This study primarily aimed to identify prognostic factors for patients with recurrent/metastatic tongue squamous cell carcinoma (R/M TSCC) undergoing re-resection and to preliminarily explore the value of baseline metabolic parameters in predicting pathological response after neoadjuvant therapy (NAT). In the primary analyses, we analyzed 114 patients with R/M TSCC who underwent direct re-resection or re-resection after NAT between 2017 and 2024. Clinical, pathological, and PET/CT parameters were collected. Lasso-Cox regression was performed to identify factors influencing disease-free survival (DFS) and overall survival (OS), with internal validation via bootstrapping with 1000 resamples. Sensitivity analysis was performed to test the robustness of the main findings by restricting the analysis to the 100 patients who underwent elective neck dissection (a subgroup of the 114 patients). Patients undergoing re-resection after NAT were grouped by pathological response (pCR/MPR vs. non-MPR) for comparison. Median follow-up was 43.0 months (110 were evaluable), with 53 deaths and 46 remaining recurrence-free. Initial pathological N status and differentiation at recurrence were prognostic factors for both DFS and OS, with HRs of 2.29 (95

OBJECTIVES:Patients with recurrent tongue squamous cell carcinoma (RTSCC) receiving nonsurgical treatment have a poor prognosis. This study aims to identify independent factors associated with survival in these patients and to evaluate the effects of treatment response on survival outcomes. METHODS:Patients with RTSCC who received nonsurgical treatment at Hunan Cancer Hospital between January 2017 and July 2024 were retrospectively enrolled. Pretreatment metabolic parameters derived from 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) were measured, including the maximum, mean, and peak standardized uptake values corrected for lean body mass (SULmax, SULmean, and SULpeak), the lesion-to-mediastinal blood-pool SULmean ratio (SULR), whole-body total metabolic tumor volume (MTV), and whole-body total lesion glycolysis (TLG). Baseline clinical characteristics, pathological features from the initial surgery, and treatment modalities after recurrence were also collected. Treatment response was evaluated according to the Response Evaluation Criteria in Solid Tumors, version 1.1 (RECIST 1.1), or the immune Response Evaluation Criteria in Solid Tumors (iRECIST), and patients were classified into response and nonresponse groups. Progression-free survival (PFS) and overall survival (OS) were followed. Univariate and multivariate Cox regression analyses were performed to identify independent factors associated with PFS and OS. Two sensitivity analyses, restricted to patients scanned using the same scanner model and to those who underwent whole-body scanning, respectively, were conducted to assess the robustness of the primary findings. Model performance was evaluated using the concordance index (C-index), time-dependent receiver operating characteristic (ROC) curves, and calibration curves. Time-dependent Cox regression and landmark analyses were used to assess the effects of treatment response on survival. RESULTS:A total of 93 patients with RTSCC were included. The follow-up duration ranged from 2 to 81 months, with a median of 38 months. Disease progression occurred in 72 patients, and 66 patients died. PFS ranged from 1 to 81 months, with a median of 4 months, whereas OS ranged from 2 to 81 months, with a median of 11 months. In the primary analysis, radiotherapy after recurrence was an independent protective factor for PFS (HR=0.461, 95% CI 0.233 to 0.912, P=0.026). This association remained significant in the sensitivity analysis restricted to patients scanned using the same scanner model (P=0.032), but was not significant in the analysis restricted to patients who underwent whole-body scanning (P=0.159). The corrected C-index of the PFS prediction model was 0.609, indicating limited predictive performance for 3- and 6-month PFS. In the analysis of OS, the natural logarithm of MTV [ln(MTV); HR=1.299, 95% CI 1.092 to 1.546, P=0.003] and radiotherapy after recurrence (HR=0.377, 95% CI 0.180 to 0.790, P=0.010) were independent predictors of OS. Both sensitivity analyses supported the robustness of these findings. The corrected C-index of the OS prediction model was 0.663, indicating moderate discrimination for 1- and 2-year OS. Time-dependent Cox regression analysis showed that treatment response was not significantly associated with PFS (HR=0.618, 95% CI 0.327 to 1.167, P=0.138; C-index=0.517), whereas treatment response had a significant protective effect on OS (HR=0.340, 95% CI 0.196 to 0.590, P<0.001; C-index=0.620). The 2-month landmark analysis showed that both PFS and OS were significantly longer in the response group than in the nonresponse group (both P<0.001). CONCLUSIONS:Whole-body total MTV and radiotherapy after recurrence have potential prognostic value for OS in patients with RTSCC receiving nonsurgical treatment. The protective association between radiotherapy after recurrence and PFS requires further validation. Patients who achieved a treatment response had better OS than those who did not respond.

