Deep learning models have shown promise in lung pathology detection from chest X-rays, but widespread clinical adoption remains limited due to opaque model decision-making. In prior work, we introduced ClinicXAI, a human-centric, expert-guided concept bottleneck model (CBM) designed for interpretable lung cancer diagnosis. We now extend that approach and present XpertXAI, a generalizable expert-driven model that preserves human-interpretable clinical concepts while scaling to detect multiple lung pathologies. Using a high-performing InceptionV3-based classifier and a public dataset of chest X-rays with radiology reports, we compare XpertXAI against leading post-hoc explainability methods and an unsupervised CBM, XCBs. We assess explanations through comparison with expert radiologist annotations and medical ground truth. Although XpertXAI is trained for multiple pathologies, our expert validation focuses on lung cancer. We find that existing techniques frequently fail to produce clinically meaningful explanations, omitting key diagnostic features and disagreeing with radiologist judgments. XpertXAI not only outperforms these baselines in predictive accuracy but also delivers concept-level explanations that better align with expert reasoning. While our focus remains on explainability in lung cancer detection, this work illustrates how human-centric model design can be effectively extended to broader diagnostic contexts - offering a scalable path toward clinically meaningful explainable AI in medical diagnostics.

Acute kidney injury (AKI) post-renal transplantation often has a poor prognosis. This study aimed to identify patients with elevated risks of AKI after kidney transplantation. A retrospective analysis was conducted on 422 patients who underwent kidney transplants from January 2020 to April 2023. Participants from 2020 to 2022 were randomized to training group (n=261) and validation group 1 (n=113), and those in 2023, as validation group 2 (n=48). Risk factors were determined by employing logistic regression analysis alongside the least absolute shrinkage and selection operator, making use of ultrasound hemodynamic, clinical, and laboratory information. Models for prediction were developed using logistic regression analysis and six machine-learning techniques. The evaluation of the logistic regression model encompassed its discrimination, calibration, and applicability in clinical settings, and a nomogram was created to illustrate the model. SHapley Additive exPlanations were used to explain and visualize the best of the six machine learning models. The least absolute shrinkage and selection operator combined with logistic regression identified and incorporated five risk factors into the predictive model. The logistic regression model (AUC=0.927 in the validation set 1; AUC=0.968 in the validation set 2) and the random forest model (AUC=0.946 in the validation set 1;AUC=0.996 in the validation set 2) showed good performance post-validation, with no significant difference in their predictive accuracy. These findings can assist clinicians in the early identification of patients at high risk for AKI, allowing for timely interventions and potentially enhancing the prognosis following kidney transplantation.

Musculoskeletal ultrasound (MSUS) and magnetic resonance imaging (MRI) are advanced imaging techniques that are increasingly important in the diagnosis and management of rheumatoid arthritis (RA) and have significantly enhanced the rheumatologist's ability to assess RA disease activity and progression. This review serves as a five-year update to our previous publication on the contemporary role of imaging in RA, emphasizing the continued importance of MSUS and MRI in clinical practice and their expanding utility. The review examines the role of MSUS in diagnosing RA, differentiating RA from mimickers, scoring systems and quality control measures, novel longitudinal approaches to disease monitoring, and patient populations that may benefit most from MSUS. It also examines the role of MRI in diagnosing pre-clinical and early RA, disease activity monitoring, research and clinical trials, and development of alternative scoring approaches utilizing artificial intelligence. Finally, the role of MRI in RA diagnosis and management is summarized, and selected practice points offer key tips for integrating MSUS and MRI into clinical practice.

Automated Whole-Breast Ultrasound (ABUS) has been widely used as an important tool in breast cancer diagnosis due to the ability of this technique to provide complete three-dimensional (3D) images of breasts. To eliminate the risk of misdiagnosis, computer-aided diagnosis (CADx) systems have been proposed to assist radiologists. Convolutional neural networks (CNNs), renowned for the automatic feature extraction capabilities, have developed rapidly in medical image analysis, and this study proposes a CADx system based on 3D CNN for ABUS. This study used a private dataset collected at Sun Yat-Sen University Cancer Center (SYSUCC) from 396 breast tumor patients. First, the tumor volume of interest (VOI) was extracted and resized, and then the tumor was enhanced by histogram equalization. Second, a 3D U-Net++ was employed to segment the tumor mask. Finally, the VOI, the enhanced VOI, and the corresponding tumor mask were fed into a 3D Attention-Inception network to classify the tumor as benign or malignant. The experiment results indicate an accuracy of 89.4%, a sensitivity of 91.2%, a specificity of 87.6%, and an area under the receiver operating characteristic curve (AUC) of 0.9262, which suggests that the proposed CADx system for ABUS images rivals the performance of experienced radiologists in tumor diagnosis tasks. This study proposes a CADx system consisting of a 3D U-Net++ tumor segmentation model and a 3D attention inception neural network tumor classification model for diagnosis in ABUS images. The results indicate that the proposed CADx system is effective and efficient in tumor diagnosis tasks.

