Radiomics has become an area of interest for tumor characterization in ¹⁸F-Fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) imaging. The aim of the present study was to demonstrate how imaging phenotypes was connected to somatic mutations through an integrated analysis of 115 non-small cell lung cancer (NSCLC) patients with somatic mutation testings and engineered computed PET/CT image analytics. A total of 38 radiomic features quantifying tumor morphological, grayscale statistic, and texture features were extracted from the segmented entire-tumor region of interest (ROI) of the primary PET/CT images. The ensembles for boosting machine learning scheme were employed for classification, and the least absolute shrink age and selection operator (LASSO) method was used to select the most predictive radiomic features for the classifiers. A radiomic signature based on both PET and CT radiomic features outperformed individual radiomic features, the PET or CT radiomic signature, and the conventional PET parameters including the maximum standardized uptake value (SUVmax), SUVmean, SUVpeak, metabolic tumor volume (MTV), and total lesion glycolysis (TLG), in discriminating between mutant-type of epidermal growth factor receptor (EGFR) and wild-type of EGFR- cases with an AUC of 0.805, an accuracy of 80.798%, a sensitivity of 0.826 and a specificity of 0.783. Consistently, a combined radiomic signature with clinical factors exhibited a further improved performance in EGFR mutation differentiation in NSCLC. In conclusion, tumor imaging phenotypes that are driven by somatic mutations may be predicted by radiomics based on PET/CT images.

Objective: This study aimed to evaluate the performance of the deep convolutional neural network (DCNN) to discriminate between benign, borderline, and malignant serous ovarian tumors (SOTs) on ultrasound(US) images.Material and Methods: This retrospective study included 279 pathology-confirmed SOTs US images from 265 patients from March 2013 to December 2016. Two- and three-class classification task based on US images were proposed to classify benign, borderline, and malignant SOTs using a DCNN. The 2-class classification task was divided into two subtasks: benign vs. borderline & malignant (task A), borderline vs. malignant (task B). Five DCNN architectures, namely VGG16, GoogLeNet, ResNet34, MobileNet, and DenseNet, were trained and model performance before and after transfer learning was tested. Model performance was analyzed using accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC).Results: The best overall performance was for the ResNet34 model, which also achieved the better performance after transfer learning. When classifying benign and non-benign tumors, the AUC was 0.96, the sensitivity was 0.91, and the specificity was 0.91. When predicting malignancy and borderline tumors, the AUC was 0.91, the sensitivity was 0.98, and the specificity was 0.74. The model had an overall accuracy of 0.75 for in directly classifying the three categories of benign, malignant and borderline SOTs, and a sensitivity of 0.89 for malignant, which was better than the overall diagnostic accuracy of 0.67 and sensitivity of 0.75 for malignant of the senior ultrasonographer.Conclusion: DCNN model analysis of US images can provide complementary clinical diagnostic information and is thus a promising technique for effective differentiation of benign, borderline, and malignant SOTs.

Artificial intelligence (AI) is significantly transforming surgery by enhancing precision, decision-making, and patient outcomes. This bibliometric analysis examines AI’s impact on surgery, highlighting research trends, key contributors, and evolving themes from 1998 to 2024. Utilizing data from the Web of Science Core Collection and analyzed through the Bibliometrix tool, the study reviews publication trends, author impact, institutional contributions, country-specific research activities, and keyword frequency. A total of 821 articles were examined, revealing a 14.53% annual growth rate in publications, increasing from one in 1998 to 328 in 2023. Influential contributors include 10 157 authors, notably HASHIMOTO DA and ITO M. Prominent institutions such as Harvard University and Stanford University, along with leading countries like the USA and China, play major roles in this field. High-frequency keywords identify core research areas: surgery, artificial intelligence, classification, diagnosis, and outcomes. Thematic evolution shows a shift from foundational concepts to advanced applications and interdisciplinary collaborations. AI integration into surgical practices is revolutionizing the field, driving advancements in precision, efficiency, and patient care. The study underscores significant research growth, influential contributors, and key trends, emphasizing the importance of continued interdisciplinary collaboration and innovation. Future research should focus on enhancing AI applications, addressing data quality and security challenges, and expanding into diverse surgical contexts to further improve surgical outcomes and patient care. AI in surgery is a rapidly evolving and promising field for innovation, with its full potential reliant on enhanced collaboration across disciplines.