To develop and validate a magnetic resonance imaging (MRI)-based radiomics model of the mesorectum for predicting extramural venous invasion (EMVI) in patients with rectal cancer (RC). A retrospective study included 238 patients with RC from two hospitals between May 2020 and March 2023. Patients were divided into a training set (n = 114, from institution 1), an internal validation set (n = 48, from institution 1), and an external validation set (n = 76, from institution 2). A total of 963 radiomics features were extracted from the mesorectum region using T2-weighted imaging (T2WI). The radiomics model was developed using the methods of the minimum redundancy of the maximum relevance (mRMR) and the least absolute shrinkage (LASSO) regression. After univariate and multivariate logistic analysis, a clinical model was constructed based on clinical characteristics. A combined model was built and demonstrated as a nomogram. These models were evaluated by discrimination, calibration, and clinical application. Among 238 patients, 98 (41.1

Abstract Predicting response to induction chemotherapy (IC) and overall survival (OS) is critical for optimizing treatment in patients with locally advanced nasopharyngeal carcinoma (LANPC). This study aimed to develop and validate a multi-task deep learning model integrating pretreatment MRI and whole slide images (WSIs) to predict IC response and OS in LANPC. Pretreatment MRI and WSIs from 404 patients with LANPC were retrospectively collected to construct a multi-task model (MoEMIL) for the simultaneous prediction of early IC response and OS. MoEMIL employed multi-instance learning to process WSIs, PyRadiomics and a convolutional neural network (ResNet50) to extract MRI features, and fused multimodal features through a multi-gate mixture-of-experts architecture. Clustering-constrained attention multiple instance learning and gradient-weighted class activation mapping were applied for visualization and interpretation. MoEMIL effectively stratified patients into good and poor IC response groups, achieving areas under the curve of 0.917, 0.869, and 0.801 in the train, validation, and test sets, respectively, and outperformed the deep learning radiomics model, the pathomics model and TNM staging. The model also stratified patients into high- and low-risk OS groups ( P < 0.05 ). MoEMIL shows promise as a decision-support tool for early IC response prediction and prognostication in LANPC. Author Summary We have developed a deep learning model that integrates two types of medical images, including magnetic resonance imaging (MRI) and digital pathological slices, to simultaneously predict response to induction chemotherapy and prognosis in patients with locally advanced nasopharyngeal carcinoma. Current treatment decisions primarily rely on traditional tumor staging (TNM), which often fails to comprehensively reflect the complexity of the disease. Our model, named MoEMIL, was trained and tested on data from 404 patients across two hospitals and consistently outperformed both single-model approaches and TNM staging methods. By identifying patients who exhibit poor response to induction chemotherapy or higher prognostic risk, our tool can assist clinicians in achieving personalized treatment, enabling intensified management for high-risk patients and avoiding unnecessary side effects for low-risk patients. Additionally, we visualize the model’s reasoning process through heat map generation, which highlights the image regions exerting the greatest influence on prediction outcomes. This work represents a step toward more precise treatment for nasopharyngeal carcinoma; however, larger-scale prospective studies are required before the model can be integrated into routine clinical practice.

Ferroptosis arises when iron-dependent phospholipid peroxidation overwhelms the system xc--glutathione-GPX4 axis and parallel antioxidant defenses. Within tumors, however, the immune consequence of this death process depends on how iron and oxidized material move between malignant and immune compartments. Tumor-associated macrophages (TAMs) occupy this interface because they recycle iron, engulf dying cells and oxidized membranes, and modify the redox state of neighboring cells. These activities may confine injury to tumor cells, propagate lipid damage into immune cells, or protect malignant cells through vesicle cargo and antioxidant exchange. Ferroptotic death combines loss of viability with iron-dependent phospholipid peroxidation attenuated by an appropriate inhibitor, with genetic corroboration where feasible. Tumor-restricted ferroptosis can support antigen handling while macrophage and dendritic-cell functions remain intact. As oxidized material exceeds local clearance and antioxidant capacity, the same insult can impair CD8+ T cells and phagocytic macrophages and favor immune suppression. Three linked modules organize this process: iron-flux redistribution, lipid-hydroperoxide spectra and receptor sensing, and phagocytic clearance and antioxidant buffering. Iron flux identifies the first injured compartment, lipid species and receptor distribution shape the ensuing immune response, and clearance determines the duration and spread of injury. The framework thereby explains how TAM state, tumor niche, and treatment schedule redirect a common oxidative insult without proposing an additional ferroptosis execution pathway. Clinical translation will require ferroptosis to remain concentrated in the intended compartment while CD8+ T cells and homeostatic phagocytes retain function. Bulk iron, oxidative markers, and transcriptomic signatures provide complementary signals but cannot resolve the injured cell population.

