Silanol-Stabilized Atomically Dispersed Ptδ+-Ox-Sn Active Sites in Protozeolite for Propane Dehydrogenation.

Crystalline zeolites have been proven to be excellent supports for confining subnanometric metal catalysts to boost the propane dehydrogenation (PDH) reaction. However, the introduced metallic species may suffer from severe sintering and limited stability during the catalytic process, especially when utilizing an industrial impregnation method for metal incorporation. In this study, we developed a new type of support based on amorphous protozeolite (PZ), taking advantage of its adjustable silanol chemistry and zeolitic microporous characteristic for stabilizing atomically dispersed PtSn catalyst via a simple, cost-effective coimpregnation process. The combination of X-ray absorption spectroscopy, X-ray photoelectron spectroscopy, in situ diffuse reflectance infrared Fourier transform spectroscopy under CO atmosphere, and density functional theory calculations confirmed the formation of highly dispersed active Ptδ+-Ox-Sn species in PtSn/PZ. The PtSn/PZ catalyst exhibited a high propane conversion of 45.4% and a high propylene selectivity of 99% (WHSV= 3.6 h-1, 550 °C), with a high apparent rate coefficient of 565 molC3H6·gPt-1·h-1·bar-1 at a high WHSV of 108 h-1, presenting a top-level performance among the state-of-the-art Pt-based catalysts prepared by in situ synthesis and impregnation methods. The silanol density determined the chemical state of PtSn species, showing a change from atomically dispersed Ptδ+-Ox-Sn sites to PtSn alloy with decreasing silanol density of supports. This work provides a general strategy using silanol-rich amorphous protozeolite as support for stabilizing various metal catalysts by the simple impregnation method and also offers an effective way for fine tailoring the chemical state of metallic species via a silanol-engineered approach.

Deep Learning Radiomics Nomogram Based on Enhanced CT to Predict the Response of Metastatic Lymph Nodes to Neoadjuvant Chemotherapy in Locally Advanced Gastric Cancer.

BACKGROUND: We aimed to construct and validate a deep learning (DL) radiomics nomogram using baseline and restage enhanced computed tomography (CT) images and clinical characteristics to predict the response of metastatic lymph nodes to neoadjuvant chemotherapy (NACT) in locally advanced gastric cancer (LAGC). METHODS: We prospectively enrolled 112 patients with LAGC who received NACT from January 2021 to August 2022. After applying the inclusion and exclusion criteria, 98 patients were randomized 7:3 to the training cohort (n = 68) and validation cohort (n = 30). We established and compared three radiomics signatures based on three phases of CT images before and after NACT, namely radiomics-baseline, radiomics-delta, and radiomics-restage. Then, we developed a clinical model, DL model, and a nomogram to predict the response of LAGC after NACT. We evaluated the predictive accuracy and clinical validity of each model using the receiver operating characteristic curve and decision curve analysis, respectively. RESULTS: The radiomics-delta signature was the best predictor among the three radiomics signatures. So, we developed and validated a DL delta radiomics nomogram (DLDRN). In the validation cohort, the DLDRN produced an area under the receiver operating curve of 0.94 (95% confidence interval, 0.82-0.96) and demonstrated adequate differentiation of good response to NACT. Furthermore, the DLDRN significantly outperformed the clinical model and DL model (p < 0.001). The clinical utility of the DLDRN was confirmed through decision curve analysis. CONCLUSIONS: In patients with LAGC, the DLDRN effectively predicted a therapeutic response in metastatic lymph nodes, which could provide valuable information for individualized treatment.

Parallel CNN-Deep Learning Clinical-Imaging Signature for Assessing Pathologic Grade and Prognosis of Soft Tissue Sarcoma Patients.

BACKGROUND: Traditional biopsies pose risks and may not accurately reflect soft tissue sarcoma (STS) heterogeneity. MRI provides a noninvasive, comprehensive alternative. PURPOSE: To assess the diagnostic accuracy of histological grading and prognosis in STS patients when integrating clinical-imaging parameters with deep learning (DL) features from preoperative MR images. STUDY TYPE: Retrospective/prospective. POPULATION: 354 pathologically confirmed STS patients (226 low-grade, 128 high-grade) from three hospitals and the Cancer Imaging Archive (TCIA), divided into training (n = 185), external test (n = 125), and TCIA cohorts (n = 44). 12 patients (6 low-grade, 6 high-grade) were enrolled into prospective validation cohort. FIELD STRENGTH/SEQUENCE: 1.5 T and 3.0 T/Unenhanced T1-weighted and fat-suppressed-T2-weighted. ASSESSMENT: DL features were extracted from MR images using a parallel ResNet-18 model to construct DL signature. Clinical-imaging characteristics included age, gender, tumor-node-metastasis stage and MRI semantic features (depth, number, heterogeneity at T1WI/FS-T2WI, necrosis, and peritumoral edema). Logistic regression analysis identified significant risk factors for the clinical model. A DL clinical-imaging signature (DLCS) was constructed by incorporating DL signature with risk factors, evaluated for risk stratification, and assessed for progression-free survival (PFS) in retrospective cohorts, with an average follow-up of 23 ± 22 months. STATISTICAL TESTS: Logistic regression, Cox regression, Kaplan-Meier curves, log-rank test, area under the receiver operating characteristic curve (AUC)，and decision curve analysis. A P-value <0.05 was considered significant. RESULTS: The AUC values for DLCS in the external test, TCIA, and prospective test cohorts (0.834, 0.838, 0.819) were superior to clinical model (0.662, 0.685, 0.694). Decision curve analysis showed that the DLCS model provided greater clinical net benefit over the DL and clinical models. Also, the DLCS model was able to risk-stratify patients and assess PFS. DATA CONCLUSION: The DLCS exhibited strong capabilities in histological grading and prognosis assessment for STS patients, and may have potential to aid in the formulation of personalized treatment plans. TECHNICAL EFFICACY: Stage 2.

