Insights into Imaging最新文献

This educational review provides a comprehensive guide for radiologists on the imaging interpretation of persistent spinal pain syndrome (PSPS) and complications following spine surgery. PSPS, previously known as failed back surgery syndrome, describes persistent or recurrent, primarily neuropathic, pain after spine surgery affecting 10-40% of patients. Radiologists often encounter challenges in diagnosing PSPS due to unfamiliarity with postoperative anatomical modifications and the complexity of surgical interventions. This review emphasises the necessity of correlating imaging findings with the clinical context through an interdisciplinary collaboration, while keeping in mind the particular psychological context of postoperative patients in chronic pain. We focus on lumbar spine surgery such as lumbar spine discectomy, lumbar spine stenosis, posterior decompression and stabilisation-fusion procedures. The review offers practical insights into managing key clinical scenarios: early complications with genuine emergencies, but also more subtle diagnoses such as low-grade infections or hardware failures. We underscore the utility of various imaging modalities-radiography, CT, MRI, PET and SPECT, and propose the ideal combination for each clinical situation. Plain radiographs are useful for assessing patients in standing positions and detecting intervertebral instability. CT is ideal for examining bone fusion and surgical hardware, while MRI excels in soft tissue analysis. PET and SPECT provide crucial insights into bone metabolism, detecting micromobility or infections. Based on 15 years of interdisciplinary collaboration, this guide, based on clinical scenarios, aims to enhance radiologists' confidence and accuracy in interpreting postoperative spine imaging, improving diagnostic precision, patient management and communication with referring clinicians. KEY POINTS: Managing postoperative spine imaging is often challenging for surgeons and radiologists. Postoperative spine imaging requires precise clinical correlation and careful multidisciplinary evaluation. Different imaging modalities can be combined to answer difficult issues.

Fetal MRI has become an essential tool for evaluating abdominal cystic lesions detected on prenatal ultrasound, offering superior soft tissue contrast and multiplanar imaging capabilities. This observational case series, conducted at Quironsalud Madrid University Hospital, analyzed fetuses diagnosed with abdominal cystic lesions who underwent fetal MRI. Lesions were classified into gastrointestinal, genitourinary, teratomatous, and syndromic categories. Fetal MRI allowed for precise lesion characterization, differentiating cystic masses from solid or mixed lesions, and identifying associated structural abnormalities. MRI findings were correlated with fetal ultrasound and, when available, postnatal imaging or surgical outcomes, demonstrating complementary information and improved diagnostic confidence compared to ultrasound alone. This improved accuracy has direct clinical implications, aiding in prenatal counseling, optimizing perinatal management, and guiding postnatal surgical planning. Our results reinforce the role of fetal MRI as a complementary imaging modality for refining the diagnosis of congenital abdominal cystic lesions and improving neonatal outcomes. CRITICAL RELEVANCE STATEMENT: This article critically evaluates the role of fetal MRI, in conjunction with prenatal ultrasound, in characterizing abdominal cystic lesions, highlighting its diagnostic advantages over ultrasound and its clinical impact on prenatal counseling, perinatal management, and postnatal surgical planning in radiological practice. KEY POINTS: Abdominal cystic lesions are frequently detected on prenatal ultrasound, but their characterization and differentiation remain challenging. Fetal MRI characterizes lesions, assesses their extent, improves classification and diagnosis, and offers superior soft tissue contrast for evaluating complex anomalies. Fetal MRI complements prenatal ultrasound, allowing a more precise assessment of lesion characteristics and facilitating prenatal counseling and perinatal planning.

Objectives: This study aims to develop a multimodal nomogram to predict neoadjuvant chemoimmunotherapy (NCIT) outcomes in head and neck squamous cell carcinoma (HNSCC).

Materials and methods: Treatment-naive HNSCC patients receiving neoadjuvant NCIT were retrospectively analyzed. Clinical information, conventional MR imaging features, dynamic contrast-enhanced-MRI (DCE-MRI) parameters and ADC values were analyzed in relation to pathological complete response (pCR). The predictive accuracy of clinical and MRI parameters was evaluated using the receiver operating characteristic (ROC) curve, with the area under the curve (AUC) serving as a key metric.

