Congenital heart defect (CHD) detection in ultrasound videos is hindered by image noise and probe positioning variability. While automated methods can reduce operator dependence, current machine learning approaches often neglect temporal information, limit themselves to binary classification, and do not account for prediction calibration. We propose Temporal Prompt Alignment (TPA), a method leveraging foundation image-text model and prompt-aware contrastive learning to classify fetal CHD on cardiac ultrasound videos. TPA extracts features from each frame of video subclips using an image encoder, aggregates them with a trainable temporal extractor to capture heart motion, and aligns the video representation with class-specific text prompts via a margin-hinge contrastive loss. To enhance calibration for clinical reliability, we introduce a Conditional Variational Autoencoder Style Modulation (CVAESM) module, which learns a latent style vector to modulate embeddings and quantifies classification uncertainty. Evaluated on a private dataset for CHD detection and on a large public dataset, EchoNet-Dynamic, for systolic dysfunction, TPA achieves state-of-the-art macro F1 scores of 85.40% for CHD diagnosis, while also reducing expected calibration error by 5.38% and adaptive ECE by 6.8%. On EchoNet-Dynamic's three-class task, it boosts macro F1 by 4.73% (from 53.89% to 58.62%). Temporal Prompt Alignment (TPA) is a framework for fetal congenital heart defect (CHD) classification in ultrasound videos that integrates temporal modeling, prompt-aware contrastive learning, and uncertainty quantification.

Ascending aortic (AscAo) dimensions partially depend on body size. Ratiometric (linear) indexing of AscAo dimensions to height and body surface area (BSA) are currently recommended, but it is unclear whether these allometric relationships are indeed linear. This study aimed to evaluate allometric relations, normative values, and the prognostic performance of AscAo dimension indices. We studied UK Biobank (UKB) (n = 49,271) and Penn Medicine BioBank (PMBB) (n = 8,426) participants. A convolutional neural network was used to segment the thoracic aorta from available magnetic resonance and computed tomography thoracic images. Normal allometric exponents of AscAo dimensions were derived from log-log models among healthy reference subgroups. Prognostic associations of AscAo dimensions were assessed with the use of Cox models. Among reference subgroups of both UKB (n = 11,310; age 52 ± 8 years; 37% male) and PMBB (n = 799; age 50 ± 16 years; 41% male), diameter/height, diameter/BSA, and area/BSA exhibited highly nonlinear relationships. In contrast, the allometric exponent of the area/height index was close to unity (UKB: 1.04; PMBB: 1.13). Accordingly, the linear ratio of area/height index did not exhibit residual associations with height (UKB: R² = 0.04 [P = 0.411]; PMBB: R² = 0.08 [P = 0.759]). Across quintiles of height and BSA, area/height was the only ratiometric index that consistently classified aortic dilation, whereas all other indices systematically underestimated or overestimated AscAo dilation at the extremes of body size. Area/height was robustly associated with thoracic aorta events in the UKB (HR: 3.73; P < 0.001) and the PMBB (HR: 1.83; P < 0.001). Among AscAo indices, area/height was allometrically correct, did not exhibit residual associations with body size, and was consistently associated with adverse events.

To construct a prediction model for radiation pneumonitis (RP) in lung cancer patients based on clinical information, medical text, and 2.5D deep learning (DL) features. A total of 356 patients with lung cancer from the Heping Campus of the First Hospital of China Medical University were randomly divided at a 7:3 ratio into training and validation cohorts, and 238 patients from 3 other centers were included in the testing cohort for assessing model generalizability. We used the term frequency-inverse document frequency method to generate numerical vectors from computed tomography (CT) report texts. The CT and radiation therapy dose slices demonstrating the largest lung region of interest across the coronal and transverse planes were considered as the central slice; moreover, 3 slices above and below the central slice were selected to create comprehensive 2.5D data. We extracted DL features via DenseNet121, DenseNet201, and Twins-SVT and integrated them via multi-instance learning (MIL) fusion. The performances of the 2D and 3D DL models were also compared with the performance of the 2.5D MIL model. Finally, RP prediction models based on clinical information, medical text, and 2.5D DL features were constructed, validated, and tested. The 2.5D MIL model based on CT was significantly better than the 2D and 3D DL models in the training, validation, and test cohorts. The 2.5D MIL model based on radiation therapy dose was considered to be the optimal model in the test1 cohort, whereas the 2D model was considered to be the optimal model in the training, validation, and test3 cohorts, with the 3D model being the optimal model in the test2 cohort. A combined model achieved Area Under Curve values of 0.964, 0.877, 0.868, 0.884, and 0.849 in the training, validation, test1, test2, and test3 cohorts, respectively. We propose an RP prediction model that integrates clinical information, medical text, and 2.5D MIL features, which provides new ideas for predicting the side effects of radiation therapy.