Development and validation of a CT-based deep learning radiomics signature to predict lymph node metastasis in oropharyngeal squamous cell carcinoma: a multicenter study.

OBJECTIVES: Lymph node metastasis (LNM) is a pivotal determinant that influences the treatment strategies and prognosis for oropharyngeal squamous cell carcinoma (OPSCC) patients. This study aims to establish and verify a deep learning (DL) radiomics model for the prediction of LNM in OPSCCs using contrast-enhanced computed tomography (CECT). METHODS: A retrospective analysis included 279 OPSCC patients from three institutions. CECT images were used for handcrafted (HCR) and DL feature extraction. Dimensionality reduction for HCR features used recursive feature elimination and least absolute shrinkage and selection operator algorithms, whereas DL feature dimensionality reduction used variance-threshold and recursive feature elimination algorithms. Radiomics signatures were constructed using support vector machine, decision tree, random forest, k-nearest neighbor, gaussian naive bayes classifiers and light gradient boosting machine. A combined model was then constructed using the screened DL, HCR, and clinical features. The area under the receiver operating characteristic curve (AUC) served to quantify the model's performance, and calibration curves were utilized to assess its calibration. RESULTS: The combined model exhibited robust performance, achieving AUC values of 0.909 (95% CI: 0.861-0.957) in the training cohort, 0.884 (95% CI: 0.800-0.968) in the internal validation cohort, and 0.865 (95% CI: 0.791-0.939) in the external validation cohort. It outperformed both the clinical model and best-performing radiomics model. Moreover, calibration was deemed satisfactory. CONCLUSIONS: The combined model based on CECT demonstrates the potential to predict LNM in OPSCCs preoperatively, offering a valuable tool for more precise and tailored treatment strategies. ADVANCES IN KNOWLEDGE: This study presents a novel combined model integrating clinical factors with deep learning radiomics, significantly enhancing preoperative LNM prediction in OPSCC.

An MRI-Based Radiomics Nomogram to Assess Recurrence Risk in Sinonasal Malignant Tumors.

BACKGROUND: Sinonasal malignant tumors (SNMTs) have a high recurrence risk, which is responsible for the poor prognosis of patients. Assessing recurrence risk in SNMT patients is a current problem. PURPOSE: To establish an MRI-based radiomics nomogram for assessing relapse risk in patients with SNMT. STUDY TYPE: Retrospective. POPULATION: A total of 143 patients with 68.5% females (development/validation set, 98/45 patients). FIELD STRENGTH/SEQUENCE: A 1.5-T and 3-T, fat-suppressed fast spin echo (FSE) T2-weighted imaging (FS-T2WI), FSE T1-weighted imaging (T1WI), and FSE contrast-enhanced T1WI (T1WI + C). ASSESSMENT: Three MRI sequences were used to manually delineate the region of interest. Three radiomics signatures (T1WI and FS-T2WI sequences, T1WI + C sequence, and three sequences combined) were built through dimensional reduction of high-dimensional features. The clinical model was built based on clinical and MRI features. The Ki-67-based and tumor-node-metastasis (TNM) model were established for comparison. The radiomics nomogram was built by combining the clinical model and best radiomics signature. The relapse-free survival analysis was used among 143 patients. STATISTICAL TESTS: The intraclass/interclass correlation coefficients, univariate/multivariate Cox regression analysis, least absolute shrinkage and selection operator Cox regression algorithm, concordance index (C index), area under the curve (AUC), integrated Brier score (IBS), DeLong test, Kaplan-Meier curve, log-rank test, optimal cutoff values. A P value < 0.05 was considered statistically significant. RESULTS: The T1 + C-based radiomics signature had best prognostic ability than the other two signatures (T1WI and FS-T2WI sequences, and three sequences combined). The radiomics nomogram had better prognostic ability and less error than the clinical model, Ki-67-based model, and TNM model (C index, 0.732; AUC, 0.765; IBS, 0.185 in the validation set). The cutoff values were 0.2 and 0.7 and then the cumulative risk rates were calculated. DATA CONCLUSION: A radiomics nomogram for assessing relapse risk in patients with SNMT may provide better prognostic ability than the clinical model, Ki-67-based model, and TNM model. EVIDENCE LEVEL: 3. TECHNICAL EFFICACY: Stage 5.

