Cancer Imaging最新文献

Background: This study aimed to develop a predictive model integrating multi-sequence MRI radiomics, deep learning features, and habitat imaging to forecast pathological complete response (pCR) in breast cancer patients undergoing neoadjuvant therapy (NAT).

Methods: A retrospective analysis included 203 breast cancer patients treated with NAT from May 2018 to January 2023. Patients were divided into training (n = 162) and test (n = 41) sets. Radiomics features were extracted from intratumoral and peritumoral regions in multi-sequence MRI (T2WI, DWI, and DCE-MRI) datasets. Habitat imaging was employed to analyze tumor subregions, characterizing heterogeneity within the tumor. We constructed and validated machine learning models, including a fusion model integrating all features, using Receiver Operating Characteristic (ROC) and Precision-Recall (PR) curves, decision curve analysis (DCA), and confusion matrices. Shapley Additive Explanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) analyses were performed for model interpretability.

Results: The fusion model achieved superior predictive performance compared to single-region models, with AUCs of 0.913 (95% CI: 0.770-1.000) in the test set. PR curve analysis showed improved precision-recall balance, while DCA indicated higher clinical benefit. Confusion matrix analysis confirmed the model's classification accuracy. SHAP revealed DCE_LLL_DependenceUniformity as the most critical feature for predicting pCR and PC72 for non-pCR. LIME provided patient-specific insights into feature contributions.

Conclusion: Integrating multi-dimensional MRI features with habitat imaging enhances pCR prediction in breast cancer. The fusion model offers a robust, non-invasive tool for guiding individualized treatment strategies while providing transparent interpretability through SHAP and LIME analyses.

Background: Pathologically, intrahepatic cholangiocarcinoma (ICC) is classified into small-duct (SD) type and large-duct (LD) type, each with distinct clinicopathological characteristics. The contrast-enhanced ultrasound (CEUS) features of the two ICC types remain insufficiently explored.

Purpose: To evaluate liver CEUS imaging for differentiating the SD and LD types of ICC and further compare them with poorly differentiated hepatocellular carcinoma (pHCC).

Materials and methods: A single-center retrospective study enrolled 252 patients with SD-type ICC, LD-type ICC, or pHCC between October 2017 and August 2023. Logistic regression analyses identified independent clinical, pathological, ultrasound, and CEUS predictors. Based on these features, a decision tree-based diagnostic model was developed. The model's performance was evaluated using receiver operating characteristic (ROC) curve analysis in both the training and validation cohorts, as well as in subgroup stratified by tumor size ≤ 5 cm and > 5 cm. Differences in overall survival (OS) and recurrence-free survival (RFS) based on the model were further analyzed.

Results: Overall, 252 patients (mean age, 58.4 ± 10.7 years; 174 males) with 140 SD-type ICC, 55 LD-type ICC and 57 pHCC were enrolled. Multivariate analysis revealed that AFP, CEA, CA19-9, HBsAg status, arterial phase enhancement pattern, washout time ≤ 45 s, and marked washout were independent predictors for tumor categories differentiation (all P <.05). The decision tree-based model incorporating the major features demonstrated excellent performance in both the training cohort (AUC 0.89) and validation cohort (AUC 0.88), as well as in tumor size ≤ 5 cm (AUC 0.90) and > 5 cm (AUC 0.84). OS was significantly worse in LD-type ICC patients compared to SD-type and pHCC (P <.05 for both), while RFS showed no significant difference.

Conclusions: A user-friendly, decision tree-based diagnostic model was developed to accurately predict ICC subtypes and pHCC, facilitating improved clinical decision-making. The decision tree-based diagnostic model effectively diagnosed small-duct type and large-duct type intrahepatic cholangiocarcinoma, as well as poorly differentiated hepatocellular carcinoma.

Background: Machine learning (ML) applied to radiomics has revolutionized neuro-oncological imaging, yet the diagnostic performance of ML models based specifically on ^18F-FDG PET features in glioma remains poorly characterized.

Objective: To systematically evaluate and quantitatively synthesize the diagnostic accuracy of ML models trained on ^18F-FDG PET radiomics for glioma classification.

Methods: We conducted a PRISMA-compliant systematic review and meta-analysis registered on OSF ( https://doi.org/10.17605/OSF.IO/XJG6P ). PubMed, Scopus, and Web of Science were searched up to January 2025. Studies were included if they applied ML algorithms to ^18F-FDG PET radiomic features for glioma classification and reported at least one performance metric. Data extraction included demographics, imaging protocols, feature types, ML models, and validation design. Meta-analysis was performed using random-effects models with pooled estimates of accuracy, sensitivity, specificity, AUC, F1 score, and precision. Heterogeneity was explored via meta-regression and Galbraith plots.

Results: Twelve studies comprising 2,321 patients were included. Pooled diagnostic metrics were: accuracy 92.6% (95% CI: 91.3-93.9%), AUC 0.95 (95% CI: 0.94-0.95), sensitivity 85.4%, specificity 89.7%, F1 score 0.78, and precision 0.90. Heterogeneity was high across all domains (I² >75%). Meta-regression identified ML model type and validation strategy as partial moderators. Models using CNNs or PET/MRI integration achieved superior performance.

