This study presents an unsupervised, motion-resolved reconstruction framework for high-resolution, free-breathing pulmonary magnetic resonance imaging (MRI), utilizing a three-dimensional Gaussian representation (3DGS). The proposed method leverages 3DGS to address the challenges of motion-resolved 3D isotropic pulmonary MRI reconstruction by enabling data smoothing between voxels for continuous spatial representation. Pulmonary MRI data acquisition is performed using a golden-angle radial sampling trajectory, with respiratory motion signals extracted from the center of k-space in each radial spoke. Based on the estimated motion signal, the k-space data is sorted into multiple respiratory phases. A 3DGS framework is then applied to reconstruct a reference image volume from the first motion state. Subsequently, a patient-specific convolutional neural network is trained to estimate the deformation vector fields (DVFs), which are used to generate the remaining motion states through spatial transformation of the reference volume. The proposed reconstruction pipeline is evaluated on six datasets from six subjects and bench-marked against three state-of-the-art reconstruction methods. The experimental findings demonstrate that the proposed reconstruction framework effectively reconstructs high-resolution, motion-resolved pulmonary MR images. Compared with existing approaches, it achieves superior image quality, reflected by higher signal-to-noise ratio and contrast-to-noise ratio. The proposed unsupervised 3DGS-based reconstruction method enables accurate motion-resolved pulmonary MRI with isotropic spatial resolution. Its superior performance in image quality metrics over state-of-the-art methods highlights its potential as a robust solution for clinical pulmonary MR imaging.

Radiologists' eye movements during medical image interpretation reflect their perceptual-cognitive processes of diagnostic decisions. The eye movement data can be modeled to represent clinically relevant regions in a medical image and potentially integrated into an artificial intelligence (AI) system for automatic diagnosis in medical imaging. In this article, we first conduct a large-scale eye-tracking study involving 13 radiologists interpreting 191 chest X-ray (CXR) images, establishing a best-of-its-kind CXR visual saliency benchmark. We then perform analysis to quantify the reliability and clinical relevance of saliency maps (SMs) generated for CXR images. We develop CXR image saliency prediction method (CXRSalNet), a novel saliency prediction model that leverages radiologists' gaze information to optimize the use of unlabeled CXR images, enhancing training and mitigating data scarcity. We also demonstrate the application of our CXR saliency model in enhancing the performance of AI-powered diagnostic imaging systems.

The use of Artificial Intelligence (AI) methods for the analysis of CT (computed tomography) images has greatly contributed to the development of an effective computer-assisted diagnosis (CAD) system for lung cancer (LC). However, complex structures, multiple radiographic interrelations, and the dynamic locations of abnormalities within lung CT images make extracting relevant information to process and implement LC CAD systems difficult. These prominent problems are addressed in this paper by presenting a hybrid method of LC malignancy classification, which may help researchers and experts properly engineer the model's performance by observing how the model makes decisions. The proposed methodology is named IncCat-LCC: Explainer (Inception Net Cat Boost LC Classification: Explainer), which consists of feature extraction (FE) using the handcrafted radiomic Feature (HcRdF) extraction technique, InceptionNet CNN Feature (INCF) extraction, Vision Transformer Feature (ViTF) extraction, and XGBOOST (XGB)-based feature selection, and the GPU based CATBOOST (CB) classification technique. The proposed framework achieves better and highest performance scores for lung nodule multiclass malignancy classification when evaluated using metrics such as accuracy, precision, recall, f-1 score, specificity, and area under the roc curve as 96.74 %, 93.68 %, 96.74 %, 95.19 %, 98.47 % and 99.76 % consecutively for classifying highly normal class. Observing the explainable artificial intelligence (XAI) explanations will help readers understand the model performance and the statistical outcomes of the evaluation parameter. The work presented in this article may improve the existing LC CAD system and help assess the important parameters using XAI to recognize the factors contributing to enhanced performance and reliability.

