Chest X-rays (CXR) rank among the most conducted X-ray examinations. They often require repeat imaging due to inadequate quality, leading to increased radiation exposure and delays in patient care and diagnosis. This research assesses the efficacy of DenseNet121 and YOLOv8 neural networks in detecting suboptimal CXRs, which may minimise delays and enhance patient outcomes. The study included 3587 patients with a median age of 67 (0-102). It utilised an initial dataset comprising 10,000 CXRs randomly divided into a training subset (4000 optimal and 4000 suboptimal) and a validation subset (400 optimal and 400 suboptimal). The test subset (25 optimal and 25 suboptimal) was curated from the remaining images to provide adequate variation. Neural networks DenseNet121 and YOLOv8 were chosen due to their capabilities in image classification. DenseNet121 is a robust, well-tested model in the medical industry with high accuracy in object recognition. YOLOv8 is a cutting-edge commercial model targeted at all industries. Their performance was assessed via the area under the receiver operating curve (AUROC) and compared to radiologist classification, utilising the chi-squared test. DenseNet121 attained an AUROC of 0.97, while YOLOv8 recorded a score of 0.95, indicating a strong capability in differentiating between optimal and suboptimal CXRs. The alignment between radiologists and models exhibited variability, partly due to the lack of clinical indications. However, the performance was not statistically significant. Both AI models effectively classified chest X-ray quality, demonstrating the potential for providing radiographers with feedback to improve image quality. Notably, this was the first study to include both PA and lateral CXRs as well as paediatric cases and the first to evaluate YOLOv8 for this application.

Annotation variability remains a substantial challenge in medical image segmentation, stemming from ambiguous imaging boundaries and diverse clinical expertise. Traditional deep learning methods producing single deterministic segmentation predictions often fail to capture these annotator biases. Although recent studies have explored multi-rater segmentation, existing methods typically focus on a single perspective -- either generating a probabilistic ``gold standard'' consensus or preserving expert-specific preferences -- thus struggling to provide a more omni view. In this study, we propose DiffOSeg, a two-stage diffusion-based framework, which aims to simultaneously achieve both consensus-driven (combining all experts' opinions) and preference-driven (reflecting experts' individual assessments) segmentation. Stage I establishes population consensus through a probabilistic consensus strategy, while Stage II captures expert-specific preference via adaptive prompts. Demonstrated on two public datasets (LIDC-IDRI and NPC-170), our model outperforms existing state-of-the-art methods across all evaluated metrics. Source code is available at https://github.com/string-ellipses/DiffOSeg .

Precise liver segmentation is critical for accurate diagnosis and effective treatment planning, serving as a foundation for medical image analysis. However, existing methods struggle with limited labeled data, poor generalizability, and insufficient integration of anatomical and clinical features. To address these limitations, we propose a novel Few-Shot Segmentation model with Unified Liver Representation (FSS-ULivR), which employs a ResNet-based encoder enhanced with Squeeze-and-Excitation modules to improve feature learning, an enhanced prototype module that utilizes a transformer block and channel attention for dynamic feature refinement, and a decoder with improved attention gates and residual refinement strategies to recover spatial details from encoder skip connections. Through extensive experiments, our FSS-ULivR model achieved an outstanding Dice coefficient of 98.94%, Intersection over Union (IoU) of 97.44% and a specificity of 93.78% on the Liver Tumor Segmentation Challenge dataset. Cross-dataset evaluations further demonstrated its generalizability, with Dice scores of 95.43%, 92.98%, 90.72%, and 94.05% on 3DIRCADB01, Colorectal Liver Metastases, Computed Tomography Organs (CT-ORG), and Medical Segmentation Decathlon Task 3: Liver datasets, respectively. In multi-organ segmentation on CT-ORG, it delivered Dice scores ranging from 85.93% to 94.26% across bladder, bones, kidneys, and lungs. For brain tumor segmentation on BraTS 2019 and 2020 datasets, average Dice scores were 90.64% and 89.36% across whole tumor, tumor core, and enhancing tumor regions. These results emphasize the clinical importance of our model by demonstrating its ability to deliver precise and reliable segmentation through artificial intelligence techniques and engineering solutions, even in scenarios with scarce annotated data.