Primary bone tumor detection and classification in full-field bone radiographs via YOLO deep learning model.

OBJECTIVES: Automatic bone lesions detection and classifications present a critical challenge and are essential to support radiologists in making an accurate diagnosis of bone lesions. In this paper, we aimed to develop a novel deep learning model called You Only Look Once (YOLO) to handle detecting and classifying bone lesions on full-field radiographs with limited manual intervention. METHODS: In this retrospective study, we used 1085 bone tumor radiographs and 345 normal bone radiographs from two centers between January 2009 and December 2020 to train and test our YOLO deep learning (DL) model. The trained model detected bone lesions and then classified these radiographs into normal, benign, intermediate, or malignant types. The intersection over union (IoU) was used to assess the model's performance in the detection task. Confusion matrices and Cohen's kappa scores were used for evaluating classification performance. Two radiologists compared diagnostic performance with the trained model using the external validation set. RESULTS: In the detection task, the model achieved accuracies of 86.36% and 85.37% in the internal and external validation sets, respectively. In the DL model, radiologist 1 and radiologist 2 achieved Cohen's kappa scores of 0.8187, 0.7927, and 0.9077 for four-way classification in the external validation set, respectively. The YOLO DL model illustrated a significantly higher accuracy for intermediate bone tumor classification than radiologist 1 (95.73% vs 88.08%, p = 0.004). CONCLUSIONS: The developed YOLO DL model could be used to assist radiologists at all stages of bone lesion detection and classification in full-field bone radiographs. KEY POINTS: • YOLO DL model can automatically detect bone neoplasms from full-field radiographs in one shot and then simultaneously classify radiographs into normal, benign, intermediate, or malignant. • The dataset used in this retrospective study includes normal bone radiographs. • YOLO can detect even some challenging cases with small volumes.

Na Cocations and Hydrothermal Aging Cooperatively Boost the Regeneration of Phosphorus-Poisoned Pd/SSZ-13 for Passive NOx Adsorption.

Pd/SSZ-13 has been proposed as a passive NOx adsorber (PNA) for low-temperature NOx adsorption. However, it remains challenging for Pd/SSZ-13 to work efficiently when suffering from phosphorus poisoning. Herein, we report a simple and efficient strategy to regenerate the phosphorus-poisoned Pd/SSZ-13 based on the cooperation between hydrothermal aging treatment and Na cocations. It was found that hydrothermal aging treatment enabled the redispersion of Pd and P-containing species in phosphorus-poisoned Pd/SSZ-13. Meanwhile, the presence of Na cocations significantly reduced the formation of AlPO4 and retained more paired Al sites for highly dispersed Pd2+ ions, which was of great importance for the recovery of adsorption performance. To our satisfaction, the restoration ratio of the adsorption capacity of poisoned Pd/SSZ-13 was >90% after regeneration. Strikingly, the NOx adsorption activities of phosphorus-poisoned Pd/SSZ-13 with phosphorus loadings of 0.2 and 0.4 mmol g-1 almost completely recovered upon regeneration. This study demonstrates the promoting effect of Na cocations on the regeneration of phosphorus-poisoned Pd/SSZ-13 by hydrothermal aging treatment, which provides useful guidance for the design of PNA materials with excellent durability for cold-start application.

A Computed Tomography Radiomics Nomogram in Differentiating Chordoma From Giant Cell Tumor in the Axial Skeleton.

OBJECTIVE: The aim of the study is to develop and validate a computed tomography (CT) radiomics nomogram for preoperatively differentiating chordoma from giant cell tumor (GCT) in the axial skeleton. METHODS: Seventy-three chordomas and 38 GCTs in axial skeleton were retrospectively included and were divided into a training cohort (n = 63) and a test cohort (n = 48). The radiomics features were extracted from CT images. A radiomics signature was developed by using the least absolute shrinkage and selection operator model, and a radiomics score (Rad-score) was acquired. By combining the Rad-score with independent clinical risk factors using multivariate logistic regression model, a radiomics nomogram was established. Calibration and receiver operator characteristic curves were used to assess the performance of the nomogram. RESULTS: Five features were selected to construct the radiomics signature. The radiomics signature showed favorable discrimination in the training cohort (area under the curve [AUC], 0.860; 95% confidence interval [CI], 0.760-0.960) and the test cohort (AUC, 0.830; 95% CI, 0.710-0.950). Age and location were the independent clinical factors. The radiomics nomogram combining the Rad-score with independent clinical factors showed good discrimination capability in the training cohort (AUC, 0.930; 95% CI, 0.880-0.990) and the test cohort (AUC, 0.980; 95% CI, 0.940-1.000) and outperformed the radiomics signature ( z = 2.768, P = 0.006) in the test cohort. CONCLUSIONS: The CT radiomics nomogram shows good predictive efficacy in differentiating chordoma from GCT in the axial skeleton, which might facilitate clinical decision making.

