Convolutional neural networks (CNNs) have been studied for detecting bone metastases on bone scans; however, the application of ConvNeXt and transformer models has not yet been explored. This study aims to evaluate the performance of various deep learning models, including the ConvNeXt and transformer models, in diagnosing metastatic lesions from bone scans. We retrospectively analyzed bone scans from patients with cancer obtained at 2 institutions: the training and validation sets (n=4626) were from Hospital 1 and the test set (n=1428) was from Hospital 2. The deep learning models evaluated included ResNet18, the Data-Efficient Image Transformer (DeiT), the Vision Transformer (ViT Large 16), the Swin Transformer (Swin Base), and ConvNeXt Large. Gradient-weighted class activation mapping (Grad-CAM) was used for visualization. Both the validation set and the test set demonstrated that the ConvNeXt large model (0.969 and 0.885, respectively) exhibited the best performance, followed by the Swin Base model (0.965 and 0.840, respectively), both of which significantly outperformed ResNet (0.892 and 0.725, respectively). Subgroup analyses revealed that all the models demonstrated greater diagnostic accuracy for patients with polymetastasis compared with those with oligometastasis. Grad-CAM visualization revealed that the ConvNeXt Large model focused more on identifying local lesions, whereas the Swin Base model focused on global areas such as the axial skeleton and pelvis. Compared with traditional CNN and transformer models, the ConvNeXt model demonstrated superior diagnostic performance in detecting bone metastases from bone scans, especially in cases of polymetastasis, suggesting its potential in medical image analysis.

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.

In this paper, we introduce the Visual Query-based task of Video Clip Localization (VQ-VCL) for medical video understanding. Specifically, we aim to retrieve a video clip containing frames similar to a given exemplar frame from a given input video. To solve the task, we propose a novel visual query-based video clip localization model called TIER-LOC. TIER-LOC is designed to improve video clip retrieval, especially in fine-grained videos by extracting features from different levels, i.e., coarse to fine-grained, referred to as TIERS. The aim is to utilize multi-Tier features for detecting subtle differences, and adapting to scale or resolution variations, leading to improved video-clip retrieval. TIER-LOC has three main components: (1) a Multi-Tier Spatio-Temporal Transformer to fuse spatio-temporal features extracted from multiple Tiers of video frames with features from multiple Tiers of the visual query enabling better video understanding. (2) a Multi-Tier, Dual Anchor Contrastive Loss to deal with real-world annotation noise which can be notable at event boundaries and in videos featuring highly similar objects. (3) a Temporal Uncertainty-Aware Localization Loss designed to reduce the model sensitivity to imprecise event boundary. This is achieved by relaxing hard boundary constraints thus allowing the model to learn underlying class patterns and not be influenced by individual noisy samples. To demonstrate the efficacy of TIER-LOC, we evaluate it on two ultrasound video datasets and an open-source egocentric video dataset. First, we develop a sonographer workflow assistive task model to detect standard-frame clips in fetal ultrasound heart sweeps. Second, we assess our model's performance in retrieving standard-frame clips for detecting fetal anomalies in routine ultrasound scans, using the large-scale PULSE dataset. Lastly, we test our model's performance on an open-source computer vision video dataset by creating a VQ-VCL fine-grained video dataset based on the Ego4D dataset. Our model outperforms the best-performing state-of-the-art model by 7%, 4%, and 4% on the three video datasets, respectively.

This study aims to develop and validate an artificial intelligence (AI) model based on ultrasound (US) videos and images to improve the performance of junior sonologists in detecting deep infiltrating endometriosis (DE). In this retrospective study, data were collected from female patients who underwent US examinations and had DE. The US image records were divided into two parts. First, during the model development phase, an AI-DE model was trained employing YOLOv8 to detect pelvic DE nodules. Subsequently, its clinical applicability was evaluated by comparing the diagnostic performance of junior sonologists with and without AI-model assistance. The AI-DE model was trained using 248 images, which demonstrated high performance, with a mAP50 (mean Average Precision at IoU threshold 0.5) of 0.9779 on the test set. Total 147 images were used for evaluate the diagnostic performance. The diagnostic performance of junior sonologists improved with the assistance of the AI-DE model. The area under the receiver operating characteristic (AUROC) curve improved from 0.748 (95% CI, 0.624-0.867) to 0.878 (95% CI, 0.792-0.964; p < 0.0001) for junior sonologist A, and from 0.713 (95% CI, 0.592-0.835) to 0.798 (95% CI, 0.677-0.919; p < 0.0001) for junior sonologist B. Notably, the sensitivity of both sonologists increased significantly, with the largest increase from 77.42% to 94.35%. The AI-DE model based on US images showed good performance in DE detection and significantly improved the diagnostic performance of junior sonologists.

