Pneumonia detection in chest X-rays (CXR) increasingly relies on AI-driven diagnostic systems. However, their "black-box" nature often lacks transparency, underscoring the need for interpretability to improve patient outcomes. This study presents the first application of the Deformable Prototypical Part Network (D-ProtoPNet), an ante-hoc interpretable deep learning (DL) model, for pneumonia classification in pediatric patients' CXR images. Clinical insights were integrated through expert radiologist evaluation of the model's learned prototypes and activated image patches, ensuring that explanations aligned with medically meaningful features. The model was developed and tested on a retrospective dataset of 5,856 CXR images of pediatric patients, ages 1-5 years. The images were originally acquired at a tertiary academic medical center as part of routine clinical care and were publicly hosted on a Kaggle platform. This dataset comprised anterior-posterior images labeled normal, viral, and bacterial. It was divided into 80 % training and 20 % validation splits, and utilised in a supervised five-fold cross-validation. Performance metrics were compared with the original ProtoPNet, utilising ResNet50 as the base model. An experienced radiologist assessed the clinical relevance of the learned prototypes, patch activations, and model explanations. The D-ProtoPNet achieved an accuracy of 86 %, precision of 86 %, recall of 85 %, and AUC of 93 %, marking a 3 % improvement over the original ProtoPNet. While further optimisation is required before clinical use, the radiologist praised D-ProtoPNet's intuitive explanations, highlighting its interpretability and potential to aid clinical decision-making. Prototypical part learning offers a balance between classification performance and explanation quality, but requires improvements to match the accuracy of black-box models. This study underscores the importance of integrating domain expertise during model evaluation to ensure the interpretability of XAI models is grounded in clinically valid insights.

Predicting distant metastases in soft tissue sarcomas (STS) is vital for guiding clinical decision-making. Recent advancements in radiomics and deep learning (DL) models have shown promise, but their diagnostic accuracy remains unclear. This meta-analysis aims to assess the performance of radiomics and DL-based models in predicting metastases in STS by analyzing pooled sensitivity and specificity. Following PRISMA guidelines, a thorough search was conducted in PubMed, Web of Science, and Embase. A random-effects model was used to estimate the pooled area under the curve (AUC), sensitivity, and specificity. Subgroup analyses were performed based on imaging modality (MRI, PET, PET/CT), feature extraction method (DL radiomics [DLR] vs. handcrafted radiomics [HCR]), incorporation of clinical features, and dataset used. Heterogeneity by I² statistic, leave-one-out sensitivity analyses, and publication bias by Egger's test assessed model robustness and potential biases. Ninetheen studies involving 1712 patients were included. The pooled AUC for predicting metastasis was 0.88 (95% CI: 0.80-0.92). The pooled AUC values were 88% (95% CI: 77-89%) for MRI-based models, 80% (95% CI: 76-92%) for PET-based models, and 91% (95% CI: 78-93%) for PET/CT-based models, with no significant differences (p = 0.75). DL-based models showed significantly higher sensitivity than HCR models (p < 0.01). Including clinical features did not significantly improve model performance (AUC: 0.90 vs. 0.88, p = 0.99). Significant heterogeneity was noted (I² > 25%), and Egger's test suggested potential publication bias (p < 0.001). Radiomics models showed promising potential for predicting metastases in STSs, with DL approaches outperforming traditional HCR. While integrating this approach into routine clinical practice is still evolving, it can aid physicians in identifying high-risk patients and implementing targeted monitoring strategies to reduce the risk of severe complications associated with metastasis. However, challenges such as heterogeneity, limited external validation, and potential publication bias persist. Future research should concentrate on standardizing imaging protocols and conducting multi-center validation studies to improve the clinical applicability of radiomics predictive models.