Results: Following NCIT, 55.0% (67/122) of patients achieved pCR. Significant differences were observed in clinical variables, including tumor location, combined positive score (CPS) and neutrophil-to-lymphocyte ratio (NLR) between pCR and non-pCR groups (p < 0.05). Imaging features (tumor margin, growth pattern, T2 homogeneity, necrosis, three distinct enhancement patterns, tumor diameter and lymph node short-axis diameter) also differed significantly (p < 0.05). The enhancement pattern was the most efficient predictor of pCR (AUC = 0.83). A combined model incorporating CPS, tumor diameter, and enhancement pattern achieved an AUC of 0.86. The baseline K^trans and ADC values demonstrated an AUC of 0.712 and 0.715 for pCR prediction. The H&E-stained whole-slide analyses revealed significant correlations between specific MRI features and tumor lymphocyte densities/ratios.

Conclusions: We developed a novel combined model integrating CPS and routine pretreatment MRI features to predict NCIT response in HNSCC. The enhancement pattern was the strongest predictor of pCR, while functional MRI parameters also showed significant predictive value.

Critical relevance statement: This study demonstrates that systematically integrating combined positive score with routine pretreatment MRI features can effectively predict neoadjuvant chemoimmunotherapy response. These findings may help optimize therapeutic strategies for head and neck squamous cell carcinoma.

Key points: Predicting neoadjuvant chemoimmunotherapy response in head and neck cancer remains challenging. A novel clinical-MRI model improves chemoimmunotherapy response prediction in head-neck cancer. The three enhancement patterns emerged as the most robust predictors.

Background: Recent PET studies suggest a link between amygdala activity and cardiovascular disease. Altered amygdala volumes are associated with increased stressor-evoked cardiovascular reactivity, which potentially increases the risk for cardiovascular disease. Therefore, we investigated the association between amygdala volume and MRI-based markers of cardiovascular disease in order to evaluate morphological alterations of the amygdala in persons with early, clinically inapparent signs of cardiovascular complications.

Materials and methods: 400 subjects underwent a comprehensive 3-T MRI to estimate amygdala volume and imaging-based markers of cardiovascular disease, specifically carotid plaque presence and grading, media wall thickening, left ventricular myocardial mass, myocardial late gadolinium enhancement, and left ventricular function. Amygdala volume was automatically segmented based on FLAIR images and corrected for total intracranial volume. Logistic and linear regression analyses of amygdala volume and cardiovascular parameters were conducted while controlling for age, gender and cardiovascular risk factors.

Results: Among 339 included subjects (mean age: 56.3 ± 9.1, 57% males), the average absolute amygdala volume was 3.04 ± 0.24 mL, and the average amygdala ratio was 0.213 ± 0.017% of total intracranial volume. Carotid plaque was present in 22.6%, and myocardial late gadolinium enhancement in 3.2%. Mean media wall thickening was 0.76 ± 0.1 mm, mean left ventricular myocardial mass 71.6 ± 14.1 g/m², and mean ejection fraction 69.1 ± 8.2%. Logistic and linear regression analyses showed no significant association of amygdala volume and any of the MRI-based cardiovascular parameters (p > 0.05, respectively).

Conclusions: Amygdala volume was not associated with early MRI-based markers of cardiovascular disease, suggesting that the amygdala is not morphologically altered in the initial phase of cardiovascular disease.

Critical relevance statement: This first large MRI study demonstrates that amygdala volume is not associated with subclinical cardiovascular disease, critically refining prior PET-based hypotheses and advancing clinical radiology by clarifying the preserved role of amygdala morphology in early cardiovascular pathology.

Key points: PET studies link amygdala activity to cardiovascular disease, while the role of amygdala volume in early cardiovascular disease is unclear. In this large population-based study, 339 asymptomatic adults who underwent comprehensive 3-T MRI with cardiovascular assessment were analyzed. Amygdala volume showed no association with MRI markers of subclinical cardiovascular disease. This is the first large MRI study linking amygdala volume and early cardiovascular disease.

Objectives: This study was designed to develop a multiregional MRI-based deep learning radiomics nomogram (DLRN) for predicting axillary pathological complete response (apCR) after neoadjuvant chemotherapy (NAC) in breast cancer.

