Retinal diseases are a serious global threat to human vision, and early identification is essential for effective prevention and treatment. However, current diagnostic methods rely on manual analysis of fundus images, which heavily depends on the expertise of ophthalmologists. This manual process is time-consuming and labor-intensive and can sometimes lead to missed diagnoses. With advancements in computer vision technology, several automated models have been proposed to improve diagnostic accuracy for retinal diseases and medical imaging in general. However, these methods face challenges in accurately detecting specific diseases within images due to inherent issues associated with fundus images, including inter-class similarities, intra-class variations, limited local information, insufficient contextual understanding, and class imbalances within datasets. To address these challenges, we propose a novel deep learning framework for accurate retinal disease classification. This framework is designed to achieve high accuracy in identifying various retinal diseases while overcoming inherent challenges associated with fundus images. Generally, the framework consists of three main modules. The first module is Densely Connected Multidilated Convolution Neural Network (DCM-CNN) that extracts global contextual information by effectively integrating novel Casual Dilated Dense Convolutional Blocks (CDDCBs). The second module of the framework, namely, Local-Patch-based Convolution Neural Network (LP-CNN), utilizes Class Activation Map (CAM) (obtained from DCM-CNN) to extract local and fine-grained information. To identify the correct class and minimize the error, a synergic network is utilized that takes the feature maps of both DCM-CNN and LP-CNN and connects both maps in a fully connected fashion to identify the correct class and minimize the errors. The framework is evaluated through a comprehensive set of experiments, both quantitatively and qualitatively, using two publicly available benchmark datasets: RFMiD and ODIR-5K. Our experimental results demonstrate the effectiveness of the proposed framework and achieves higher performance on RFMiD and ODIR-5K datasets compared to reference methods.

The aim of this study was to intraindividually compare the conspicuity of focal liver lesions (FLLs) between low- and ultra-low-dose computed tomography (CT) with deep learning reconstruction (DLR) and standard-dose CT with model-based iterative reconstruction (MBIR) from a single CT using dual-split scan in patients with suspected liver metastasis via a noninferiority design. This prospective study enrolled participants who met the eligibility criteria at 2 tertiary hospitals in South Korea from June 2022 to January 2023. The criteria included ( a ) being aged between 20 and 85 years and ( b ) having suspected or known liver metastases. Dual-source CT scans were conducted, with the standard radiation dose divided in a 2:1 ratio between tubes A and B (67% and 33%, respectively). The voltage settings of 100/120 kVp were selected based on the participant's body mass index (<30 vs ≥30 kg/m 2 ). For image reconstruction, MBIR was utilized for standard-dose (100%) images, whereas DLR was employed for both low-dose (67%) and ultra-low-dose (33%) images. Three radiologists independently evaluated FLL conspicuity, the probability of metastasis, and subjective image quality using a 5-point Likert scale, in addition to quantitative signal-to-noise and contrast-to-noise ratios. The noninferiority margins were set at -0.5 for conspicuity and -0.1 for detection. One hundred thirty-three participants (male = 58, mean body mass index = 23.0 ± 3.4 kg/m 2 ) were included in the analysis. The low- and ultra-low- dose had a lower radiation dose than the standard-dose (median CT dose index volume: 3.75, 1.87 vs 5.62 mGy, respectively, in the arterial phase; 3.89, 1.95 vs 5.84 in the portal venous phase, P < 0.001 for all). Median FLL conspicuity was lower in the low- and ultra-low-dose scans compared with the standard-dose (3.0 [interquartile range, IQR: 2.0, 4.0], 3.0 [IQR: 1.0, 4.0] vs 3.0 [IQR: 2.0, 4.0] in the arterial phase; 4.0 [IQR: 1.0, 5.0], 3.0 [IQR: 1.0, 4.0] vs 4.0 [IQR: 2.0, 5.0] in the portal venous phases), yet within the noninferiority margin ( P < 0.001 for all). FLL detection was also lower but remained within the margin (lesion detection rate: 0.772 [95% confidence interval, CI: 0.727, 0.812], 0.754 [0.708, 0.795], respectively) compared with the standard-dose (0.810 [95% CI: 0.770, 0.844]). Sensitivity for liver metastasis differed between the standard- (80.6% [95% CI: 76.0, 84.5]), low-, and ultra-low-doses (75.7% [95% CI: 70.2, 80.5], 73.7 [95% CI: 68.3, 78.5], respectively, P < 0.001 for both), whereas specificity was similar ( P > 0.05). Low- and ultra-low-dose CT with DLR showed noninferior FLL conspicuity and detection compared with standard-dose CT with MBIR. Caution is needed due to a potential decrease in sensitivity for metastasis ( clinicaltrials.gov/NCT05324046 ).