Pneumonia is the leading cause of hospitalisation and mortality among children under five, particularly in low-resource settings. Accurate differentiation between viral and bacterial pneumonia is essential for guiding appropriate treatment, yet it remains challenging due to overlapping clinical and radiographic features. Advances in machine learning (ML), particularly deep learning (DL), have shown promise in classifying pneumonia using chest X-ray (CXR) images. This scoping review summarises the evidence on ML techniques for classifying viral and bacterial pneumonia using CXR images in paediatric patients. This scoping review was conducted following the Joanna Briggs Institute methodology and the PRISMA-ScR guidelines. A comprehensive search was performed in PubMed, Embase, and Scopus to identify studies involving children (0-18 years) with pneumonia diagnosed through CXR, using ML models for binary or multiclass classification. Data extraction included ML models, dataset characteristics, and performance metrics. A total of 35 studies, published between 2018 and 2025, were included in this review. Of these, 31 studies used the publicly available Kermany dataset, raising concerns about overfitting and limited generalisability to broader, real-world clinical populations. Most studies (n=33) used convolutional neural networks (CNNs) for pneumonia classification. While many models demonstrated promising performance, significant variability was observed due to differences in methodologies, dataset sizes, and validation strategies, complicating direct comparisons. For binary classification (viral vs bacterial pneumonia), a median accuracy of 92.3% (range: 80.8% to 97.9%) was reported. For multiclass classification (healthy, viral pneumonia, and bacterial pneumonia), the median accuracy was 91.8% (range: 76.8% to 99.7%). Current evidence is constrained by a predominant reliance on a single dataset and variability in methodologies, which limit the generalisability and clinical applicability of findings. To address these limitations, future research should focus on developing diverse and representative datasets while adhering to standardised reporting guidelines. Such efforts are essential to improve the reliability, reproducibility, and translational potential of machine learning models in clinical settings.

Uncertainty assessment of deep learning autosegmentation (DLAS) models can support contour corrections in adaptive radiotherapy (ART), e.g. by utilizing Monte Carlo Dropout (MCD) uncertainty maps. However, poorly calibrated uncertainties at the patient level often render these clinically nonviable. We evaluated population-based and patient-specific DLAS accuracy and uncertainty calibration and propose a patient-specific post-training uncertainty calibration method for DLAS in ART.&#xD;&#xD;Approach. The study included 122 lung cancer patients treated with a low-field MR-linac (80/19/23 training/validation/test cases). Ten single-label 3D-U-Net population-based baseline models (BM) were trained with dropout using planning MRIs (pMRIs) and contours for nine organs-at-riks (OARs) and gross tumor volumes (GTVs). Patient-specific models (PS) were created by fine-tuning BMs with each test patient's pMRI. Model uncertainty was assessed with MCD, averaged into probability maps. Uncertainty calibration was evaluated with reliability diagrams and expected calibration error (ECE). A proposed post-training calibration method rescaled MCD probabilities for fraction images in BM (calBM) and PS (calPS) after fitting reliability diagrams from pMRIs. All models were evaluated on fraction images using Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95) and ECE. Metrics were compared among models for all OARs combined (n=163), and the GTV (n=23), using Friedman and posthoc-Nemenyi tests (α=0.05).&#xD;&#xD;Main results. For the OARs, patient-specific fine-tuning significantly (p<0.001) increased median DSC from 0.78 (BM) to 0.86 (PS) and reduced HD95 from 14mm (BM) to 6.0mm (PS). Uncertainty calibration achieved substantial reductions in ECE, from 0.25 (BM) to 0.091 (calBM) and 0.22 (PS) to 0.11 (calPS) (p<0.001), without significantly affecting DSC or HD95 (p>0.05). For the GTV, BM performance was poor (DSC=0.05) but significantly (p<0.001) improved with PS training (DSC=0.75) while uncertainty calibration reduced ECE from 0.22 (PS) to 0.15 (calPS) (p=0.45).&#xD;&#xD;Significance. Post-training uncertainty calibration yields geometrically accurate DLAS models with well-calibrated uncertainty estimates, crucial for ART applications.