Conclusion: ML models based on ^18F-FDG PET radiomics demonstrate strong and balanced diagnostic performance for glioma classification. However, methodological heterogeneity underscores the need for standardized pipelines, external validation, and transparent reporting before clinical integration.

Background: Accurate preoperative assessment of occult lymph node metastasis (OLNM) plays a crucial role in informing therapeutic decision-making for lung cancer patients. Computed tomography (CT) is the most widely used imaging modality for preoperative work-up. The aim of this study was to develop and validate a CT-based machine learning model integrating intra-and peri-tumoral features to predict OLNM in lung cancer patients.

Methods: Eligible patients with peripheral lung cancer confirmed by radical surgical excision with systematic lymphadenectomy were retrospectively recruited from January 2019 to December 2021. 1688 radiomics features were obtained from each manually segmented VOI which was composed of gross tumor volume (GTV) covering the boundary of entire tumor and three peritumoral volumes (PTV3, PTV6 and PTV9) that capture the region outside the tumor. A clinical-radiomics model incorporating radiomics signature, independent clinical factors and CT semantic features was established via multivariable logistic regression analysis and presented as a nomogram. Model performance was evaluated by discrimination, calibration, and clinical utility.

Results: Overall, 591 patients were recruited in the training cohort and 253 in the validation cohort. The radiomics signature of PTV9 showed superior diagnostic performance compared to PTV3 and PTV6 models. Integrating GPTV radiomics signature (incorporating Rad-score of GTV and PTV9) with clinical risk factor of serum CEA levels and CT imaging features of lobulation sign and tumor-pleura relationship demonstrated favorable accuracy in predicting OLNM in the training cohort (AUC, 0.819; 95% CI: 0.780-0.857) and validation cohort (AUC, 0.801; 95% CI: 0.741-0.860). The predictive performance of the clinical-radiomics model demonstrated statistically significant superiority over that of the clinical model in both cohorts (all p < 0.05).

Conclusions: The clinical-radiomics model was able to serve as a noninvasive preoperative prediction tool for personalized risk assessment of OLNM in peripheral lung cancer patients.

Background: According to PI-RADS v2.1, peripheral PI-RADS 3 lesions are upgraded to PI-RADS 4 if dynamic contrast-enhanced MRI is positive (3+1 lesions), however those lesions are radiologically challenging. We aimed to define criteria by expert consensus and test applicability by other radiologists for sPC prediction of PI-RADS 3+1 lesions and determine their value in integrated regression models.

Methods: From consecutive 3 Tesla MR examinations performed between 08/2016 to 12/2018 we identified 85 MRI examinations from 83 patients with a total of 94 PI-RADS 3+1 lesions in the official clinical report. Lesions were retrospectively assessed by expert consensus with construction of a newly devised feature catalogue which was utilized subsequently by two additional radiologists specialized in prostate MRI for independent lesion assessment. With reference to extended fused targeted and systematic TRUS/MRI-biopsy histopathological correlation, relevant catalogue features were identified by univariate analysis and put into context to typically available clinical features and automated AI image assessment utilizing lasso-penalized logistic regression models, also focusing on the contribution of DCE imaging (feature-based, bi- and multiparametric AI-enhanced and solely bi- and multiparametric AI-driven).

Results: The feature catalog enabled image-based lesional risk stratification for all readers. Expert consensus provided 3 significant features in univariate analysis (adj. p-value <0.05; most relevant feature T2w configuration: "irregular/microlobulated/spiculated", OR 9.0 (95%CI 2.3-44.3); adj. p-value: 0.016). These remained after lasso penalized regression based feature reduction, while the only selected clinical feature was prostate volume (OR<1), enabling nomogram construction. While DCE-derived consensus features did not enhance model performance (bootstrapped AUC), there was a trend for increased performance by including multiparametric AI, but not biparametric AI into models, both for combined and AI-only models.

Conclusions: PI-RADS 3+1 lesions can be risk-stratified using lexicon terms and a key feature nomogram. AI potentially benefits more from DCE imaging than experienced prostate radiologists.

Clinical trial number: Not applicable.

Objective: This study aimed to construct a multimodal imaging deep learning (DL) model integrating mpMRI and ¹⁸F-PSMA-PET/CT for the prediction of extraprostatic extension (EPE) in prostate cancer, and to assess its effectiveness in enhancing the diagnostic accuracy of radiologists.

Methods: Clinical and imaging data were retrospectively collected from patients with pathologically confirmed prostate cancer (PCa) who underwent radical prostatectomy (RP). Data were collected from a primary institution (Center 1, n = 197) between January 2019 and June 2022 and an external institution (Center 2, n = 36) between July 2021 and November 2022. A multimodal DL model incorporating mpMRI and ¹⁸F-PSMA-PET/CT was developed to support radiologists in assessing EPE using the EPE-grade scoring system. The predictive performance of the DL model was compared with that of single-modality models, as well as with radiologist assessments with and without model assistance. Clinical net benefit of the model was also assessed.

