Brain metastasis (BM) significantly affects the prognosis of non-small cell lung cancer (NSCLC) patients. Increasing evidence suggests that adipose tissue influences cancer progression and metastasis. This study aimed to develop a predictive nomogram integrating mediastinal fat area (MFA) and deep learning (DL)-derived tumor characteristics to stratify postoperative‌ BM risk in NSCLC patients. A retrospective cohort of 585 surgically resected NSCLC patients was analyzed. Preoperative computed tomography (CT) scans were utilized to quantify MFA using ImageJ software (radiologist-validated measurements). Concurrently, a DL algorithm extracted tumor radiomic features, generating a deep learning brain metastasis score (DLBMS). Multivariate logistic regression identified independent BM predictors, which were incorporated into a nomogram. Model performance was assessed via area under the receiver operating characteristic curve (AUC), calibration plots, integrated discrimination improvement (IDI), net reclassification improvement (NRI), and decision curve analysis (DCA). Multivariate analysis identified N stage, EGFR mutation status, MFA, and DLBMS as independent predictors of BM. The nomogram achieved superior discriminative capacity (AUC: 0.947 in the test set), significantly outperforming conventional models. MFA contributed substantially to predictive accuracy, with IDI and NRI values confirming its incremental utility (IDI: 0.123, <i>P</i> < 0.001; NRI: 0.386, <i>P</i> = 0.023). Calibration analysis demonstrated strong concordance between predicted and observed BM probabilities, while DCA confirmed clinical net benefit across risk thresholds. This DL-enhanced nomogram, incorporating MFA and tumor radiomics, represents a robust and clinically useful tool for preoperative prediction of postoperative BM risk in NSCLC. The integration of adipose tissue metrics with advanced imaging analytics advances personalized prognostic assessment in NSCLC patients. The online version contains supplementary material available at 10.1186/s12885-025-14466-5.

Medical digitization has been intensively developed in the last decade, leading to paving the path for computer-aided medical diagnosis research. Thus, anomaly detection based on machine and deep learning techniques has been extensively employed in healthcare applications, such as medical imaging classification and monitoring of patients' vital signs. To effectively leverage digitized medical records for identifying challenges in healthcare, this manuscript presents a smart Clinical Decision Support System (CDSS) dedicated for medical multimodal data automated diagnosis. A smart healthcare system necessitating medical data management and decision-making is proposed. To deliver timely rapid diagnosis, thread-level parallelism (TLP) is utilized for parallel distribution of classification tasks on three edge computing devices, each employing an AI module for on-device AI classifications. In comparison to existing machine and deep learning classification techniques, the proposed multithreaded architecture realizes a hybrid (ML and DL) processing module on each edge node. In this context, the presented edge computing-based parallel architecture captures a high level of parallelism, tailored for dealing with multiple categories of medical records. The cluster of the proposed architecture encompasses three edge computing Raspberry Pi devices and an edge server. Furthermore, lightweight neural networks, such as MobileNet, EfficientNet, and ResNet18, are trained and optimized based on genetic algorithms to provide classification of brain tumor, pneumonia, and colon cancer. Model deployment was conducted based on Python programming, where PyCharm is run on the edge server whereas Thonny is installed on edge nodes. In terms of accuracy, the proposed GA-based optimized ResNet18 for pneumonia diagnosis achieves 93.59% predictive accuracy and reduces the classifier computation complexity by 33.59%, whereas an outstanding accuracy of 99.78% and 100% were achieved with EfficientNet-v2 for brain tumor and colon cancer prediction, respectively, while both models preserving a reduction of 25% in the model's classifier. More importantly, an inference speedup of 28.61% and 29.08% was obtained by implementing parallel 2 DL and 3 DL threads configurations compared to the sequential implementation, respectively. Thus, the proposed multimodal-multithreaded architecture offers promising prospects for comprehensive and accurate anomaly detection of patients' medical imaging and vital signs. To summarize, our proposed architecture contributes to the advancement of healthcare services, aiming to improve patient medical diagnosis and therapy outcomes.

Deep learning models have proven to be effective on medical datasets for accurate diagnostic predictions from images. However, medical datasets often contain noisy, mislabeled, or poorly generalizable images, particularly for edge cases and anomalous outcomes. Additionally, high quality datasets are often small in sample size that can result in overfitting, where models memorize noise rather than learn generalizable patterns. This in particular, could pose serious risks in medical diagnostics where the risk associated with mis-classification can impact human life. Several data-efficient training strategies have emerged to address these constraints. In particular, coreset selection identifies compact subsets of the most representative samples, enabling training that approximates full-dataset performance while reducing computational overhead. On the other hand, curriculum learning relies on gradually increasing training difficulty and accelerating convergence. However, developing a generalizable difficulty ranking mechanism that works across diverse domains, datasets, and models while reducing the computational tasks and remains challenging. In this paper, we introduce Iterative Misclassification Error Training (IMET), a novel framework inspired by curriculum learning and coreset selection. The IMET approach is aimed to identify misclassified samples in order to streamline the training process, while prioritizing the model's attention to edge case senarious and rare outcomes. The paper evaluates IMET's performance on benchmark medical image classification datasets against state-of-the-art ResNet architectures. The results demonstrating IMET's potential for enhancing model robustness and accuracy in medical image analysis are also presented in the paper.

