Diagnostic and Interventional Radiology

Objectives: We aimed to develop radiology-based models for the preoperative prediction of the initial treatment response to transarterial chemoembolization (TACE) in patients with hepatocellular carcinoma (HCC) since the integration of radiomics and deep learning (DL) has not been reported for TACE.Methods: Three hundred and ten intermediate-stage HCC patients who underwent TACE were recruited from three independent medical centers. Based on computed tomography (CT) images, recursive feature elimination (RFE) was used to select the most useful radiomics features. Five radiomics conventional machine learning (cML) models and a DL model were used for training and validation. Mutual correlations between each model were analyzed. The accuracies of integrating clinical variables, cML, and DL models were then evaluated.Results: Good predictive accuracies were showed across the two cohorts in the five cML models, especially the random forest algorithm (AUC = 0.967 and 0.964, respectively). DL showed high accuracies in the training and validation cohorts (AUC = 0.981 and 0.972, respectively). Significant mutual correlations were revealed between tumor size and the five cML models and DL model (each P < 0.001). The highest accuracies were achieved by integrating DL and the random forest algorithm in the training and validation cohorts (AUC = 0.995 and 0.994, respectively).Conclusion: The radiomics cML models and DL model showed notable accuracy for predicting the initial response to TACE treatment. Moreover, the integrated model could serve as a novel and accurate method for prediction in intermediate-stage HCC.

Although studies have reported that intestinal microbiota are associated with acute graft‐versus‐host disease (aGVHD), they lacked a satisfactory method for predicting aGVHD. We collected stool and blood samples at day 15 posttransplant from 150 patients from two centers who underwent myeloablative conditioning allogeneic hematopoietic stem cell transplantation (allo‐HSCT). Stool microbiota were detected by 16S ribosomal RNA gene sequencing; inflammatory factors and T lymphocytes were detected by multiplex immunoassays and flow cytometry, respectively. A gut microbiota score (GMS) from a LASSO (least absolute shrinkage and selection operator) model was developed and validated to predict aGVHD. In the discovery cohort, the GMS could predict II‐IV aGVHD (area under the receiver operating characteristic [ROC] curve [AUC] = 0.904, P < .0001). Furthermore, the validation model was consistent with the discovery set (AUC = 0.887, P < .0001). Regulatory T/T‐helper 17 (Treg/Th17) cells ratio in the low GMS subgroup was higher compared with the high GMS (P = .012), and the validation set is consistent with the discovery set (P = .003). In addition, high cytokine levels were associated with high GMS. In conclusion, the GMS at neutrophil engraftment could predict aGVHD, and it was a potential and novel method. The GMS was associated with the inflammatory factor and Treg/Th17 balance.

Background: Identifying precise biomarkers of immunotherapy response for non-small cell lung carcinoma (NSCLC) before treatment is challenging. This study aimed to construct and investigate the potential performance of a sub-regional radiomics model (SRRM) as a novel tumor biomarker in predicting the response of patients with NSCLC treated with immune checkpoint inhibitors, and test whether its predictive performance is superior to that of conventional radiomics, tumor mutational burden (TMB) score and programmed death ligand-1 (PD-L1) expression. Methods: We categorized 264 patients from retrospective databases of two centers into training (n = 159) and validation (n = 105) cohorts. Radiomic features were extracted from three sub-regions of the tumor region of interest using the K-means method. We extracted 1,896 features from each sub-region, resulting in 5688 features per sample. The least absolute shrinkage and selection operator regression method was used to select sub-regional radiomic features. The SRRM was constructed and validated using the support vector machine algorithm. We used next-generation sequencing to classify patients from the two cohorts into high TMB (≥ 10 muts/Mb) and low TMB (< 10 muts/Mb) groups; immunohistochemistry was performed to assess PD-L1 expression in formalin-fixed, paraffin-embedded tumor sections, with high expression defined as ≥ 50% of tumor cells being positive. Associations between the SRRM and progression-free survival (PFS) and variant genes were assessed. Results: Eleven sub-regional radiomic features were employed to develop the SRRM. The areas under the receiver operating characteristic curve (AUCs) of the proposed SRRM were 0.90 (95% confidence interval [CI] 0.84−0.96) and 0.86 (95% CI 0.76−0.95) in the training and validation cohorts, respectively. The SRRM (low vs. high; cutoff value = 0.936) was significantly associated with PFS in the training (hazard ratio [HR] = 0.35 [0.24−0.50], P < 0.001) and validation (HR = 0.42 [0.26−0.67], P = 0.001) cohorts. A significant correlation between the SRRM and three variant genes (H3C4, PAX5, and EGFR) was observed. In the validation cohort, the SRRM demonstrated a higher AUC (0.86, P < 0.001) than that for PD-L1 expression (0.66, P = 0.034) and TMB score (0.54, P = 0.552). Conclusions: The SRRM had better predictive performance and was superior to conventional radiomics, PD-L1 expression, and TMB score. The SRRM effectively stratified the progression-free survival (PFS) risk among patients with NSCLC receiving immunotherapy.