Results: For patients in Center 1, the area under the curve (AUC) for predicting EPE was 0.76 (0.72-0.80), 0.77 (0.70-0.82), and 0.82 (0.78-0.87) for the mpMRI-based DL model, PET/CT-based DL model, and the combined mpMRI + PET/CT multimodal DL model, respectively. In the external test set (Center 2), the AUCs for these models were 0.75 (0.60-0.88), 0.77 (0.72-0.88), and 0.81 (0.63-0.97), respectively. The multimodal DL model demonstrated superior predictive accuracy compared to single-modality models in both internal and external validations. The deep learning-assisted EPE-grade scoring model significantly improved AUC and sensitivity compared to radiologist EPE-grade scoring alone (P < 0.05), with a modest reduction in specificity. Additionally, the deep learning-assisted scoring model provided greater clinical net benefit than the radiologist EPE-grade score used by radiologists alone.

Conclusion: The multimodal imaging deep learning model, integrating mpMRI and 18 F-PSMA PET/CT, demonstrates promising predictive performance for EPE in prostate cancer and enhances the accuracy of radiologists in EPE assessment. The model holds potential as a supportive tool for more individualized and precise therapeutic decision-making.

Objective: To evaluate the efficacy of MWA for patients aged ≥ 75 years with stage I NSCLC, and to explore the impacts of age and comorbidities on the long-term outcomes.

Methods: Patients with stage I NSCLC underwent MWA between November 2016 and December 2020 were retrospectively enrolled. Patients were stratified into two cohorts: ≥ 75 years and < 75 years. Propensity score matching was implemented to control selection bias. Primary endpoints included overall survival (OS), cancer-specific survival (CSS), and recurrence-free survival (RFS). Secondary endpoints included independent risk factors influencing OS.

Results: 138 patients were successfully matched, with 69 in each group. The 1-, 3-, and 5-year OS were 95.7%, 82.6%, and 72.8% in patients aged ≥ 75 years, while 97.1%, 89.9%, and 80.3% in younger patients. There was no significant difference (p = 0.212). The 1-, 3-, and 5-year CSS were 100.0% vs. 98.6%, 92.2% vs. 92.6%, and 83.6% vs. 89.2%, respectively. No significant difference was observed (p = 0.661). The 1-, 3-, and 5-year RFS were 82.1% vs. 88.4%, 60.6% vs. 63.3%, and 58.9% vs. 61.6% without significant difference (p = 0.537). The multivariate COX analysis showed age and Charlson comorbidity index (CCI) were not prognostic factors. Idiopathic pulmonary fibrosis (IPF)/chronic obstructive pulmonary disease (COPD) was an independent risk factor (95% CI 1.32-8.24; p = 0.011).

Conclusion: MWA is an efficacious tool for patients aged ≥ 75 years with NSCLC. There are no significant differences in efficacy compared with younger patients. Age and CCI are not significant factors associated with prognosis, while IPF/COPD is an independent risk factor.

Background: Photon-counting detector CT (PCD-CT) offers technical advantages over energy-integrating detector CT (EID-CT) for liver imaging. However, it is unclear whether these translate into clinical improvements regarding the classification of suspicious liver lesions using the Liver Imaging Reporting and Data System (LI-RADS). This study compared the intra- and intermodal agreement of EID-CT and PCD-CT with Magnetic resonance imaging (MRI) for liver lesion classification.

Methods: This retrospective study included patients who underwent EID-CT or PCD-CT and MRI within 30 days between 02/2023 and 01/2024. Three board-certified radiologists assessed LI-RADS classification and presence of LI-RADS major features. Fleiss' Kappa and intraclass correlation coefficients (ICC) were used to evaluate rater agreement.

Results: Sixty-eight lesions in 26 patients (mean age 65.0 ± 14.2 years, 19 [73.1%] male) were analyzed. Intramodal inter-rater agreement for LI-RADS classification was 0.88 (0.62-0.88) for EID-CT, 0.90 (0.83-0.94) for PCD-CT, and 0.87 (0.81-0.91) for MRI. Agreement in PCD-CT was substantial for all LI-RADS major features, whereas in EID-CT only for washout. Intermodal agreement between CT and MRI ranged from 0.67 to 0.72. Final intermodal LI-RADS classification agreement was higher for PCD-CT (0.72-0.85) than EID-CT (0.52-0.64).

Conclusions: PCD-CT demonstrated higher intermodal and intramodal agreement for LI-RADS classification and major features than EID-CT. Additionally, PCD-CT shows significantly higher intramodal and inter-rater agreement for LI-RADS classification and greater concordance with MRI compared to EID-CT, reaching substantial to almost perfect agreement. These results suggest a potential benefit of PCD-CT in the management and treatment decision-making of HCC.