As the US Food and Drug Administration (FDA)-approved use of artificial intelligence (AI) for medical imaging rises, radiologists are increasingly integrating AI into their clinical practices. In lung cancer screening, diagnostic AI offers a second set of eyes with the potential to detect cancer earlier than human radiologists. Despite AI's promise, a potential problem with its integration is the erosion of patient confidence in clinician expertise when there is a discrepancy between the radiologist's and the AI's interpretation of the imaging findings. We examined how discrepancies between AI-derived recommendations and radiologists' recommendations affect patients' agreement with radiologists' recommendations and satisfaction with their radiologists. We also analyzed how patients' medical maximizing-minimizing preferences moderate these relationships. We conducted a randomized, between-subjects experiment with 1606 US adult participants. Assuming the role of patients, participants imagined undergoing a low-dose computerized tomography scan for lung cancer screening and receiving results and recommendations from (1) a radiologist only, (2) AI and a radiologist in agreement, (3) a radiologist who recommended more testing than AI (ie, radiologist overcalled AI), or (4) a radiologist who recommended less testing than AI (ie, radiologist undercalled AI). Participants rated the radiologist on three criteria: agreement with the radiologist's recommendation, how likely they would be to recommend the radiologist to family and friends, and how good of a provider they perceived the radiologist to be. We measured medical maximizing-minimizing preferences and categorized participants as maximizers (ie, those who seek aggressive intervention), minimizers (ie, those who prefer no or passive intervention), and neutrals (ie, those in the middle). Participants' agreement with the radiologist's recommendation was significantly lower when the radiologist undercalled AI (mean 4.01, SE 0.07, P<.001) than in the other 3 conditions, with no significant differences among them (radiologist overcalled AI [mean 4.63, SE 0.06], agreed with AI [mean 4.55, SE 0.07], or had no AI [mean 4.57, SE 0.06]). Similarly, participants were least likely to recommend (P<.001) and positively rate (P<.001) the radiologist who undercalled AI, with no significant differences among the other conditions. Maximizers agreed with the radiologist who overcalled AI (β=0.82, SE 0.14; P<.001) and disagreed with the radiologist who undercalled AI (β=-0.47, SE 0.14; P=.001). However, whereas minimizers disagreed with the radiologist who overcalled AI (β=-0.43, SE 0.18, P=.02), they did not significantly agree with the radiologist who undercalled AI (β=0.14, SE 0.17, P=.41). Radiologists who recommend less testing than AI may face decreased patient confidence in their expertise, but they may not face this same penalty for giving more aggressive recommendations than AI. Patients' reactions may depend in part on whether their general preferences to maximize or minimize align with the radiologists' recommendations. Future research should test communication strategies for radiologists' disclosure of AI discrepancies to patients.

To investigate whether a content-based image retrieval (CBIR) of similar chest CT images can help usual interstitial pneumonia (UIP) CT pattern classifications among readers with varying levels of experience. This retrospective study included patients who underwent high-resolution chest CT between 2013 and 2015 for the initial workup for fibrosing interstitial lung disease. UIP classifications were assigned to CT images by three thoracic radiologists, which served as the ground truth. One hundred patients were selected as queries. The CBIR retrieved the top three similar CT images with UIP classifications using a deep learning algorithm. The diagnostic accuracies and inter-reader agreement of nine readers before and after CBIR were evaluated. Of 587 patients (mean age, 63 years; 356 men), 100 query cases (26 UIP patterns, 26 probable UIP patterns, 5 indeterminate for UIP, and 43 alternative diagnoses) were selected. After CBIR, the mean accuracy (61.3% to 67.1%; p = 0.011) and inter-reader agreement (Fleiss Kappa, 0.400 to 0.476; p = 0.003) were slightly improved. The accuracies of the radiologist group for all CT patterns except indeterminate for UIP increased after CBIR; however, they did not reach statistical significance. The resident and pulmonologist groups demonstrated mixed results: accuracy decreased for UIP pattern, increased for alternative diagnosis, and varied for others. CBIR slightly improved diagnostic accuracy and inter-reader agreement in UIP pattern classifications. However, its impact varied depending on the readers' level of experience, suggesting that the current CBIR system may be beneficial when used to complement the interpretations of experienced readers. Question CT pattern classification is important for the standardized assessment and management of idiopathic pulmonary fibrosis, but requires radiologic expertise and shows inter-reader variability. Findings CBIR slightly improved diagnostic accuracy and inter-reader agreement for UIP CT pattern classifications overall. Clinical relevance The proposed CBIR system may guide consistent work-up and treatment strategies by enhancing accuracy and inter-reader agreement in UIP CT pattern classifications by experienced readers whose expertise and experience can effectively interact with CBIR results.