Background: Since the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) disease (COVID-19) outbreaks in Wuhan, China, healthcare systems capacities in highly endemic areas have been overwhelmed. Approaches to efficient management are urgently needed and key to a quicker control of the outbreaks and casualties. We aimed to characterize the clinical features of hospitalized patients with confirmed or suspected COVID-19, and develop a mortality risk index for COVID-19 patients. Methods: In this retrospective one-centre cohort study, we included all the confirmed or suspected COVID-19 patients hospitalized in a COVID-19-designated hospital from January 21 to February 5, 2020. Demographic, clinical, laboratory, radiological and clinical outcome data were collected from the hospital information system, nursing records and laboratory reports. Findings: Of 577 patients with at least one post-admission evaluation, the median age was 55 years (interquartile range [IQR], 39 - 66); 254 (44·0%) were men; 22·8% (100/438) were severe pneumonia on admission, and 37·7% (75/199) patients were SARS-CoV-2 positive. The clinical, laboratory and radiological data were comparable between positive and negative SARS-CoV-2 patients. During a median follow-up of 8·4 days (IQR, 5·8 - 12·0), 39 patients died with a 12-day cumulative mortality of 8·7% (95% CI, 5·9% to 11·5%). A simple mortality risk index (called ACP index), composed of Age and C-reactive Protein, was developed. By applying the ACP index, patients were categorized into three grades. The 12-day cumulative mortality in grade three (age ≥ 60 years and CRP ≥ 34 mg/L) was 33·2% (95% CI, 19·8% to 44·3%), which was significantly higher than those of grade two (age ≥ 60 years and CRP < 34 mg/L; age < 60 years and CRP ≥ 34 mg/L; 5·6% [95% CI, 0 to 11·3%]) and grade one (age < 60 years and CRP < 34 mg/L, 0%) (P <0·001), respectively. Interpretation: The ACP index can predict COVID-19 related short-term mortality, which may be a useful and convenient tool for quickly establishing a COVID-19 hierarchical management system that can greatly reduce the medical burden and therefore mortality in highly endemic areas. Funding Statement: Local Innovative and Research Teams Project of Guangdong Pearl River Talents Program. Declaration of Interests: The authors stated: "None reported." Ethics Approval Statement: The study was conducted in accordance with the guidelines of the Declaration of Helsinki and the principles of good clinical practice, and was approved by the Nanfang Hospital Ethics Committee (NFEC-2020-026).

Although several biomarkers have been proposed to predict the response of patients with lung adenocarcinoma (LUAD) to immune checkpoint blockade (ICB) therapy, existing challenges such as test platform uniformity, cutoff value definition, and low frequencies restrict their effective clinical application. Here, we attempted to use deep neural networks (DNNs) based on somatic mutations to predict the clinical benefit of ICB to LUAD patients undergoing immunotherapy. We used DNNs to train and validate the predictive model in three cohorts. Kaplan-Meier estimates determined the overall survival (OS) and progression-free survival (PFS) between specific subgroups. Then, we performed a relevant analysis on the multiple-dimension data types including immune cell infiltration, programmed death receptor 1 ligand (PD-L1) expression, and tumor mutational burden (TMB) from cohorts of LUAD public database and immunotherapeutic patients. Two classification groups (C1 and C2) in the training and two validation sets were identified for the efficacy of ICB via the DNN algorithm. Patients in C1 showed remarkably long OS and PFS to programmed death 1 (PD-1) inhibitors. The C1 group was significantly associated with increased expression of immune cell infiltration, immune checkpoints, activated T-effectors, and interferon gamma signature. C1 group also exhibited significantly higher TMB, neoantigens, transversion, or transition than the C2 group. This work provides novel insights that classification of DNNs using somatic mutations in LUAD could serve as a potentially predictive approach in developing a strategy for anti-PD-1/PD-L1 immunotherapy.