Background:The Node Reporting and Data System (Node-RADS) provides a standardized and effective assessment of lymph nodes, but its relationship with the prognosis of small cell lung cancer (SCLC) remains unknown. This study aimed to assess the value of Node-RADS for predicting overall survival (OS) in extensive-stage SCLC patients treated with chemoimmunotherapy. Methods:The clinical data including OS of 297 patients with extensive-stage SCLC who underwent chemoimmunotherapy were collected retrospectively. On the pretherapeutic chest computed tomography (CT) scans, we evaluated the maximum Node-RADS score per patient and the number of positive nodal stations, defined using two thresholds: LNM-Station3 (score ≥3) and LNM-Station4 (score ≥4). The Clinical-NR3 model, incorporating pretreatment clinical variables, the maximum Node-RADS score, and LNM-Station3, was developed using Cox regression analyses to predict OS. Similarly, the Clinical-NR4 model was constructed using clinical variables, the Maximum Node-RADS score, and LNM-Station4, whereas the Clinical-cN model was created as a control based on the clinical variables and cN stage. Results:LNM-Station3 and LNM-Station4 acted as independent predictors for OS in the Clinical-NR3 and Clinical-NR4 models, respectively. The cN stage was not significantly associated with OS in the Clinical-cN model (P>0.05). The Clinical-NR4 model demonstrated a higher concordance index (C-index) than the Clinical-cN model (0.759 vs. 0.726, P=0.009). The C-index (0.748) of the Clinical-NR3 model did not show a statistically significant difference from that of the Clinical-NR4 (P=0.093) and Clinical-cN (P=0.059) models. The Clinical-NR4 model exhibited more favorable area under the curve (AUC) values of the time-dependent receiver operating characteristic (ROC) curves than the Clinical-cN model. Conclusions:The baseline LNM-Station based on Node-RADS is an effective prognostic indicator for extensive-stage SCLC. The pretherapeutic CT-based Node-RADS models provide incremental prognostic value beyond conventional clinical N (cN) staging in patients with SCLC.

BACKGROUND:To explore and compare the potential value of radiomics models based on contrast-enhanced computed tomography (CT) for noninvasive preoperative prediction of lymphovascular invasion (LVI) in laryngeal squamous cell carcinoma (LSCC). MATERIALS AND METHODS:This multicenter diagnostic study retrospectively enrolled patients with LSCC from three tertiary hospitals who underwent surgical treatment. Standardized preprocessing was performed on the CT images, followed by region-of-interest segmentation and extraction of traditional radiomics features and deep learning (DL) features. Features were selected using least absolute shrinkage and selection operator (LASSO) regression. Traditional radiomics models and deep learning radiomics (DLR) models were established using logistic regression, random forest, and multilayer perceptron algorithms, respectively. A transformer-based hybrid model was developed by integrating radiomics and DL features. The predictive performance of the three types of models was evaluated and compared using the area under the curve (AUC), decision curve analysis (DCA), sample probability distribution histograms, confusion matrices, calibration curves, net reclassification index (NRI), and integrated discrimination improvement (IDI). RESULTS:A total of 1024 patients were allocated to the training set (center1, n = 291), internal validation set ( n = 126), and external test sets (Center 2, n = 437; Center 3, n = 170). Three radiomics models and three DLR models were constructed, and the optimal performance was observed in the DLR_ Random Forest model (AUC: 0.812-0.867). The transformer hybrid model demonstrated superior predictive performance, with AUC values of 0.881, 0.843, 0.833, and 0.836 in the training, internal validation, and external test sets, respectively. DCA indicated a higher net benefit for the Transformer model, along with an improved NRI and IDI. CONCLUSION:Radiomics models based on CT images exhibit potential for noninvasive prediction of LVI in LSCC, with the transformer hybrid model achieving the highest diagnostic performance. This approach may provide clinicians with a preoperative decision support tool to optimize treatment strategies for patients with LSCC.