To assess artificial intelligence (AI)'s added value in detecting prostate cancer lesions on MRI by comparing radiologists' performance with and without AI assistance. A fully-crossed multi-reader multi-case clinical trial was conducted across three institutions with 10 non-expert radiologists. Biparametric MRI cases comprising T2WI, diffusion-weighted images, and apparent diffusion coefficient were retrospectively collected. Three reading modes were evaluated: AI alone, radiologists alone (unaided), and radiologists with AI (aided). Aided and unaided readings were compared using the Dorfman-Berbaum-Metz method. Reference standards were established by senior radiologists based on pathological reports. Performance was quantified via sensitivity, specificity, and area under the alternative free-response receiver operating characteristic curve (AFROC-AUC). Among 407 eligible male patients (69.5±9.3years), aided reading significantly improved lesion-level sensitivity from 67.3% (95% confidence intervals [CI]: 58.8%, 75.8%) to 85.5% (95% CI: 81.3%, 89.7%), with a substantial difference of 18.2% (95% CI: 10.7%, 25.7%, p<0.001). Case-level specificity increased from 75.9% (95% CI: 68.7%, 83.1%) to 79.5% (95% CI: 74.1%, 84.8%), demonstrating non-inferiority (p<0.001). AFROC-AUC was also higher for aided than unaided reading (86.9% vs 76.1%, p<0.001). AI alone achieved robust performance (AFROC-AUC=83.1%, 95%CI: 79.7%, 86.6%), with lesion-level sensitivity of 88.4% (95% CI: 84.0%, 92.0%) and case-level specificity of 77.8% (95% CI: 71.5%, 83.3%). Subgroup analysis revealed improved detection for lesions with smaller size and lower prostate imaging reporting and data system scores. AI-aided reading significantly enhances lesion detection compared to unaided reading, while AI alone also demonstrates high diagnostic accuracy.

Deep learning-based fast kV-switching CT (DL-FKSCT) generates complete sinograms for fast kV-switching dual-energy CT (DECT) scans by using a trained neural network to restore missing views. Such restoration significantly enhances the image quality of coronary CT angiography (CCTA), and the allowable heart rate (HR) may vary between DECT and single-energy CT (SECT). This study aimed to examine HR's effect onCCTA using DL-FKSCT. We scanned stenotic coronary artery phantoms attached to a pulsating cardiac phantom with DECT and SECT modes on a DL-FKSCT scanner. The phantom unit was operated with simulated HRs ranging from 0 (static) to 50-70 beats per minute (bpm). The sharpness and stenosis ratio of the coronary model were quantitatively compared between DECT and SECT, stratified by simulated HR settings using the paired t-test (significance was set at p < 0.01 with a Bonferroni adjustment for multiple comparisons). Regarding image sharpness, DECT showed significant superiority over SECT. In terms of the stenosis ratio compared to a static image reference, 70 keV virtual monochromatic image in DECT exhibited errors exceeding 10 % at HRs surpassing 65 bpm (p < 0.01), whereas 120 kVp SECT registered errors below 10 % across all HR settings, with no significant differences observed. In DL-FKSCT, DECT exhibited a lower upper limit of HR than SECT. Therefore, HR control is important for DECT scans in DL-FKSCT.