TIGIT is the central player in T-cell suppression associated with CAR T-cell relapse in mantle cell lymphoma.

BACKGROUND: Chimeric antigen receptor (CAR) T-cell therapy using brexucabtagene autoleucel (BA) induces remission in many patients with mantle cell lymphoma (MCL), and BA is the only CAR T-cell therapy approved by the FDA for MCL. However, development of relapses to BA is recognized with poor patient outcomes. Multiple CAR T-cell therapies have been approved for other lymphomas and the resistance mechanisms have been investigated. However, the mechanisms underlying BA relapse in MCL have not been investigated and whether any previously reported resistance mechanisms apply to BA-relapsed patients with MCL is unknown. METHODS: To interrogate BA resistance mechanisms in MCL, we performed single-cell RNA sequencing on 39 longitudinally collected samples from 15 BA-treated patients, and multiplex cytokine profiling on 80 serial samples from 20 patients. RESULTS: We demonstrate that after BA relapse, the proportion of T cells, especially cytotoxic T cells (CTLs), decreased among non-tumor cells, while the proportion of myeloid cells correspondingly increased. TIGIT, LAG3, and CD96 were the predominant checkpoint molecules expressed on exhausted T cells and CTLs; only TIGIT was significantly increased after relapse. CTLs expanded during remission, and then contracted during relapse with upregulated TIGIT expression. Tumor cells also acquired TIGIT expression after relapse, leading to the enhanced interaction of tumor cell TIGIT with monocyte CD155/PVR. In myeloid cells, post-relapse HLA-II expression was reduced relative to pretreatment and during remission. Myeloid-derived suppressor cells (MDSCs) were enriched after relapse with elevated expression of activation markers, including CLU (clusterin) and VCAN (versican). Extracellular chemokines (CCL4, CXCL9, CXCL13), soluble checkpoint inhibitors (sPD-L1, sTIM3, s4-1BB), and soluble receptors (sIL-2R, sTNFRII) were decreased during remission but elevated after relapse. CONCLUSIONS: Our data demonstrate that multiple tumor-intrinsic and -extrinsic factors are associated with T-cell suppression and BA relapse. Among these, TIGIT appears to be the central player given its elevated expression after BA relapse in not only CTLs but also MCL cells. The acquisition of TIGIT expression on tumor cells is MCL-specific and has not been reported in other CAR T-treated diseases. Together, our data suggest that co-targeting TIGIT may prevent CAR T relapses and thus promote long-term progression-free survival in MCL patients.

Immuno-genomic characterisation of high-grade serous ovarian cancer reveals immune evasion mechanisms and identifies an immunological subtype with a favourable prognosis and improved therapeutic efficacy.

BACKGROUND: Immunotherapy has revolutionised the field of cancer therapy and immunology, but has demonstrated limited therapeutic efficacy in high-grade serous ovarian cancer (HGSOC). METHODS: Multi-omics data of 495 TCGA HGSOC tumours and RNA-seq data of 1708 HGSOC tumours were analyzed. Multivariate Cox regression analysis and meta-analyses were used to identify prognostic genes. The immune microenvironment was characterised using the ssGSEA methods for 28 immune cell types. Immunohistochemistry staining of tumour tissues of 14 patients was used to validate the key findings further. RESULTS: A total of 1142 genes were identified as favourable prognostic genes, which are prevailing in immune-related pathways and the infiltration of most immune subpopulations was observed to be associated with a favourable prognosis suggesting that tumour immunogenicity was the most prominent factor associated with improved clinical outcomes and response to chemotherapy of HGSOC. We identified multiple genomic and transcriptomic determinants of immunogenicity, including the copy loss of chromosome 4q and deficiencies of the homologous recombination pathway. Finally, an immunological subtype characterised by increased infiltration of activated CD8 T cells and decreased Tregs was associated with favourable prognosis and improved therapeutic efficacy. CONCLUSIONS: Our study characterised the immunogenomic landscape and refined the immunological classifications of HGSOC. This may improve the selection of patients with HGSOC who are suitable candidates for immunotherapy.

The radiomics-based tumor heterogeneity adds incremental value to the existing prognostic models for predicting outcome in localized clear cell renal cell carcinoma: a multicenter study.