Manual interpretation of CT images for bone metastasis (BM) detection in primary cancer remains challenging. We present an automated Bone Lesion Detection System (BLDS) developed using CT scans from 2518 patients (9177 BMs; 12,824 non-BM lesions) across five hospitals. The system, developed on 1271 patients and tested on 1247 multicenter cases, demonstrates 89.1% lesion-wise sensitivity (1.40 false-positives/case [FPPC]) in detecting bone lesions on non-contrast CT scans, with 92.3% and 91.1% accuracy in classifying BM/non-BM lesions for internal and external test sets, respectively. Outperforming radiologists in lesion detection (40.5% sensitivity; 0.65 FPPC), BLDS shows lower BM detection sensitivity than junior radiologists, though comparable to trainees. BLDS improves radiologists' lesion-wise sensitivity by 22.2% in BM detection and reduces reading time by 26.4%, while maintaining 90.2% patient-wise sensitivity and 98.2% negative predictive value in real-world validation (n = 54,610). The system demonstrates significant potential to enhance CT-based BM interpretation, particularly benefiting trainees.

OBJECTIVES:The Node Reporting and Data System (Node-RADS) offers a reliable framework for lymph node assessment, but its prognostic significance remains unexplored. This study aims to investigate the added prognostic value of Node-RADS in patients with locally advanced gastric cancer (LAGC) undergoing neoadjuvant chemotherapy (NAC) followed by gastrectomy. MATERIALS AND METHODS:This single-center retrospective study included 118 patients with LAGC underwent NAC and gastrectomy. The maximum Node-RADS score and the number of metastatic lymph node stations (defined as LNM-Station) were evaluated on pretreatment CT. The pretreatment Node-RADS-CT and Node-RADS-integrated models were developed using Cox regression to predict overall survival (OS) and disease-free survival (DFS). The pretreatment cN-CT models, cN-integrated models, as well as post-NAC pathological models were also developed in comparison. The performance of the models was assessed in terms of discrimination, calibration and clinical applicability. RESULTS:The LNM-Station was significantly associated with OS and DFS (all p < 0.05). The Node-RADS-CT model showed higher Harrell's consistency index (C-index) than cN-CT model (0.755 vs. 0.693 for OS, p = 0.017; 0.759 vs. 0.706 for DFS, p = 0.018). The Node-RADS-integrated model also achieved higher C-index than cN-integrated model (0.771 vs. 0.731 for OS, p = 0.091; 0.773 vs. 0.733 for DFS, p = 0.053). The net reclassification improvement (NRI) of the Node-RADS-integrated model at 5 years was 0.379 for OS and 0.364 for DFS (all p < 0.05). The integrated discrimination improvement (IDI) of the Node-RADS-integrated model was 0.103 for OS and 0.107 for DFS (all p < 0.05). The C-indices (OS: 0.745; DFS: 0.746) of pathological models were slightly lower than those of Node-RADS-based models (all p > 0.05). CONCLUSION:The baseline Node-RADS score and LNM-Station were effective prognostic indicators for LAGC. The pretreatment CT Node-RADS-based models can offer added prognostic value for LAGC, compared with clinical N stage.

Hepatocellular carcinoma (HCC) resists immunotherapy due to its immunosuppressive microenvironment. Sarcoma homology 2 domain-containing protein tyrosine phosphatase-1 (SHP-1) inhibits T cell receptor signaling, and its pharmacological inhibition is limited by poor selectivity and membrane permeability. Here, we generated CRISPR-edited SHP-1-knockout (KO) CD8+ T cells to enhance adoptive therapy against HCC. Single-cell RNA sequencing of HCC patient T cells revealed elevated SHP-1 in exhausted subsets. SHP-1-KO T cells exhibited increased effector memory T cells (TEM) proportions and enhanced IFN-γ/Granzyme B/perforin secretion, improving cytotoxicity against HCC lines. In humanized PDX models, SHP-1-KO T cells demonstrated superior tumor-killing activity. Transcriptomics identified upregulated lipid metabolism pathways, with HMGCR as a hub gene. Combining SHP-1-KO T cells with simvastatin (HMGCR inhibitor) synergistically amplified anti-HCC efficacy. This study proposes a dual strategy combining SHP-1-targeted cell therapy and metabolic modulation to overcome immunotherapy resistance, offering a translatable approach for HCC treatment.