Accurate stratification of the activity index of Crohn's disease (CD) using computed tomography enterography (CTE) radiomics and serum markers can aid in predicting disease progression and assist physicians in personalizing therapeutic regimens for patients with CD. This retrospective study enrolled 233 patients diagnosed with CD between January 2019 and August 2024. Patients were divided into training and testing cohorts at a ratio of 7:3 and further categorized into remission, mild active phase, and moderate-severe active phase groups based on simple endoscopic score for CD (SEC-CD). Radiomics features were extracted from CTE venous images, and T-test and least absolute shrinkage and selection operator (LASSO) regression were applied for feature selection. The serum markers were selected based on the variance analysis. We also developed a random forest (RF) model for multi-class stratification of CD. The model performance was evaluated by the area under the receiver operating characteristic curve (AUC) and quantified the contribution of each feature in the dataset to CD activity via Shapley additive exPlanations (SHAP) values. Finally, we enrolled gender, radiomics scores, and serum scores to develop a nomogram model to verify the effectiveness of feature extraction. 14 non-zero coefficient radiomics features and six serum markers with significant differences (P<0.01) were ultimately selected to predict CD activity. The AUC (micro/macro) for the ensemble machine learning model combining the radiomics features and serum markers is 0.931/0.928 for three-class. The AUC for the remission phase, the mild active phase, and the moderate-severe active phase were 0.983, 0.852, and 0.917, respectively. The mean AUC for the nomogram model was 0.940. A radiomics model was developed by integrating radiomics and serum markers of CD patients, achieving enhanced consistency with SEC-CD in grade CD. This model has the potential to assist clinicians in accurate diagnosis and treatment.

This research aimed to compare the classification accuracy of three machine learning (ML) methods (random forest (RF), support vector machines (SVM), linear discriminant analysis (LDA)) for sex estimation of sub-adults using cranial computed tomography (CCT) images. A total of 521 CCT scans from sub-adult Malaysians aged 0 to 20 were analysed using Mimics software (Materialise Mimics Ver. 21). Plane-to-plane (PTP) protocol was used for measuring 14 chosen craniometric parameters. A trio of machine learning algorithms RF, SVM, and LDA with GridSearchCV was used to produce classification models for sex estimation. In addition, performance was measured in the form of accuracy, precision, recall, and F1-score, among others. RF produced testing accuracy of 73%, with the best hyperparameters of max_depth = 6, max_samples = 40, and n_estimators = 45. SVM obtained an accuracy of 67% with the best hyperparameters: learning rate (C) = 10, gamma = 0.01, and kernel = radial basis function (RBF). LDA obtained the lowest accuracy of 65% with shrinkage of 0.02. Among the tested ML methods, RF showed the highest testing accuracy in comparison to SVM and LDA. This is the first AI-based classification model that can be used for estimating sex in sub-adults using CCT scans.

Deep learning (DL) methods are increasingly outperforming classical approaches in brain imaging, yet their generalizability across diverse imaging cohorts remains inadequately assessed. As age and sex are key neurobiological markers in clinical neuroscience, influencing brain structure and disease risk, this study evaluates three of the existing three-dimensional architectures, namely Simple Fully Connected Network (SFCN), DenseNet, and Shifted Window (Swin) Transformers, for age and sex prediction using T1-weighted MRI from four independent cohorts: UK Biobank (UKB, n=47,390), Dallas Lifespan Brain Study (DLBS, n=132), Parkinson's Progression Markers Initiative (PPMI, n=108 healthy controls), and Information eXtraction from Images (IXI, n=319). We found that SFCN consistently outperformed more complex architectures with AUC of 1.00 [1.00-1.00] in UKB (internal test set) and 0.85-0.91 in external test sets for sex classification. For the age prediction task, SFCN demonstrated a mean absolute error (MAE) of 2.66 (r=0.89) in UKB and 4.98-5.81 (r=0.55-0.70) across external datasets. Pairwise DeLong and Wilcoxon signed-rank tests with Bonferroni corrections confirmed SFCN's superiority over Swin Transformer across most cohorts (p<0.017, for three comparisons). Explainability analysis further demonstrates the regional consistency of model attention across cohorts and specific to each task. Our findings reveal that simpler convolutional networks outperform the denser and more complex attention-based DL architectures in brain image analysis by demonstrating better generalizability across different datasets.

