To assess the performance of an industry-developed deep learning (DL) algorithm to reconstruct low-resolution Cartesian T1-weighted dynamic contrast-enhanced (T1w) and T2-weighted turbo-spin-echo (T2w) sequences and compare them to standard sequences. Female patients with indications for breast MRI were included in this prospective study. The study protocol at 1.5 Tesla MRI included T1w and T2w. Both sequences were acquired in standard resolution (T1_S and T2_S) and in low-resolution with following DL reconstructions (T1_DL and T2_DL). For DL reconstruction, two convolutional networks were used: (1) Adaptive-CS-Net for denoising with compressed sensing, and (2) Precise-Image-Net for resolution upscaling of previously downscaled images. Overall image quality was assessed using 5-point-Likert scale (from 1=non-diagnostic to 5=excellent). Apparent signal-to-noise (aSNR) and contrast-to-noise (aCNR) ratios were calculated. Breast Imaging Reporting and Data System (BI-RADS) agreement between different sequence types was assessed. A total of 47 patients were included (mean age, 58±11 years). Acquisition time for T1_DL and T2_DL were reduced by 51% (44 vs. 90 s per dynamic phase) and 46% (102 vs. 192 s), respectively. T1_DL and T2_DL showed higher overall image quality (e.g., 4 [IQR, 4-4] for T1_S vs. 5 [IQR, 5-5] for T1_DL, P<0.001). Both, T1_DL and T2_DL revealed higher aSNR and aCNR than T1_S and T2_S (e.g., aSNR: 32.35±10.23 for T2_S vs. 27.88±6.86 for T2_DL, P=0.014). Cohen k agreement by BI-RADS assessment was excellent (0.962, P<0.001). DL for denoising and resolution upscaling reduces acquisition time and improves image quality for T1w and T2w breast MRI.

The accelerating development of general medical artificial intelligence (GMAI), powered by multimodal large language models (MLLMs), offers transformative potential for addressing persistent healthcare challenges, including workforce deficits and escalating costs. The parallel development of systematic evaluation benchmarks emerges as a critical imperative to enable performance assessment and provide technological guidance. Meanwhile, as an invaluable knowledge source, the potential of medical textbooks for benchmark development remains underexploited. Here, we present MedBookVQA, a systematic and comprehensive multimodal benchmark derived from open-access medical textbooks. To curate this benchmark, we propose a standardized pipeline for automated extraction of medical figures while contextually aligning them with corresponding medical narratives. Based on this curated data, we generate 5,000 clinically relevant questions spanning modality recognition, disease classification, anatomical identification, symptom diagnosis, and surgical procedures. A multi-tier annotation system categorizes queries through hierarchical taxonomies encompassing medical imaging modalities (42 categories), body anatomies (125 structures), and clinical specialties (31 departments), enabling nuanced analysis across medical subdomains. We evaluate a wide array of MLLMs, including proprietary, open-sourced, medical, and reasoning models, revealing significant performance disparities across task types and model categories. Our findings highlight critical capability gaps in current GMAI systems while establishing textbook-derived multimodal benchmarks as essential evaluation tools. MedBookVQA establishes textbook-derived benchmarking as a critical paradigm for advancing clinical AI, exposing limitations in GMAI systems while providing anatomically structured performance metrics across specialties.

Acute ischemic stroke (AIS) is a major cause of mortality and morbidity, with hemorrhagic transformation (HT) as a severe complication. Accurate prediction of HT is essential for optimizing treatment strategies. This review assesses the accuracy and utility of deep learning (DL) and radiomics in predicting HT through imaging, regarding clinical decision-making for AIS patients. A literature search was conducted across five databases (Pubmed, Scopus, Web of Science, Embase, IEEE) up to January 23, 2025. Studies involving DL or radiomics-based ML models for predicting HT in AIS patients were included. Data from training, validation, and clinical-combined models were extracted and analyzed separately. Pooled sensitivity, specificity, and AUC were calculated with a random-effects bivariate model. For the quality assessment of studies, the Methodological Radiomics Score (METRICS) and QUADAS-2 tool were used. 16 studies consisting of 3,083 individual participants were included in the meta-analysis. The pooled AUC for training cohorts was 0.87, sensitivity 0.80, and specificity 0.85. For validation cohorts, AUC was 0.87, sensitivity 0.81, and specificity 0.86. Clinical-combined models showed an AUC of 0.93, sensitivity 0.84, and specificity 0.89. Moderate to severe heterogeneity was noted and addressed. Deep-learning models outperformed radiomics models, while clinical-combined models outperformed deep learning-only and radiomics-only models. The average METRICS score was 62.85%. No publication bias was detected. DL and radiomics models showed great potential in predicting HT in AIS patients. However, addressing methodological issues-such as inconsistent reference standards and limited external validation-is essential for the clinical implementation of these models.