Computed Tomography (CT) scan, which produces 3D volumetric medical data that can be viewed as hundreds of cross-sectional images (a.k.a. slices), provides detailed anatomical information for diagnosis. For radiologists, creating CT radiology reports is time-consuming and error-prone. A visual question answering (VQA) system that can answer radiologists' questions about some anatomical regions on the CT scan and even automatically generate a radiology report is urgently needed. However, existing VQA systems cannot adequately handle the CT radiology question answering (CTQA) task for: (1) anatomic complexity makes CT images difficult to understand; (2) spatial relationship across hundreds slices is difficult to capture. To address these issues, this paper proposes CT-Agent, a multimodal agentic framework for CTQA. CT-Agent adopts anatomically independent tools to break down the anatomic complexity; furthermore, it efficiently captures the across-slice spatial relationship with a global-local token compression strategy. Experimental results on two 3D chest CT datasets, CT-RATE and RadGenome-ChestCT, verify the superior performance of CT-Agent.

The aim of this study is to develop a deep learning-based multimodal feature interaction-guided fusion (DL-MFIF) framework that integrates macroscopic information from computed tomography (CT) images with microscopic information from whole-slide images (WSIs) to predict the epidermal growth factor receptor (EGFR) mutations of primary lung adenocarcinoma in patients with advanced-stage disease. Data from 396 patients with lung adenocarcinoma across two medical institutions were analyzed. The data from 243 cases were divided into a training set (n=145) and an internal validation set (n=98) in a 6:4 ratio, and data from an additional 153 cases from another medical institution were included as an external validation set. All cases included CT scan images and WSIs. To integrate multimodal information, we developed the DL-MFIF framework, which leverages deep learning techniques to capture the interactions between radiomic macrofeatures derived from CT images and microfeatures obtained from WSIs. Compared to other classification models, the DL-MFIF model achieved significantly higher area under the curve (AUC) values. Specifically, the model outperformed others on both the internal validation set (AUC=0.856, accuracy=0.750) and the external validation set (AUC=0.817, accuracy=0.708). Decision curve analysis (DCA) demonstrated that the model provided superior net benefits(range 0.15-0.87). Delong's test for external validation confirmed the statistical significance of the results (P<0.05). The DL-MFIF model demonstrated excellent performance in evaluating and distinguishing the EGFR in patients with advanced lung adenocarcinoma. This model effectively aids radiologists in accurately classifying EGFR mutations in patients with primary lung adenocarcinoma, thereby improving treatment outcomes for this population.

