Fetal diffusion-weighted magnetic resonance imaging (dMRI) represents a promising modality for the assessment of white matter fiber organization, microstructure and development during pregnancy. Over the past two decades, research using this technology has significantly increased, but no consensus has yet been established on how to best implement and standardize the use of fetal dMRI across clinical and research settings. This scoping review aims to synthesize the various methodological approaches for the analysis of fetal dMRI brain data and their applications. We identified a total of 54 relevant articles and analyzed them across five primary domains: (1) datasets, (2) acquisition protocols, (3) image preprocessing/denoising, (4) image processing/modeling, and (5) brain atlas construction. The review of these articles reveals a predominant reliance on Diffusion Tensor Imaging (DTI) (n=37) to study fiber properties, and deterministic tractography approaches to investigate fiber organization (n=23). However, there is an emerging trend towards the adoption of more advanced techniques that address the inherent limitations of fetal dMRI (e.g. maternal and fetal motion, intensity artifacts, fetus's fast and uneven development), particularly through the application of artificial intelligence-based approaches (n=8). In our view, the results suggest that the potential of fetal brain dMRI is hindered by the methodological heterogeneity of the proposed solutions and the lack of publicly available data and tools. Nevertheless, clinical applications demonstrate its utility in studying brain development in both healthy and pathological conditions.

In many contemporary laboratories a completely normal stress perfusion SPECT-MPI is required for rest imaging cancelation. We hypothesized that an artificial intelligence (AI)-derived CAC score of 0 from computed tomography attenuation correction (CTAC) scans obtained during hybrid SPECT/CT, may identify additional patients at low risk of MACE who could be selected for stress-only imaging. Patients without known coronary artery disease who underwent SPECT/CT MPI and had stress total perfusion deficit (TPD) <5% were included. Stress TPD was categorized as no abnormality (stress TPD 0%) or minimal abnormality (stress TPD 1-4%). CAC was automatically quantified from the CTAC scans. We evaluated associations with major adverse cardiovascular events (MACE). In total, 6,884 patients (49.4% males and median age 63 years) were included. Of these, 9.7% experienced MACE (15% non-fatal MI, 2.7% unstable angina, 38.5% coronary revascularization and 43.8% deaths). Compared to patients with TPD 0%, those with TPD 1-4% and CAC 0 had lower MACE risk (hazard ratio [HR] 0.58; 95% confidence interval [CI] 0.45-0.76), while those with TPD 1-4% and CAC score>0 had a higher MACE risk (HR 1.90; 95%CI 1.56-2.30). Compared to canceling rest scans only in patients with normal perfusion (TPD 0%), by canceling rest scans in patients with CAC 0, more than twice as many rest scans (55% vs 25%) could be cancelled. Using AI-derived CAC 0 on CT scans with hybrid SPECT/CT in patients with a stress TPD<5% can double the proportion of patients in whom stress-only procedures could be safely performed.

Sensory experience impacts brain development. In the mouse somatosensory cortex, sensory deprivation via whisker trimming induces reductions in the perineuronal net, the size of neuronal cell bodies, the size and orientation of dendritic arbors, the density of dendritic spines, and the level of myelination, among other effects. Using a custom-developed laboratory diffractometer, we measured the X-ray diffraction patterns of mouse brain tissue to establish a novel method for examining nanoscale brain structures. Two groups of mice were examined: a control group and one that underwent 30 days of whisker-trimming from birth an established method of sensory deprivation that affects the mouse barrel cortex (whisker sensory processing region of the primary somatosensory cortex). Mice were perfused, and primary somatosensory cortices were isolated for immunocytochemistry and X-ray diffraction imaging. X-ray images were characterized using a specially developed machine-learning approach, and the clusters that correspond to the two groups are well separated in principal components space. We obtained the perfect values for sensitivity and specificity, as well as for the receiver operator curve classifier. New machine-learning approaches allow for the first time x-ray diffraction to identify cortex that has undergone sensory deprivation without the use of stains. We hypothesize that our results are related to the alteration of different nanoscale structural components in the brains of sensory deprived mice. The effects of these nanoscale structural formations can be reflective of changes in the micro- and macro-scale structures and assemblies with the neocortex.