This study aims to evaluate the potential of Dual-Energy Computed Tomography (DECT)-based radiomics in preoperative risk stratification for the prediction of initial recurrence in Papillary Thyroid Carcinoma (PTC). The retrospective analysis included 236 PTC cases (165 in the training cohort, 71 in the validation cohort) collected between July 2020 and June 2021. Tumor segmentation was carried out in both intratumoral and peritumoral areas (1 mm inner and outer to the tumor boundary). Three regionspecific rad-scores were developed (rad-score [VOI^whole], rad-score [VOI^{outer layer}], and rad-score [VOI^{inner layer}]), respectively. Three radiomics models incorporating these rad-scores and additional risk factors were compared to a clinical model alone. The optimal radiomics model was presented as a nomogram. Rad-scores from peritumoral regions (VOI^{outer layer} and VOI^{inner layer}) outperformed the intratumoral rad-score (VOI^whole). All radiomics models surpassed the clinical model, with peritumoral-based models (radiomics models 2 and 3) outperforming the intratumoral-based model (radiomics model 1). The top-performing nomogram, which included tumor size, tumor site, and rad-score (VOI^{inner layer}), achieved an Area Under the Curve (AUC) of 0.877 in the training cohort and 0.876 in the validation cohort. The nomogram demonstrated good calibration, clinical utility, and stability. DECT-based intratumoral and peritumoral radiomics advance PTC initial recurrence risk prediction, providing clinical radiology with precise predictive tools. Further work is needed to refine the model and enhance its clinical application. Radiomics analysis of DECT, particularly in peritumoral regions, offers valuable predictive information for assessing the risk of initial recurrence in PTC.

Accurate preoperative assessment of occult lymph node metastasis (OLNM) plays a crucial role in informing therapeutic decision-making for lung cancer patients. Computed tomography (CT) is the most widely used imaging modality for preoperative work-up. The aim of this study was to develop and validate a CT-based machine learning model integrating intra-and peri-tumoral features to predict OLNM in lung cancer patients. Eligible patients with peripheral lung cancer confirmed by radical surgical excision with systematic lymphadenectomy were retrospectively recruited from January 2019 to December 2021. 1688 radiomics features were obtained from each manually segmented VOI which was composed of gross tumor volume (GTV) covering the boundary of entire tumor and three peritumoral volumes (PTV3, PTV6 and PTV9) that capture the region outside the tumor. A clinical-radiomics model incorporating radiomics signature, independent clinical factors and CT semantic features was established via multivariable logistic regression analysis and presented as a nomogram. Model performance was evaluated by discrimination, calibration, and clinical utility. Overall, 591 patients were recruited in the training cohort and 253 in the validation cohort. The radiomics signature of PTV9 showed superior diagnostic performance compared to PTV3 and PTV6 models. Integrating GPTV radiomics signature (incorporating Rad-score of GTV and PTV9) with clinical risk factor of serum CEA levels and CT imaging features of lobulation sign and tumor-pleura relationship demonstrated favorable accuracy in predicting OLNM in the training cohort (AUC, 0.819; 95% CI: 0.780-0.857) and validation cohort (AUC, 0.801; 95% CI: 0.741-0.860). The predictive performance of the clinical-radiomics model demonstrated statistically significant superiority over that of the clinical model in both cohorts (all p < 0.05). The clinical-radiomics model was able to serve as a noninvasive preoperative prediction tool for personalized risk assessment of OLNM in peripheral lung cancer patients.