The application of artificial intelligence (AI) in medicine has garnered significant attention in recent years, offering new possibilities for improving patient care across various domains. For herpes zoster, a viral infection caused by the reactivation of the varicella-zoster virus, AI technologies have shown remarkable potential in enhancing disease diagnosis, treatment, and management. This study aims to investigate the current research status in the use of AI for herpes zoster, offering a comprehensive synthesis of existing advancements. A systematic literature review was conducted following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Three databases of Web of Science Core Collection, PubMed, and IEEE were searched to identify relevant studies on AI applications in herpes zoster research on November 17, 2023. Inclusion criteria were as follows: (1) research articles, (2) published in English, (3) involving actual AI applications, and (4) focusing on herpes zoster. Exclusion criteria comprised nonresearch articles, non-English papers, and studies only mentioning AI without application. Two independent clinicians screened the studies, with a third senior clinician resolving disagreements. In total, 26 articles were included. Data were extracted on AI task types; algorithms; data sources; data types; and clinical applications in diagnosis, treatment, and management. Trend analysis revealed an increasing annual interest in AI applications for herpes zoster. Hospital-derived data were the primary source (15/26, 57.7%), followed by public databases (6/26, 23.1%) and internet data (5/26, 19.2%). Medical images (9/26, 34.6%) and electronic medical records (7/26, 26.9%) were the most commonly used data types. Classification tasks (85.2%) dominated AI applications, with neural networks, particularly multilayer perceptron and convolutional neural networks being the most frequently used algorithms. AI applications were analyzed across three domains: (1) diagnosis, where mobile deep neural networks, convolutional neural network ensemble models, and mixed-scale attention-based models have improved diagnostic accuracy and efficiency; (2) treatment, where machine learning models, such as deep autoencoders combined with functional magnetic resonance imaging, electroencephalography, and clinical data, have enhanced treatment outcome predictions; and (3) management, where AI has facilitated case identification, epidemiological research, health care burden assessment, and risk factor exploration for postherpetic neuralgia and other complications. Overall, this study provides a comprehensive overview of AI applications in herpes zoster from clinical, data, and algorithmic perspectives, offering valuable insights for future research in this rapidly evolving field. AI has significantly advanced herpes zoster research by enhancing diagnostic accuracy, predicting treatment outcomes, and optimizing disease management. However, several limitations exist, including potential omissions from excluding databases like Embase and Scopus, language bias due to the inclusion of only English publications, and the risk of subjective bias in study selection. Broader studies and continuous updates are needed to fully capture the scope of AI applications in herpes zoster in the future.

This study focuses on automating the classification of certain thoracic lung cancer stages in 3D ¹⁸FDG-PET/CT images according to the 9th Edition of the TNM Classification for Lung Cancer (2024). By leveraging advanced segmentation and classification techniques, we aim to enhance the accuracy of distinguishing between T4 (pulmonary nodules) Thoracic M0 and M1a (pulmonary nodules) stages. Precise segmentation of pulmonary lobes using the Pulmonary Toolkit enables the identification of tumor locations and additional malignant nodules, ensuring reliable differentiation between ipsilateral and contralateral spread. A modified ResNet-50 model is employed to classify the segmented regions. The performance evaluation shows that the model achieves high accuracy. The unchanged class has the best recall 93% and an excellent F1 score 91%. The M1a (pulmonary nodules) class performs well with an F1 score of 94%, though recall is slightly lower 91%. For T4 (pulmonary nodules) Thoracic M0, the model shows balanced performance with an F1 score of 87%. The overall accuracy is 87%, indicating a robust classification model.

Based on preoperative clinical text data and lumbar magnetic resonance imaging (MRI), we applied machine learning (ML) algorithms to construct a model that would predict early recurrence in lumbar-disc herniation (LDH) patients who underwent percutaneous endoscopic lumbar discectomy (PELD). We then explored the clinical performance of this prognostic prediction model via multimodal-data fusion. Clinical text data and radiological images of LDH patients who underwent PELD at the Intervertebral Disc Center of the Affiliated Hospital of Gansu University of Traditional Chinese Medicine (AHGUTCM; Lanzhou, China) were retrospectively collected. Two radiologists with clinical-image reading experience independently outlined regions of interest (ROI) on the MRI images and extracted radiomic features using 3D Slicer software. We then randomly separated the samples into a training set and a test set at a 7:3 ratio, used eight ML algorithms to construct predictive radiomic-feature models, evaluated model performance by the area under the curve (AUC), and selected the optimal model for screening radiomic features and calculating radiomic scores (Rad-scores). Finally, after using logistic regression to construct a nomogram for predicting the early-recurrence rate, we evaluated the nomogram's clinical applicability using a clinical-decision curve. We initially extracted 851 radiomic features. After constructing our models, we determined based on AUC values that the optimal ML algorithm was least absolute shrinkage and selection operator (LASSO) regression, which had an AUC of 0.76 and an accuracy rate of 91%. After screening features using the LASSO model, we predicted Rad-score for each sample of recurrent LDH using nine radiomic features. Next, we fused three of these clinical features -age, diabetes, and heavy manual labor-to construct a nomogram with an AUC of 0.86 (95% confidence interval [CI], 0.79-0.94). Analysis of the clinical-decision and impact curves showed that the prognostic prediction model with multimodal-data fusion had good clinical validity and applicability. We developed and analyzed a prognostic prediction model for LDH with multimodal-data fusion. Our model demonstrated good performance in predicting early postoperative recurrence in LDH patients; therefore, it has good prospects for clinical application and can provide clinicians with objective, accurate information to help them decide on presurgical treatment plans. However, external-validation studies are still needed to further validate the model's comprehensive performance and improve its generalization and extrapolation.