To develop a new high-resolution (HR)CT abnormalities quantification tool (CVILDES) for interstitial lung diseases (ILDs) based on the nnU-Net network structure and to determine whether the quantitative parameters derived from this new software could offer a reliable and precise assessment in a clinical setting that is in line with expert visual evaluation. HRCT scans from 83 cases of ILDs and 20 cases of other diffuse lung diseases were labeled section by section by multiple radiologists and were used as training data for developing a deep learning model based on nnU-Net, employing a supervised learning approach. For clinical validation, a cohort including 51 cases of interstitial pneumonia with autoimmune features (IPAF) and 14 cases of idiopathic pulmonary fibrosis (IPF) had CT parenchymal patterns evaluated quantitatively with CVILDES and by visual evaluation. Subsequently, we assessed the correlation of the two methodologies for ILD features quantification. Furthermore, the correlation between the quantitative results derived from the two methods and pulmonary function parameters (DL_CO%, FVC%, and FEV%) was compared. All CT data were successfully quantified using CVILDES. CVILDES-quantified results (total ILD extent, ground-glass opacity, consolidation, reticular pattern and honeycombing) showed a strong correlation with visual evaluation and were numerically close to the visual evaluation results (r = 0.64-0.89, p < 0.0001), particularly for the extent of fibrosis (r = 0.82, p < 0.0001). As judged by correlation with pulmonary function parameters, CVILDES quantification was comparable or even superior to visual evaluation. nnU-Net-based CVILDES was comparable to visual evaluation for ILD abnormalities quantification. Question Visual assessment of ILD on HRCT is time-consuming and exhibits poor inter-observer agreement, making it challenging to accurately evaluate the therapeutic efficacy. Findings nnU-Net-based Computer vision-based ILD evaluation system (CVILDES) accurately segmented and quantified the HRCT features of ILD, and results were comparable to visual evaluation. Clinical relevance This study developed a new tool that has the potential to be applied in the quantitative assessment of ILD.

CT images and circulating tumor cells (CTCs) are indispensable for diagnosing the mediastinal lesions by providing radiological and intra-tumoral information. This study aimed to develop and validate a deep multimodal fusion network (DMFN) combining CTCs and CT images for the multi-classification of mediastinal lesions. In this retrospective diagnostic study, we enrolled 1074 patients with 1500 enhanced CT images and 1074 CTCs results between Jan 1, 2020, and Dec 31, 2023. Patients were divided into the training cohort (n = 434), validation cohort (n = 288), and test cohort (n = 352). The DMFN and monomodal convolutional neural network (CNN) models were developed and validated using the CT images and CTCs results. The diagnostic performances of DMFN and monomodal CNN models were based on the Paraffin-embedded pathologies from surgical tissues. The predictive abilities were compared with thoracic resident physicians, attending physicians, and chief physicians by the area under the receiver operating characteristic (ROC) curve, and diagnostic results were visualized in the heatmap. For binary classification, the predictive performances of DMFN (AUC = 0.941, 95% CI 0.901-0.982) were better than the monomodal CNN model (AUC = 0.710, 95% CI 0.664-0.756). In addition, the DMFN model achieved better predictive performances than the thoracic chief physicians, attending physicians, and resident physicians (P = 0.054, 0.020, 0.016) respectively. For the multiclassification, the DMFN achieved encouraging predictive abilities (AUC = 0.884, 95%CI 0.837-0.931), significantly outperforming the monomodal CNN (AUC = 0.722, 95%CI 0.705-0.739), also better than the chief physicians (AUC = 0.787, 95%CI 0.714-0.862), attending physicians (AUC = 0.632, 95%CI 0.612-0.654), and resident physicians (AUC = 0.541, 95%CI 0.508-0.574). This study showed the feasibility and effectiveness of CNN model combing CT images and CTCs levels in predicting the diagnosis of mediastinal lesions. It could serve as a useful method to assist thoracic surgeons in improving diagnostic accuracy and has the potential to make management decisions.