In recent years, spinal X-ray image segmentation has played a vital role in the computer-aided diagnosis of various adolescent spinal disorders. However, due to the complex morphology of lesions and the fact that most existing methods are tailored to single-disease scenarios, current segmentation networks struggle to balance local detail preservation and global structural understanding across different disease types. As a result, they often suffer from limited accuracy, insufficient robustness, and poor adaptability. To address these challenges, we propose a novel fully automated spinal segmentation network, DCE-UNet, which integrates the local modeling strength of convolutional neural networks (CNNs) with the global contextual awareness of Transformers. The network introduces several architectural and feature fusion innovations. Specifically, a lightweight Transformer module is incorporated in the encoder to model high-level semantic features and enhance global contextual understanding. In the decoder, a Rec-Block module combining residual convolution and channel attention is designed to improve feature reconstruction and multi-scale fusion during the upsampling process. Additionally, the downsampling feature extraction path integrates a novel DC-Block that fuses channel and spatial attention mechanisms, enhancing the network's ability to represent complex lesion structures. Experiments conducted on a self-constructed large-scale multi-disease adolescent spinal X-ray dataset demonstrate that DCE-UNet achieves a Dice score of 91.3%, a mean Intersection over Union (mIoU) of 84.1, and a Hausdorff Distance (HD) of 4.007, outperforming several state-of-the-art comparison networks. Validation on real segmentation tasks further confirms that DCE-UNet delivers consistently superior performance across various lesion regions, highlighting its strong adaptability to multiple pathologies and promising potential for clinical application.

Development and verification of a convolutional neural network (CNN)-based deep learning (DL) model for mandibular canal (MC) localization on multicenter cone beam computed tomography (CBCT) images. In this study, a total 1056 CBCT scans in multiple centers were collected. Of these, 836 CBCT scans of one manufacturer were used for development of CNN model (training set: validation set: internal testing set = 640:360:36) and an external testing dataset of 220 CBCT scans from other four manufacturers were tested. The convolution module was built using a stack of Conv + InstanceNorm + LeakyReLU. Average symmetric surface distance (ASSD) and symmetric mean curve distance (SMCD) were used for quantitative evaluation of this model for both internal testing data and partial external testing data. Visual scoring (1-5 points) were performed to evaluate the accuracy and generalizability of MC localization for all external testing data. The differences of ASSD, SMCD and visual scores among the four manufacturers were compared for external testing dataset. The time of manual and automatic MC localization were recorded. For the internal testing dataset, the average ASSD and SMCD was 0.486 mm and 0.298 mm respectively. For the external testing dataset, 86.8% CBCT scans' visual scores ≥ 4 points; the average ASSD and SMCD of 40 CBCT scans with visual scores ≥ 4 points were 0.438 mm and 0.185 mm respectively; there were significant differences among the four manufacturers for ASSD, SMCD and visual scores (p < 0.05). And the time for bilateral automatic MC localization was 8.52s (± 0.97s). In this study, a CNN model was developed for automatic MC localization, and external testing of large sample on multicenter CBCT images showed its excellent clinical application potential.