Presence of spot sign on CT Angiography (CTA) is associated with hematoma growth in patients with intracerebral hemorrhage. Measuring spot sign volume over time may aid to predict hematoma expansion. Due to the difficulties that imaging characteristics of spot sign are similar with vein and calcification and spot signs are tiny appeared in CTA images to detect, our aim is to develop an automated method to pick up spot signs accurately. We proposed a novel collaborative architecture of network based on a student-teacher model by efficiently exploiting additional negative samples with contrastive learning. In particular, a set of dynamic-updated memory banks is proposed to learn more distinctive features from the extremely imbalanced positive and negative samples. Alongside, a two-steam network with an additional contextual-decoder is designed for learning more contextual information at different scales in a collaborative way. Besides, to better inhibit the false positive detection rate, a region restriction loss function is further designed to confine the spot sign segmentation within the hemorrhage. Quantitative evaluations using dice, volume correlation, sensitivity, specificity, area under the curve show that the proposed method is able to segment and detect spot signs accurately. Our proposed contractive learning framework obtained the best segmentation performance regarding a mean Dice of 0.638 ± 0211, a mean VC of 0.871 and a mean VDP of 0.348 ± 0.237 and detection performance regarding sensitivity of 0.956 with CI(0.895,1.000), specificity of 0.833 with CI(0.766,0.900), and AUC of 0.892 with CI(0.888,0.896), outperforming nnuNet, cascade-nnuNet, nnuNet++, SegRegNet, UNETR and SwinUNETR. This paper proposed a novel segmentation approach that leverages contrastive learning to explore additional negative samples concurrently for the automatic segmentation of spot signs on mCTA images. The experimental results demonstrate the effectiveness of our method and highlight its potential applicability in clinical settings for measuring spot sign volumes.

Neurological Disorders (ND) affect a large portion of the global population, impacting the brain, spinal cord, and nerves. These disorders fall into categories such as NeuroDevelopmental (NDD), NeuroBiological (NBD), and NeuroDegenerative (ND_e) disorders, which range from common to rare conditions. While Artificial Intelligence (AI) has advanced healthcare diagnostics, training Machine Learning (ML) and Deep Learning (DL) models for early detection of rare neurological disorders remains a challenge due to limited patient data. This data scarcity poses a significant public health issue. Meta_Trans Learning (M_TAL), which integrates Meta-Learning (M_tL) and Transfer Learning (TL), offers a promising solution by leveraging small datasets to extract expert patterns, generalize findings, and reduce AI bias in healthcare. This research systematically reviews studies from 2018 to 2024 to explore how ML and M_TAL techniques are applied in diagnosing NDD, NBD, and ND_e disorders. It also provides statistical and parametric analysis of ML and DL methods for neurological disorder diagnosis. Lastly, the study introduces a MRI-based ND_e-M_TAL framework to aid healthcare professionals in early detection of rare neuro disorders, aiming to enhance diagnostic accuracy and advance healthcare practices.

Robust and accurate segmentation of subcortical structures in brain MR images lays the foundation for observation, analysis and treatment planning of various brain diseases. Deep learning techniques based on Deep Neural Networks (DNNs) have achieved remarkable results in medical image segmentation by using abundant labeled data. However, due to the time-consuming and expensive of acquiring high quality annotations of brain subcortical structures, semi-supervised algorithms become practical in application. In this paper, we propose a novel framework for semi-supervised subcortical brain structure segmentation, based on pseudo-labels Cross Supervising and Confidence Enhancement (CSCE). Our framework comprises dual student-teacher models, specifically a U-Net and a TransUNet. For unlabeled data training, the TransUNet teacher generates pseudo-labels to supervise the U-Net student, while the U-Net teacher generates pseudo-labels to supervise the TransUNet student. This mutual supervision between the two models promotes and enhances their performance synergistically. We have designed two mechanisms to enhance the confidence of pseudo-labels to improve the reliability of cross-supervision: a) Using information entropy to describe uncertainty quantitatively; b) Design an auxiliary detection task to perform uncertainty detection on the pseudo-labels output by the teacher model, and then screened out reliable pseudo-labels for cross-supervision. Finally, we construct an end-to-end deep brain structure segmentation network only using one teacher network (U-Net or TransUNet) for inference, the segmentation results are significantly improved without increasing the parameters amount and segmentation time compared with supervised U-Net or TransUNet based segmentation algorithms. Comprehensive experiments are performed on two public benchmark brain MRI datasets. The proposed method achieves the best Dice scores and MHD values on both datasets compared to several recent state-of-the-art semi-supervised segmentation methods.

