Medical image-language pre-training aims to align medical images with clinically relevant text to improve model performance on various downstream tasks. However, existing models often struggle with the variability and ambiguity inherent in medical data, limiting their ability to capture nuanced clinical information and uncertainty. This work introduces an uncertainty-aware medical image-text pre-training model that enhances generalization capabilities in medical image analysis. Building on previous methods and focusing on Chest X-Rays, our approach utilizes structured text reports generated by a large language model (LLM) to augment image data with clinically relevant context. These reports begin with a definition of the disease, followed by the `appearance' section to highlight critical regions of interest, and finally `observations' and `verdicts' that ground model predictions in clinical semantics. By modeling both inter- and intra-modal uncertainty, our framework captures the inherent ambiguity in medical images and text, yielding improved representations and performance on downstream tasks. Our model demonstrates significant advances in medical image-text pre-training, obtaining state-of-the-art performance on multiple downstream tasks.

ObjectiveDetecting and accurately diagnosing rib fractures in chest radiographs is a challenging and time-consuming task for radiologists. This study presents a novel deep learning system designed to automate the detection and segmentation of rib fractures in chest radiographs.MethodsThe proposed method combines CenterNet with HRNet v2 for precise fracture region identification and HRNet-W48 with contextual representation to enhance rib segmentation. A dataset consisting of 1006 chest radiographs from a tertiary hospital in Korea was used, with a split of 7:2:1 for training, validation, and testing.ResultsThe rib fracture detection component achieved a sensitivity of 0.7171, indicating its effectiveness in identifying fractures. Additionally, the rib segmentation performance was measured by a dice score of 0.86, demonstrating its accuracy in delineating rib structures. Visual assessment results further highlight the model's capability to pinpoint fractures and segment ribs accurately.ConclusionThis innovative approach holds promise for improving rib fracture detection and rib segmentation, offering potential benefits in clinical practice for more efficient and accurate diagnosis in the field of medical image analysis.

Clinical information associated with chest X-ray images, such as view position, patient age and gender, plays a crucial role in image interpretation, as it influences the visibility of anatomical structures and pathologies. However, most classification models using the ChestX-ray14 dataset relied solely on image data, disregarding the impact of these clinical variables. This study aims to investigate which clinical variable affects image characteristics and assess its impact on classification performance. To explore the relationships between clinical variables and image characteristics, unsupervised clustering was applied to group images based on their similarities. Afterwards, a statistical analysis was then conducted on each cluster to examine their clinical composition, by analyzing the distribution of age, gender, and view position. An attention-based CNN model was developed separately for each value of the clinical variable with the greatest influence on image characteristics to assess its impact on lung disease classification. The analysis identified view position as the most influential variable affecting image characteristics. Accounting for this, the proposed approach achieved a weighted area under the curve (AUC) of 0.8176 for pneumonia classification, surpassing the base model (without considering view position) by 1.65% and outperforming previous studies by 6.76%. Furthermore, it demonstrated improved performance across all 14 diseases in the ChestX-ray14 dataset. The findings highlight the importance of considering view position when developing classification models for chest X-ray analysis. Accounting for this characteristic allows for more precise disease identification, demonstrating potential for broader clinical application in lung disease evaluation.

Incorrectly placed endotracheal tubes (ETTs) can lead to serious clinical harm. Studies have demonstrated the potential for artificial intelligence (AI)-led algorithms to detect ETT placement on chest X-Ray (CXR) images, however their effect on clinician accuracy remains unexplored. This study measured the impact of an AI-assisted ETT detection algorithm on the ability of clinical staff to correctly identify ETT misplacement on CXR images. Four hundred CXRs of intubated adult patients were retrospectively sourced from the John Radcliffe Hospital (Oxford) and two other UK NHS hospitals. Images were de-identified and selected from a range of clinical settings, including the intensive care unit (ICU) and emergency department (ED). Each image was independently reported by a panel of thoracic radiologists, whose consensus classification of ETT placement (correct, too low [distal], or too high [proximal]) served as the reference standard for the study. Correct ETT position was defined as the tip located 3-7 cm above the carina, in line with established guidelines. Eighteen clinical readers of varying seniority from six clinical specialties were recruited across four NHS hospitals. Readers viewed the dataset using an online platform and recorded a blinded classification of ETT position for each image. After a four-week washout period, this was repeated with assistance from an AI-assisted image interpretation tool. Reader accuracy, reported confidence, and timings were measured during each study phase. 14,400 image interpretations were undertaken. Pooled accuracy for tube placement classification improved from 73.6 to 77.4% (p = 0.002). Accuracy for identification of critically misplaced tubes increased from 79.3 to 89.0% (p = 0.001). Reader confidence improved with AI assistance, with no change in mean interpretation time at 36 s per image. Use of assistive AI technology improved accuracy and confidence in interpreting ETT placement on CXR, especially for identification of critically misplaced tubes. AI assistance may potentially provide a useful adjunct to support clinicians in identifying misplaced ETTs on CXR.

