Introduction: We used habitat radiomics as an innovative tumor biomarker to predict the outcome of neoadjuvant therapy for esophageal cancer.Methods: This was a two-center retrospective clinical study in which pretreatment CT scans of 112 patients with esophageal cancer treated with neoadjuvant chemoimmunotherapy and surgery between November 2020 and July 2023 were retrospectively collected from two institutions. For training (n = 85) and external testing (n = 27), patients from both institutions were allocated. We employed unsupervised methods to delineate distinct heterogeneous regions within the tumor area.Results: To represent the prediction effect of different models, we plotted the AUC curves. The AUCs of the habitat models were 0.909 (0.8418–0.9758, 95% CI) and 0.829 (0.6423–1.0000, 95% CI) in the training and external test cohorts, respectively. The AUCs of the nomogram models were 0.914 (0.8483–0.9801, 95% CI) and 0.849 (0.6752–1.0000, 95% CI) in the training and external test cohorts, respectively.Discussion: The results revealed that the model based on habitat data outperforms traditional radiomic analysis models. In addition, when the model is combined with clinical features, it improves the predictive accuracy of pathological complete response in patients undergoing neoadjuvant chemoimmunotherapy.

Frailty becomes more pronounced with advancing age, tightly intertwined with adverse clinical outcomes. Across diverse medical disciplines, frailty is now universally recognized as not only a risk factor but also a predictive indicator for unfavorable clinical prognosis. This study was a retrospective cohort study that included clinical data from patients (aged ≥ 65 years) with esophageal cancer treated surgically at the First Affiliated Hospital of Anhui Medical University in 2021. For each patient, we calculated their 11-index modified frailty index(mFI-11) scores and categorized the patients into a frailty group (mFI-11hign) and a non-frailty group (mFI-11low) based on the optimal grouping cutoff value of 0.27 from a previous study. The primary study index was the incidence of postoperative pulmonary infection, arrhythmia, anastomotic fistula, chylothorax, and electrolyte disturbance complications. Secondary study indicators included postoperative ICU stay, total hospitalization time, readmission rate within 30 days of discharge, and mortality within 30 days after surgery. We performed univariate and multivariate analyses to assess the association between mFI-11 and adverse outcomes as well as postoperative complications. Five hundred and fifteen patients were included, including 64.9% (334/515) in the non-frailty group and 35.1% (181/515) in the frailty group. Comparing postoperative complication rates between the two groups revealed lower incidences of postoperative anastomotic fistula (21.5% vs. 4.5%), chylothorax (16.0% vs. 2.1%), cardiac arrhythmia (61.9% vs. 9.9%), pulmonary infections (85.1% vs. 26.6%), and electrolyte disturbance (84.5% vs. 15.0%) in patients of the non-frailty group was lower than that in the frailty group (p < 0.05). mFI-11 showed better prognostic results in predicting postoperative complications. anastomotic fistula (area under the ROC curve AUROC = 0.707), chylothorax (area under the ROC curve AUROC = 0.744), pulmonary infection (area under the ROC curve AUROC = 0.767), arrhythmia (area under the ROC curve AUROC = 0.793), electrolyte disturbance (area under the ROC curve AUROC = 0.832), and admission to ICU (area under the ROC curve AUROC = 0.700). Preoperative frail elderly patients with esophageal cancer have a high rate of postoperative complications. mFI-11 can be used as an objective indicator for identifying elderly patients at risk for esophageal cancer.

Primary mediastinal choriocarcinoma, also known as non‐pregnant choriocarcinoma, is a rare malignancy unrelated to pregnancy, with a higher incidence in males. And primary mediastinal choriocarcinoma is mostly associated with organ and lymph node metastasis, with rapid progression and poor prognosis. Here, we report an extremely rare case of the primary anterior mediastinal choriocarcinoma that occurred in an 18‐year‐old man with multiple metastases of the lung and brain.