BackgroundAccurate left ventricular outflow tract obstruction (LVOTO) assessment is crucial for hypertrophic cardiomyopathy (HCM) management and prognosis. Traditional methods, requiring multiple views, Doppler, and provocation, is often infeasible, especially where resources are limited. This study aimed to develop and validate a deep learning (DL) model capable of predicting severe LVOTO in HCM patients using only the parasternal long-axis (PLAX) view from transthoracic echocardiography (TTE). MethodsA DL model was trained on PLAX videos extracted from TTE examinations (developmental dataset, n=1,007) to capture both morphological and dynamic motion features, generating a DL index for LVOTO (DLi-LVOTO, range 0-100). Performance was evaluated in an internal test dataset (ITDS, n=87) and externally validated in the distinct hospital dataset (DHDS, n=1,334) and the LVOTO reduction treatment dataset (n=156). ResultsThe model achieved high accuracy in detecting severe LVOTO (pressure gradient[&ge;] 50mmHg), with area under the receiver operating characteristics curve (AUROC) of 0.97 (95% confidence interval: 0.92-1.00) in ITDS and 0.93 (0.92-0.95) in DHDS. At a DLi-LVOTO threshold of 70, the model demonstrated a specificity of 97.3% and negative predictive value (NPV) of 96.1% in ITDS. In DHDS, a cutoff of 60 yielded a specificity of 94.6% and NPV of 95.5%. DLi-LVOTO also decreased significantly after surgical myectomy or Mavacamten treatment, correlating with reductions in peak pressure gradient (p<0.001 for all). ConclusionsOur DL-based approach predicts severe LVOTO using only the PLAX view from TTE, serving as a complementary tool, particularly in resource-limited settings or when Doppler is unavailable, and for monitoring treatment response.

Evaluate an Artificial Intelligence (AI) system in breast screening through stratified results across age, breast density, ethnicity and screening centres, from different UK regions. A large-scale retrospective study evaluating two variations of using AI as an independent second reader in double reading was executed. Stratifications were conducted for clinical and operational metrics. Data from 306 839 mammography cases screened between 2017 and 2021 were used and included three different UK regions.The impact on safety and effectiveness was assessed using clinical metrics: cancer detection rate and positive predictive value, stratified according to age, breast density and ethnicity. Operational impact was assessed through reading workload and recall rate, measured overall and per centre.Non-inferiority was tested for AI workflows compared with human double reading, and when passed, superiority was tested. AI interval cancer (IC) flag rate was assessed to estimate additional cancer detection opportunity with AI that cannot be assessed retrospectively. The AI workflows passed non-inferiority or superiority tests for every metric across all subgroups, with workload savings between 38.3% and 43.7%. The AI standalone flagged 41.2% of ICs overall, ranging between 33.3% and 46.8% across subgroups, with the highest detection rate for dense breasts. Human double reading and AI workflows showed the same performance disparities across subgroups. The AI integrations maintained or improved performance at all metrics for all subgroups while achieving significant workload reduction. Moreover, complementing these integrations with AI as an additional reader can improve cancer detection. The granularity of assessment showed that screening with the AI-system integrations was as safe as standard double reading across heterogeneous populations.

This study aimed to establish and validate a prediction model based on machine learning methods and SHAP algorithm to predict response to anti-vascular endothelial growth factor (VEGF) therapy in neovascular age-related macular degeneration (AMD). In this retrospective study, we extracted data including demographic characteristics, laboratory test results, and imaging features from optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA). Eight machine learning methods, including Logistic Regression, Gradient Boosting Decision Tree, Random Forest, CatBoost, Support Vector Machine, XGboost, LightGBM, K Nearest Neighbors were employed to develop the predictive model. The machine learning method with optimal performance was selected for further interpretation. Finally, the SHAP algorithm was applied to explain the model's predictions. The study included 145 patients with neovascular AMD. Among the eight models developed, the Random Forest model demonstrated general optimal performance, achieving a high accuracy of 75.86% and the highest area under the receiver operating characteristic curve (AUC) value of 0.91. In this model, important features identified as significant contributors to the response to anti-VEGF therapy in neovascular AMD patients included fractal dimension, total number of end points, total number of junctions, total vessels length, vessels area, average lacunarity, choroidal neovascularization (CNV) type, age, duration and logMAR BCVA. SHAP analysis and visualization provided interpretation at both the factor level and individual level. The Random Forest model for predicting response to anti-VEGF therapy in neovascular AMD using SHAP algorithm proved to be feasible and effective. OCTA imaging features, such as fractal dimension, total number of end points et al, were the most effective predictive factors.