In this work, we address the challenge of binary lung nodule classification (benign vs malignant) using CT images by proposing a multi-level attention stacked ensemble of deep neural networks. Three pretrained backbones - EfficientNet V2 S, MobileViT XXS, and DenseNet201 - are each adapted with a custom classification head tailored to 96 x 96 pixel inputs. A two-stage attention mechanism learns both model-wise and class-wise importance scores from concatenated logits, and a lightweight meta-learner refines the final prediction. To mitigate class imbalance and improve generalization, we employ dynamic focal loss with empirically calculated class weights, MixUp augmentation during training, and test-time augmentation at inference. Experiments on the LIDC-IDRI dataset demonstrate exceptional performance, achieving 98.09 accuracy and 0.9961 AUC, representing a 35 percent reduction in error rate compared to state-of-the-art methods. The model exhibits balanced performance across sensitivity (98.73) and specificity (98.96), with particularly strong results on challenging cases where radiologist disagreement was high. Statistical significance testing confirms the robustness of these improvements across multiple experimental runs. Our approach can serve as a robust, automated aid for radiologists in lung cancer screening.

Computed tomography (CT) images are reconstructed from raw datasets including sinogram using various convolution kernels through back projection. Kernels are typically chosen depending on the anatomical structure being imaged and the specific purpose of the scan, balancing the trade-off between image sharpness and pixel noise. Generally, a sinogram requires large storage capacity, and storage space is often limited in clinical settings. Thus, CT images are generally reconstructed with only one specific kernel in clinical settings, and the sinogram is typically discarded after a week. Therefore, many researchers have proposed deep learning-based image-to-image translation methods for CT kernel conversion. However, transferring the style of the target kernel while preserving anatomical structure remains challenging, particularly when translating CT images from a source domain to a target domain in an unpaired manner, which is often encountered in real-world settings. Thus, we propose a novel kernel conversion method using unpaired image-to-image translation (KC-UNIT). This approach utilizes discriminator regularization, using feature maps from the generator to improve semantic representation learning. To capture content and style features, cosine similarity content and contrastive style losses were defined between the feature map of generator and semantic label map of discriminator. This can be easily incorporated by modifying the discriminator's architecture without requiring any additional learnable or pre-trained networks. The KC-UNIT demonstrated the ability to preserve fine-grained anatomical structure from the source domain during transfer. Our method outperformed existing generative adversarial network-based methods across most kernel conversion methods in three kernel domains. The code is available at https://github.com/cychoi97/KC-UNIT.

Cystic fibrosis (CF) is a prevalent autosomal recessive disorder, with lung complications being the primary cause of morbidity and mortality. In paediatric patients, structural lung changes begin early, necessitating prompt detection to guide treatment and delay disease progression. This study evaluates ultra-low-dose CT (ULDCT) versus chest x-rays  (CXR) for children with CF (CwCF) lung disease assessment. ULDCT uses AI-enhanced deep-learning iterative reconstruction to achieve radiation doses comparable to a CXR. This prospective study recruited radiographers and radiologists to assess the image quality (IQ) of ten paired ULDCT and CXR images of CwCF from a single centre. Statistical analyses, including the Wilcoxon Signed Rank test and visual grading characteristic (VGC) analysis, compared diagnostic confidence and anatomical detail. Seventy-five participants were enrolled, 25 radiologists and 50 radiographers. The majority (88%) preferred ULDCT over CXR for monitoring CF lung disease due to higher perceived confidence (p ≤ 0.001) and better IQ ratings (p ≤ 0.05), especially among radiologists (area under the VGC curve and its 95% CI was 0.63 (asymmetric 95% CI: 0.51-0.73; p ≤ 0.05). While ULDCT showed no significant differences in anatomical visualisation compared to CXR, the overall IQ for lung pathology assessment was rated superior. ULDCT offers superior IQ over CXR in CwCF, with similar radiation doses. It also enhances diagnostic confidence, supporting its use as a viable CXR alternative. Standardising CT protocols to optimise IQ and minimise radiation is essential to improve disease monitoring in this vulnerable group. Question How does chest X-ray (CXR) IQ in children compare to ULDCT at similar radiation doses for assessing CF-related lung disease? Findings ULDCT offers superior IQ over CXR in CwCF. Participants preferred ULDCT due to higher perceived confidence levels and superior IQ. Clinical relevance ULDCT can enhance diagnosis in CwCF while maintaining comparable radiation doses. ULDCT also enhances diagnostic confidence, supporting its use as a viable CXR alternative.