The Node Reporting and Data System (Node-RADS) provides structured and effective evaluation for lymph nodes in malignancies. This study aims to investigate its value in predicting residual lymph node metastasis (LNM) and survival outcome of locally advanced gastric cancer (LAGC). This retrospective study included 118 patients with LAGC underwent neoadjuvant chemotherapy (NAC) and gastrectomy from April 2015 to June 2020. The diagnostic performance of the post-NAC CT-based Node-RADS score for regional LNM, both at the patient level and at the perigastric/extragastric subgroup level, was estimated using area under receiver operating characteristic curve (AUC) and Youden’s index. Kaplan-Meier curve was employed for prognostic analyses between high/low Node-RADS score group. A predictive Node-RADS (NR) model for LNM was developed using logistic regression analyses and a prognostic NR model for overall survival (OS) was developed using Cox regression analyses. In the prediction of LNM, the Node-RADS score exhibited an AUC of 0.843 (95

OBJECTIVE:To evaluate the myocardial ischemic segments and related factors in stable coronary artery disease (SCAD) patients by native T1 mapping. METHODS:316 SCAD patients and 30 healthy controls (all right coronary dominant) underwent CMR native T1 mapping within 90 days of CCTA. Segmental native T1 values were measured using AHA 16-segment model. Patients were grouped by number of diseased coronary arteries (DCA [1-3]) with the largest diameter stenosis (DS [< or ≥ 50 %]) and culprit coronary artery (CCA [LAD, LCX, RCA]), or number of coronary artery stenosis ≥50 % (CAS [0-3]), respectively. Ischemic segments were defined as native T1 values significantly elevated versus controls. Multivariable generalized estimating equations (GEE) model was used to identify independent factors. RESULTS:Single-vessel disease showed localized native T1 increases in corresponding perfusion territories, while multi-vessel disease exhibited complex ischemia patterns. Anterior and anteroseptal segments had significantly higher native T1 values in groups CAS 2 and 3 than CAS 0 and 1 (Bonferroni-adjusted P < 0.05). GEE model identified DCA (two-vessel disease: β = 13.6 ms, P = 0.010), CAS (1-3: β = 10.5, 34.4 and 57.2 ms, P < 0.05, respectively), and coronary artery calcium (CAC) score 3 and 4 (β = 12.2 and 14.5 ms, P < 0.05), LAD-fractional flow reserves (LAD-FFR) (β = -47.3 ms, P = 0.010) and CCA (LCX: β = -9.5 ms, P = 0.019) as independent factors. CONCLUSION:Native T1 mapping reveals spatially heterogenous ischemia in SCAD and is independently associated with both anatomical and functional parameters, supporting its value in personalized evaluation and management.

We developed and evaluated a skeletal muscle deep-learning (SMDL) model using skeletal muscle computed tomography (CT) imaging to predict the survival of patients with gastric cancer (GC). This multicenter retrospective study included patients who underwent curative resection of GC between April 2008 and December 2020. Preoperative CT images at the third lumbar vertebra were used to develop a Transformer-based SMDL model for predicting recurrence-free survival (RFS) and disease-specific survival (DSS). The predictive performance of the SMDL model was assessed using the area under the curve (AUC) and benchmarked against both alternative artificial intelligence models and conventional body composition parameters. The association between the model score and survival was assessed using Cox regression analysis. An integrated model combining SMDL signature with clinical variables was constructed, and its discrimination and fairness were evaluated. A total of 1242, 311, and 94 patients were assigned to the training, internal, and external validation cohorts, respectively. The Transformer-based SMDL model yielded AUCs of 0.791–0.943 for predicting RFS and DSS across all three cohorts and significantly outperformed other models and body composition parameters. The model score was a strong independent prognostic factor for survival. Incorporating the SMDL signature into the clinical model resulted in better prognostic prediction performance. The false-negative and false-positive rates of the integrated model were similar across sex and age subgroups, indicating robust fairness. The Transformer-based SMDL model could accurately predict survival of GC and identify patients at high risk of recurrence or death, thereby assisting clinical decision-making.