The generalizability and reproducibility of AI-assisted detection for cerebral aneurysms on 3D time-of-flight MR angiography remain unclear. We aimed to evaluate physician performance using AI assistance, focusing on inter- and intra-user variability, identifying factors influencing performance and clinical implications. In this retrospective study, four state-of-the-art AI models were hyperparameter-optimized on an in-house dataset (2019-2021) and evaluated via 5-fold cross-validation on a public external dataset. The two best-performing models were selected for evaluation on an expert-revised external dataset. saccular aneurysms without prior treatment. Five physicians, grouped by expertise, each performed two AI-assisted evaluations, one with each model. Lesion-wise sensitivity and false positives per case (FPs/case) were calculated for each physician-AI pair and AI models alone. Agreement was assessed using kappa. Aneurysm size comparisons used the Mann-Whitney U test. The in-house dataset included 132 patients with 206 aneurysms (mean size: 4.0 mm); the revised external dataset, 270 patients with 174 aneurysms (mean size: 3.7 mm). Standalone AI achieved 86.8% sensitivity and 0.58 FPs/case. With AI assistance, non-experts achieved 72.1% sensitivity and 0.037 FPs/case; experts, 88.6% and 0.076 FPs/case; the intermediate-level physician, 78.5% and 0.037 FPs/case. Intra-group agreement was 80% for non-experts (kappa: 0.57, 95% CI: 0.54-0.59) and 77.7% for experts (kappa: 0.53, 95% CI: 0.51-0.55). In experts, false positives were smaller than true positives (2.7 vs. 3.8 mm, p < 0.001); no difference in non-experts (p = 0.09). Missed aneurysm locations were mainly model-dependent, while true- and false-positive locations reflected physician expertise. Non-experts more often rejected AI suggestions and added fewer annotations; experts were more conservative and added more. Evaluating AI models in isolation provides an incomplete view of their clinical applicability. Detection performance and patterns differ between standalone AI and AI-assisted use, and are modulated by physician expertise. Rigorous external validation is essential before clinical deployment.

This study focused on developing and validating a composite model that integrates radiomic and dosiomic features based on a lung biologically equivalent dose segmentation approach to predict symptomatic radiation pneumonitis (SRP) following lung SBRT. A dual-centered cohorts of 182 lung cancer patients treated with SBRT were divided into training, validation, and external testing sets. Radiomic and dosiomic features were extracted from two distinct regions of interest (ROIs) in the planning computed tomography (CT) images and 3D dose distribution maps, which encompassed both the entire lung and biologically equivalent dose (BED) regions. Feature selection involved correlation filters and LASSO regularization. Five machine learning algorithms generated three individual models (dose-volume histogram [DVH], radiomic [R], dosiomic [D]) and three combined models (R + DVH, R + D, R + D + DVH). Performance was evaluated via ROC analysis, calibration, and decision curve analysis. Among the clinical and dosimetric factors, V_BED70 (α/β = 3 Gy) of the lung was recognized as an independent risk factor for SRP. BED-based radiomic and dosiomic models outperformed whole-lung models (AUCs: 0.806 vs. 0.674 and 0.821 vs. 0.647, respectively). The R + D + DVH trio model achieved the highest predictive accuracy (AUC: 0.889, 95 % CI: 0.701-0.956), with robust calibration and clinical utility. The R + D + DVH trio model based on lung biologically equivalent dose segmentation approach outperforms other models in predicting SRP across various SBRT fractionation schemes.

Neoadjuvant chemoradiotherapy (nCRT) followed by esophagectomy remains standard for locally advanced esophageal squamous cell carcinoma (ESCC). However, accurately predicting pathological complete response (pCR) and treatment outcomes remains challenging. This study aimed to develop and validate a multidimensional deep ensemble learning model (DELRN) using pretreatment CT imaging to predict pCR and stratify prognostic risk in ESCC patients undergoing nCRT. In this multicenter, retrospective cohort study, 485 ESCC patients were enrolled from four hospitals (May 2009-August 2023, December 2017-September 2021, May 2014-September 2019, and March 2013-July 2019). Patients were divided into a discovery cohort (n = 194), an internal cohort (n = 49), and three external validation cohorts (n = 242). A multidimensional deep ensemble learning model (DELRN) integrating radiomics and 3D convolutional neural networks was developed based on pretreatment CT images to predict pCR and clinical outcomes. The model's performance was evaluated by discrimination, calibration, and clinical utility. Kaplan-Meier analysis assessed overall survival (OS) and disease-free survival (DFS) at two follow-up centers. The DELRN model demonstrated robust predictive performance for pCR across the discovery, internal, and external validation cohorts, with area under the curve (AUC) values of 0.943 (95 % CI: 0.912-0.973), 0.796 (95 % CI: 0.661-0.930), 0.767 (95 % CI: 0.646-0.887), 0.829 (95 % CI: 0.715-0.942), and 0.782 (95 % CI: 0.664-0.900), respectively, surpassing single-domain radiomics or deep learning models. DELRN effectively stratified patients into high-risk and low-risk groups for OS (log-rank P = 0.018 and 0.0053) and DFS (log-rank P = 0.00042 and 0.035). Multivariate analysis confirmed DELRN as an independent prognostic factor for OS and DFS. The DELRN model demonstrated promising clinical potential as an effective, non-invasive tool for predicting nCRT response and treatment outcome in ESCC patients, enabling personalized treatment strategies and improving clinical decision-making with future prospective multicenter validation.

