Following Neoadjuvant Chemotherapy (NAC), there exists a probability of changes occurring in the Human Epidermal Growth Factor Receptor 2 (HER2) status. If these changes are not promptly addressed, it could hinder the timely adjustment of treatment plans, thereby affecting the optimal management of breast cancer. Consequently, the accurate prediction of HER2 status changes holds significant clinical value, underscoring the need for a model capable of precisely forecasting these alterations. In this paper, we elucidate the intricacies surrounding HER2 status changes, and propose a deep learning architecture combined with radiomics techniques, named as Ultrasound Radiomics Attention Network (URAN), to predict HER2 status changes. Firstly, radiomics technology is used to extract ultrasound image features to provide rich and comprehensive medical information. Secondly, HER2 Key Feature Selection (HKFS) network is constructed for retain crucial features relevant to HER2 status change. Thirdly, we design Max and Average Attention and Excitation (MAAE) network to adjust the model's focus on different key features. Finally, a fully connected neural network is utilized to predict HER2 status changes. The code to reproduce our experiments can be found at https://github.com/joanaapa/Foundation-Medical. Our research was carried out using genuine ultrasound images sourced from hospitals. On this dataset, URAN outperformed both state-of-the-art and traditional methods in predicting HER2 status changes, achieving an accuracy of 0.8679 and an AUC of 0.8328 (95% CI: 0.77-0.90). Comparative experiments on the public BUS_UCLM dataset further demonstrated URAN's superiority, attaining an accuracy of 0.9283 and an AUC of 0.9161 (95% CI: 0.91-0.92). Additionally, we undertook rigorously crafted ablation studies, which validated the logicality and effectiveness of the radiomics techniques, as well as the HKFS and MAAE modules integrated within the URAN model. The results pertaining to specific HER2 statuses indicate that URAN exhibits superior accuracy in predicting changes in HER2 status characterized by low expression and IHC scores of 2+ or below. Furthermore, we examined the radiomics attributes of ultrasound images and discovered that various wavelet transform features significantly impacted the changes in HER2 status. We have developed a URAN method for predicting HER2 status changes that combines radiomics techniques and deep learning. URAN model have better predictive performance compared to other competing algorithms, and can mine key radiomics features related to HER2 status changes.

Many existing methods that use functional magnetic resonance imaging (fMRI) to classify brain disorders, such as autism spectrum disorder (ASD) and attention deficit hyperactivity disorder (ADHD), often overlook the integration of spatial and temporal dependencies of the blood oxygen level-dependent (BOLD) signals, which may lead to inaccurate or imprecise classification results. To solve this problem, we propose a spatio-temporal aggregation reorganization transformer (STARFormer) that effectively captures both spatial and temporal features of BOLD signals by incorporating three key modules. The region of interest (ROI) spatial structure analysis module uses eigenvector centrality (EC) to reorganize brain regions based on effective connectivity, highlighting critical spatial relationships relevant to the brain disorder. The temporal feature reorganization module systematically segments the time series into equal-dimensional window tokens and captures multiscale features through variable window and cross-window attention. The spatio-temporal feature fusion module employs a parallel transformer architecture with dedicated temporal and spatial branches to extract integrated features. The proposed STARFormer has been rigorously evaluated on two publicly available datasets for the classification of ASD and ADHD. The experimental results confirm that STARFormer achieves state-of-the-art performance across multiple evaluation metrics, providing a more accurate and reliable tool for the diagnosis of brain disorders and biomedical research. The official implementation codes are available at: https://github.com/NZWANG/STARFormer.

To evaluate the feasibility of machine learning (ML) models using preprocedural MRI-based Whole-Organ Magnetic Resonance Imaging Score (WORMS) and clinical parameters to predict treatment response after genicular artery embolization in patients with knee osteoarthritis. This retrospective study included 66 patients (72 knees) who underwent GAE between December 2022 and June 2024. Preprocedural assessments included WORMS and Kellgren-Lawrence grading. Clinical response was defined as a ≥ 50% reduction in Visual Analog Scale (VAS) score. Feature selection was performed using recursive feature elimination and correlation analysis. Multiple ML algorithms (Random Forest, Support Vector Machine, Logistic Regression) were trained using stratified fivefold cross-validation. Conventional statistical analyses assessed group differences and correlations. Of 72 knees, 33 (45.8%) achieved a clinically significant response. Responders showed significantly lower WORMSs for cartilage, bone marrow, and total joint damage (p < 0.05). The Random Forest model demonstrated the best performance, with an accuracy of 81.8%, AUC-ROC of 86.2%, sensitivity of 90%, and specificity of 75%. Key predictive features included total WORMS, ligament score, and baseline VAS. Bone marrow score showed the strongest correlation with VAS reduction (r = -0.430, p < 0.001). ML models integrating WORMS and clinical data suggest that greater cartilage loss, bone marrow edema, joint damage, and higher baseline VAS scores may help to identify patients less likely to respond to GAE for knee OA.