Unsupervised anomaly detection (UAD) is crucial in low-dose computed tomography (LDCT). Recent AI technologies, leveraging global features, have enabled effective UAD with minimal training data of normal patients. However, this approach, devoid of utilizing local features, exhibits vulnerability in detecting deep lesions within the lungs. In other words, while the conventional use of global features can achieve high specificity, it often comes with limited sensitivity. Developing a UAD AI model with high sensitivity is essential to prevent false negatives, especially in screening patients with diseases demonstrating high mortality rates. We have successfully pioneered a new LDCT UAD AI model that leverages local features, achieving a previously unattainable increase in sensitivity compared to global methods (17.5% improvement). Furthermore, by integrating this approach with conventional global-based techniques, we have successfully consolidated the advantages of each model - high sensitivity from the local model and high specificity from the global model - into a single, unified, trained model (17.6% and 33.5% improvement, respectively). Without the need for additional training, we anticipate achieving significant diagnostic efficacy in various LDCT applications, where both high sensitivity and specificity are essential, using our fixed model. Code is available at https://github.com/kskim-phd/Fusion-UADL.

To assess the added value of artificial intelligence (AI) for radiologists and emergency physicians in the radiographic detection of pelvic fractures. In this retrospective study, one junior radiologist reviewed 940 X-rays of patients admitted to emergency for a fall with suspicion of pelvic fracture between March 2020 and June 2021. The radiologist analyzed the X-rays alone and then using an AI system (BoneView). In a random sample of 100 exams, the same procedure was repeated alongside five other readers (three radiologists and two emergency physicians with 3-30 years of experience). The reference diagnosis was based on the patient's full set of medical imaging exams and medical records in the months following emergency admission. A total of 633 confirmed pelvic fractures (64.8% from hip and 35.2% from pelvic ring) in 940 patients and 68 pelvic fractures (60% from hip and 40% from pelvic ring) in the 100-patient sample were included. In the whole dataset, the junior radiologist achieved a significant sensitivity improvement with AI assistance (Se_-PELVIC = 77.25% to 83.73%; p < 0.001, Se_-HIP 93.24 to 96.49%; p < 0.001 and Se_{-PELVIC RING} 54.60% to 64.50%; p < 0.001). However, there was a significant decrease in specificity with AI assistance (Spe_-PELVIC = 95.24% to 93.25%; p = 0.005 and Spe_-HIP = 98.30% to 96.90%; p = 0.005). In the 100-patient sample, the two emergency physicians obtained an improvement in fracture detection sensitivity across the pelvic area + 14.70% (p = 0.0011) and + 10.29% (p < 0.007) respectively without a significant decrease in specificity. For hip fractures, E1's sensitivity increased from 59.46% to 70.27% (p = 0.04), and E2's sensitivity increased from 78.38% to 86.49% (p = 0.08). For pelvic ring fractures, E1's sensitivity increased from 12.90% to 32.26% (p = 0.012), and E2's sensitivity increased from 19.35% to 32.26% (p = 0.043). AI improved the diagnostic performance for emergency physicians and radiologists with limited experience in pelvic fracture screening.

Embolic protection devices (EPDs) used during carotid artery stenting (CAS) are crucial in reducing ischemic complications. Although minimizing the filter-type EPD movement is considered important, limited research has demonstrated this practice. We used an artificial intelligence (AI)-based device recognition technology to investigate the correlation between filter movements and ischemic complications. We retrospectively studied 28 consecutive patients who underwent CAS using FilterWire EZ (Boston Scientific, Marlborough, MA, USA) from April 2022 to September 2023. Clinical data, procedural videos, and postoperative magnetic resonance imaging were collected. An AI-based device detection function in the Neuro-Vascular Assist (iMed Technologies, Tokyo, Japan) was used to quantify the filter movement. Multivariate proportional odds model analysis was performed to explore the correlations between postoperative diffusion-weighted imaging (DWI) hyperintense lesions and potential ischemic risk factors, including filter movement. In total, 23 patients had sufficient information and were eligible for quantitative analysis. Fourteen patients (60.9 %) showed postoperative DWI hyperintense lesions. Multivariate analysis revealed significant associations between filter movement distance (odds ratio, 1.01; 95 % confidence interval, 1.00-1.02; p = 0.003) and high-intensity signals in time-of-flight magnetic resonance angiography with DWI hyperintense lesions. Age, symptomatic status, and operative time were not significantly correlated. Increased filter movement during CAS was correlated with a higher incidence of postoperative DWI hyperintense lesions. AI-based quantitative evaluation of endovascular techniques may enable demonstration of previously unproven recommendations. To the best of our knowledge, this is the first study to use an AI system for quantitative evaluation to address real-world clinical issues.