PURPOSE:To develop an integrative radiopathomic model based on deep learning to predict overall survival (OS) in locally advanced nasopharyngeal carcinoma (LANPC) patients. MATERIALS AND METHODS:A cohort of 343 LANPC patients with pretreatment MRI and whole slide image (WSI) were randomly divided into training (n = 202), validation (n = 91), and external test (n = 50) sets. For WSIs, a self-attention mechanism was employed to assess the significance of different patches for the prognostic task, aggregating them into a WSI-level representation. For MRI, a multilayer perceptron was used to encode the extracted radiomic features, resulting in an MRI-level representation. These were combined in a multimodal fusion model to produce prognostic predictions. Model performances were evaluated using the concordance index (C-index), and Kaplan-Meier curves were employed for risk stratification. To enhance model interpretability, attention-based and Integrated Gradients techniques were applied to explain how WSIs and MRI features contribute to prognosis predictions. RESULTS:The radiopathomics model achieved high predictive accuracy in predicting the OS, with a C-index of 0.755 (95 % CI: 0.673-0.838) and 0.744 (95 % CI: 0.623-0.808) in the training and validation sets, respectively, outperforming single-modality models (radiomic signature: 0.636, 95 % CI: 0.584-0.688; deep pathomic signature: 0.736, 95 % CI: 0.684-0.810). In the external test, similar findings were observed for the predictive performance of the radiopathomics, radiomic signature, and deep pathomic signature, with their C-indices being 0.735, 0.626, and 0.660 respectively. The radiopathomics model effectively stratified patients into high- and low-risk groups (P < 0.001). Additionally, attention heatmaps revealed that high-attention regions corresponded with tumor areas in both risk groups. CONCLUSION:The radiopathomics model holds promise for predicting clinical outcomes in LANPC patients, offering a potential tool for improving clinical decision-making.

Background Accurate prediction of tumor response to neoadjuvant immunochemotherapy (NAIC) enables personalized perioperative therapy for resectable non-small cell lung cancer (NSCLC). Objective The present aimed to evaluate the predictive value of radiomics derived from the tumor-parenchyma invasive zone for response to NAIC in resectable NSCLC, with the goal of developing a more accurate and clinically applicable model. Methods Patients with pathologically proven NSCLC from August 2019 and March 2025 were retrospectively included from two medical centers. In the training set, radiomics features were extracted from the whole tumor region and tumor margin region (6mm) respectively. Following feature selection via intraclass correlation coefficient and least absolute shrinkage and selection operator, the Whole Tumor Model (WTM) and Tumor Margin model (TMM) were developed to non-invasively predict major pathological response (MPR) following NAIC. The performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value, and negative predictive value in the internal validation and external test sets. The optimal radiomics model and clinical characteristics were combined to build the hybrid model (HM). Results A total of 169 patients (median age, 60 years; 154 men) were divided into training, internal validation and external test sets, with 104 patients (61.5%) achieving MPR. In the test dataset, WTM and TMM achieved AUCs of 0.71 (95% CI: 0.54–0.89) and 0.84 (95% CI: 0.71–0.97), respectively. After incorporating tumor margin radiomics features and clinical predictors(pathology), the HM demonstrated satisfactory performance in the training set (AUC: 0.88, 95% CI: 0.81–0.95) and internal validation set (AUC: 0.86, 95% CI: 0.74–0.98). In the independent external test set, the HM obtained satisfactory performance (AUC = 0.87, 95% CI: 0.76–0.98). Decision curves analysis indicated that the radiomics-clinical combined nomogram provided significant clinical utility. Conclusion A radiomics model based on the tumor margin region outperformed the whole-tumor model in predicting MPR in NSCLC. Our study developed a novel tool to predict the response of NSCLC to NAIC, which demonstrated excellent performance.

ObjectiveTo develop and validate a radiomics model based on vertebral calcium-suppressed (CaSupp) images derived from dual-layer computed tomography (DLCT) for predicting chemotherapy-induced myelosuppression in patients with locally advanced nasopharyngeal carcinoma (LANPC).MethodsThis retrospective study included 150 LANPC patients treated with induction chemotherapy (IC). Radiomics features were extracted from lumbar vertebral CaSupp obtained from baseline DLCT scans. Models were developed to predict myelosuppression after the first chemotherapy cycle (IC - 1) and entire chemotherapy cycles (IC-n). The clinics, radiomics, and combined models were conducted via multivariate logistic regression. Models performance was evaluated by the area under the receiver operating characteristic curve (AUC). Clinical utility was analyzed with decision curve analysis.ResultsFor predict myelosuppression after IC - 1, the clinics, radiomics, and combined models had AUC values of 0.716, 0.825 and 0.859 in the train cohort, respectively; and AUC of 0.687, 0.752 and 0.790 in the test cohort, respectively. And for IC-n, the clinics, radiomics, and combined models exhibited AUC values of 0.771, 0.824, and 0.889 in the train cohort, respectively; and AUC of 0.652, 0.740 and 0.806 in the test cohort, respectively. For predicting myelosuppression after both IC - 1 and IC-n,the combined models demonstrated significantly higher AUC values than the clinics models for both IC - 1 and IC-n (all P<0.05).ConclusionsRadiomics model based on vertebral CaSupp images from DLCT could predict chemotherapy-induced myelosuppression in LANPC patients. This study highlights the potential of DLCT technology to provide quantitative bone marrow assessments and aid in personalized treatment planning. External validation and comparison with other imaging modalities are warranted in the future.