Ultrasonography and D-dimer testing are established modalities for evaluating potential lower extremity deep venous thrombosis (DVT). The ThinkSono Guidance system is an AI based software allowing non-ultrasound trained providers to perform compression ultrasounds for evaluation by remote interpreters. This study evaluates its clinical utilisation and potential reduction of venous duplexes and waiting times. Patients with suspected DVTs were prospectively recruited through the institution's emergency department. Patients underwent an AI guided two region proximal DVT compression examination by non-ultrasound trained providers using the ThinkSono Guidance system and D-dimer testing. Ultrasound images remotely reviewed by the on call radiologist were rated for diagnostic quality; all images of sufficient quality were assessed as either "Compressible/no proximal DVT" or "Inadequate imaging/possible DVT". All patients assessed as "compressible" with negative D-dimers were discharged. All other patients were sent for a venous duplex scan. Time to diagnosis, sensitivity, and specificity of ThinkSono Guidance against D-dimers and full duplex scans were calculated. Fifty three patients (average age 56 ± 18 years, 45% females) were scanned with ThinkSono Guidance by one of three non-ultrasound trained providers. All scans were of diagnostic quality. ThinkSono Guidance with radiologist review yielded 45 negative DVT diagnoses (85%). Seventeen of these with negative D-dimers were discharged (32%), 28 required duplex ultrasound testing per trial protocol (23 due to positive D-dimers, five due to unavailability of D-dimer). All of these duplexes were negative (100% sensitivity). Eight patients were suspected to have DVT by the reviewing radiologist, and duplex confirmed DVT in six patients (96% ThinkSono Guidance specificity, 36% D-dimer specificity). ThinkSono Guidance scans averaged 6.75 minutes for scan and review. The median time from scan initiation to review was 37.5 minutes. This suggests a significant proportion of patients with suspected DVT could safely avoid duplex ultrasound and D-dimer testing using the ThinkSono system, setting the basis for a novel AI assisted diagnostic pathway.

BackgroundRetinal fundus images provide a noninvasive window into systemic health, offering opportunities for early detection of metabolic disorders such as metabolic syndrome (METS). ObjectiveThis study aimed to develop a deep learning model to predict METS from fundus images obtained during routine health checkups, leveraging a multi-task learning approach. MethodsWe retrospectively analyzed 5,000 fundus images from Japanese health checkup participants. Convolutional neural network (CNN) models were trained to classify METS status, incorporating fundus-specific data augmentation strategies and auxiliary regression tasks targeting clinical parameters such as abdominal circumference (AC). Model performance was evaluated using validation accuracy, test accuracy, and the area under the receiver operating characteristic curve (AUC). ResultsModels employing fundus-specific augmentation demonstrated more stable convergence and superior validation accuracy compared to general-purpose augmentation. Incorporating AC as an auxiliary task further enhanced performance across architectures. The final ensemble model with test-time augmentation achieved a test accuracy of 0.696 and an AUC of 0.73178. ConclusionCombining multi-task learning, fundus-specific data augmentation, and ensemble prediction substantially improves deep learning-based METS classification from fundus images. This approach may offer a practical, noninvasive screening tool for metabolic syndrome in general health checkup settings.

Diagnosis of peritoneal invasion, lymph node metastasis, and hepatic metastasis is crucial in the decision-making process of ovarian tumor treatment. This study aimed to test the feasibility of low-dose abdominopelvic CT with an artificial intelligence iterative reconstruction (AIIR) for diagnosing peritoneal invasion, lymph node metastasis, and hepatic metastasis in pre-operative imaging of ovarian tumor. This study prospectively enrolled 88 patients with pathology-confirmed ovarian tumors, where routine-dose CT at portal venous phase (120 kVp/ref. 200 mAs) with hybrid iterative reconstruction (HIR) was followed by a low-dose scan (120 kVp/ref. 40 mAs) with AIIR. The performance of diagnosing peritoneal invasion and lymph node metastasis was assessed using receiver operating characteristic (ROC) analysis with pathological results serving as the reference. The hepatic parenchymal metastases were diagnosed and signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were measured. The perihepatic structures were also scored on the clarity of porta hepatis, gallbladder fossa and intersegmental fissure. The effective dose of low-dose CT was 79.8% lower than that of routine-dose scan (2.64 ± 0.46 vs. 13.04 ± 2.25 mSv, p < 0.001). The low-dose AIIR showed similar area under the ROC curve (AUC) with routine-dose HIR for diagnosing both peritoneal invasion (0.961 vs. 0.960, p = 0.734) and lymph node metastasis (0.711 vs. 0.715, p = 0.355). The 10 hepatic parenchymal metastases were all accurately diagnosed on the two image sets. The low-dose AIIR exhibited higher SNR and CNR for hepatic parenchymal metastases and superior clarity for perihepatic structures. In low-dose pre-operative CT of ovarian tumor, AIIR delivers similar diagnostic accuracy for peritoneal invasion, lymph node metastasis, and hepatic metastasis, as compared to routine-dose abdominopelvic CT. It is feasible and diagnostically safe to apply up to 80% dose reduction in CT imaging of ovarian tumor by using AIIR.