BackgroundFree-running (FR) cardiac MRI enables free-breathing ECG-free fully dynamic 5D (3D spatial+cardiac+respiration dimensions) imaging but poses significant challenges for clinical integration due to the volume and complexity of image analysis. Existing segmentation methods are tailored to 2D cine or static 3D acquisitions and cannot leverage the unique spatial-temporal wealth of FR data. PurposeTo develop and validate a deep learning (DL)-based segmentation framework for isotropic 3D+cardiac cycle FR cardiac MRI that enables accurate, fast, and clinically meaningful anatomical and functional analysis. MethodsFree-running, contrast-free bSSFP acquisitions at 1.5T and contrast-enhanced GRE acquisitions at 3T were used to reconstruct motion-resolved 5D datasets. From these, the end-expiratory respiratory phase was retained to yield fully isotropic 4D datasets. Automatic propagation of a limited set of manual segmentations was used to segment the left and right ventricular blood pool (LVB, RVB) and left ventricular myocardium (LVM) on reformatted short-axis (SAX) end-systolic (ES) and end-diastolic (ED) images. These were used to train a 3D nnU-Net model. Validation was performed using geometric metrics (Dice similarity coefficient [DSC], relative volume difference [RVD]), clinical metrics (ED and ES volumes, ejection fraction [EF]), and physiological consistency metrics (systole-diastole LVM volume mismatch and LV-RV stroke volume agreement). To assess the robustness and flexibility of the approach, we evaluated multiple additional DL training configurations such as using 4D propagation-based data augmentation to incorporate all cardiac phases into training. ResultsThe main proposed method achieved automatic segmentation within a minute, delivering high geometric accuracy and consistency (DSC: 0.94 {+/-} 0.01 [LVB], 0.86 {+/-} 0.02 [LVM], 0.92 {+/-} 0.01 [RVB]; RVD: 2.7%, 5.8%, 4.5%). Clinical LV metrics showed excellent agreement (ICC > 0.98 for EDV/ESV/EF, bias < 2 mL for EDV/ESV, < 1% for EF), while RV metrics remained clinically reliable (ICC > 0.93 for EDV/ESV/EF, bias < 1 mL for EDV/ESV, < 1% for EF) but exhibited wider limits of agreement. Training on all cardiac phases improved temporal coherence, reducing LVM volume mismatch from 4.0% to 2.6%. ConclusionThis study validates a DL-based method for fast and accurate segmentation of whole-heart free-running 4D cardiac MRI. Robust performance across diverse protocols and evaluation with complementary metrics that match state-of-the-art benchmarks supports its integration into clinical and research workflows, helping to overcome a key barrier to the broader adoption of free-running imaging.

Sparse-view computed tomography (CT) holds promise for reducing radiation exposure and enabling novel system designs. Traditional reconstruction algorithms, including Filtered Backprojection (FBP) and Model-Based Iterative Reconstruction (MBIR), often produce artifacts in sparse-view data. Deep Learning Reconstruction (DLR) offers potential improvements, but task-based evaluations of DLR in sparse-view CT remain limited. This study employs an Artificial Intelligence (AI) observer to evaluate the diagnostic accuracy of FBP, MBIR, and DLR for intracranial hemorrhage detection and classification, offering a cost-effective alternative to human radiologist studies. A public brain CT dataset with labeled intracranial hemorrhages was used to train an AI observer model. Sparse-view CT data were simulated, with reconstructions performed using FBP, MBIR, and DLR. Reconstruction quality was assessed using metrics such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and Learned Perceptual Image Patch Similarity (LPIPS). Diagnostic utility was evaluated using Receiver Operating Characteristic (ROC) analysis and Area Under the Curve (AUC) values for One-vs-Rest and One-vs-One classification tasks. DLR outperformed FBP and MBIR in all quality metrics, demonstrating reduced noise, improved structural similarity, and fewer artifacts. The AI observer achieved the highest classification accuracy with DLR, while FBP surpassed MBIR in task-based accuracy despite inferior image quality metrics, emphasizing the value of task-based evaluations. DLR provides an effective balance of artifact reduction and anatomical detail in sparse-view CT brain imaging. This proof-of-concept study highlights AI observer models as a viable, cost-effective alternative for evaluating CT reconstruction techniques.