CT angiography (CTA) is a commonly used clinical examination to detect abnormal arteries and diagnose pulmonary sequestration (PS). Reducing the radiation dose, contrast medium dosage, and injection pressure in CTA, especially in children, has always been an important research topic, but few research is proven by pathology. The current study aimed to evaluate the diagnostic accuracy for children with PS in a quadruple-low CTA (4L-CTA: low tube voltage, radiation, contrast medium, and injection flow rate) using deep learning image reconstruction (DLIR) in comparison with routine protocol CTA with adaptive statistical iterative reconstruction-V (ASIR-V) MATERIALS AND METHODS: 53 patients (1.50±1.36years) suspected with PS were enrolled to undergo chest 4L-CTA using 70kVp tube voltage with radiation dose or 0.90 mGy in volumetric CT dose index (CTDIvol) and contrast medium dose of 0.8 ml/kg injected in 16 s. Images were reconstructed using DLIR. Another 53 patients (1.25±1.02years) with a routine dose protocol was used for comparison, and images were reconstructed with ASIR-V. The contrast-to-noise ratio (CNR) and edge-rise distance (ERD) of the aorta were calculated. The subjective overall image quality and artery visualization were evaluated using a 5-point scale (5, excellent; 3, acceptable). All patients underwent surgery after CT, the sensitivity and specificity for diagnosing PS were calculated. 4L-CTA reduced radiation dose by 51%, contrast dose by 47%, injection flow rate by 44% and injection pressure by 44% compared to the routine CTA (all p<0.05). Both groups had satisfactory subjective image quality and achieved 100% in both sensitivity and specificity for diagnosing PS. 4L-CTA had a reduced CNR (by 27%, p<0.05) but similar ERD, which reflects the image spatial resolution (p>0.05) compared to the routine CTA. 4L-CTA revealed small arteries with a diameter of 0.8 mm. DLIR ensures the realization of 4L-CTA in children with PS for significant radiation and contrast dose reduction, while maintaining image quality, visualization of small arteries, and high diagnostic accuracy.

This research aims to enhance X-ray lung segmentation by addressing boundary distortions in anatomical structures, with the objective of refining segmentation boundaries and improving the morphological shape of segmented objects. The proposed approach combines the K-segment principal curve with Gaussian Process Regression (GPR) to refine segmentation boundaries, evaluated using lung X-ray datasets at varying resolutions. Several state-of-the-art models, including U-Net, SegNet, and TransUnet, were also assessed for comparison. The model employed a custom kernel for GPR, combining Radial Basis Function (RBF) with a cosine similarity term. The effectiveness of the model was evaluated using metrics such as the Dice Coefficient (DC) and Jaccard Index (JC) for segmentation accuracy, along with Average Symmetric Surface Distance (ASSD) and Hausdorff Distance (HD) for boundary alignment. The proposed method achieved superior segmentation performance, particularly at the highest resolution (1024x1024 pixels), with a DC of 95.7% for the left lung and 94.1% for the right lung. Among the different models, TransUnet outperformed others across both the semantic segmentation and boundary refinement stages, showing significant improvements in DC, JC, ASSD, and HD. The results indicate that the proposed boundary refinement approach effectively improves the segmentation quality of lung X-rays, excelling in refining well-defined structures and achieving superior boundary alignment, showcasing its potential for clinical applications. However, limitations exist when dealing with irregular or unpredictable shapes, suggesting areas for future enhancement.

To evaluate the variability of fully automated airway quantitative CT (QCT) measures caused by different kernels and the effect of kernel conversion. This retrospective study included 96 patients who underwent non-enhanced chest CT at two centers. CT scans were reconstructed using four kernels (medium soft, medium sharp, sharp, very sharp) from three vendors. Kernel conversion targeting the medium soft kernel as reference was applied to sharp kernel images. Fully automated airway quantification was performed before and after conversion. The effects of kernel type and conversion on airway quantification were evaluated using analysis of variance, paired t-tests, and concordance correlation coefficient (CCC). Airway QCT measures (e.g., Pi10, wall thickness, wall area percentage, lumen diameter) decreased with sharper kernels (all, p < 0.001), with varying degrees of variability across variables and vendors. Kernel conversion substantially reduced variability between medium soft and sharp kernel images for vendors A (pooled CCC: 0.59 vs. 0.92) and B (0.40 vs. 0.91) and lung-dedicated sharp kernels of vendor C (0.26 vs. 0.71). However, it was ineffective for non-lung-dedicated sharp kernels of vendor C (0.81 vs. 0.43) and showed limited improvement in variability of QCT measures at the subsegmental level. Consistent airway segmentation and identical anatomic labeling improved subsegmental airway variability in theoretical tests. Deep learning-based kernel conversion reduced the measurement variability of airway QCT across various kernels and vendors but was less effective for non-lung-dedicated kernels and subsegmental airways. Consistent airway segmentation and precise anatomic labeling can further enhance reproducibility for reliable automated quantification. Question How do different CT reconstruction kernels affect the measurement variability of automated airway measurements, and can deep learning-based kernel conversion reduce this variability? Findings Kernel conversion improved measurement consistency across vendors for lung-dedicated kernels, but showed limited effectiveness for non-lung-dedicated kernels and subsegmental airways. Clinical relevance Understanding kernel-related variability in airway quantification and mitigating it through deep learning enables standardized analysis, but further refinements are needed for robust airway segmentation, particularly for improving measurement variability in subsegmental airways and specific kernels.