The US healthcare system faces significant challenges, including clinician burnout, operational inefficiencies, and concerns about patient safety. Artificial intelligence (AI), particularly generative AI, has the potential to address these challenges, but its adoption, effectiveness, and barriers to implementation are not well understood. To evaluate the current state of AI adoption in US healthcare systems, assess successes and barriers to implementation during the early generative AI era. This cross-sectional survey was conducted in Fall 2024, and included 67 health systems members of the Scottsdale Institute, a collaborative of US non-profit healthcare organizations. Forty-three health systems completed the survey (64% response rate). Respondents provided data on the deployment status and perceived success of 37 AI use cases across 10 categories. The primary outcomes were the extent of AI use case development, piloting, or deployment, the degree of reported success for AI use cases, and the most significant barriers to adoption. Across the 43 responding health systems, AI adoption and perceptions of success varied significantly. Ambient Notes, a generative AI tool for clinical documentation, was the only use case with 100% of respondents reporting adoption activities, and 53% reported a high degree of success with using AI for Clinical Documentation. Imaging and radiology emerged as the most widely deployed clinical AI use case, with 90% of organizations reporting at least partial deployment, although successes with diagnostic use cases were limited. Similarly, many organizations have deployed AI for clinical risk stratification such as early sepsis detection, but only 38% report high success in this area. Immature AI tools were identified a significant barrier to adoption, cited by 77% of respondents, followed by financial concerns (47%) and regulatory uncertainty (40%). Ambient Notes is rapidly advancing in US healthcare systems and demonstrating early success. Other AI use cases show varying degrees of adoption and success, constrained by barriers such as immature AI tools, financial concerns, and regulatory uncertainty. Addressing these challenges through robust evaluations, shared strategies, and governance models will be essential to ensure effective integration and adoption of AI into healthcare practice.

We aimed to compare the diagnostic performance of physicians in the detection of arthroscopically confirmed meniscus and anterior cruciate ligament (ACL) tears on knee magnetic resonance imaging (MRI), with and without assistance from a deep learning (DL) model. We obtained preoperative MR images from 88 knees of patients who underwent arthroscopic meniscal repair, with or without ACL reconstruction. Ninety-eight MR images of knees without signs of meniscus or ACL tears were obtained from a publicly available database after matching on age and ACL status (normal or torn), resulting in a global dataset of 186 MRI examinations. The Keros^® (Incepto, Paris) DL algorithm, previously trained for the detection and characterization of meniscus and ACL tears, was used for MRI assessment. Magnetic resonance images were individually, and blindly annotated by three physicians and the DL algorithm. After three weeks, the three human raters repeated image assessment with model assistance, performed in a different order. The Keros^® algorithm achieved an area under the curve (AUC) of 0.96 (95% CI 0.93, 0.99), 0.91 (95% CI 0.85, 0.96), and 0.99 (95% CI 0.98, 0.997) in the detection of medial meniscus, lateral meniscus and ACL tears, respectively. With model assistance, physicians achieved higher sensitivity (91% vs. 83%, p = 0.04) and similar specificity (91% vs. 87%, p = 0.09) in the detection of medial meniscus tears. Regarding lateral meniscus tears, sensitivity and specificity were similar with/without model assistance. Regarding ACL tears, physicians achieved higher specificity when assisted by the algorithm (70% vs. 51%, p = 0.01) but similar sensitivity with/without model assistance (93% vs. 96%, p = 0.13). The current model consistently helped physicians in the detection of medial meniscus and ACL tears, notably when they were combined. Diagnostic study, Level III.

To evaluate the image quality and lung nodule detectability of ultralow-dose CT (ULDCT) with adaptive statistical iterative reconstruction-V (ASiR-V) post-processed using a deep learning image reconstruction (DLIR)-based image domain compared to low-dose CT (LDCT) and ULDCT without DLIR. A total of 210 patients undergoing lung cancer screening underwent LDCT (mean ± SD, 0.81 ± 0.28 mSv) and ULDCT (0.17 ± 0.03 mSv) scans. ULDCT images were reconstructed with ASiR-V (ULDCT-ASiR-V) and post-processed using DLIR (ULDCT-DLIR). The quality of the three CT images was analyzed. Three radiologists detected and measured pulmonary nodules on all CT images, with LDCT results serving as references. Nodule conspicuity was assessed using a five-point Likert scale, followed by further statistical analyses. A total of 463 nodules were detected using LDCT. The image noise of ULDCT-DLIR decreased by 60% compared to that of ULDCT-ASiR-V and was lower than that of LDCT (p < 0.001). The subjective image quality scores for ULDCT-DLIR (4.4 [4.1, 4.6]) were also higher than those for ULDCT-ASiR-V (3.6 [3.1, 3.9]) (p < 0.001). The overall nodule detection rates for ULDCT-ASiR-V and ULDCT-DLIR were 82.1% (380/463) and 87.0% (403/463), respectively (p < 0.001). The percentage difference between diameters > 1 mm was 2.9% (ULDCT-ASiR-V vs. LDCT) and 0.5% (ULDCT-DLIR vs. LDCT) (p = 0.009). Scores of nodule imaging sharpness on ULDCT-DLIR (4.0 ± 0.68) were significantly higher than those on ULDCT-ASiR-V (3.2 ± 0.50) (p < 0.001). DLIR-based image domain improves image quality, nodule detection rate, nodule imaging sharpness, and nodule measurement accuracy of ASiR-V on ULDCT. Question Deep learning post-processing is simple and cheap compared with raw data processing, but its performance is not clear on ultralow-dose CT. Findings Deep learning post-processing enhanced image quality and improved the nodule detection rate and accuracy of nodule measurement of ultralow-dose CT. Clinical relevance Deep learning post-processing improves the practicability of ultralow-dose CT and makes it possible for patients with less radiation exposure during lung cancer screening.