PURPOSE: Tumor heterogeneity, which is associated with poor outcomes, has not been exhibited in the University of California, Los Angeles, Integrated Staging System (UISS), and the Stage, Size, Grade and Necrosis (SSIGN) scores. Radiomics allows an in-depth characterization of heterogeneity across the tumor, but its incremental value to the existing prognostic models for clear cell renal cell carcinoma (ccRCC) outcome is unknown. The purpose of this study was to evaluate the association between the radiomics-based tumor heterogeneity and postoperative risk of recurrence in localized ccRCC, and to assess its incremental value to UISS and SSIGN. METHODS: A multicenter 866 ccRCC patients derived from 12 Chinese hospitals were studied. The endpoint was recurrence-free survival (RFS). A CT-based radiomics signature (RS) was developed and assessed in the whole cohort and in the subgroups stratified by UISS and SSIGN. Two combined nomograms, the R-UISS (combining RS and UISS) and R-SSIGN (combining RS and SSIGN), were developed. The incremental value of RS to UISS and SSIGN in RFS prediction was evaluated. R statistical software was used for statistics. RESULTS: Patients with low radiomics scores were 4.44 times more likely to experience recurrence than those with high radiomics scores (P<0.001). Stratified analysis suggested the association is significant among low- and intermediate-risk patients identified by UISS and SSIGN. The R-UISS and R-SSIGN showed better predictive capability than UISS and SSIGN did with higher C-indices (R-UISS vs. UISS, 0.74 vs. 0.64; R-SSIGN vs. SSIGN, 0.78 vs. 0.76) and higher clinical net benefit. CONCLUSIONS: The radiomics-based tumor heterogeneity can predict outcome and add incremental value to the existing prognostic models in localized ccRCC patients. Incorporating radiomics-based tumor heterogeneity in ccRCC prognostic models may provide the opportunity to better surveillance and adjuvant clinical trial design.

Multi-parametric MRI-based radiomics signature for preoperative prediction of Ki-67 proliferation status in sinonasal malignancies: a two-centre study.

OBJECTIVE: To assess the predictive ability of a multi-parametric MRI-based radiomics signature (RS) for the preoperative evaluation of Ki-67 proliferation status in sinonasal malignancies. METHODS: A total of 128 patients with sinonasal malignancies that underwent multi-parametric MRIs at two medical centres were retrospectively analysed. Data from one medical centre (n = 77) were used to develop the predictive models and data from the other medical centre (n = 51) constitute the test dataset. Clinical data and conventional MRI findings were reviewed to identify significant predictors. Radiomics features were determined using maximum relevance minimum redundancy and least absolute shrinkage and selection operator algorithms. Subsequently, RSs were established using a logistic regression (LR) algorithm. The predictive performance of RSs was assessed using calibration, decision curve analysis (DCA), accuracy, and AUC. RESULTS: No independent predictors of high Ki-67 proliferation were observed based on clinical data and conventional MRI findings. RS-T1, RS-T2, and RS-T1c (contrast enhancement T1WI) were established based on a single-parametric MRI. RS-Combined (combining T1WI, FS-T2WI, and T1c features) was developed based on multi-parametric MRI and achieved an AUC and accuracy of 0.852 (0.733-0.971) and 86.3%, respectively, on the test dataset. The calibration curve and DCA demonstrated an improved fitness and benefits in clinical practice. CONCLUSIONS: A multi-parametric MRI-based RS may be used as a non-invasive, dependable, and accurate tool for preoperative evaluation of the Ki-67 proliferation status to overcome the sampling bias in sinonasal malignancies. KEY POINTS: • Multi-parametric MRI-based radiomics signatures (RSs) are used to preoperatively evaluate the proliferation status of Ki-67 in sinonasal malignancies. • Radiomics features are determined using maximum relevance minimum redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) algorithms. • RSs are established using a logistic regression (LR) algorithm.

A CT-based radiomics nomogram for differentiation of squamous cell carcinoma and non-Hodgkin's lymphoma of the palatine tonsil.