Background: The rapid advancement of radiomics and artificial intelligence (AI) technology has provided novel tools for the diagnosis of esophageal cancer. This study innovatively combines muscle imaging features with conventional esophageal imaging features to construct deep learning diagnostic models. Methods: This retrospective study included 1066 patients undergoing radical esophagectomy. Preoperative computed tomography (CT) images covering esophageal, stomach, and muscle (bilateral iliopsoas and erector spinae) regions were segmented automatically with manual adjustments. Diagnostic models were developed using deep learning (2D and 3D neural networks) and traditional machine learning (11 algorithms with PyRadiomics-derived features). Multimodal features underwent Principal Component Analysis (PCA) for dimension reduction and were fused for final analysis. Results: Comparative analysis of 1066 patients’ CT imaging revealed the muscle-based model outperformed the esophageal plus stomach model in predicting N2 staging (0.63 ± 0.11 vs. 0.52 ± 0.11, p = 0.03). Subsequently, multimodal fusion models were established for predicting pathological subtypes, T staging, and N staging. The logistic regression (LR) fusion model showed optimal performance in predicting pathological subtypes, achieving accuracy (ACC) of 0.919 in the training set and 0.884 in the validation set. For predicting T staging, the support vector machine (SVM) model demonstrated the highest accuracy, with training and validation accuracies of 0.909 and 0.907, respectively. The multilayer perceptron (MLP) fusion model achieved the best performance among all models tested for N staging prediction, although the accuracy remained moderate (ACC = 0.704 in the training set and 0.685 in the validation set), indicating potential for further optimization. Fusion models significantly outperformed single-modality models. Conclusions: Based on CT imaging data from 1066 patients, this study systematically constructed predictive models for pathological subtypes, T staging, and N staging of esophageal cancer. Comparative analysis of models using esophageal, esophageal plus stomach, and muscle modalities demonstrated that muscle imaging features contribute to diagnostic accuracy. Multimodal fusion models consistently showed superior performance.

Objective: This study aims to construct an effective prediction model for the two-year postoperative survival probability of patients with non-small cell lung cancer (NSCLC). It particularly focuses on integrating radiomics features, including the erector spinae and whole-lung imaging features, to enhance the accuracy and stability of prognostic predictions.Materials and methods: The study included 37 NSCLC patients diagnosed and surgically treated at the First Affiliated Hospital of Anhui Medical University from January 2020 to December 2021. The average age of the patients was 59 years, with the majority being female and non-smokers. Additionally, CT imaging data from 98 patients were obtained from The Cancer Imaging Archive (TCIA) public database. All imaging data were derived from preoperative chest CT scans and standardized using 3D Slicer software. The study extracted radiomic features from the tumor, whole lung, and erector spinae muscles of the patients and applied 11 machine learning algorithms to construct prediction models. Subsequently, the classification performance of all constructed models was compared to select the optimal prediction model.Results: Univariate Cox regression analysis showed no significant correlation between the collected clinical factors and patient survival time. In the external validation set, the K-Nearest Neighbors (KNN) model based on bilateral erector spinae features performed the best, with accuracy and AUC (Area Under the Curve) values consistently above 0.7 in both the training and external testing sets. Among the prognostic models based on whole-lung imaging features, the AdaBoost model also performed well, but its AUC value was below 0.6 in the external validation set, indicating overall classification performance still inferior to the KNN model based on erector spinae features.Conclusion: This study is the first to introduce erector spinae imaging features into lung cancer research, successfully developing a stable and well-performing prediction model for the postoperative survival of NSCLC patients. The research results provide new perspectives and directions for the application of radiomics in cancer research and emphasize the importance of incorporating multi-organ imaging features to improve the accuracy and stability of prediction models.

Oesophageal cancer (EC) is a common gastrointestinal malignancy and includes oesophageal squamous cell carcinoma (ESCC) and oesophageal adenocarcinoma (EAC) sub‐types. Gene signatures predicting patient outcomes are not routinely used in clinical practice, particularly owing to batch effects and data standardisation. Here, we sought to establish and validate a reliable signature of senescence‐related genes (SRGs) that would aid in predicting prognosis in patients with EC. We downloaded transcriptomics data, and a novel pairwise comparison algorithm selected valid SRG pairs (SRGPs) to construct a prognostic SRGP signature. The SRGPs were verified using Kaplan–Meier survival and receiver operating characteristic curve analyses. Additionally, the relationships between the SRGP signatures and prognosis, immune cell infiltration and chemotherapeutic drug responsiveness were evaluated. The random forest algorithm identified the most clinically significant genes, followed by experimental validation. 19 and 26 SRGP signatures were created for ESCC (n = 81) and EAC (n = 79), respectively. Patients with EC were divided into two groups based on the median risk score. The Kaplan–Meier analysis demonstrated significant differences in overall survival between the ESCC and EAC groups (p < 0.001). The sub‐types exhibited different immune signatures. IRF5 was the most clinically significant gene for ESCC. It was highly expressed in ESCC cells, and IRF5 knockdown inhibited cell migration and proliferation, while promoting apoptosis and senescence. The SRGP signature may predict prognosis and immunotherapeutic responses, and IRF5 is a potential target gene for ESCC.