The rapid advancement of the civil aviation industry has attracted significant attention to research on pilots. However, the brain changes experienced by flight cadets following their training remain, to some extent, an unexplored territory compared to those of the general population. The aim of this study was to examine the impact of flight training on brain function by employing machine learning(ML) techniques. We collected resting-state functional magnetic resonance imaging (resting-state fMRI) data from 79 flight cadets and ground program cadets, extracting blood oxygenation level-dependent (BOLD) signal, amplitude of low frequency fluctuation (ALFF), regional homogeneity (ReHo), and functional connectivity (FC) metrics as feature inputs for ML models. After conducting feature selection using a two-sample t-test, we established various ML classification models, including Extreme Gradient Boosting (XGBoost), Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), and Gaussian Naive Bayes (GNB). Comparative analysis of the model results revealed that the LR classifier based on BOLD signals could accurately distinguish flight cadets from the general population, achieving an AUC of 83.75% and an accuracy of 0.93. Furthermore, an analysis of the features contributing significantly to the ML classification models indicated that these features were predominantly located in brain regions associated with auditory-visual processing, motor function, emotional regulation, and cognition, primarily within the Default Mode Network (DMN), Visual Network (VN), and SomatoMotor Network (SMN). These findings suggest that flight-trained cadets may exhibit enhanced functional dynamics and cognitive flexibility.

Cervical spine disorders are becoming increasingly common, particularly among sedentary populations. The accurate segmentation of cervical vertebrae is critical for diagnostic and research applications. Traditional segmentation methods are limited in terms of precision and applicability across imaging modalities. The aim of this study is to develop and evaluate a fully automatic segmentation method and a user-friendly tool for detecting cervical vertebral body using a combined neural network model based on the YOLOv11 and U-Net3 + models. A dataset of X-ray and magnetic resonance imaging (MRI) images was collected, enhanced, and annotated to include 2136 X-ray images and 2184 MRI images. The proposed YOLO-UNet ensemble model was trained and compared with four other groups of image extraction models, including YOLOv11, DeepLabV3+, U-Net3 + for direct image segmentation, and the YOLO-DeepLab network. The evaluation metrics included the Dice coefficient, Hausdorff distance, intersection over union, positive predictive value, and sensitivity. The YOLO-UNet model combined the advantages of the YOLO and U-Net models and demonstrated excellent vertebral body segmentation capabilities on both X-ray and MRI datasets, which were closer to the ground truth images. Compared with other models, it achieved greater accuracy and a more accurate depiction of the vertebral body shape, demonstrated better versatility, and exhibited superior performance across all evaluation indicators. The YOLO-UNet network model provided a robust and versatile solution for cervical vertebral body segmentation, demonstrating excellent accuracy and adaptability across imaging modalities on both X-ray and MRI datasets. The accompanying user-friendly tool enhanced usability, making it accessible to both clinical and research users. In this study, the challenge of large-scale medical annotation tasks was addressed, thereby reducing project costs and supporting advancements in medical information technology and clinical research.

Machine learning (ML) classification of myocardial scarring in cardiac MRI is often hindered by limited explainability, particularly with convolutional neural networks (CNNs). To address this, we developed One Match (OM), an algorithm that builds on template matching to improve on both the explainability and performance of ML myocardial scaring classification. By incorporating OM, we aim to foster trust in AI models for medical diagnostics and demonstrate that improved interpretability does not have to compromise classification accuracy. Using a cardiac MRI dataset from 279 patients, this study evaluates One Match, which classifies myocardial scarring in images by matching each image to a set of labeled template images. It uses the highest correlation score from these matches for classification and is compared to a traditional sequential CNN. Enhancements such as autodidactic enhancement (AE) and patient-level classifications (PLCs) were applied to improve the predictive accuracy of both methods. Results are reported as follows: accuracy, sensitivity, specificity, precision, and F1-score. The highest classification performance was observed with the OM algorithm when enhanced by both AE and PLCs, 95.3% accuracy, 92.3% sensitivity, 96.7% specificity, 92.3% precision, and 92.3% F1-score, marking a significant improvement over the base configurations. AE alone had a positive impact on OM increasing accuracy from 89.0% to 93.2%, but decreased the accuracy of the CNN from 85.3% to 82.9%. In contrast, PLCs improved accuracy for both the CNN and OM, raising the CNN's accuracy by 4.2% and OM's by 7.4%. This study demonstrates the effectiveness of OM in classifying myocardial scars, particularly when enhanced with AE and PLCs. The interpretability of OM also enabled the examination of misclassifications, providing insights that could accelerate development and foster greater trust among clinical stakeholders.