The spinal column is a frequent site for metastases, affecting over 30% of solid tumor patients. Identifying the primary tumor is essential for guiding clinical decisions but often requires resource-intensive diagnostics. To develop and validate artificial intelligence (AI) models using noncontrast MRI to identify primary sites of spinal metastases, aiming to enhance diagnostic efficiency. Retrospective. A total of 514 patients with pathologically confirmed spinal metastases (mean age, 59.3 ± 11.2 years; 294 males) were included, split into a development set (360) and a test set (154). Noncontrast sagittal MRI sequences (T1-weighted, T2-weighted, and fat-suppressed T2) were acquired using 1.5 T and 3 T scanners. Two models were evaluated for identifying primary sites of spinal metastases: the expert-derived features (EDF) model using radiologist-identified imaging features and a ResNet50-based deep learning (DL) model trained on noncontrast MRI. Performance was assessed using accuracy, precision, recall, F1 score, and the area under the receiver operating characteristic curve (ROC-AUC) for top-1, top-2, and top-3 indicators. Statistical analyses included Shapiro-Wilk, t tests, Mann-Whitney U test, and chi-squared tests. ROC-AUCs were compared via DeLong tests, with 95% confidence intervals from 1000 bootstrap replications and significance at P < 0.05. The EDF model outperformed the DL model in top-3 accuracy (0.88 vs. 0.69) and AUC (0.80 vs. 0.71). Subgroup analysis showed superior EDF performance for common sites like lung and kidney (e.g., kidney F1: 0.94 vs. 0.76), while the DL model had higher recall for rare sites like thyroid (0.80 vs. 0.20). SHapley Additive exPlanations (SHAP) analysis identified sex (SHAP: -0.57 to 0.68), age (-0.48 to 0.98), T1WI signal intensity (-0.29 to 0.72), and pathological fractures (-0.76 to 0.25) as key features. AI techniques using noncontrast MRI improve diagnostic efficiency for spinal metastases. The EDF model outperformed the DL model, showing greater clinical potential. Spinal metastases, or cancer spreading to the spine, are common in patients with advanced cancer, often requiring extensive tests to determine the original tumor site. Our study explored whether artificial intelligence could make this process faster and more accurate using noncontrast MRI scans. We tested two methods: one based on radiologists' expertise in identifying imaging features and another using a deep learning model trained to analyze MRI images. The expert-based method was more reliable, correctly identifying the tumor site in 88% of cases when considering the top three likely diagnoses. This approach may help doctors reduce diagnostic time and improve patient care. 3 TECHNICAL EFFICACY: Stage 2.