Materials and methods: In total, 539 patients in our hospital were randomly split into a training cohort (TC; n = 431) and an internal validation cohort (IVC; n = 108), and 703 patients were recruited from three external centers as external validation cohorts (EVC1-3). Uni- and multivariate analyses were performed to select clinicopathological characteristics and establish a clinical model. DLR models were constructed based on DL and handcrafted radiomics features extracted from gross tumor volume (GTV) and GTV incorporating 3-, 5-, 7-, and 9-mm peritumoral regions (GPTV₃, GPTV₅, GPTV₇, and GPTV₉, respectively). A DLRN model incorporating the optimal DLR model and clinicopathological predictors was developed. Model performance was assessed employing the area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis.

Results: The GPTV₅_DLR model surpassed the other DLR models, with an average AUC of 0.876 in the validation cohorts. The DLRN model better predicted apCR after NAC than the clinical model, demonstrating superior AUCs of 0.958 in the TC, 0.906 in the IVC, and 0.876-0.911 in EVC1-3. It also showed improved accuracy and clinical benefits for apCR prediction. Furthermore, the DLRN model achieved robust performance across different age, menstrual status, and clinical stage subgroups.

Conclusion: The DLRN model, based on the GPTV₅_DLR model and clinicopathological features, exhibited high predictive efficiency for apCR after NAC.

Critical relevance statement: The deep learning radiomics nomogram based on intra- and peritumoral regions could noninvasively predict axillary pCR in breast cancer patients receiving NAC, which might prevent patients from undergoing unnecessary axillary lymph node dissection.

Key points: Combining intratumoral and 5-mm peritumoral region radiomics had the highest predictive efficiency for axillary pCR after NAC in breast cancer. The deep learning radiomics nomogram based on intra- and peritumoral regions outperformed the clinical model. The proposed model could provide a noninvasive and easy-to-use tool to offer decision support for optimizing treatments.

Objectives: To assess a deep learning (DL) model using portal-venous phase CT for discriminating colorectal cancer liver metastasis (CRLMs) and hemangiomas (HMs).

Materials and methods: Colorectal cancer (CRC) patients diagnosed with CRLMs or HMs at two medical centers from January 2018 and April 2024 were retrospectively included. Lesions were automatically segmented using TotalSegmentator. DL models, DenseNet-201 and ResNet-152, were trained to classify CRLMs and HMs. Their performance, measured by AUC, was evaluated on validation and test sets. Subgroup analyses were conducted for lesions ≤ 10 mm (subcentimeter) and 10-30 mm. Radiologists' diagnostic performance with and without DL assistance was compared using a multi-reader multi-case analysis.

Results: 534 CRLMs (134 CRC-patients; median, 60 years) and 262 HMs (154 CRC-patients; median, 62 years) were divided into the training, validation and test set. The Dice coefficients of TotalSegmentor for automatically segmenting subcentimeter and 10-30 mm lesions were 0.692 ± 0.099 and 0.861 ± 0.033, respectively (p < 0.01). ResNet-152 model achieved AUCs of 0.875 (95% CI: 0.838-0.912), 0.858 (95% CI: 0.781-0.935), 0.776 (95% CI: 0.703-0.848) for classifying CRLMs and HMs on the training, validation, and test sets, respectively. The AUCs for distinguishing between 10-30 mm CRLMs and HMs improved from 0.851 (95% CI: 0.821-0.880) to 0.879 (95% CI: 0.853-0.906) with DL assistance compared to without (p = 0.015). For subcentimeter CRLMs and HMs, the AUCs for the radiologists and the DL-assisted diagnosis were 0.742 (95% CI: 0.669-0.814) and 0.763 (95% CI: 0.681-0.845), respectively (p = 0.558).

Conclusion: DL can assist radiologists in distinguishing 10-30 mm CRLMs from HMs in CRC patients. The value of DL-assisted diagnosis is limited for subcentimetre CRLMs and HMs.

Critical relevance statement: Dynamic detection of hypoenhancing liver lesions in patients with CRC is exceptionally challenging. The DL tool we have developed can assist in evaluating CRLMs and HMs.

Key points: TotalSegmentator can perform automatic segmentation of CRLMs and HMs, but demonstrates poorer segmentation consistency for subcentimeter lesions. This DL model assists radiologists in distinguishing 10-30 mm CRLMs from HMs in CRC patients. Subcentimeter CRLMs and HMs can require further MRI scanning.

Objectives: To evaluate the feasibility and safety (primary endpoints), and performance (secondary endpoint) of a new artificial intelligence (AI) software for detecting clinically significant prostate cancer (csPCa) on biparametric MRI (bpMRI) compared to an expert radiologist.