Diagnostic imaging studies are increasingly important in the management of acutely presenting patients. However, ordering appropriate imaging studies in the emergency department is a challenging task with a high degree of variability among healthcare providers. To address this issue, recent work has investigated whether generative AI and large language models can be leveraged to recommend diagnostic imaging studies in accordance with evidence-based medical guidelines. However, it remains challenging to ensure that these tools can provide recommendations that correctly align with medical guidelines, especially given the limited diagnostic information available in acute care settings. In this study, we introduce a framework to intelligently leverage language models by recommending imaging studies for patient cases that align with the American College of Radiology's Appropriateness Criteria, a set of evidence-based guidelines. To power our experiments, we introduce RadCases, a dataset of over 1500 annotated case summaries reflecting common patient presentations, and apply our framework to enable state-of-the-art language models to reason about appropriate imaging choices. Using our framework, state-of-the-art language models achieve accuracy comparable to clinicians in ordering imaging studies. Furthermore, we demonstrate that our language model-based pipeline can be used as an intelligent assistant by clinicians to support image ordering workflows and improve the accuracy of acute image ordering according to the American College of Radiology's Appropriateness Criteria. Our work demonstrates and validates a strategy to leverage AI-based software to improve trustworthy clinical decision-making in alignment with expert evidence-based guidelines.

Positron emission tomography-computed tomography (PET-CT) is recommended for response evaluation in aggressive large B-cell lymphoma (LBCL) but cannot detect minimal residual disease (MRD). Circulating tumor DNA (ctDNA) has emerged as a promising biomarker for real-time disease monitoring. This study evaluated longitudinal ctDNA monitoring as an MRD marker in LBCL. In this prospective, single-center study, 14 newly diagnosed LBCL patients receiving first-line immunochemotherapy underwent frequent longitudinal blood sampling. A 53-gene targeted sequencing panel quantified ctDNA and evaluated its kinetics, correlating it with clinical parameters and PET-CT, including total metabolic tumor volume (TMTV) calculated using AI-based analysis via RECOMIA. Baseline ctDNA was detected in 11 out of 14 patients (79%), with a median variant allele frequency of 6.88% (interquartile range: 1.19-10.20%). ctDNA levels correlated significantly with TMTV (ρ = 0.91, p < 0.0001) and lactate dehydrogenase. Circulating tumor DNA kinetics, including after one treatment cycle, mirrored PET-CT metabolic changes and identified relapsing or refractory cases. This study demonstrates ctDNA-based MRD monitoring in LBCL using a fixed targeted assay with an analytical sensitivity of at least 10-3. The kinetics of ctDNA reflects the clinical course and PET-CT findings, underscoring its complementary potential to PET-CT.

This systematic review and meta-analysis evaluated the performance of imaging-based artificial intelligence (AI) models in diagnosing preoperative cervical lymph node metastasis (LNM) in clinically node-negative (cN0) papillary thyroid carcinoma (PTC). We conducted a literature search in PubMed, Embase, and Web of Science until February 25, 2025. Studies were selected that focused on imaging-based AI models for predicting cervical LNM in cN0 PTC. The diagnostic performance metrics were analyzed using a bivariate random-effects model, and study quality was assessed with the QUADAS-2 tool. From 671 articles, 11 studies involving 3366 patients were included. Ultrasound (US)-based AI models showed pooled sensitivity of 0.79 and specificity of 0.82, significantly higher than radiologists (p < 0.001). CT-based AI models demonstrated sensitivity of 0.78 and specificity of 0.89. Imaging-based AI models, particularly US-based AI, show promising diagnostic performance. There is a need for further multicenter prospective studies for validation. PROSPERO: (CRD420251063416).

Hand-wrist radiographs are used in bone age prediction. Computer-assisted clinical decision support systems offer solutions to the limitations of the radiographic bone age assessment methods. In this study, a multi-output prediction model was designed to predict bone age and gender using digital hand-wrist radiographs. The InceptionV3 architecture was used as the backbone, and the model was trained and tested using the open-access dataset of 2017 RSNA Pediatric Bone Age Challenge. A total of 14,048 samples were divided to training, validation, and testing subsets with the ratio of 7:2:1, and additional specialized convolutional neural network layers were implemented for robust feature management, such as Squeeze-and-Excitation block. The proposed model achieved a mean squared error of approximately 25 and a mean absolute error of 3.1 for predicting bone age. In gender classification, an accuracy of 95% and an area under the curve of 97% were achieved. The intra-class correlation coefficient for the continuous bone age predictions was found to be 0.997, while the Cohen's <math xmlns="http://www.w3.org/1998/Math/MathML"><mi>κ</mi></math> coefficient for the gender predictions was found to be 0.898 ( <math xmlns="http://www.w3.org/1998/Math/MathML"><mrow><mi>p</mi> <mo><</mo></mrow> </math> 0.001). The proposed model aims to increase model efficiency by identifying common and discrete features. Based on the results, the proposed algorithm is promising; however, the mid-high-end hardware requirement may be a limitation for its use on local machines in the clinic. The future studies may consider increasing the dataset and simplification of the algorithms.