The REgistry of Flow and Perfusion Imaging for Artificial INtelligEnce with PET (REFINE PET) was established to aggregate PET and associated computed tomography (CT) images with clinical data from hospitals around the world into one comprehensive research resource. REFINE PET is a multicenter, international registry that contains both clinical and imaging data. The PET scans were processed using QPET software (Cedars-Sinai Medical Center, Los Angeles, CA), while the CT scans were processed using deep learning (DL) to detect coronary artery calcium (CAC). Patients were followed up for the occurrence of major adverse cardiovascular events (MACE), which include death, myocardial infarction, unstable angina, and late revascularization (>90 days from PET). The REFINE PET registry currently contains data for 35,588 patients from 14 sites, with additional patient data and sites anticipated. Comprehensive clinical data (including demographics, medical history, and stress test results) were integrated with more than 2200 imaging variables across 42 categories. The registry is poised to address a broad range of clinical questions, supported by correlating invasive angiography (within 6 months of MPI) in 5972 patients and a total of 9252 major adverse cardiovascular events during a median follow-up of 4.2 years. The REFINE PET registry leverages the integration of clinical, multimodality imaging, and novel quantitative and AI tools to advance the role of PET/CT MPI in diagnosis and risk stratification.

Gliomas are the most common malignant primary brain tumors, and grading their severity, particularly the diagnosis of low-grade gliomas, remains a challenging task for clinicians and radiologists. With advancements in deep learning and medical image processing technologies, the development of Clinical Decision Support Systems (CDSS) for glioma grading offers significant benefits for clinical treatment. This study proposes a CDSS for glioma grading, integrating a novel feature extraction framework. The method is based on combining ensemble learning and knowledge distillation: teacher models were constructed through ensemble learning, while uncertainty-weighted ensemble averaging is applied during student model training to refine knowledge transfer. This approach bridges the teacher-student performance gap, enhancing grading accuracy, reliability, and clinical applicability with lightweight deployment. Experimental results show 85.96 % Accuracy (5.2 % improvement over baseline), with Precision (83.90 %), Recall (87.40 %), and F1-score (83.90 %) increasing by 7.5 %, 5.1 %, and 5.1 % respectively. The teacher-student performance gap is reduced to 3.2 %, confirming effectiveness. Furthermore, the developed CDSS not only ensures rapid and accurate glioma grading but also includes critical features influencing the grading results, seamlessly integrating a methodology for generating comprehensive diagnostic reports. Consequently, the glioma grading CDSS represents a practical clinical decision support tool capable of delivering accurate and efficient auxiliary diagnostic decisions for physicians and patients.

Currently, radiomics focuses on intratumoral regions and fixed peritumoral regions, and lacks an optimal peritumoral region taken to predict KI-67 expression. The aim of this study was to develop a machine learning model to analyze ultrasound radiomics features with different regions of peri-tumor fetch values to determine the optimal peri-tumor region for predicting KI-67 expression. A total of 453 breast cancer patients were included. They were randomly assigned to training and validation sets in a 7:3 ratio. In the training cohort, machine learning models were constructed for intra-tumor and different peri-tumor regions (2 mm, 4 mm, 6 mm, 8 mm, 10 mm), identifying the relevant Ki-67 features for each ROI and comparing the different models to determine the best model. These models were validated using a test cohort to find the most accurate peri-tumor region for Ki-67 prediction. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of predicting KI-67 expression, and the Delong test was used to assess the difference between each AUC.SHAP (Shapley Additive Decomposition) was performed to analyze the optimal prediction model and quantify the contribution of major radiomics features. In the validation cohort, the SVM model with the combination of intratumoral and peritumoral 6 mm regions showed the highest prediction effect, with an AUC of 0.9342.The intratumoral and peritumoral 6-mm SVM models showed statistically significant differences (P < 0.05) compared to the other models. SHAP analysis showed that peri-tumoral 6 mm features were more important than intratumoral features. SVM models using intratumoral and peritumoral 6 mm regions showed the best results in prediction of KI-67 expression.