Materials and methods: In this prospective study at St. Olavs Hospital, Norway (December 2023-October 2024), 89 consecutive biopsy-naïve men underwent bpMRI for suspected PCa. Scans were interpreted by a radiologist using PI-RADS v2.1 and a radiomics-based AI software. Biopsies were obtained from all radiologist- and/or AI-identified lesions. csPCa was defined as ISUP ≥ 2. Feasibility was defined by a < 10% software-failure rate, and safety by the absence of serious adverse device effects (SADEs). Performance was evaluated with ROC, free-response ROC, and precision-recall curves.

Results: Among 89 patients eligible for primary endpoints evaluation, the software demonstrated feasibility (7% failure rate) and safety (no SADEs). Among 76 eligible for secondary endpoint evaluation (median age 68 years [IQR: 63-73]), csPCa was found in 51% (39/76). Patient-level, software achieved an area under the ROC curve [95% CI] of 0.90 [0.83, 0.96] versus 0.86 [0.76, 0.93] (p = 0.25). At a retrospectively optimized threshold matching the radiologist's patient-level sensitivity at PI-RADS 3 (0.92), software achieved specificity of 0.68 [0.57, 0.78] versus 0.57 [0.46, 0.68] (p = 0.29). Lesion-level, software achieved higher average precision (0.61 [0.52, 0.71] vs. 0.56 [0.46, 0.67]) and lower average false-positive per patient (0.33 [0.22, 0.43] vs. 0.41 [0.30, 0.52]) at the optimized threshold.

Conclusion: The software was feasible and safe, and diagnostic performance showed potential to reduce unnecessary biopsies.

Critical relevance statement: This clinically validated artificial intelligence software enables feasible and safe detection of clinically significant prostate cancer on biparametric MRI, with demonstrated potential to reduce unnecessary biopsies and improve diagnostic accuracy, indicating potential for integration into clinical prostate cancer care.

Key points: A fully automated radiomics software for clinically significant prostate cancer detection on biparametric MRI was prospectively clinically validated. The software demonstrated feasibility and safety, with potential to reduce unnecessary biopsies and improve diagnostic accuracy. The investigated radiomics software has the potential for integration into clinical prostate cancer care.

Objective: Deep learning signatures (DLS) extracted from CT images can noninvasively reflect tumor heterogeneity and have shown promise in prognostic modeling for esophageal squamous cell carcinoma (ESCC). To develop and validate a CT-based DL model combined with nutritional biomarkers to predict 3-year overall survival (OS) in ESCC, and to investigate transcriptomic differences between DLS-based risk groups.

Materials and methods: This retrospective multicenter study included 662 postoperative ESCC patients from three hospitals and 16 additional patients from The Cancer Genome Atlas (TCGA). DL features extraction from CT images based on the Crossformer architecture. Skeletal muscle index was measured at the L3 vertebra to assess low skeletal muscle mass (LSMM). Cox regression was used to build clinical, DL, and combined models. Model performance was evaluated using the concordance index (C-index). Transcriptomic analysis of the TCGA cohort was performed to identify metabolic pathway differences between DLS-based risk groups.

Results: The DL model achieved a C-index of 0.743 (95% CI: 0.683-0.803) in the internal validation cohort and 0.692 (95% CI: 0.576-0.809) in the external cohort. Pathological T and N stages, Neuroaggression, Vascular invasion, and LSMM were identified as independent clinical predictors. The combined model achieved a C-index of 0.753 (95% CI: 0.697-0.808) internally and 0.725 (95% CI: 0.613-0.838) externally. DLS-based risk stratification revealed significant differences in metabolic activity between groups, supporting its biological relevance.

Conclusion: The combined model enables preoperative OS prediction in ESCC. DLS-based stratification reflects transcriptomic metabolic heterogeneity and enhances the biological interpretability of imaging features.

Critical relevance statement: This study developed a CT-based DLS and combined it with nutritional markers for prognostic modeling in ESCC. Transcriptomic analysis of DLS-based groups revealed metabolic heterogeneity, enhancing the biological interpretability of the DL model.

Key points: A combined DLS and nutritional model enables individualized preoperative survival prediction in ESCC. DLS-based risk groups defined by the DLS exhibited transcriptomic differences in key metabolic pathways, revealing biological underpinnings of imaging-based phenotypes. Attention map visualization revealed consistent spatial focus on morphologically distinct tumor regions, enhancing the interpretability of deep learning predictions.