Objective: Based on a large public cohort, we aimed to investigate the prevalence of distant metastases in patients with osteosarcoma, to evaluate the survival of patients with different metastases and to reveal the related risk and prognostic factors for distant metastases.Methods: The information of osteosarcoma patients with or without distant metastases was retrospectively extracted from the Surveillance, Epidemiology, and End Result database from January 2010 to December 2015. Patients were excluded if they were diagnosed at autopsy or via death certification. The Kaplan–Meier method was used to calculate the overall survival in the entire cohort and across patients with metastases to different organs. The related prognostic factors were investigated by univariate and multivariate Cox proportional hazard regression analysis. The logistic regression method was used to reveal the risk factors for the development of different metastases. The effects of different variables on the survival and prevalence of distant metastases were compared using subgroup analysis. Variables with P < 0.05 in the univariate regression analysis were further examined using multivariate regression analysis.Results: In total, 1470 osteosarcoma patients (mean age 30 ± 22 years) were included, among which 278 patients (18.9%) were initially diagnosed with distant metastasis. The median follow‐up duration was 33.0 (30.2–35.8) months. The lung was the most common metastatic site (83.8%), followed by the bone (21.9%), liver (2.9%), and brain (2.2%). A total of 232 patients (83.5%) presented only one distant metastatic site, while the other 46 patients showed two or more metastatic sites. A lower proportion of metastasis was observed in patients aged from 25 to 59 years [odds ratio (OR) = 0.59; 95% confidence interval (CI): 0.37–0.95]. More metastases were noted in patients with T2/T1 (OR = 1.91; 95% CI: 1.28–2.84), T3/T1 (OR = 4.48; 95% CI: 1.78–11.30) and N1/N0 stages (OR = 6.66; 95% CI: 2.68–16.56). The 1‐, 3‐, and 5‐year overall survival rates for metastatic patients were 57.3% (95% CI: 50.8%–63.8%), 25.3% (95% CI: 18.8%–31.9%), and 18.1% (95% CI: 10.2%–26.0%), respectively. Metastatic patients older than 25 years were prone to have poor survival and a relatively better prognosis (hazard ratio = 0.41; 95% CI: 0.25–0.69) was noticed among those who underwent surgery on the primary site. Different metastatic organs have homogeneous and heterogeneous risk and prognostic factors.Conclusion: The high incidence of initial distant metastasis in osteosarcoma and the inconsistent predictive factors should be given more attention in the clinical management of patients with osteosarcoma.

Objectives: To establish and validate a nomogram integrating radiomics signatures from ultrasound and clinical factors to discriminate between benign, borderline, and malignant serous ovarian tumors.Materials and methods: In this study, a total of 279 pathology-confirmed serous ovarian tumors collected from 265 patients between March 2013 and December 2016 were used. The training cohort was generated by randomly selecting 70% of each of the three types (benign, borderline, and malignant) of tumors, while the remaining 30% was included in the validation cohort. From the transabdominal ultrasound scanning of ovarian tumors, the radiomics features were extracted, and a score was calculated. The ability of radiomics to differentiate between the grades of ovarian tumors was tested by comparing benign vs borderline and malignant (task 1) and borderline vs malignant (task 2). These results were compared with the diagnostic performance and subjective assessment by junior and senior sonographers. Finally, a clinical-feature alone model and a combined clinical-radiomics (CCR) model were built using predictive nomograms for the two tasks. Receiver operating characteristic (ROC) analysis, calibration curve, and decision curve analysis (DCA) were performed to evaluate the model performance.Results: The US-based radiomics models performed satisfactorily in both the tasks, showing especially higher accuracy in the second task by successfully discriminating borderline and malignant ovarian serous tumors compared to the evaluations by senior sonographers (AUC = 0.789 for seniors and 0.877 for radiomics models in task one; AUC = 0.612 for senior and 0.839 for radiomics model in task 2). We showed that the CCR model, comprising CA125 level, lesion location, ascites, and radiomics signatures, performed the best (AUC = 0.937, 95%CI 0.905–0.969 in task 1, AUC = 0.924, 95%CI 0.876–0.971 in task 2) in the training as well as in the validation cohorts (AUC = 0.914, 95%CI 0.851–0.976 in task 1, AUC = 0.890, 95%CI 0.794–0.987 in task 2). The calibration curve and DCA analysis of the CCR model more accurately predicted the classification of the tumors than the clinical features alone.Conclusion: This study integrates novel radiomics signatures from ultrasound and clinical factors to create a nomogram to provide preoperative diagnostic information for differentiating between benign, borderline, and malignant ovarian serous tumors, thereby reducing unnecessary and risky biopsies and surgeries.