OBJECTIVES: Accurate preoperative differentiation between squamous cell carcinoma (SCC) and non-Hodgkin's lymphoma (NHL) in the palatine tonsil is crucial because of their different treatment. This study aimed to construct and validate a contrast-enhanced CT (CECT)-based radiomics nomogram for preoperative differentiation of SCC and NHL in the palatine tonsil. METHODS: This study enrolled 135 patients with a pathological diagnosis of SCC or NHL from two clinical centers, who were divided into training (n = 94; SCC = 50, NHL = 44) and external validation sets (n = 41; SCC = 22, NHL = 19). A radiomics signature was constructed from radiomics features extracted from routine CECT images and a radiomics score (Rad-score) was calculated. A clinical model was established using demographic features and CT findings. The independent clinical factors and Rad-score were combined to construct a radiomics nomogram. Performance of the clinical model, radiomics signature, and nomogram was assessed using receiver operating characteristics analysis and decision curve analysis. RESULTS: Eleven features were finally selected to construct the radiomics signature. The radiomics nomogram incorporating gender, mean CECT value, and radiomics signature showed better predictive value for differentiating SCC from NHL than the clinical model for training (AUC, 0.919 vs. 0.801, p = 0.004) and validation (AUC, 0.876 vs. 0.703, p = 0.029) sets. Decision curve analysis demonstrated that the radiomics nomogram was more clinically useful than the clinical model. CONCLUSIONS: A CECT-based radiomics nomogram was constructed incorporating gender, mean CECT value, and radiomics signature. This nomogram showed favorable predictive efficacy for differentiating SCC from NHL in the palatine tonsil, and might be useful for clinical decision-making. KEY POINTS: • Differential diagnosis between SCC and NHL in the palatine tonsil is difficult by conventional imaging modalities. • A radiomics nomogram integrated with the radiomics signature, gender, and mean contrast-enhanced CT value facilitates differentiation of SCC from NHL with improved diagnostic efficacy.

Deep learning radiomic nomogram to predict recurrence in soft tissue sarcoma: a multi-institutional study.

OBJECTIVES: To evaluate the performance of a deep learning radiomic nomogram (DLRN) model at predicting tumor relapse in patients with soft tissue sarcomas (STS) who underwent surgical resection. METHODS: In total, 282 patients who underwent MRI and resection for STS at three independent centers were retrospectively enrolled. In addition, 113 of the 282 patients received additional contrast-enhanced MRI scans. We separated the participants into a development cohort and an external test cohort. The development cohort consisted of patients from one center and the external test cohort consisted of patients from two other centers. Two MRI-based DLRNs for prediction of tumor relapse after resection of STS were established. We universally tested the DLRNs and compared them with other prediction models constructed by using widespread adopted predictors (i.e., staging systems and Ki67) instead of radiomics features. RESULTS: The DLRN1 model incorporated plain MRI-based radiomics signature into the clinical data, and the DLRN2 model integrated radiomics signature extracted from plain and contrast-enhanced MRI with the clinical predictors. Across both study sets, the two MRI-based DLRNs had relatively better prognostic capability (C index ≥ 0.721 and median AUC ≥ 0.746; p < 0.05 compared with most other models and predictors) and less opportunity for prediction error (integrated Brier score ≤ 0.159). The decision curve analysis indicates that the DLRNs have greater benefits than staging systems, Ki67, and other models. We selected appropriate cutoff values for the DLRNs to divide STS recurrence into three risk strata (low, medium, and high) and calculated those groups' cumulative risk rates. CONCLUSION: The DLRNs were shown to be a reliable and externally validated tool for predicting STS recurrence by comparing with other prediction models. KEY POINTS: • The prediction of a high recurrence rate of STS before emergence of local recurrence can help to determine whether more active treatment should be implemented. • Two MRI-based DLRNs for prediction of tumor relapse were shown to be a reliable and externally validated tool for predicting STS recurrence. • We used the DLRNs to divide STS recurrence into three risk strata (low, medium, and high) to facilitate more targeted postoperative management in the clinic.

A computed tomography-based radiomics signature for predicting expression of programmed death ligand 1 in head and neck squamous cell carcinoma.

OBJECTIVES: Accurate prediction of the expression of programmed death ligand 1 (PD-L1) in head and neck squamous cell carcinoma (HNSCC) before immunotherapy is crucial. This study was performed to construct and validate a contrast-enhanced computed tomography (CECT)-based radiomics signature to predict the expression of PD-L1 in HNSCC. METHODS: In total, 157 patients with confirmed HNSCC who underwent CECT scans and immunohistochemical examination of tumor PD-L1 expression were enrolled in this study. The patients were divided into a training set (n = 104; 62 PD-L1-positive and 42 PD-L1-negative) and an external validation set (n = 53; 34 PD-L1-positive and 19 PD-L1-negative). A radiomics signature was constructed from radiomics features extracted from the CECT images, and a radiomics score was calculated. Performance of the radiomics signature was assessed using receiver operating characteristics analysis. RESULTS: Nine features were finally selected to construct the radiomics signature. The performance of the radiomics signature to distinguish between a PD-L1-positive and PD-L1-negative status in both the training and validation sets was good, with an area under the receiver operating characteristics curve of 0.852 and 0.802 for the training and validation sets, respectively. CONCLUSIONS: A CECT-based radiomics signature was constructed to predict the expression of PD-L1 in HNSCC. This model showed favorable predictive efficacy and might be useful for identifying patients with HNSCC who can benefit from anti-PD-L1 immunotherapy. KEY POINTS: • Accurate prediction of the expression of PD-L1 in HNSCC before immunotherapy is crucial. • A CECT-based radiomics signature showed favorable predictive efficacy in estimation of the PD-L1 expression status in patients with HNSCC.