CT-based opportunistic screening using artificial intelligence finds a high prevalence (43%) of osteoporosis in CT scans obtained for planning of transcatheter aortic valve replacement. Thus, opportunistic screening may be a cost-effective way to assess osteoporosis in high-risk populations. Osteoporosis is an underdiagnosed condition associated with fractures and frailty, but may be detected in routine computed tomography (CT) scans. Volumetric bone mineral density (vBMD) was measured in clinical routine thoraco-abdominal CT scans of 207 patients for planning of transcatheter aortic valve replacement (TAVR) using an artificial intelligence (AI)-based algorithm. 43% of patients had osteoporosis (vBMD < 80 mg/cm³ L1-L3) and were elderly (83.0 {interquartile range [IQR]: 78.0-85.5} vs. 79.0 {IQR: 71.8-84.0} years, p < 0.001), more often female (55.1 vs. 28.8%, p < 0.001), and had a higher Society of Thoracic Surgeon's score for mortality (3.0 {IQR:1.8-4.6} vs. 2.1 {IQR: 1.4-3.2}%, p < 0.001). In addition to lumbar vBMD (58.2 ± 14.7 vs. 106 ± 21.4 mg/cm³, p < 0.001), thoracic vBMD (79.5 ± 17.9 vs. 127.4 ± 26.0 mg/cm³, p < 0.001) was also significantly reduced in these patients and showed high diagnostic accuracy for osteoporosis assessment (area under curve: 0.96, p < 0.001). Osteoporotic patients were significantly more often at risk for falls (40.4 vs. 22.9%, p = 0.007) and required help in activities of daily life (ADL) more frequently (48.3 vs. 33.1%, p = 0.026), while direct-to-home discharges were fewer (88.8 vs. 96.6%, p = 0.026). In-hospital bleeding complications (3.4 vs. 5.1%), stroke (1.1 vs. 2.5%), and death (1.1 vs. 0.8%) were equally low, while in-hospital device success was equally high (94.4 vs. 94.9%, p > 0.05 for all comparisons). However, one-year probability of survival was significantly lower (84.0 vs. 98.2%, log-rank p < 0.01). Applying an AI-based algorithm to TAVR planning CT scans can reveal a high rate of 43% patients having osteoporosis. Osteoporosis may represent a marker related to frailty and worsened outcome in TAVR patients.

Vascular aging is an important phenotype characterized by structural and geometric remodeling. Some individuals exhibit supernormal vascular aging, associated with improved cardiovascular outcomes; others experience early vascular aging, linked to adverse cardiovascular outcomes. The aorta is the artery that exhibits the most prominent age-related changes; however, the biological mechanisms underlying aortic aging, its genetic architecture, and its relationship with cardiovascular structure, function, and disease states remain poorly understood. We developed sex-specific models to quantify aortic age on the basis of aortic geometric phenotypes derived from 3-dimensional tomographic imaging data in 2 large biobanks: the UK Biobank and the Penn Medicine BioBank. Convolutional neural ne2rk-assisted 3-dimensional segmentation of the aorta was performed in 56 104 magnetic resonance imaging scans in the UK Biobank and 6757 computed tomography scans in the Penn Medicine BioBank. Aortic vascular age index (AVAI) was calculated as the difference between the vascular age predicted from geometric phenotypes and the chronological age, expressed as a percent of chronological age. We assessed associations with cardiovascular structure and function using multivariate linear regression and examined the genetic architecture of AVAI through genome-wide association studies, followed by Mendelian randomization to assess causal associations. We also constructed a polygenic risk score for AVAI. AVAI displayed numerous associations with cardiac structure and function, including increased left ventricular mass (standardized β=0.144 [95% CI, 0.138, 0.149]; <i>P</i><0.0001), wall thickness (standardized β=0.061 [95% CI, 0.054, 0.068]; <i>P</i><0.0001), and left atrial volume maximum (standardized β=0.060 [95% CI, 0.050, 0.069]; <i>P</i><0.0001). AVAI exhibited high genetic heritability (<i>h</i>²=40.24%). We identified 54 independent genetic loci (<i>P</i><5×10^-⁸) associated with AVAI, which further exhibited gene-level associations with the fibrillin-1 (<i>FBN1</i>) and elastin (<i>ELN1</i>) genes. Mendelian randomization supported causal associations between AVAI and atrial fibrillation, vascular dementia, aortic aneurysm, and aortic dissection. A polygenic risk score for AVAI was associated with an increased prevalence of atrial fibrillation, hypertension, aortic aneurysm, and aortic dissection. Early aortic aging is significantly associated with adverse cardiac remodeling and important cardiovascular disease states. AVAI exhibits a polygenic, highly heritable genetic architecture. Mendelian randomization analyses support a causal association between AVAI and cardiovascular diseases, including atrial fibrillation, vascular dementia, aortic aneurysms, and aortic dissection.