Background:Anemia negatively affects an individual's overall prognosis and quality of life, and thus represents a significant health burden. Dual-layer computed tomography (DLCT) detector imaging enables substance differentiation. This study aimed to compare the performance of DLCT parameters for different blood vessels in detecting anemia. Methods:DLCT parameter values [i.e., the computed tomography (CT) value, effective atomic number, and electron density] were retrospectively derived from the aortic arch, pulmonary artery, and portal vein of 240 patients. Differences in DLCT parameters between the anemia and normal groups were analyzed. Pearson correlation analysis and logistic regression models were employed to examine the relationships between the DLCT parameters and hemoglobin concentration. The diagnostic performance of DLCT parameters for anemia among different blood vessels was evaluated by receiver operating characteristic (ROC) analysis. Results:The anemia group (n=101) had significantly lower hemoglobin concentration than the normal group (n=139) (107.96±13.95 vs. 138.40±12.64 g/L, P<0.001), as well as significantly lower CT and electron density values for the three vessels (all P<0.05). The CT value and effective atomic number of the portal vein were significantly lower than those of the aortic arch and pulmonary artery (all P<0.05). The correlation of the CT value of the portal vein to hemoglobin concentration was significantly lower than that of the aortic arch (r=0.435 vs. 0.583, P=0.029) and slightly lower than that of the pulmonary artery (r=0.435 vs. 0.527, P=0.192). Regarding the correlation between electron density and hemoglobin concentration, there were no significant differences among the three blood vessels (all P>0.05). When using the CT value to detect anemia, the aortic arch had an area under the curve (AUC) value of 0.79, which was significantly higher than that of the portal vein (AUC =0.68, P=0.008) and slightly higher than that of the pulmonary artery (AUC =0.73, P=0.126). In relation to electron density, the aortic arch had an AUC value of 0.81, which was slightly higher than that of both the portal vein (AUC =0.77, P=0.239) and the pulmonary artery (AUC =0.75, P=0.095). Among the six CT predictors, the CT value of the portal vein had the lowest AUC value (AUC =0.68), and the value was significantly lower than that of the aortic arch (P=0.008), that of the electron density of the aortic arch (P=0.002), and that of electron density of the portal vein (P=0.007). The multivariable logistic regression showed that the CT value of the aortic arch, electron density of the pulmonary artery, and electron density of the portal vein were independent predictors of anemia. The logistic regression model that integrated the above three CT indicators showed the best performance (AUC =0.85) in predicting anemia, outperforming any single CT predictor of an individual vessel (all P<0.05). Conclusions:DLCT may assist in the detection of anemia. The DLCT parameters of the aortic arch demonstrated higher performance than those of the pulmonary artery and portal vein. Additionally, integrating different DLCT parameters (i.e., the CT value and electron density) of multiple vessels may improve diagnostic performance.

INTRODUCTION:Stable coronary artery disease (CAD) is a leading cause of cardiac morbidity and mortality worldwide, with elevated native T1 value linked to major adverse cardiovascular events. However, predictors of elevated native T1 value in stable CAD still need to be studied. This study aimed to identify clinical and imaging predictors of elevated native T1 values in CAD patients. METHODS:A total of 316 consecutive stable CAD patients (median age 58 years, 91.8% male) undergoing coronary computed tomography angiography and cardiovascular magnetic resonance native T1 mapping were included, along with 30 age- and sex-matched healthy controls. Patients were divided into normal and elevated native T1 groups based on the normal global native T1 reference; logistic regressions were used to identify predictors. RESULTS:Patients with elevated native T1 values were more likely to be aged ≥60 years, abstain from alcohol, have abnormal electrocardiogram findings, multivessel disease, noncalcified plaques, greater degrees of stenosis, stenosis ≥50% in two or three coronary arteries, and computed tomography-derived fractional flow reserve ≤0.8 (p < 0.05). Multivariate logistic regression identified age ≥60 years (odd ratio [OR]: 2.23, 95% confidence interval [95% CI]: 1.15-4.30, p = 0.018), stenosis ≥50% in two (OR: 13.27, 95% CI: 3.38-56.94, p < 0.001) or three coronary arteries (OR: 114.19, 95% CI: 20.53-276.59, p < 0.001), and left anterior descending FFR ≤0.8 (OR: 2.69, 95% CI: 1.16-6.29, p = 0.021) as independent risk factors, whereas alcohol consumption (OR: 0.47, 95% CI: 0.25-0.88, p = 0.019) was a predictor of normal native T1 values, with strong predictive performance (area under the curve = 0.832, Brier score = 0.142). CONCLUSION:Our findings could help clinicians make individualized diagnosis and treatment of stable CAD patients, which also provide a foundation for predicting prognosis. This research has been registered in the National Medical Research Registration and Filing Information System, numbered MR-32-24-030226.