Adenomatous colorectal polyps require endoscopic resection, as opposed to non-adenomatous hyperplastic colorectal polyps. This study aims to evaluate the effect of artificial intelligence (AI)-assisted differentiation of adenomatous and non-adenomatous colorectal polyps at CT colonography on radiologists' therapy management. Five board-certified radiologists evaluated CT colonography images with colorectal polyps of all sizes and morphologies retrospectively and decided whether the depicted polyps required endoscopic resection. After a primary unassisted reading based on current guidelines, a second reading with access to the classification of a radiomics-based random-forest AI-model labelling each polyp as "non-adenomatous" or "adenomatous" was performed. Performance was evaluated using polyp histopathology as the reference standard. 77 polyps in 59 patients comprising 118 polyp image series (47% supine position, 53% prone position) were evaluated unassisted and AI-assisted by five independent board-certified radiologists, resulting in a total of 1180 readings (subsequent polypectomy: yes or no). AI-assisted readings had higher accuracy (76% +/- 1% vs. 84% +/- 1%), sensitivity (78% +/- 6% vs. 85% +/- 1%), and specificity (73% +/- 8% vs. 82% +/- 2%) in selecting polyps eligible for polypectomy (p < 0.001). Inter-reader agreement was improved in the AI-assisted readings (Fleiss' kappa 0.69 vs. 0.92). AI-based characterisation of colorectal polyps at CT colonography as a second reader might enable a more precise selection of polyps eligible for subsequent endoscopic resection. However, further studies are needed to confirm this finding and histopathologic polyp evaluation is still mandatory. Question This is the first study evaluating the impact of AI-based polyp classification in CT colonography on radiologists' therapy management. Findings Compared with unassisted reading, AI-assisted reading had higher accuracy, sensitivity, and specificity in selecting polyps eligible for polypectomy. Clinical relevance Integrating an AI tool for colorectal polyp classification in CT colonography could further improve radiologists' therapy recommendations.

To develop and validate an ultrasomics-based machine-learning (ML) model for non-invasive assessment of interstitial fibrosis and tubular atrophy (IF/TA) in patients with IgA nephropathy (IgAN). In this multi-center retrospective study, 471 patients with primary IgA nephropathy from four institutions were included (training, n = 275; internal testing, n = 69; external testing, n = 127; respectively). The least absolute shrinkage and selection operator logistic regression with tenfold cross-validation was used to identify the most relevant features. The ML models were constructed based on ultrasomics. The Shapley Additive Explanation (SHAP) was used to explore the interpretability of the models. Logistic regression analysis was employed to combine ultrasomics, clinical data, and ultrasound imaging characteristics, creating a comprehensive model. A receiver operating characteristic curve, calibration, decision curve, and clinical impact curve were used to evaluate prediction performance. To differentiate between mild and moderate-to-severe IF/TA, three prediction models were developed: the Rad_SVM_Model, Clinic_LR_Model, and Rad_Clinic_Model. The area under curves of these three models were 0.861, 0.884, and 0.913 in the training cohort, and 0.760, 0.860, and 0.894 in the internal validation cohort, as well as 0.794, 0.865, and 0.904 in the external validation cohort. SHAP identified the contribution of radiomics features. Difference analysis showed that there were significant differences between radiomics features and fibrosis. The comprehensive model was superior to that of individual indicators and performed well. We developed and validated a model that combined ultrasomics, clinical data, and clinical ultrasonic characteristics based on ML to assess the extent of fibrosis in IgAN. Question Currently, there is a lack of a comprehensive ultrasomics-based machine-learning model for non-invasive assessment of the extent of Immunoglobulin A nephropathy (IgAN) fibrosis. Findings We have developed and validated a robust and interpretable machine-learning model based on ultrasomics for assessing the degree of fibrosis in IgAN. Clinical relevance The machine-learning model developed in this study has significant interpretable clinical relevance. The ultrasomics-based comprehensive model had the potential for non-invasive assessment of fibrosis in IgAN, which helped evaluate disease progress.