Effective intervention for mild cognitive impairment (MCI) is key for preventing dementia. As a neuroprotective agent, butylphthalide has the potential to treat MCI due to Alzheimer disease (AD). However, the pharmacological mechanism of butylphthalide from the brain network perspective is not clear. Therefore, we aimed to investigate the multimodal brain network changes associated with butylphthalide treatment in MCI due to AD. A total of 270 patients with MCI due to AD received either butylphthalide or placebo at a ratio of 1:1 for 1 year. Effective treatment was defined as a decrease in the Alzheimer's Disease Assessment Scale-Cognitive Subscale (ADAS-cog) > 2.5. Brain networks were constructed using T1-magnetic resonance imaging and fluorodeoxyglucose positron emission tomography. A support vector machine was applied to develop predictive models. Both treatment (drug vs. placebo)-time interactions and efficacy (effective vs. ineffective)-time interactions were detected on some overlapping structural network metrics. Simple effects analyses revealed a significantly increased global efficiency in the structural network under both treatment and effective treatment of butylphthalide. Among the overlapping metrics, an increased degree centrality of left paracentral lobule was significantly related to poorer cognitive improvement. The predictive model based on baseline multimodal network metrics exhibited high accuracy (88.93%) of predicting butylphthalide's efficacy. Butylphthalide may restore abnormal organization in structural networks of patients with MCI due to AD, and baseline network metrics could be predictive markers for therapeutic efficacy of butylphthalide. This study was registered in the Chinese Clinical Trial Registry (Registration Number: ChiCTR1800018362, Registration Date: 2018-09-13).

The precise prediction of response to neoadjuvant chemoradiotherapy is crucial for tailoring perioperative treatment in patients diagnosed with locally advanced rectal cancer (LARC). This retrospective study aims to develop and validate a model that integrates deep learning and sub-regional radiomics from MRI imaging to predict pathological complete response (pCR) in patients with LARC. We retrospectively enrolled 768 eligible participants from three independent hospitals who had received neoadjuvant chemoradiotherapy followed by radical surgery. Pretreatment pelvic MRI scans (T2-weighted), were collected for annotation and feature extraction. The K-means approach was used to segment the tumor into sub-regions. Radiomics and deep learning features were extracted by the Pyradiomics and 3D ResNet50, respectively. The predictive models were developed using the radiomics, sub-regional radiomics, and deep learning features with the machine learning algorithm in training cohort, and then validated in the external tests. The models' performance was assessed using various metrics, including the area under the curve (AUC), decision curve analysis, Kaplan-Meier survival analysis. We constructed a combined model, named SRADL, which includes deep learning with sub-regional radiomics signatures, enabling precise prediction of pCR in LARC patients. SRADL had satisfactory performance for the prediction of pCR in the training cohort (AUC 0.925 [95% CI 0.894 to 0.948]), and in test 1 (AUC 0.915 [95% CI 0.869 to 0.949]) and in test 2 (AUC 0.902 [95% CI 0.846 to 0.945]). By employing optimal threshold of 0.486, the predicted pCR group had longer survival compared to predicted non-pCR group across three cohorts. SRADL also outperformed other single-modality prediction models. The novel SRADL, which integrates deep learning with sub-regional signatures, showed high accuracy and robustness in predicting pCR to neoadjuvant chemoradiotherapy using pretreatment MRI images, making it a promising tool for the personalized management of LARC.