Prognostic prediction plays a pivotal role in guiding personalized treatment for patients with locoregionally advanced nasopharyngeal carcinoma (LANPC). However, few studies have investigated the incremental value of functional MRI to the conventional MRI-based radiomic models. Here, we aimed to develop a radiomic model including functional MRI to predict the prognosis of LANPC patients. One hundred and twenty-six patients (training dataset, n = 88; validation dataset, n = 38) with LANPC were retrospectively included. Radiomic features were extracted from T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), contrast-enhanced T1WI (cT1WI), and diffusion-weighted imaging (DWI). Pearson correlation analysis and recursive feature elimination or Relief were used for identifying features associated with progression-free survival (PFS). Five machine learning algorithms with cross-validation were compared to develop the optimal single-layer and fusion radiomic models. Clinical and combined models were developed via multivariate Cox regression model. The clinical model based on TNM stage achieved a C-index of 0.544 in the validation dataset. The fusion radiomic model, incorporating DWI-, T1WI-, and cT1WI-derived imaging features, yielded the highest C-index of 0.788, outperforming DWI-based (C-index = 0.739), T1WI-based (C-index = 0.734), cT1WI-based (C-index = 0.722), and T1WI plus cT1WI-based models (C-index = 0.747) in predicting PFS. The fusion radiomic model yielded the C-index of 0.786 and 0.690 in predicting distant metastasis-free survival and overall survival, respectively. However, the addition of TNM stage to the fusion radiomic model could not improve the predictive power. The fusion radiomic model demonstrates favorable performance in predicting survival outcomes in LANPC patients, surpassing TNM staging alone. Integration of DWI-derived features into conventional MRI radiomic models could enhance predictive accuracy.

BACKGROUND:Pulmonary sclerosing pneumocytoma (PSP) and pulmonary carcinoid (PC) are difficult to distinguish based on conventional imaging examinations. In recent years, radiomics has been used to discriminate benign from malignant pulmonary lesions. However, the value of radiomics based on computed tomography (CT) images to differentiate PSP from PC has not been well explored.PURPOSE:We aimed to investigate the feasibility of radiomics in the differentiation between PSP and PC.METHODS:Fifty-three PSP and fifty-five PC were retrospectively enrolled and then were randomly divided into the training and test sets. Univariate and multivariable logistic analyses were carried to select clinical predictor related to differential diagnosis of PSP and PC. A total of 1316 radiomics features were extracted from the unenhanced CT (UECT) and contrast-enhanced CT (CECT) images, respectively. The minimum redundancy maximum relevance and the least absolute shrinkage and selection operator were used to select the most significant radiomics features to construct radiomics models. The clinical predictor and radiomics features were integrated to develop combined models. Two senior radiologists independently categorized each patient into PSP or PC group based on traditional CT method. The performances of clinical, radiomics, and combined models in differentiating PSP from PC were investigated by the receiver operating characteristic (ROC) curve. The diagnostic performance was also compared between the combined models and radiologists.RESULTS:In regard to differentiating PSP from PC, the area under the curves (AUCs) of the clinical, radiomics, and combined models were 0.87, 0.96, and 0.99 in the training set UECT, and were 0.87, 0.97, and 0.98 in the training set CECT, respectively. The AUCs of the clinical, radiomics, and combined models were 0.84, 0.92, and 0.97 in the test set UECT, and were 0.84, 0.93, and 0.98 in the test set CECT, respectively. In regard to the differentiation between PSP and PC, the combined model was comparable to the radiomics model, but outperformed the clinical model and the two radiologists, whether in the test set UECT or CECT.CONCLUSIONS:Radiomics approaches show promise in distinguishing between PSP and PC. Moreover, the integration of clinical predictor (gender) has the potential to enhance the diagnostic performance even further.