Bronchopulmonary dysplasia (BPD) is a chronic lung disease affecting 35% of extremely low birth weight infants. Defined by oxygen dependence at 36 weeks postmenstrual age, it causes lifelong respiratory complications. However, preventive interventions carry severe risks, including neurodevelopmental impairment, ventilator-induced lung injury, and systemic complications. Therefore, early BPD prognosis and prediction of BPD outcome is crucial to avoid unnecessary toxicity in low risk infants. Admission radiographs of extremely preterm infants are routinely acquired within 24h of life and could serve as a non-invasive prognostic tool. In this work, we developed and investigated a deep learning approach using chest X-rays from 163 extremely low-birth-weight infants ($\leq$32 weeks gestation, 401-999g) obtained within 24 hours of birth. We fine-tuned a ResNet-50 pretrained specifically on adult chest radiographs, employing progressive layer freezing with discriminative learning rates to prevent overfitting and evaluated a CutMix augmentation and linear probing. For moderate/severe BPD outcome prediction, our best performing model with progressive freezing, linear probing and CutMix achieved an AUROC of 0.78 $\pm$ 0.10, balanced accuracy of 0.69 $\pm$ 0.10, and an F1-score of 0.67 $\pm$ 0.11. In-domain pre-training significantly outperformed ImageNet initialization (p = 0.031) which confirms domain-specific pretraining to be important for BPD outcome prediction. Routine IRDS grades showed limited prognostic value (AUROC 0.57 $\pm$ 0.11), confirming the need of learned markers. Our approach demonstrates that domain-specific pretraining enables accurate BPD prediction from routine day-1 radiographs. Through progressive freezing and linear probing, the method remains computationally feasible for site-level implementation and future federated learning deployments.

Foundation models have significantly revolutionized the field of chest X-ray diagnosis with their ability to transfer across various diseases and tasks. However, previous works have predominantly utilized self-supervised learning from medical image-text pairs, which falls short in dense medical prediction tasks due to their sole reliance on such coarse pair supervision, thereby limiting their applicability to detailed diagnostics. In this paper, we introduce a Dense Chest X-ray Foundation Model (DCXFM), which utilizes mixed supervision types (i.e., text, label, and segmentation masks) to significantly enhance the scalability of foundation models across various medical tasks. Our model involves two training stages: we first employ a novel self-distilled multimodal pretraining paradigm to exploit text and label supervision, along with local-to-global self-distillation and soft cross-modal contrastive alignment strategies to enhance localization capabilities. Subsequently, we introduce an efficient cost aggregation module, comprising spatial and class aggregation mechanisms, to further advance dense prediction tasks with densely annotated datasets. Comprehensive evaluations on three tasks (phrase grounding, zero-shot semantic segmentation, and zero-shot classification) demonstrate DCXFM's superior performance over other state-of-the-art medical image-text pretraining models. Remarkably, DCXFM exhibits powerful zero-shot capabilities across various datasets in phrase grounding and zero-shot semantic segmentation, underscoring its superior generalization in dense prediction tasks.

Radiologists rely on eye movements to navigate and interpret medical images. A trained radiologist possesses knowledge about the potential diseases that may be present in the images and, when searching, follows a mental checklist to locate them using their gaze. This is a key observation, yet existing models fail to capture the underlying intent behind each fixation. In this paper, we introduce a deep learning-based approach, RadGazeIntent, designed to model this behavior: having an intention to find something and actively searching for it. Our transformer-based architecture processes both the temporal and spatial dimensions of gaze data, transforming fine-grained fixation features into coarse, meaningful representations of diagnostic intent to interpret radiologists' goals. To capture the nuances of radiologists' varied intention-driven behaviors, we process existing medical eye-tracking datasets to create three intention-labeled subsets: RadSeq (Systematic Sequential Search), RadExplore (Uncertainty-driven Exploration), and RadHybrid (Hybrid Pattern). Experimental results demonstrate RadGazeIntent's ability to predict which findings radiologists are examining at specific moments, outperforming baseline methods across all intention-labeled datasets.