Aging of the brain is characterized by deleterious processes at various levels including cellular/molecular and structural/functional changes. Many of these processes can be assessed in vivo by means of modern neuroimaging procedures, allowing the quantification of brain age in different modalities. Brain age can be measured by suitable machine learning strategies. The deviation (in both directions) between a person's measured brain age and chronologic age is referred to as the brain age gap (BAG). Although brain age, as defined by these methods, generally is related to the chronologic age of a person, this relationship is not always parallel and can also vary significantly between individuals. Importantly, whereas neurodegenerative disorders are not equivalent to accelerated brain aging, they may induce brain changes that resemble those of older adults, which can be captured by brain age models. Inversely, healthy brain aging may involve a resistance or delay of the onset of neurodegenerative pathologies in the brain. This continuing education article elaborates how the BAG can be computed and explores how BAGs, derived from diverse neuroimaging modalities, offer unique insights into the phenotypes of age-related neurodegenerative diseases. Structural BAGs from T1-weighted MRI have shown promise as phenotypic biomarkers for monitoring neurodegenerative disease progression especially in Alzheimer disease. Additionally, metabolic and molecular BAGs from molecular imaging, functional BAGs from functional MRI, and microstructural BAGs from diffusion MRI, although researched considerably less, each may provide distinct perspectives on particular brain aging processes and their deviations from healthy aging. We suggest that BAG estimation, when based on the appropriate modality, could potentially be useful for disease monitoring and offer interesting insights concerning the impact of therapeutic interventions.

Multimodal data integration has emerged as a transformative approach in the health care sector, systematically combining complementary biological and clinical data sources such as genomics, medical imaging, electronic health records, and wearable device outputs. This approach provides a multidimensional perspective of patient health that enhances the diagnosis, treatment, and management of various medical conditions. This viewpoint presents an overview of the current state of multimodal integration in health care, spanning clinical applications, current challenges, and future directions. We focus primarily on its applications across different disease domains, particularly in oncology and ophthalmology. Other diseases are briefly discussed due to the few available literature. In oncology, the integration of multimodal data enables more precise tumor characterization and personalized treatment plans. Multimodal fusion demonstrates accurate prediction of anti-human epidermal growth factor receptor 2 therapy response (area under the curve=0.91). In ophthalmology, multimodal integration through the combination of genetic and imaging data facilitates the early diagnosis of retinal diseases. However, substantial challenges remain regarding data standardization, model deployment, and model interpretability. We also highlight the future directions of multimodal integration, including its expanded disease applications, such as neurological and otolaryngological diseases, and the trend toward large-scale multimodal models, which enhance accuracy. Overall, the innovative potential of multimodal integration is expected to further revolutionize the health care industry, providing more comprehensive and personalized solutions for disease management.

Inherently lower signal-to-noise ratios hamper the broad clinical use of low-field abdominal MRI. This study aimed to investigate the technical feasibility and image quality of deep learning (DL)-enhanced T2 HASTE and T1 VIBE-Dixon abdominal MRI at 0.55 T. From July 2024 to September 2024, healthy volunteers underwent conventional and DL-enhanced 0.55 T abdominal MRI, including conventional T2 HASTE, fat-suppressed T2 HASTE (HASTE FS), and T1 VIBE-Dixon acquisitions, and DL-enhanced single- (HASTE DL_SBH) and multi-breath-hold HASTE (HASTE DL_MBH), fat-suppressed single- (HASTE FS DL_SBH) and multi-breath-hold HASTE (HASTE FS DL_MBH), and T1 VIBE-Dixon (VIBE-Dixon_DL) acquisitions. Three abdominal radiologists evaluated the scans for quality parameters and artifacts (Likert scale 1-5), and incidental findings. Interreader agreement and comparative analyses were conducted. 33 healthy volunteers (mean age: 30±4years) were evaluated. Image quality was better for single breath-hold DL-enhanced MRI (all P<0.001) with good or better interreader agreement (κ≥0.61), including T2 HASTE (HASTE DL_SBH: 4 [IQR: 4-4] vs. HASTE: 3 [3-3]), T2 HASTE FS (4 [4-4] vs. 3 [3-3]), and T1 VIBE-Dixon (4 [4-5] vs. 4 [3-4]). Similarly, image noise and spatial resolution were better for DL-MRI scans (P<0.001). No quality differences were found between single- and multi-breath-hold HASTE DL or HASTE FS DL (both: 4 [4-4]; P>0.572). The number and size of incidental lesions were identical between techniques (16 lesions; mean diameter 8±5 mm; P=1.000). DL-based image reconstruction enables single breath-hold T2 HASTE and T1 VIBE-Dixon abdominal imaging at 0.55 T with better image quality than conventional MRI.