Aiming to evaluate the effects of the smart metal artifact reduction (MAR) algorithm and combinations of various scanning parameters, including radiation dose levels, tube voltage, and reconstruction algorithms, on metal artifact reduction and overall image quality, to identify the optimal protocol for clinical application. A phantom with a pacemaker was examined using standard dose (effective dose (ED): 3 mSv) and low dose (ED: 0.5 mSv), with three scan voltages (70, 100, and 120 kVp) selected for each dose. Raw data were reconstructed using 50% adaptive statistical iterative reconstruction-V (ASIR-V), ASIR-V with MAR, high-strength deep learning image reconstruction (DLIR-H), and DLIR-H with MAR. Quantitative analyses (artifact index (AI), noise, signal-to-noise ratio (SNR) of artifact-impaired pulmonary nodules (PNs), and noise power spectrum (NPS) of artifact-free regions) and qualitative evaluation were performed. Quantitatively, the deep learning image recognition (DLIR) algorithm or high tube voltages exhibited lower noise compared to the ASIR-V or low tube voltages (<i>p</i> < 0.001). AI of images with MAR or high tube voltages was significantly lower than that of images without MAR or low tube voltages (<i>p</i> < 0.001). No significant difference was observed in AI between low-dose images with 120 kVp DLIR-H MAR and standard-dose images with 70 kVp ASIR-V MAR (<i>p</i> = 0.143). Only the 70 kVp 3 mSv protocol demonstrated statistically significant differences in SNR for artifact-impaired PNs (<i>p</i> = 0.041). The f_peak and f_avg values were similar across various scenarios, indicating that the MAR algorithm did not alter the image texture in artifact-free regions. The qualitative results of the extent of metal artifacts, the confidence in diagnosing artifact-impaired PNs, and the overall image quality were generally consistent with the quantitative results. The MAR algorithm combined with DLIR-H can reduce metal artifacts and enhance the overall image quality, particularly at high kVp tube voltages.

Currently, plaque segmentation in Optical Coherence Tomography (OCT) images of coronary arteries is primarily carried out manually by physicians, and the accuracy of existing automatic segmentation techniques needs further improvement. To furnish efficient and precise decision support, automated detection of plaques in coronary OCT images holds paramount importance. For addressing these challenges, we propose a novel deep learning algorithm featuring Dense Atrous Convolution (DAC) and attention mechanism to realize high-precision segmentation and classification of Coronary artery plaques. Then, a relatively well-established dataset covering 760 original images, expanded to 8,000 using data enhancement. This dataset serves as a significant resource for future research endeavors. The experimental results demonstrate that the dice coefficients of calcified, fibrous, and lipid plaques are 0.913, 0.900, and 0.879, respectively, surpassing those generated by five other conventional medical image segmentation networks. These outcomes strongly attest to the effectiveness and superiority of our proposed algorithm in the task of automatic coronary artery plaque segmentation.

Acute ischemic stroke (AIS) has a poor prognosis and a high recurrence rate. Predicting the outcomes of AIS patients in the early stages of the disease is therefore important. The establishment of intracerebral collateral circulation significantly improves the survival of brain cells and the outcomes of AIS patients. However, no machine learning method has been applied to investigate the correlation between the dynamic evolution of intracerebral venous collateral circulation and AIS prognosis. Therefore, we employed a support vector machine (SVM) algorithm to analyze asymmetrically prominent cortical veins (APCVs) and deep medullary veins (DMVs) to establish a radiomic model for predicting the prognosis of AIS by combining clinical indicators. The magnetic resonance imaging (MRI) data and clinical indicators of 150 AIS patients were retrospectively analyzed. Regions of interest corresponding to the DMVs and APCVs were delineated, and least absolute shrinkage and selection operator (LASSO) regression was used to select features extracted from these regions. An APCV-DMV radiomic model was created via the SVM algorithm, and independent clinical risk factors associated with AIS were combined with the radiomic model to generate a joint model. The SVM algorithm was selected because of its proven efficacy in handling high-dimensional radiomic data compared with alternative classifiers (<i>e.g.</i>, random forest) in pilot experiments. Nine radiomic features associated with AIS patient outcomes were ultimately selected. In the internal training test set, the AUCs of the clinical, DMV-APCV radiomic and joint models were 0.816, 0.976 and 0.996, respectively. The DeLong test revealed that the predictive performance of the joint model was better than that of the individual models, with a test set AUC of 0.996, sensitivity of 0.905, and specificity of 1.000 (<i>P</i> < 0.05). Using radiomic methods, we propose a novel joint predictive model that combines the imaging histologic features of the APCV and DMV with clinical indicators. This model quantitatively characterizes the morphological and functional attributes of venous collateral circulation, elucidating its important role in accurately evaluating the prognosis of patients with AIS and providing a noninvasive and highly accurate imaging tool for early prognostic prediction.

Magnetic Resonance Imaging (MRI) is a crucial diagnostic tool in medicine, widely used to detect and assess various health conditions. Different MRI sequences, such as T1-weighted, T2-weighted, and FLAIR, serve distinct roles by highlighting different tissue characteristics and contrasts. However, distinguishing them based solely on the description file is currently impossible due to confusing or incorrect annotations. Additionally, there is a notable lack of effective tools to differentiate these sequences. In response, we developed a deep learning-based toolkit tailored for small, unrefined MRI datasets. This toolkit enables precise sequence classification and delivers performance comparable to systems trained on large, meticulously curated datasets. Utilizing lightweight model architectures and incorporating a voting ensemble method, the toolkit enhances accuracy and stability. It achieves a 99% accuracy rate using only 10% of the data typically required in other research. The code is available at https://github.com/JinqianPan/MRISeqClassifier.