Evaluating the impact of an AI-based automated cardiac MRI (CMR) planning software on procedure errors and scan times compared to manual planning alone. Consecutive patients undergoing non-stress CMR were prospectively enrolled at a single center (August 2023-February 2024) and randomized into manual, or automated scan execution using prototype software. Patients with pacemakers, targeted indications, or inability to consent were excluded. All patients underwent the same CMR protocol with contrast, in breath-hold (BH) or free breathing (FB). Supervising radiologists recorded procedure errors (plane prescription, forgotten views, incorrect propagation of cardiac planes, and field-of-view mismanagement). Scan times and idle phase (non-acquisition portion) were computed from scanner logs. Most data were non-normally distributed and compared using non-parametric tests. Eighty-two patients (mean age, 51.6 years ± 17.5; 56 men) were included. Forty-four patients underwent automated and 38 manual CMRs. The mean rate of procedure errors was significantly (p = 0.01) lower in the automated (0.45) than in the manual group (1.13). The rate of error-free examinations was higher (p = 0.03) in the automated (31/44; 70.5%) than in the manual group (17/38; 44.7%). Automated studies were shorter than manual studies in FB (30.3 vs 36.5 min, p < 0.001) but had similar durations in BH (42.0 vs 43.5 min, p = 0.42). The idle phase was lower in automated studies for FB and BH strategies (both p < 0.001). An AI-based automated software performed CMR at a clinical level with fewer planning errors and improved efficiency compared to manual planning. Question What is the impact of an AI-based automated CMR planning software on procedure errors and scan times compared to manual planning alone? Findings Software-driven examinations were more reliable (71% error-free) than human-planned ones (45% error-free) and showed improved efficiency with reduced idle time. Clinical relevance CMR examinations require extensive technologist training, and continuous attention, and involve many planning steps. A fully automated software reliably acquired non-stress CMR potentially reducing mistake risk and increasing data homogeneity.

This study aimed to develop an open-source multimodal large language model (CXR-LLaVA) for interpreting chest X-ray images (CXRs), leveraging recent advances in large language models (LLMs) to potentially replicate the image interpretation skills of human radiologists. For training, we collected 592,580 publicly available CXRs, of which 374,881 had labels for certain radiographic abnormalities (Dataset 1) and 217,699 provided free-text radiology reports (Dataset 2). After pre-training a vision transformer with Dataset 1, we integrated it with an LLM influenced by the LLaVA network. Then, the model was fine-tuned, primarily using Dataset 2. The model's diagnostic performance for major pathological findings was evaluated, along with the acceptability of radiologic reports by human radiologists, to gauge its potential for autonomous reporting. The model demonstrated impressive performance in test sets, achieving an average F1 score of 0.81 for six major pathological findings in the MIMIC internal test set and 0.56 for six major pathological findings in the external test set. The model's F1 scores surpassed those of GPT-4-vision and Gemini-Pro-Vision in both test sets. In human radiologist evaluations of the external test set, the model achieved a 72.7% success rate in autonomous reporting, slightly below the 84.0% rate of ground truth reports. This study highlights the significant potential of multimodal LLMs for CXR interpretation, while also acknowledging the performance limitations. Despite these challenges, we believe that making our model open-source will catalyze further research, expanding its effectiveness and applicability in various clinical contexts. Question How can a multimodal large language model be adapted to interpret chest X-rays and generate radiologic reports? Findings The developed CXR-LLaVA model effectively detects major pathological findings in chest X-rays and generates radiologic reports with a higher accuracy compared to general-purpose models. Clinical relevance This study demonstrates the potential of multimodal large language models to support radiologists by autonomously generating chest X-ray reports, potentially reducing diagnostic workloads and improving radiologist efficiency.