We developed an MRI-based habitat radiomics model (HRM) to predict p53-abnormal (p53abn) molecular subtypes of endometrial cancer (EC). Patients with pathologically confirmed EC were retrospectively enrolled from three hospitals and categorized into a training cohort (n = 270), test cohort 1 (n = 70), and test cohort 2 (n = 154). The tumour was divided into habitat sub-regions using diffusion-weighted imaging (DWI) and contrast-enhanced (CE) images with the K-means algorithm. Radiomics features were extracted from T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), DWI, and CE images. Three machine learning classifiers-logistic regression, support vector machines, and random forests-were applied to develop predictive models for p53abn EC. Model performance was validated using receiver operating characteristic (ROC) curves, and the model with the best predictive performance was selected as the HRM. A whole-region radiomics model (WRM) was also constructed, and a clinical model (CM) with five clinical features was developed. The SHApley Additive ExPlanations (SHAP) method was used to explain the outputs of the models. DeLong's test evaluated and compared the performance across the cohorts. A total of 1920 habitat radiomics features were considered. Eight features were selected for the HRM, ten for the WRM, and three clinical features for the CM. The HRM achieved the highest AUC: 0.855 (training), 0.769 (test1), and 0.766 (test2). The AUCs of the WRM were 0.707 (training), 0.703 (test1), and 0.738 (test2). The AUCs of the CM were 0.709 (training), 0.641 (test1), and 0.665 (test2). The MRI-based HRM successfully predicted p53abn EC. The results indicate that habitat combined with machine learning, radiomics, and SHAP can effectively predict p53abn EC, providing clinicians with intuitive insights and interpretability regarding the impact of risk factors in the model.

In pelvic MRI, Turbo Spin Echo (TSE) pulse sequences are used for T2-weighted imaging. However, its lengthy acquisition time increases the potential for artifacts. Deep learning (DL) reconstruction achieves reduced scan times without the degradation in image quality associated with other accelerated techniques. Unfortunately, a comprehensive assessment of DL-reconstruction in pelvic MRI has not been performed. The objective of this prospective study was to compare the performance of DL-TSE and conventional TSE pulse sequences in a broad spectrum of pelvic MRI indications. Fifty-five subjects (33 females and 22 males) were scanned at 3 T using DL-TSE and conventional TSE sequences in axial and/or oblique acquisition planes. Two radiologists independently assessed image quality in 6 categories: edge definition, vessel margin sharpness, T2 Contrast Dynamic Range, artifacts, overall image quality, and lesion features. The contrast ratio was calculated for quantitative assessment. A two-tailed sign test was used for assessment. The 2 readers found DL-TSE to deliver equal or superior image quality than conventional TSE in most cases. There were only 3 instances out of 24 where conventional TSE was scored as providing better image quality. Readers agreed on DL-TSE superiority/inferiority/equivalence in 67% of categories in the axial plane and 75% in the oblique plane. DL-TSE also demonstrated a better contrast ratio in 75% of cases. DL-TSE reduced scan time by approximately 50%. DL-accelerated TSE sequences generally provide equal or better image quality in pelvic MRI than standard TSE with significantly reduced acquisition times.

Artificial intelligence (AI) is increasingly being explored as a complementary tool to traditional fracture risk assessment methods. Conventional approaches, such as bone mineral density measurement and established clinical risk calculators, provide populationlevel stratification but often fail to capture the structural nuances of bone fragility. Recent advances in AI-particularly deep learning techniques applied to imaging-enable opportunistic screening and individualized risk estimation using routinely acquired radiographs and computed tomography (CT) data. These models demonstrate improved discrimination for osteoporotic fracture detection and risk prediction, supporting applications such as time-to-event modeling and short-term prognosis. CT- and radiograph-based models have shown superiority over conventional metrics in diverse cohorts, while innovations like multitask learning and survival plots contribute to enhanced interpretability and patient-centered communication. Nevertheless, challenges related to model generalizability, data bias, and automation bias persist. Successful clinical integration will require rigorous external validation, transparent reporting, and seamless embedding into electronic medical systems. This review summarizes recent advances in AI-driven fracture assessment, critically evaluates their clinical promise, and outlines a roadmap for translation into real-world practice.