Despite significant progress in applying large language models (LLMs) to the medical domain, several limitations still prevent them from practical applications. Among these are the constraints on model size and the lack of cohort-specific labeled datasets. In this work, we investigated the potential of improving a lightweight LLM, such as Llama 3.1-8B, through fine-tuning with datasets using synthetic labels. Two tasks are jointly trained by combining their respective instruction datasets. When the quality of the task-specific synthetic labels is relatively high (e.g., generated by GPT4-o), Llama 3.1-8B achieves satisfactory performance on the open-ended disease detection task, with a micro F1 score of 0.91. Conversely, when the quality of the task-relevant synthetic labels is relatively low (e.g., from the MIMIC-CXR dataset), fine-tuned Llama 3.1-8B is able to surpass its noisy teacher labels (micro F1 score of 0.67 v.s. 0.63) when calibrated against curated labels, indicating the strong inherent underlying capability of the model. These findings demonstrate the potential offine-tuning LLMs with synthetic labels, offering a promising direction for future research on LLM specialization in the medical domain.

Non-contrast Computed Tomography (NCCT) quickly diagnoses acute cerebral hemorrhage or infarction. However, Deep-Learning (DL) algorithms often generate false alarms (FA) beyond the cerebral region. We introduce an enhanced brain tissue segmentation method for infarction lesion segmentation (ILS). This method integrates an adaptive result fusion strategy to confine the search operation within cerebral tissue, effectively reducing FAs. By leveraging fused brain masks, DL-based ILS algorithms focus on pertinent radiomic correlations. Various U-Net models underwent rigorous training, with exploration of diverse fusion strategies. Further refinement entailed applying a 9x9 Gaussian filter with unit standard deviation followed by binarization to mitigate false positives. Performance evaluation utilized Intersection over Union (IoU) and Hausdorff Distance (HD) metrics, complemented by external validation on a subset of the COCO dataset. Our study comprised 20 ischemic stroke patients (14 males, 4 females) with an average age of 68.9 ± 11.7 years. Fusion with UNet2+ and UNet3 + yielded an IoU of 0.955 and an HD of 1.33, while fusion with U-net, UNet2 + , and UNet3 + resulted in an IoU of 0.952 and an HD of 1.61. Evaluation on the COCO dataset demonstrated an IoU of 0.463 and an HD of 584.1 for fusion with UNet2+ and UNet3 + , and an IoU of 0.453 and an HD of 728.0 for fusion with U-net, UNet2 + , and UNet3 + . Our adaptive fusion strategy significantly diminishes FAs and enhances the training efficacy of DL-based ILS algorithms, surpassing individual U-Net models. This methodology holds promise as a versatile, data-independent approach for cerebral lesion segmentation.

Currently, there are inconsistencies among different studies on preoperative prediction of Cytokeratin 19 (CK19) expression in HCC using traditional imaging, radiomics, and deep learning. We aimed to systematically analyze and compare the performance of non-invasive methods for predicting CK19-positive HCC, thereby providing insights for the stratified management of HCC patients. A comprehensive literature search was conducted in PubMed, EMBASE, Web of Science, and the Cochrane Library from inception to February 2025. Two investigators independently screened and extracted data based on inclusion and exclusion criteria. Eligible studies were included, and key findings were summarized in tables to provide a clear overview. Ultimately, 22 studies involving 3395 HCC patients were included. 72.7% (16/22) focused on traditional imaging, 36.4% (8/22) on radiomics, 9.1% (2/22) on deep learning, and 54.5% (12/22) on combined models. The magnetic resonance imaging was the most commonly used imaging modality (19/22), and over half of the studies (12/22) were published between 2022 and 2025. Moreover, 27.3% (6/22) were multicenter studies, 36.4% (8/22) included a validation set, and only 13.6% (3/22) were prospective. The area under the curve (AUC) range of using clinical and traditional imaging was 0.560 to 0.917. The AUC ranges of radiomics were 0.648 to 0.951, and the AUC ranges of deep learning were 0.718 to 0.820. Notably, the AUC ranges of combined models of clinical, imaging, radiomics and deep learning were 0.614 to 0.995. Nevertheless, the multicenter external data were limited, with only 13.6% (3/22) incorporating validation. The combined model integrating traditional imaging, radiomics and deep learning achieves excellent potential and performance for predicting CK19 in HCC. Based on current limitations, future research should focus on building an easy-to-use dynamic online tool, combining multicenter-multimodal imaging and advanced deep learning approaches to enhance the accuracy and robustness of model predictions.