The variability and biases in the real-world performance benchmarking of deep learning models for medical imaging compromise their trustworthiness for real-world deployment. The common approach of holding out a single fixed test set fails to quantify the variance in the estimation of test performance metrics. This study introduces NACHOS (Nested and Automated Cross-validation and Hyperparameter Optimization using Supercomputing) to reduce and quantify the variance of test performance metrics of deep learning models. NACHOS integrates Nested Cross-Validation (NCV) and Automated Hyperparameter Optimization (AHPO) within a parallelized high-performance computing (HPC) framework. NACHOS was demonstrated on a chest X-ray repository and an Optical Coherence Tomography (OCT) dataset under multiple data partitioning schemes. Beyond performance estimation, DACHOS (Deployment with Automated Cross-validation and Hyperparameter Optimization using Supercomputing) is introduced to leverage AHPO and cross-validation to build the final model on the full dataset, improving expected deployment performance. The findings underscore the importance of NCV in quantifying and reducing estimation variance, AHPO in optimizing hyperparameters consistently across test folds, and HPC in ensuring computational feasibility. By integrating these methodologies, NACHOS and DACHOS provide a scalable, reproducible, and trustworthy framework for DL model evaluation and deployment in medical imaging. To maximize public availability, the full open-source codebase is provided at https://github.com/thepanlab/NACHOS.

Automatic quantification of intramyocardial motion and strain from tagging MRI remains an important but challenging task. We propose a method using implicit neural representations (INRs), conditioned on learned latent codes, to predict continuous left ventricular (LV) displacement -- without requiring inference-time optimisation. Evaluated on 452 UK Biobank test cases, our method achieved the best tracking accuracy (2.14 mm RMSE) and the lowest combined error in global circumferential (2.86%) and radial (6.42%) strain compared to three deep learning baselines. In addition, our method is $\sim$380$\times$ faster than the most accurate baseline. These results highlight the suitability of INR-based models for accurate and scalable analysis of myocardial strain in large CMR datasets.

BackgroundEarly detection of autism spectrum disorder (ASD) improves outcomes, yet clinical assessment is time-intensive. Artificial intelligence (AI) may support screening in preschool children by analysing behavioural, neurophysiological, imaging, and biomarker data. AimTo synthesise studies that applied AI in ASD assessment and evaluate whether the underlying data and AI approaches can distinguish ASD characteristics in early childhood. MethodsA systematic search of 15 databases was conducted on 30 November 2024 using predefined terms. Inclusion criteria were empirical studies applying AI to ASD detection in children aged 0-7 years. Reporting followed PRISMA 2020. ResultsTwelve studies met criteria. Reported performance (AUC) ranged from 0.65 to 0.997. Modalities included behavioural (eye-tracking, home videos), motor (tablet/reaching), EEG, diffusion MRI, and blood/epigenetic biomarkers. The largest archival dataset (M-CHAT-R) achieved near-perfect AUC with neural networks. Common limitations were small samples, male-skewed cohorts, and limited external validation. ConclusionsAI can aid early ASD screening in infants and preschoolers, but larger and more diverse datasets, rigorous external validation, and multimodal integration are needed before clinical deployment.

Lung adenocarcinoma remains a leading cause of cancer-related mortality, and the diagnostic performance of computed tomography (CT) is limited when dependent solely on human interpretation. This study aimed to develop and evaluate an interpretable deep learning framework using an attention-enhanced Squeeze-and-Excitation Residual Network (SE-ResNet) to improve automated classification of lung adenocarcinoma from thoracic CT images. Furthermore, Gradient-weighted Class Activation Mapping (Grad-CAM) was applied to enhance model interpretability and assist in the visual localization of tumor regions. A total of 3800 chest CT axial slices were collected from 380 subjects (190 patients with lung adenocarcinoma and 190 controls, with 10 slices extracted from each case). This dataset was used to train and evaluate the baseline ResNet50 model as well as the proposed SE-ResNet50 model. Performance was compared using accuracy, Area Under the Curve (AUC), precision, recall, and F1-score. Grad-CAM visualizations were generated to assess the alignment between the model's attention and radiologically confirmed tumor locations. The SE-ResNet model achieved a classification accuracy of 94% and an AUC of 0.941, significantly outperforming the baseline ResNet50, which had an 85% accuracy and an AUC of 0.854. Grad-CAM heatmaps produced from the SE-ResNet demonstrated superior localization of tumor-relevant regions, confirming the enhanced focus provided by the attention mechanism. The proposed SE-ResNet framework delivers high accuracy and interpretability in classifying lung adenocarcinoma from CT images. It shows considerable potential as a decision-support tool to assist radiologists in diagnosis and may serve as a valuable clinical tool with further validation.