HER2 expression is crucial for the application of HER2-targeted antibody-drug conjugates. This study aims to construct a predictive model by integrating multiparametric magnetic resonance imaging (mpMRI) based multimodal radiomics and the Vesical Imaging-Reporting and Data System (VI-RADS) score for noninvasive identification of HER2 status in bladder urothelial carcinoma (BUC). A total of 197 patients were retrospectively enrolled and randomly divided into a training cohort (n = 145) and a testing cohort (n = 52). The multimodal radiomics features were derived from mpMRI, which were also utilized for VI-RADS score evaluation. LASSO algorithm and six machine learning methods were applied for radiomics feature screening and model construction. The optimal radiomics model was selected to integrate with VI-RADS score to predict HER2 status, which was determined by immunohistochemistry. The performance of predictive model was evaluated by receiver operating characteristic curve with area under the curve (AUC). Among the enrolled patients, 110 (55.8%) patients were demonstrated with HER2-positive and 87 (44.2%) patients were HER2-negative. Eight features were selected to establish radiomics signature. The optimal radiomics signature achieved the AUC values of 0.841 (95% CI 0.779-0.904) in the training cohort and 0.794 (95%CI 0.650-0.938) in the testing cohort, respectively. The KNN model was selected to evaluate the significance of radiomics signature and VI-RADS score, which were integrated as a predictive nomogram. The AUC values for the nomogram in the training and testing cohorts were 0.889 (95%CI 0.840-0.938) and 0.826 (95%CI 0.702-0.950), respectively. Our study indicated the predictive model based on the integration of mpMRI-based radiomics and VI-RADS score could accurately predict HER2 status in BUC. The model might aid clinicians in tailoring individualized therapeutic strategies.

Pancreatic ductal adenocarcinoma (PDAC) is the third leading cause of cancer-related deaths in the United States, largely due to its poor five-year survival rate and frequent late-stage diagnosis. A significant barrier to early detection even in high-risk cohorts is that the pancreas often appears morphologically normal during the pre-diagnostic phase. Yet, the disease can progress rapidly from subclinical stages to widespread metastasis, undermining the effectiveness of screening. Recently, artificial intelligence (AI) applied to cross-sectional imaging has shown significant potential in identifying subtle, early-stage changes in pancreatic tissue that are often imperceptible to the human eye. Moreover, AI-driven imaging also aids in the discovery of prognostic and predictive biomarkers, essential for personalized treatment planning. This article uniquely integrates a critical discussion on AI's role in detecting visually occult PDAC on pre-diagnostic imaging, addresses challenges of model generalizability, and emphasizes solutions like standardized datasets and clinical workflows. By focusing on both technical advancements and practical implementation, this article provides a forward-thinking conceptual framework that bridges current gaps in AI-driven PDAC research.

Definitive chemoradiation is the primary treatment for locally advanced head and neck carcinoma (LAHNSCC). Optimising outcome predictions requires validated biomarkers, since TNM8 and HPV could have limitations. Radiomics may enhance risk stratification. This single-centre observational study collected clinical data and baseline CT scans from 171 LAHNSCC patients treated with chemoradiation. The dataset was divided into training (80%) and test (20%) sets, with a 5-fold cross-validation on the training set. Researchers extracted 108 radiomics features from each primary tumour and applied survival analysis and classification models to predict progression-free survival (PFS) and 5-year progression, respectively. Performance was evaluated using inverse probability of censoring weights and c-index for the PFS model and AUC, sensitivity, specificity, and accuracy for the 5-year progression model. Feature importance was measured by the SHapley Additive exPlanations (SHAP) method and patient stratification was assessed through Kaplan-Meier curves. The final dataset included 171 LAHNSCC patients, with 53% experiencing disease progression at 5 years. The random survival forest model best predicted PFS, with an AUC of 0.64 and CI of 0.66 on the test set, highlighting 4 radiomics features and TNM8 as significant contributors. It successfully stratified patients into low and high-risk groups (log-rank p < 0.005). The extreme gradient boosting model most effectively predicted a 5-year progression, incorporating 12 radiomics features and four clinical variables, achieving an AUC of 0.74, sensitivity of 0.53, specificity of 0.81, and accuracy of 0.66 on the test set. The combined clinical-radiomics model improved the standard TNM8 and clinical variables in predicting 5-year progression though further validation is necessary. Question There is an unmet need for non-invasive biomarkers to guide treatment in locally advanced head and neck cancer. Findings Clinical data (TNM8 staging, primary tumour site, age, and smoking) plus radiomics improved 5-year progression prediction compared with the clinical comprehensive model or TNM staging alone. Clinical relevance SHAP simplifies complex machine learning radiomics models for clinicians by using easy-to-understand graphical representations, promoting explainability.