Spinal MRI-Based Radiomics Analysis to Predict Treatment Response in Multiple Myeloma.

OBJECTIVE: The aim of this study was to explore the clinical utility of spinal magnetic resonance imaging-based radiomics to predict treatment response (TR) in patients with multiple myeloma (MM). METHODS: A total of 123 MM patients (85 in the training cohort and 38 in the test cohort) with complete response (CR) (n = 40) or non-CR (n = 83) were retrospectively enrolled in the study. Key feature selection and data dimension reduction were performed using the least absolute shrinkage and selection operator regression. A nomogram was built by combining radiomic signatures and independent clinical risk factors. The prediction performance of the nomogram was assessed using the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis. Treatment response was assessed by determining the serum and urinary levels of M-proteins, serum-free light chain ratio, and the percentage of bone marrow plasma cells. RESULTS: Thirteen features were selected to build a radiomic signature. The International Staging System (ISS) stage was selected as an independent clinical factor. The radiomic signature and nomogram showed better calibration and higher discriminatory capacity (AUC of 0.929 and 0.917 for the radiomics and nomogram in the training cohort, respectively, and 0.862 and 0.874 for the radiomics and nomogram in the test cohort, respectively) than the clinical model (AUC of 0.661 and 0.674 in the training and test cohort, respectively). Decision curve analysis confirmed the clinical utility of the radiomics model. CONCLUSIONS: Nomograms incorporating a magnetic resonance imaging-based radiomic signature and ISS stage help predict the response to chemotherapy for MM and can be useful in clinical decision-making.

Integrated genomic profiling and modelling for risk stratification in patients with advanced oesophagogastric adenocarcinoma.

OBJECTIVE: Prognosis of patients with advanced oesophagogastric adenocarcinoma (mEGAC) is poor and molecular determinants of shorter or longer overall survivors are lacking. Our objective was to identify molecular features and develop a prognostic model by profiling the genomic features of patients with mEGAC with widely varying outcomes. DESIGN: We profiled 40 untreated mEGACs (20 shorter survivors <13 months and 20 longer survivors >36 months) with whole-exome sequencing (WES) and RNA sequencing and performed an integrated analysis of exome, transcriptome, immune profile and pathological phenotypes to identify the molecular determinants, developing an integrated model for prognosis and comparison with The Cancer Genome Atlas (TCGA) cohorts. RESULTS: KMT2C alterations were exclusively observed in shorter survivors together with high level of intratumour heterogeneity and complex clonal architectures, whereas the APOBEC mutational signatures were significantly enriched in longer survivors. Notably, the loss of heterozygosity in chromosome 4 (Chr4) was associated with shorter survival and 'cold' immune phenotype characterised by decreased B, CD8, natural killer cells and interferon-gamma responses. Unsupervised transcriptomic clustering revealed a shorter survivor subtype with distinct expression features (eg, upregulated druggable targets JAK2, MAP3K13 and MECOM). An integrated model was then built based on clinical variables and the identified molecular determinants, which significantly segregated shorter and longer survivors. All the above features and the integrated model have been validated independently in multiple TCGA cohorts. CONCLUSION: This study discovered novel molecular features prognosticating overall survival in patients with mEGAC and identified potential novel targets in shorter survivors.

Magnetic Resonance Imaging-Based Radiomics Nomogram for Prediction of the Histopathological Grade of Soft Tissue Sarcomas: A Two-Center Study.

BACKGROUND: Preoperative prediction of soft tissue sarcoma (STS) grade is important for treatment decisions. Therefore, formulation an STS grade model is strongly needed. PURPOSE: To develop and test an magnetic resonance imaging (MRI)-based radiomics nomogram for predicting the grade of STS (low-grade vs. high grade). STUDY TYPE: Retrospective POPULATION: One hundred and eighty patients with STS confirmed by pathologic results at two independent institutions were enrolled (training set, N = 109; external validation set, N = 71). FIELD STRENGTH/SEQUENCE: Unenhanced T1-weighted (T1WI) and fat-suppressed T2-weighted images (FS-T2WI) were acquired at 1.5 T and 3.0 T. ASSESSMENT: Clinical-MRI characteristics included age, gender, tumor-node-metastasis (TNM) stage, American Joint Committee on Cancer (AJCC) stage, progression-free survival (PFS), and MRI morphological features (ie, margin). Radiomics feature extraction were performed on T1WI and FS-T2WI images by minimum redundancy maximum relevance (MRMR) method and least absolute shrinkage and selection operator (LASSO) algorithm. The selected features constructed three radiomics signatures models (RS-T1， RS-FST2, and RS-Combined). Univariate and multivariate logistic regression analysis were applied for screening significant risk factors. Radiomics nomogram was constructed by incorporating the radiomics signature and risk factors. STATISTICAL TESTS: Clinical-MRI characteristics were performed by a univariate analysis. Model performances (discrimination, calibration, and clinical usefulness) were validated in the external validation set. The RS-T1 model, RS-FST2 model, and RS-Combined model had an area under curves (AUCs) of 0.645, 0.641, and 0.829, respectively, in the external validation set. The radiomics nomogram, incorporating significant risk factors and the RS-Combined model had AUCs of 0.916 (95%CI, 0.866-0.966, training set) and 0.879 (95%CI, 0.791-0.967, external validation set), and demonstrated good calibration and good clinical utility. DATA CONCLUSION: The proposed noninvasive MRI-based radiomics models showed good performance in differentiating low-grade from high-grade STSs. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY STAGE: 2.