Visual grounding (VG) is the capability to identify the specific regions in an image associated with a particular text description. In medical imaging, VG enhances interpretability by highlighting relevant pathological features corresponding to textual descriptions, improving model transparency and trustworthiness for wider adoption of deep learning models in clinical practice. Current models struggle to associate textual descriptions with disease regions due to inefficient attention mechanisms and a lack of fine-grained token representations. In this paper, we empirically demonstrate two key observations. First, current VLMs assign high norms to background tokens, diverting the model's attention from regions of disease. Second, the global tokens used for cross-modal learning are not representative of local disease tokens. This hampers identifying correlations between the text and disease tokens. To address this, we introduce simple, yet effective Disease-Aware Prompting (DAP) process, which uses the explainability map of a VLM to identify the appropriate image features. This simple strategy amplifies disease-relevant regions while suppressing background interference. Without any additional pixel-level annotations, DAP improves visual grounding accuracy by 20.74% compared to state-of-the-art methods across three major chest X-ray datasets.

Advanced diagnostic instruments are crucial for the accurate detection and treatment of lung diseases, which affect millions of individuals globally. This study examines the effectiveness of deep learning and transfer learning models using a hybrid dataset, created by merging four individual datasets from Bangladesh and global sources. The hybrid dataset significantly enhances model accuracy and generalizability, particularly in detecting COVID-19, pneumonia, lung opacity, and normal lung conditions from chest X-ray images. A range of models, including CNN, VGG16, VGG19, InceptionV3, Xception, ResNet50V2, InceptionResNetV2, MobileNetV2, and DenseNet121, were applied to both individual and hybrid datasets. The results showed superior performance on the hybrid dataset, with VGG16, Xception, ResNet50V2, and DenseNet121 each achieving an accuracy of 99%. This consistent performance across the hybrid dataset highlights the robustness of these models in handling diverse data while maintaining high accuracy. To understand the models implicit behavior, explainable AI techniques were employed to illuminate their black-box nature. Specifically, LIME was used to enhance the interpretability of model predictions, especially in cases of misclassification, contributing to the development of reliable and interpretable AI-driven solutions for medical imaging.

Lung cancer remains among the deadliest types of cancer in recent decades, and early lung nodule detection is crucial for improving patient outcomes. The limited availability of annotated medical imaging data remains a bottleneck in developing accurate computer-aided diagnosis (CAD) systems. Self-supervised learning can help leverage large amounts of unlabeled data to develop more robust CAD systems. With the recent advent of transformer-based architecture and their ability to generalize to unseen tasks, there has been an effort within the healthcare community to adapt them to various medical downstream tasks. Thus, we propose a novel "LungNodule-SSM" method, which utilizes selfsupervised learning with DINOv2 as a backbone to enhance lung nodule detection and classification without annotated data. Our methodology has two stages: firstly, the DINOv2 model is pre-trained on unlabeled CT scans to learn robust feature representations, then secondly, these features are fine-tuned using transformer-based architectures for lesionlevel detection and accurate lung nodule diagnosis. The proposed method has been evaluated on the challenging LUNA 16 dataset, consisting of 888 CT scans, and compared with SOTA methods. Our experimental results show the superiority of our proposed method with an accuracy of 98.37%, explaining its effectiveness in lung nodule detection. The source code, datasets, and pre-processed data can be accessed using the link:https://github.com/EMeRALDsNRPU/Lung-Nodule-SSM-Self-Supervised-Lung-Nodule-Detection-and-Classification/tree/main