Photon Counting CT (PCCT) offers advanced imaging capabilities with potential for substantial radiation dose reduction; however, achieving this without compromising image quality remains a challenge due to increased noise at lower doses. This study aims to evaluate the effectiveness of a deep learning (DL)-based denoising algorithm in maintaining diagnostic image quality in whole-body PCCT imaging at reduced radiation levels, using real intraindividual cadaveric scans. Twenty-four cadaveric human bodies underwent whole-body CT scans on a PCCT scanner (NAEOTOM Alpha, Siemens Healthineers) at four different dose levels (100%, 50%, 25%, and 10% mAs). Each scan was reconstructed using both QIR level 2 and a DL algorithm (ClariCT.AI, ClariPi Inc.), resulting in 192 datasets. Objective image quality was assessed by measuring CT value stability, image noise, and contrast-to-noise ratio (CNR) across consistent regions of interest (ROIs) in the liver parenchyma. Two radiologists independently evaluated subjective image quality based on overall image clarity, sharpness, and contrast. Inter-rater agreement was determined using Spearman's correlation coefficient, and statistical analysis included mixed-effects modeling to assess objective and subjective image quality. Objective analysis showed that the DL denoising algorithm did not significantly alter CT values (p ≥ 0.9975). Noise levels were consistently lower in denoised datasets compared to the Original (p < 0.0001). No significant differences were observed between the 25% mAs denoised and the 100% mAs original datasets in terms of noise and CNR (p ≥ 0.7870). Subjective analysis revealed strong inter-rater agreement (r ≥ 0.78), with the 50% mAs denoised datasets rated superior to the 100% mAs original datasets (p < 0.0001) and no significant differences detected between the 25% mAs denoised and 100% mAs original datasets (p ≥ 0.9436). The DL denoising algorithm maintains image quality in PCCT imaging while enabling up to a 75% reduction in radiation dose. This approach offers a promising method for reducing radiation exposure in clinical PCCT without compromising diagnostic quality.

This study assesses the image quality of temporal bone ultra-high-resolution (UHR) Computed tomography (CT) scans in adults and children using hybrid iterative reconstruction (HIR) and a novel, vendor-specific deep learning-based reconstruction (DLR) algorithm called AiCE Inner Ear. In a retrospective, single-center study (February 1-July 30, 2023), UHR-CT scans of 57 temporal bones of 35 patients (5 children, 23 male) with at least one anatomical unremarkable temporal bone were included. There is an adult computed tomography dose index volume (CTDIvol 25.6 mGy) and a pediatric protocol (15.3 mGy). Images were reconstructed using HIR at normal resolution (0.5-mm slice thickness, 512² matrix) and UHR (0.25-mm, 1024² and 2048² matrix) as well as with a vendor-specific DLR advanced intelligent clear-IQ engine inner ear (AiCE Inner Ear) at UHR (0.25-mm, 1024² matrix). Three radiologists evaluated 18 anatomic structures using a 5-point Likert scale. Signal-to-noise (SNR) and contrast-to-noise ratio (CNR) were measured automatically. In the adult protocol subgroup (n=30; median age: 51 [11-89]; 19 men) and the pediatric protocol subgroup (n=5; median age: 2 [1-3]; 4 men), UHR-CT with DLR significantly improved subjective image quality (p<0.024), reduced noise (p<0.001), and increased CNR and SNR (p<0.001). DLR also enhanced visualization of key structures, including the tendon of the stapedius muscle (p<0.001), tympanic membrane (p<0.009), and basal aspect of the osseous spiral lamina (p<0.018). Vendor-specific DLR-enhanced UHR-CT significantly improves temporal bone image quality and diagnostic performance.

