Programmed death ligand-1 (PD-L1) is a potentially important tumor immunotherapy target. However, whether PD-L1 expression is associated with survival in nasopharyngeal carcinoma (NPC) remains controversial. The aim of the present study was to investigate the association between PD-L1 expression and prognosis in NPC. The expression of PD-L1 was assessed in tumor specimens from 120 patients with NPC using immunohistochemistry. Staining was evaluated using the H-score method. The associations between PD-L1 expression and clinical characteristics and prognosis were analyzed. Overall, 78% of the patients had stage I–III and 22% had stage IV disease. The estimated 5-year overall survival (OS) and disease-free survival (DFS) rates for the entire cohort were 87.5 and 70.1%, respectively. PD-L1 expression was detected in 85 (71%) patients and was localized to the tumor cells. High tumor expression of PD-L1 (median H-score ≥5) was associated with significantly poorer OS (P=0.023) and DFS (P=0.002). Univariate analysis indicated that low PD-L1 expression was associated with better DFS compared with high PD-L1 expression (HR=0.163, 95% CI: 0.044–0.600, P=0.006 for DFS). Multivariate analysis revealed that T stage (HR=8.190, 95% CI: 1.355–18.152; P=0.023) and PD-L1 expression level (HR=0.124, 95% CI: 0.031–0.509; P=0.001) served as independent prognostic factors for DFS. In conclusion, tumor PD-L1 expression was found to be a significant prognostic factor in NPC, and high PD-L1 expression may be of prognostic value for recurrence and metastasis following conventional treatments.

The standard treatment for esthesioneuroblastoma, a rare malignant nasal vault neoplasm, is not established. We retrospectively assessed the clinicopathological features, prognostic factors and treatment methods for 187 patients with esthesioneuroblastoma treated in China between 1981 and 2015. Overall survival (OS) and disease-free survival (DFS) were evaluated using the Kaplan-Meier method and log-rank tests. Twenty-three (12.3%), 48 (25.7%) and 113 (60.4%) patients had Kadish stage A, B and C esthesioneuroblastoma; 3 (1.6%) had unknown stage. Overall, 117 (62.6%) patients received surgery and combined radiotherapy with or without chemotherapy; 35 (18.7%) received radiotherapy with or without chemotherapy; 32 (17.1%) received surgery alone; and 3 (1.6%) received palliative treatment. Three-year OS and DFS for the entire cohort were 66.7% and 57.5%, respectively. Three-year OS for stage A, B and C were 91.3%, 91.2% and 49.5% (P < 0.0001). Three-year OS was 16.7% and 66.7% for patients with and without distant metastasis (P < 0.0001). Surgery and combined radiotherapy with or without chemotherapy led to better OS and DFS than other treatment modes (both P < 0.0001). Univariate and multivariate analysis showed distant metastasis (hazard ratio [HR] = 2.162, 95% confidence interval [CI] = 1.145, 4.082, P = 0.017) and not receiving a combined modality treatment (HR = 2.391, 95% CI = 1.356, 4.218, P = 0.003) were independent prognostic factors for poor OS and DFS. This study indicates surgery and combined radiotherapy may currently be the optimal treatment for esthesioneuroblastoma.

With the advancement of deep learning technology, computer-aided diagnosis (CAD) is playing an increasing role in the field of medical diagnosis. In particular, the emergence of Transformer-based models has led to a wider application of computer vision technology in the field of medical image processing. In the diagnosis of thyroid diseases, the diagnosis of benign and malignant thyroid nodules based on the TI-RADS classification is greatly influenced by the subjective judgment of ultrasonographers, and at the same time, it also brings an extremely heavy workload to ultrasonographers. To address this, we propose Swin-Residual Transformer (SRT) in this paper, which incorporates residual blocks and triplet loss into Swin Transformer (SwinT). It improves the sensitivity to global and localized features of thyroid nodules and better distinguishes small feature differences. In our exploratory experiments, SRT model achieves an accuracy of 0.8832 with an AUC of 0.8660, outperforming state-of-the-art convolutional neural network (CNN) and Transformer models. Also, ablation experiments have demonstrated the improved performance in the thyroid nodule classification task after introducing residual blocks and triple loss. These results validate the potential of the proposed SRT model to improve the diagnosis of thyroid nodules' ultrasound images. It also provides a feasible guarantee to avoid excessive puncture sampling of thyroid nodules in future clinical diagnosis.

Sentinel lymph node metastasis (SLNM) is a crucial predictor for breast cancer treatment and survival. This study was designed to propose deep learning (DL) models based on grayscale ultrasound, color Doppler flow imaging (CDFI), and elastography images, and to evaluate how DL radiomics can be used to classify SLNM in breast cancer. Clinical and ultrasound data of 317 patients diagnosed with breast cancer at the Second Affiliated Hospital of Nanchang University were collected from January 2018 to December 2021 and randomly divided into training and internal validation cohorts at a ratio of 7:3. An external validation cohort comprising data from Nanchang Third Hospital with 42 patients collected. Three DL models, namely DL-grayscale, DL-CDFI, and DL-elastography, were proposed to predict SLNM by analyzing grayscale ultrasound, CDFI, and elastography images. Three DL models were compared and evaluated to assess diagnostic performance based on the area under the curve (AUC). The AUCs of the DL-grayscale were 0.855 and 0.788 in the internal and external validation cohorts, respectively. For the DL-CDFI model, the AUCs were 0.761 and 0.728, respectively. The diagnostic performance of DL-elastography was superior to that of the DL-grayscale and DL-CDFI. The AUC of the DL-elastography model was 0.879 in the internal validation cohort, with a classification accuracy of 86.13%, sensitivity of 91.60%, and specificity of 82.79%. The generalization capability of DL-elastography remained high in the external cohort, with an AUC of 0.876, and an accuracy of 85.00%. DL radiomics can be used to classify SLNM in breast cancer using ultrasound images. The proposed DL-elastography model based on elastography images achieved the best diagnostic performance and holds good potential for the management of patients with SLNM.

Malignant pleural mesothelioma (MPM) is a malignant tumor originating from the pleura, and its incidence has been increasing in recent years. Due to the insidious onset and strong local invasiveness of MPM, most patients are diagnosed in the late stage and early screening and treatment for high‐risk populations are crucial. The treatment of MPM mainly includes surgery, chemotherapy, and radiotherapy. Immunotherapy and electric field therapy have also been applied, leading to further improvements in patient survival. The Mesothelioma Group of the Yangtze River Delta Lung Cancer Cooperation Group (East China LUng caNcer Group, ECLUNG; Youth Committee) developed a national consensus on the clinical diagnosis and treatment of MPM based on existing clinical research evidence and the opinions of national experts. This consensus aims to promote the homogenization and standardization of MPM diagnosis and treatment in China, covering epidemiology, diagnosis, treatment, and follow‐up.