Objectives: Waiting for postoperative pathologic confirmation of visceral pleural invasion (VPI) may delay treatment decisions. This study aimed to develop a contrast-enhanced CT-based radiomics model for preoperative prediction of VPI in early-stage non-small cell lung cancer (NSCLC).

Materials and methods: We retrospectively enrolled 523 surgically resected NSCLC patients (195 with VPI, 328 without VPI) with clinically staged IA based on preoperative imaging between December 2019 and June 2022. Patients were randomly divided into training, validation, and testing sets at a ratio of 5:2:3. For each patient, 13 CT features were recorded, including the types I-V tumor relationships to the pleura. Regions of interest (ROIs) were segmented semi-automatically using deep learning. Least absolute shrinkage and selection operator (LASSO) regression was applied to select key radiomics features. Three models were developed: a CT-feature model, a radiomics model, and a combined model. The performance and clinical utility of these models were evaluated using the area under the curve (AUC) and decision curve analysis.

Results: The tumor relationship to the pleura, density, maximum diameter, and spiculation were selected to construct the CT-feature model. A total of 10 optimal features formed the radiomics model. The radiomics model achieved an AUC of 0.812 in the testing set, outperforming the CT-feature model (0.714). Furthermore, the combined model showed a slightly higher AUC (0.825) compared to the radiomics model.

Conclusions: The radiomics model demonstrated satisfactory performance for predicting VPI in early-stage NSCLC, outperforming the CT-feature model. The integration of radiomics and CT features may provide enhanced predictive value.

Critical relevance statement: This study constructed a contrast-enhanced CT-based radiomics model with promising performance for the preoperative prediction of VPI, which aims to guide treatment planning for early-stage NSCLC.

Key points: VPI affects the tumor-node-metastasis (TNM) staging of tumors and subsequent treatment strategies. The radiomics model outperformed the CT-feature model in predicting VPI. The contrast-enhanced CT-based radiomics model may be valuable for optimizing clinical decision-making.

Objectives: Androgen deprivation therapy (ADT) is essential for treating prostate cancer (PCa) but is limited by tumor heterogeneity. This study develops a non-invasive multiparametric Magnetic Resonance Imaging (mpMRI) radiomics framework to predict ADT response and improve risk stratification.

Materials and methods: A cohort of 550 ADT-treated PCa patients from three centers was analyzed. Patients were randomly divided into training (n = 270) and internal validation (n = 115) cohorts. An external test cohort (n = 165) from Centers 2 and 3 was used for generalizability. Radiomics models based on T2-weighted and diffusion-weighted imaging (DWI), habitat radiomics, and a 3D Vision Transformer (ViT) deep learning model were developed. Ensemble integration of these models was performed, with SHapley Additive exPlanations (SHAP) used for interpretability. Predictive performance was evaluated using receiver operating characteristic (ROC) curves and area under the curve (AUC).

Results: Habitat radiomics outperformed conventional radiomics in Gleason score stratification. For predicting ADT treatment efficacy, the radiomics model achieved AUCs of 0.969 (training), 0.767 (internal validation), and 0.771 (test). The habitat model showed AUCs of 0.987, 0.849, and 0.820, while the ViT model achieved AUCs of 0.831, 0.805, and 0.796. The ensemble model reached the highest AUC of 0.886. SHAP analysis shows that the ViT model contributes most to the combined model, followed by the habitat model, with the radiomics model contributing the least.

Conclusion: mpMRI-based habitat radiomics enables precise risk stratification in PCa. Integrated with conventional radiomics and deep learning, it forms a robust framework for predicting ADT response and guiding personalized treatment.

Critical relevance statement: This study demonstrates that integrating habitat radiomics with deep learning improves the prediction of androgen deprivation therapy response in PCa, advancing personalized radiological decision-making through interpretable multi-model analysis of tumor microenvironment heterogeneity.

Key points: Multi-model integration of habitat radiomics and 3D Vision Transformer achieves superior prediction for ADT response compared to conventional methods. Habitat radiomics outperforms traditional radiomics in Gleason score stratification. SHAP analysis provides clinical interpretability, identifying key model linked to ADT outcomes for actionable insights.