated with both disease duration and CAG repeat length, whereas intra‐SUB SC was negatively correlated with disease duration. Following TMS intervention, SC strength in two pathways that were abnormally enhanced at baseline was significantly attenuated. Conclusion: Our findings reveal extensive connectome reorganization in SCA3. The correlations between SC abnormalities and clinical metrics, coupled with the modulatory effects of TMS, suggest that network‐based metrics can serve as biomarkers and guide the development of personalized neuromodulation strategies for SCA3. Trial Registration: (ChiCTR) 1800019901, 2000039434, 2500095738.
- Open Access
- 1 July 2026
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 16 (7) , 543
7.0 Tesla MRI in fetal autopsy: a preliminary exploration of integrating image optimization with clinical practice in a multidisciplinary workflow
Original Article 7.0 Tesla MRI in fetal autopsy: a preliminary exploration of integrating image optimization with clinical practice in a multidisciplinary workflow Yuhan Zhang, Zhiming Zhen, Ping Cai, Limei Wang, Dan Wang, Chen Liu, Wei Chen, Wei Chen, Mingshan Du
- 1 July 2026
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 16 (7) , 543
Open Access7.0 Tesla MRI in fetal autopsy: a preliminary exploration of integrating image optimization with clinical practice in a multidisciplinary workflow
Original Article 7.0 Tesla MRI in fetal autopsy: a preliminary exploration of integrating image optimization with clinical practice in a multidisciplinary workflow Yuhan Zhang, Zhiming Zhen, Ping Cai, Limei Wang, Dan Wang, Chen Liu, Wei Chen, Wei Chen, Mingshan Du
- 29 June 2026
- Published by Wiley in Movement Disorders
- Vol. 41 (10) , 2650-2661
Putamen Structural–Functional Decoupling as an Early‐Stage Candidate Imaging Marker for Motor Severity in Spinocerebellar Ataxia Type 3
Background: Spinocerebellar ataxia type 3 (SCA3) shows marked phenotypic heterogeneity and clinico‐radiological dissociation, wherein macrostructural atrophy often fails to fully account for clinical severity. Although structural and functional connectivity abnormalities are well recognized, their potential interaction and neurobiological mechanisms remain poorly understood. Objective: This study aimed to identify potential biomarkers for SCA3 by linking structural connectivity–functional connectivity ( SC – FC ) coupling to mitochondrial function, neurotransmitter distribution, and gene expression. Methods: This dual‐center study included discovery (117 SCA3, 163 healthy controls [HC]) and independent validation (24 SCA3, 48 HC) cohorts. [Correction added after first online publication on 8 July 2026: The number of healthy controls has been updated in the previous sentence.] Participants underwent multimodal 3 T magnetic resonance imaging (MRI) and clinical assessments (Scale for the Assessment and Rating of Ataxia [SARA]; International Cooperative Ataxia Rating Scale [ICARS]; Montreal Cognitive Assessment [MoCA]; Hamilton Depression Rating Scale [HAMD]). Regional and network‐level SC–FC coupling was quantified using multiple regression and compared across disease‐duration strata. Coupling alterations were spatially mapped to biological atlases (Allen Human Brain Atlas, MitoBrainMap, and positron emission tomography [PET]‐based neurotransmitter receptor atlases) using bootstrapped Spearman's correlations (false discovery rate [FDR]‐corrected). Gene enrichment analysis was implemented to characterize enriched biological pathways. Results: SCA3 patients exhibited significant, atrophy‐independent SC–FC decoupling in the bilateral dorsolateral putamen (dlPu), which correlated with ICARS scores. This decoupling pattern spatially aligned with mitochondrial complex II, 5‐HT2A/5‐HT4 receptors densities, and genes enriching for synaptic regulation and cellular homeostasis. Conclusions: By integrating SC–FC coupling with biological atlases, this study reveals the pathological underpinnings of clinico‐radiological dissociation in SCA3 and identifies dlPu decoupling as a promising early‐stage candidate imaging marker, providing an early and objective target for future neuroprotective trials. Trial Registration: Chinese Clinical Trial Registry (ChiCTR): 1800019901, 2000039434. © 2026 International Parkinson and Movement Disorder Society.