Coronary artery disease (CAD) is a major worldwide health concern, contributing significantly to the global burden of cardiovascular diseases (CVDs). According to the 2023 World Health Organization (WHO) report, CVDs account for approximately 17.9 million deaths annually. This emphasizies the need for advanced diagnostic tools such as coronary computed tomography angiography (CCTA). The incorporation of deep learning (DL) technologies could significantly improve CCTA analysis by automating the quantification of plaque and stenosis, thus enhancing the precision of cardiac risk assessments. A recent meta-analysis highlights the evolving role of CCTA in patient management, showing that CCTA-guided diagnosis and management reduced adverse cardiac events and improved event-free survival in patients with stable and acute coronary syndromes. An extensive literature search was carried out across various electronic databases, such as MEDLINE, Embase, and the Cochrane Library. This search utilized a specific strategy that included both Medical Subject Headings (MeSH) terms and pertinent keywords. The review adhered to PRISMA guidelines and focused on studies published between 2019 and 2024 that employed deep learning (DL) for coronary computed tomography angiography (CCTA) in patients aged 18 years or older. After implementing specific inclusion and exclusion criteria, a total of 10 articles were selected for systematic evaluation regarding quality and bias. This systematic review included a total of 10 studies, demonstrating the high diagnostic performance and predictive capabilities of various deep learning models compared to different imaging modalities. This analysis highlights the effectiveness of these models in enhancing diagnostic accuracy in imaging techniques. Notably, strong correlations were observed between DL-derived measurements and intravascular ultrasound findings, enhancing clinical decision-making and risk stratification for CAD. Deep learning-enabled CCTA represents a promising advancement in the quantification of coronary plaques and stenosis, facilitating improved cardiac risk prediction and enhancing clinical workflow efficiency. Despite variability in study designs and potential biases, the findings support the integration of DL technologies into routine clinical practice for better patient outcomes in CAD management.

To evaluate a Compressed Sense Artificial Intelligence framework (CSAI) incorporating parallel imaging, compressed sense (CS), and deep learning for high-resolution MRI of the hip, comparing it with standard-resolution CS imaging. Thirty-two patients with femoroacetabular impingement syndrome underwent 3 T MRI scans. Coronal and sagittal intermediate-weighted TSE sequences with fat saturation were acquired using CS (0.6 ×0.8 mm resolution) and CSAI (0.3 ×0.4 mm resolution) protocols in comparable acquisition times (7:49 vs. 8:07 minutes for both planes). Two readers systematically assessed the depiction of the acetabular and femoral cartilage (in five cartilage zones), labrum, ligamentum capitis femoris, and bone using a five-point Likert scale. Diagnostic confidence and abnormality detection were recorded and analyzed using the Wilcoxon signed-rank test. CSAI significantly improved the cartilage depiction across most cartilage zones compared to CS. Overall Likert scores were 4.0 ± 0.2 (CS) vs 4.2 ± 0.6 (CSAI) for reader 1 and 4.0 ± 0.2 (CS) vs 4.3 ± 0.6 (CSAI) for reader 2 (p ≤ 0.001). Diagnostic confidence increased from 3.5 ± 0.7 and 3.9 ± 0.6 (CS) to 4.0 ± 0.6 and 4.1 ± 0.7 (CSAI) for readers 1 and 2, respectively (p ≤ 0.001). More cartilage lesions were detected with CSAI, with significant improvements in diagnostic confidence in certain cartilage zones such as femoral zone C and D for both readers. Labrum and ligamentum capitis femoris depiction remained similar, while bone depiction was rated lower. No abnormalities detected in CS were missed in CSAI. CSAI provides high-resolution hip MR images with enhanced cartilage depiction without extending acquisition times, potentially enabling more precise hip cartilage assessment.

In Computed Tomography (CT) imaging, the ring artifacts caused by the inconsistent detector response can significantly degrade the reconstructed images, having negative impacts on the subsequent applications. The new generation of CT systems based on photon-counting detectors are affected by ring artifacts more severely. The flexibility and variety of detector responses make it difficult to build a well-defined model to characterize the ring artifacts. In this context, this study proposes the global dependency-enhanced dual-domain parallel neural network for Ring Artifact Removal (RAR). First, based on the fact that the features of ring artifacts are different in Cartesian and Polar coordinates, the parallel architecture is adopted to construct the deep neural network so that it can extract and exploit the latent features from different domains to improve the performance of ring artifact removal. Besides, the ring artifacts are globally relevant whether in Cartesian or Polar coordinate systems, but convolutional neural networks show inherent shortcomings in modeling long-range dependency. To tackle this problem, this study introduces the novel Mamba mechanism to achieve a global receptive field without incurring high computational complexity. It enables effective capture of the long-range dependency, thereby enhancing the model performance in image restoration and artifact reduction. The experiments on the simulated data validate the effectiveness of the dual-domain parallel neural network and the Mamba mechanism, and the results on two unseen real datasets demonstrate the promising performance of the proposed RAR algorithm in eliminating ring artifacts and recovering image details.