An MRI-Based Radiomic Nomogram for Discrimination Between Malignant and Benign Sinonasal Tumors.

BACKGROUND: Preoperative discrimination between malignant and benign sinonasal tumors is important for treatment plan selection. PURPOSE: To build and validate a radiomic nomogram for preoperative discrimination between malignant and benign sinonasal tumors. STUDY TYPE: Retrospective. POPULATION: In all, 197 patients with histopathologically confirmed 84 benign and 113 malignant sinonasal tumors. FIELD STRENGTH/SEQUENCES: Fast-spin-echo (FSE) T1 -weighted and fat-suppressed FSE T2 -weighted imaging on a 1.5T and 3.0T MRI. ASSESSMENT: T1 and fat-suppressed T2 -weighted images were selected for feature extraction. The least absolute shrinkage selection operator (LASSO) algorithm was applied to establish a radiomic score. Multivariate logistic regression analysis was applied to determine independent risk factors, and the radiomic score was combined to build a radiomic nomogram. The nomogram was assessed in a training dataset (n = 138/3.0T MRI) and tested in a validation dataset (n = 59/1.5T MRI). STATISTICAL TESTS: Independent t-test or Wilcoxon's test, chi-square-test, or Fisher's-test, univariate analysis, LASSO, multivariate logistic regression analysis, area under the curve (AUC), Hosmer-Lemeshow test, decision curve, and the Delong test. RESULTS: In the validation dataset, the radiomic nomogram could differentiate benign from malignant sinonasal tumors with an AUC of 0.91. There was no significant difference in AUC between the combined radiomic score and radiomic nomogram (P > 0.05), and the radiomic nomogram showed a relatively higher AUC than the combined radiomic score. There was a significant difference in AUC between each two of the following models (the radiomic nomogram vs. the clinical model, all P < 0.001; the combined radiomic score vs. the clinical model, P = 0.0252 and 0.0035, respectively, in the training and validation datasets). The radiomic nomogram outperformed the radiomic scores and clinical model. DATA CONCLUSION: The radiomic nomogram combining the clinical model and radiomic score is a simple, effective, and reliable method for patient risk stratification. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY STAGE: 2.

A CT-based radiomics nomogram for differentiation of lympho-associated benign and malignant lesions of the parotid gland.

OBJECTIVES: Preoperative differentiation between benign lymphoepithelial lesion (BLEL) and mucosa-associated lymphoid tissue lymphoma (MALToma) in the parotid gland is important for treatment decisions. The purpose of this study was to develop and validate a CT-based radiomics nomogram combining radiomics signature and clinical factors for the preoperative differentiation of BLEL from MALToma in the parotid gland. METHODS: A total of 101 patients with BLEL (n = 46) or MALToma (n = 55) were divided into a training set (n = 70) and validation set (n = 31). Radiomics features were extracted from non-contrast CT images, a radiomics signature was constructed, and a radiomics score (Rad-score) was calculated. Demographics and CT findings were assessed to build a clinical factor model. A radiomics nomogram combining the Rad-score and independent clinical factors was constructed using multivariate logistic regression analysis. The performance levels of the nomogram, radiomics signature, and clinical model were evaluated and validated on the training and validation datasets, and then compared among the three models. RESULTS: Seven features were used to build the radiomics signature. The radiomics nomogram incorporating the clinical factors and radiomics signature showed favorable predictive value for differentiating parotid BLEL from MALToma, with AUCs of 0.983 and 0.950 for the training set and validation set, respectively. Decision curve analysis showed that the nomogram outperformed the clinical factor model in terms of clinical usefulness. CONCLUSIONS: The CT-based radiomics nomogram incorporating the Rad-score and clinical factors showed favorable predictive efficacy for differentiating BLEL from MALToma in the parotid gland, and may help in the clinical decision-making process. KEY POINTS: • Differential diagnosis between BLEL and MALToma in parotid gland is rather difficult by conventional imaging modalities. • A radiomics nomogram integrated with the radiomics signature, demographics, and CT findings facilitates differentiation of BLEL from MALToma with improved diagnostic efficacy.