- 29 June 2026
- Published by Wiley in Movement Disorders
- Vol. 41 (10) , 2650-2661
Putamen Structural–Functional Decoupling as an Early‐Stage Candidate Imaging Marker for Motor Severity in Spinocerebellar Ataxia Type 3
Background: Spinocerebellar ataxia type 3 (SCA3) shows marked phenotypic heterogeneity and clinico‐radiological dissociation, wherein macrostructural atrophy often fails to fully account for clinical severity. Although structural and functional connectivity abnormalities are well recognized, their potential interaction and neurobiological mechanisms remain poorly understood. Objective: This study aimed to identify potential biomarkers for SCA3 by linking structural connectivity–functional connectivity ( SC – FC ) coupling to mitochondrial function, neurotransmitter distribution, and gene expression. Methods: This dual‐center study included discovery (117 SCA3, 163 healthy controls [HC]) and independent validation (24 SCA3, 48 HC) cohorts. [Correction added after first online publication on 8 July 2026: The number of healthy controls has been updated in the previous sentence.] Participants underwent multimodal 3 T magnetic resonance imaging (MRI) and clinical assessments (Scale for the Assessment and Rating of Ataxia [SARA]; International Cooperative Ataxia Rating Scale [ICARS]; Montreal Cognitive Assessment [MoCA]; Hamilton Depression Rating Scale [HAMD]). Regional and network‐level SC–FC coupling was quantified using multiple regression and compared across disease‐duration strata. Coupling alterations were spatially mapped to biological atlases (Allen Human Brain Atlas, MitoBrainMap, and positron emission tomography [PET]‐based neurotransmitter receptor atlases) using bootstrapped Spearman's correlations (false discovery rate [FDR]‐corrected). Gene enrichment analysis was implemented to characterize enriched biological pathways. Results: SCA3 patients exhibited significant, atrophy‐independent SC–FC decoupling in the bilateral dorsolateral putamen (dlPu), which correlated with ICARS scores. This decoupling pattern spatially aligned with mitochondrial complex II, 5‐HT2A/5‐HT4 receptors densities, and genes enriching for synaptic regulation and cellular homeostasis. Conclusions: By integrating SC–FC coupling with biological atlases, this study reveals the pathological underpinnings of clinico‐radiological dissociation in SCA3 and identifies dlPu decoupling as a promising early‐stage candidate imaging marker, providing an early and objective target for future neuroprotective trials. Trial Registration: Chinese Clinical Trial Registry (ChiCTR): 1800019901, 2000039434. © 2026 International Parkinson and Movement Disorder Society.
- Open Access
- 8 May 2026
- Published by Frontiers Media SA in Frontiers in Immunology
- Vol. 17, 1806601
MRI-based clinicoradiologic model for identifying MT-HCC with distinct postoperative prognosis and potential association with postoperative TKI-ICI therapy
Background: This study aims to develop a non-invasive MRI-based clinicoradiologic model for predicting microvascular invasion-positive (MVI+) and tertiary lymphoid structures-positive (TLSs+) hepatocellular carcinoma (HCC) and to explore whether this subgroup is associated with different postoperative outcomes and a potential differential association with postoperative TKI-ICI combination therapy. Methods: A retrospective analysis was conducted on 338 HCC patients across two centers, stratified by MVI and TLSs status, and divided into training (n=237) and validation (n=101) cohorts. MRI features such as tumor size, hemorrhage, and capsule, were assessed. Model performance was assessed using the area under the receiver operating characteristic curve (AUC). Kaplan-Meier curves were used to compare recurrence-free survival (RFS). Results: The MRI-based clinicoradiologic model for predicting MVI+/TLSs+ HCC (MT-HCC) integrated AFP levels and MRI features, including absence of intratumoral hemorrhage, incomplete capsule, and mosaic structure, achieved an AUC of 0.831 in the validation cohort. In exploratory analyses, the model-predicted MT-HCC group showed a shorter RFS than the model-predicted non-MT-HCC group among patients without postoperative TKI-ICI exposure (p = 0.002), whereas a different RFS pattern was observed among patients with postoperative TKI-ICI exposure (p = 0.017). Conclusion: The MRI-based clinicoradiologic model may help identify MT-HCC preoperatively and may help identify a subgroup with distinct postoperative prognosis and a possible differential outcome pattern according to postoperative TKI-ICI exposure.
- 8 May 2026
- Published by Frontiers Media SA in Frontiers in Immunology
- Vol. 17, 1806601
Open AccessMRI-based clinicoradiologic model for identifying MT-HCC with distinct postoperative prognosis and potential association with postoperative TKI-ICI therapy
Background: This study aims to develop a non-invasive MRI-based clinicoradiologic model for predicting microvascular invasion-positive (MVI+) and tertiary lymphoid structures-positive (TLSs+) hepatocellular carcinoma (HCC) and to explore whether this subgroup is associated with different postoperative outcomes and a potential differential association with postoperative TKI-ICI combination therapy. Methods: A retrospective analysis was conducted on 338 HCC patients across two centers, stratified by MVI and TLSs status, and divided into training (n=237) and validation (n=101) cohorts. MRI features such as tumor size, hemorrhage, and capsule, were assessed. Model performance was assessed using the area under the receiver operating characteristic curve (AUC). Kaplan-Meier curves were used to compare recurrence-free survival (RFS). Results: The MRI-based clinicoradiologic model for predicting MVI+/TLSs+ HCC (MT-HCC) integrated AFP levels and MRI features, including absence of intratumoral hemorrhage, incomplete capsule, and mosaic structure, achieved an AUC of 0.831 in the validation cohort. In exploratory analyses, the model-predicted MT-HCC group showed a shorter RFS than the model-predicted non-MT-HCC group among patients without postoperative TKI-ICI exposure (p = 0.002), whereas a different RFS pattern was observed among patients with postoperative TKI-ICI exposure (p = 0.017). Conclusion: The MRI-based clinicoradiologic model may help identify MT-HCC preoperatively and may help identify a subgroup with distinct postoperative prognosis and a possible differential outcome pattern according to postoperative TKI-ICI exposure.