This review evaluates the role of artificial intelligence (AI) in diagnosing solitary pulmonary nodules (SPNs), focusing on clinical applications and limitations in pulmonary medicine. It explores AI's utility in imaging and blood/tissue-based diagnostics, emphasizing practical challenges over technical details of deep learning methods. AI enhances computed tomography (CT)-based computer-aided diagnosis (CAD) through steps like nodule detection, false positive reduction, segmentation, and classification, leveraging convolutional neural networks and machine learning. Segmentation achieves Dice similarity coefficients of 0.70-0.92, while malignancy classification yields areas under the curve of 0.86-0.97. AI-driven blood tests, incorporating RNA sequencing and clinical data, report AUCs up to 0.907 for distinguishing benign from malignant nodules. However, most models lack prospective, multiinstitutional validation, risking overfitting and limited generalizability. The "black box" nature of AI, coupled with overlapping inputs (e.g., nodule size, smoking history) with physician assessments, complicates integration into clinical workflows and precludes standard Bayesian analysis. AI shows promise for SPN diagnosis but requires rigorous validation in diverse populations and better clinician training for effective use. Rather than replacing judgment, AI should serve as a second opinion, with its reported performance metrics understood as study-specific, not directly applicable at the bedside due to double-counting issues.

Reliable methods for predicting pathological complete response (pCR) in non-small cell lung cancer (NSCLC) patients undergoing neoadjuvant chemoimmunotherapy are still under exploration. Although Fluorine-18 fluorodeoxyglucose-positron emission tomography/computed tomography (18F-FDG PET/CT) features reflect tumour response, their utility in predicting pCR remains controversial. This retrospective analysis included NSCLC patients who received neoadjuvant chemoimmunotherapy followed by 18F-FDG PET/CT imaging at Shanghai Pulmonary Hospital from October 2019 to August 2024. Eligible patients were randomly divided into training and validation cohort at a 7:3 ratio. Relevant 18F-FDG PET/CT features were evaluated as individual predictors and incorporated into 5 machine learning (ML) models. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), and Shapley additive explanation was applied for model interpretation. A total of 205 patients were included, with 91 (44.4%) achieving pCR. Post-treatment tumour maximum standardized uptake value (SUVmax) demonstrated the highest predictive performance among individual predictors, achieving an AUC of 0.72 (95% CI 0.65-0.79), while ΔT SUVmax achieved an AUC of 0.65 (95% CI 0.53-0.77). The Light Gradient Boosting Machine algorithm outperformed other models and individual predictors, achieving an average AUC of 0.87 (95% CI 0.78-0.97) in training cohort and 0.83 (95% CI 0.72-0.94) in validation cohort. Shapley additive explanation analysis identified post-treatment tumour SUVmax and post-treatment nodal volume as key contributors. This ML models offer a non-invasive and effective approach for predicting pCR after neoadjuvant chemoimmunotherapy in NSCLC.

Chest X-ray (CXR) is a diagnostic tool for cardiothoracic assessment. They make up 50% of all diagnostic imaging tests. With hundreds of images examined every day, radiologists can suffer from fatigue. This fatigue may reduce diagnostic accuracy and slow down report generation. We describe a prototype computer-assisted diagnosis (CAD) pipeline employing computer vision (CV) and Natural Language Processing (NLP). It was trained and evaluated on the publicly available MIMIC-CXR dataset. We perform image quality assessment, view labelling, and segmentation-based cardiomegaly severity classification. We use the output of the severity classification for large language model-based report generation. Four board-certified radiologists assessed the output accuracy of our CAD pipeline. Across the dataset composed of 377,100 CXR images and 227,827 free-text radiology reports, our system identified 0.18% of cases with mixed-sex mentions, 0.02% of poor quality images (F1 = 0.81), and 0.28% of wrongly labelled views (accuracy 99.4%). We assigned views for 4.18% of images which have unlabelled views. Our binary cardiomegaly classification model has 95.2% accuracy. The inter-radiologist agreement on evaluating the generated report's semantics and correctness for radiologist-MIMIC is 0.62 (strict agreement) and 0.85 (relaxed agreement) similar to the radiologist-CAD agreement of 0.55 (strict) and 0.93 (relaxed). Our work found and corrected several incorrect or missing metadata annotations for the MIMIC-CXR dataset. The performance of our CAD system suggests performance on par with human radiologists. Future improvements revolve around improved text generation and the development of CV tools for other diseases.