Artificial intelligence is increasingly leveraged across various domains to automate decision-making processes that significantly impact human lives. In medical image analysis, deep learning models have demonstrated remarkable performance. However, their inherent complexity makes them black box systems, raising concerns about reliability and interpretability. Counterfactual explanations provide comprehensible insights into decision processes by presenting hypothetical "what-if" scenarios that alter model classifications. By examining input alterations, counterfactual explanations provide patterns that influence the decision-making process. Despite their potential, generating plausible counterfactuals that adhere to similarity constraints providing human-interpretable explanations remains a challenge. In this paper, we investigate this challenge by a model-specific optimization approach. While deep generative models such as variational autoencoders (VAEs) exhibit significant generative power, probabilistic models like sum-product networks (SPNs) efficiently represent complex joint probability distributions. By modeling the likelihood of a semi-supervised VAE's latent space with an SPN, we leverage its dual role as both a latent space descriptor and a classifier for a given discrimination task. This formulation enables the optimization of latent space counterfactuals that are both close to the original data distribution and aligned with the target class distribution. We conduct experimental evaluation on the cheXpert dataset. To evaluate the effectiveness of the integration of SPNs, our SPN-guided latent space manipulation is compared against a neural network baseline. Additionally, the trade-off between latent variable regularization and counterfactual quality is analyzed.

Lung cancer is the leading cause of cancer-related mortality. While early detection improves survival, distinguishing malignant from benign pulmonary nodules remains challenging. Artificial intelligence (AI) has been proposed to enhance diagnostic accuracy, but its clinical reliability is still under investigation. Here, we aimed to evaluate the diagnostic performance of AI models in classifying pulmonary nodules. This single-center retrospective study analyzed pulmonary nodules (4-30 mm) detected on CT scans, using three AI software models. Sensitivity, specificity, false-positive and false-negative rates were calculated. The diagnostic accuracy was assessed using the area under the receiver operating characteristic (ROC) curve (AUC), with histopathology serving as the gold standard. Subgroup analyses were based on nodule size and histopathological classification. The impact of imaging parameters was evaluated using regression analysis. A total of 158 nodules (n = 30 benign, n = 128 malignant) were analyzed. One AI model classified most nodules as intermediate risk, preventing further accuracy assessment. The other models demonstrated moderate sensitivity (53.1-70.3%) but low specificity (46.7-66.7%), leading to a high false-positive rate (45.5-52.4%). AUC values were between 0.5 and 0.6 (95% CI). Subgroup analyses revealed decreased sensitivity (47.8-61.5%) but increased specificity (100%), highlighting inconsistencies. In total, up to 49.0% of the pulmonary nodules were classified as intermediate risk. CT scan type influenced performance (p = 0.03), with better classification accuracy on breath-held CT scans. AI-based software models are not ready for standalone clinical use in pulmonary nodule classification due to low specificity, a high false-negative rate and a high proportion of intermediate-risk classifications. Question How accurate are commercially available AI models for the classification of pulmonary nodules compared to the gold standard of histopathology? Findings The evaluated AI models demonstrated moderate sensitivity, low specificity and high false-negative rates. Up to 49% of pulmonary nodules were classified as intermediate risk. Clinical relevance The high false-negative rates could influence radiologists' decision-making, leading to an increased number of interventions or unnecessary surgical procedures.

Lung cancer is the leading cause of cancer-related mortality worldwide, largely due to late-stage diagnosis. Low-dose computed tomography (LDCT) screening has emerged as a powerful tool for early detection, enabling diagnosis at curable stages and reducing lung cancer mortality. Despite strong evidence, LDCT screening uptake remains suboptimal globally. This review synthesizes current evidence supporting LDCT screening, highlights ongoing global implementation efforts, and discusses key insights from the 1st AGILE conference. Lung cancer screening is gaining global momentum, with many countries advancing plans for national LDCT programs. Expanding eligibility through risk-based models and targeting high-risk never- and light-smokers are emerging strategies to improve efficiency and equity. Technological advancements, including AI-assisted interpretation and image-based biomarkers, are addressing concerns around false positives, overdiagnosis, and workforce burden. Integrating cardiac and smoking-related disease assessment within LDCT screening offers added preventive health benefits. To maximize global impact, screening strategies must be tailored to local health systems and populations. Efforts should focus on increasing awareness, standardizing protocols, optimizing screening intervals, and strengthening multidisciplinary care pathways. International collaboration and shared infrastructure can accelerate progress and ensure sustainability. LDCT screening represents a cost-effective opportunity to reduce lung cancer mortality and premature deaths.