This paper presents a rapid and robust approach for 3D volumetric segmentation, labelling, and registration of human spinal vertebrae from CT scans using an optimised and improved 3D U-Net neural network architecture. The network is designed by incorporating residual and dense interconnections, followed by an extensive evaluation of different network setups by optimising the network components like activation functions, optimisers, and pooling operations. In addition, the network architecture is optimised for varying numbers of convolution layers per block and U-Net levels with fixed and cascading numbers of filters. For 3D virtual reality visualisation, the segmentation output of the improved 3D U-Net network is registered with the original scans through a corner point registration process. The registration takes into account the spatial coordinates of each segmented vertebra as a 3D volume and eight virtual fiducial markers to ensure alignment in all rotational planes. Trained on the VerSe'20 dataset, the proposed pipeline achieves a Dice score coefficient of 92.38% for vertebrae instance segmentation and a Hausdorff distance of 5.26 mm for vertebrae localisation on the VerSe'20 public test dataset, which outperforms many existing methods that participated in the VerSe'20 challenge. Integrated with Singular Health's MedVR software for virtual reality visualisation, the proposed solution has been deployed on standard edge-computing hardware in medical institutions. Depending on the scan size, the deployed solution takes between 90 and 210 s to label and segment vertebrae, including the cervical vertebrae. It is hoped that the acceleration of the segmentation and registration process will facilitate the easier preparation of future training datasets and benefit pre-surgical visualisation and planning.

The aim of this study is to validate the effectiveness of an AI tool trained on Indian data in a Dutch medical center and to assess its ability to classify and localize fractures. Conventional radiographs acquired between January 2019 and November 2022 were analyzed using a multitask deep neural network. The tool, trained on Indian data, identified and localized fractures in 17 body parts. The reference standard was based on radiology reports resulting from routine clinical workflow and confirmed by an experienced musculoskeletal radiologist. The analysis included both patient-wise and fracture-wise evaluations, employing binary and Intersection over Union (IoU) metrics to assess fracture detection and localization accuracy. In total, 14,311 radiographs (median age, 48 years (range 18-98), 7265 male) were analyzed and categorized by body parts; clavicle, shoulder, humerus, elbow, forearm, wrist, hand and finger, pelvis, hip, femur, knee, lower leg, ankle, foot and toe. 4156/14,311 (29%) had fractures. The AI tool demonstrated overall patient-wise sensitivity, specificity, and AUC of 87.1% (95% CI: 86.1-88.1%), 87.1% (95% CI: 86.4-87.7%), and 0.92 (95% CI: 0.91-0.93), respectively. Fracture detection rate was 60% overall, ranging from 7% for rib fractures to 90% for clavicle fractures. This study validates a fracture detection AI tool on a Western-European dataset, originally trained on Indian data. While classification performance is robust on real clinical data, fracture-wise analysis reveals variability in localization accuracy, underscoring the need for refinement in fracture localization. AI may provide help by enabling optimal use of limited resources or personnel. This study evaluates an AI tool designed to aid in detecting fractures, possibly reducing reading time or optimization of radiology workflow by prioritizing fracture-positive cases. Cross-validation on a consecutive Dutch cohort confirms this AI tool's clinical robustness. The tool detected fractures with 87% sensitivity, 87% specificity, and 0.92 AUC. AI localizes 60% of fractures, the highest for clavicle (90%) and lowest for ribs (7%).

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.

To determine the accuracy of automatic Cobb angle measurements by deep learning (DL) on full spine radiographs. Full spine radiographs of patients aged > 2 years were screened using the radiology reports to identify radiographs for performing Cobb angle measurements. Two senior musculoskeletal radiologists and one senior orthopedic surgeon independently annotated Cobb angles exceeding 7° indicating the angle location as either proximal thoracic (apices between T3 and T5), main thoracic (apices between T6 and T11), or thoraco-lumbar (apices between T12 and L4). If at least two readers agreed on the number of angles, location of the angles, and difference between comparable angles was < 8°, then the ground truth was defined as the mean of their measurements. Otherwise, the radiographs were reviewed by the three annotators in consensus. The DL software (BoneMetrics, Gleamer) was evaluated against the manual annotation in terms of mean absolute error (MAE). A total of 345 patients were included in the study (age 33 ± 24 years, 221 women): 179 pediatric patients (< 22 years old) and 166 adult patients (22 to 85 years old). Fifty-three cases were reviewed in consensus. The MAE of the DL algorithm for the main curvature was 2.6° (95% CI [2.0; 3.3]). For the subgroup of pediatric patients, the MAE was 1.9° (95% CI [1.6; 2.2]) versus 3.3° (95% CI [2.2; 4.8]) for adults. The DL algorithm predicted the Cobb angle of scoliotic patients with high accuracy.

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.

Knee kinematics during daily activities reflect disease severity preoperatively and are associated with clinical outcomes after total knee arthroplasty (TKA). It is widely believed that measured kinematics would be useful for preoperative planning and postoperative assessment. Despite decades-long interest in measuring three-dimensional (3D) knee kinematics, no methods are available for routine, practical clinical examinations. We report a clinically practical method utilizing machine-learning-enhanced software and upgraded C-arm fluoroscopy for the accurate and time-efficient measurement of pre-TKA and post-TKA 3D dynamic knee kinematics. Using a common C-arm with an upgraded detector and software, we performed an 8-s horizontal sweeping pulsed fluoroscopic scan of the weight-bearing knee joint. The patient's knee was then imaged using pulsed C-arm fluoroscopy while performing standing, kneeling, squatting, stair, chair, and gait motion activities. We used limited-arc cone-beam reconstruction methods to create 3D models of the femur and tibia/fibula bones with implants, which can then be used to perform model-image registration to quantify the 3D knee kinematics. The proposed protocol can be accomplished by an individual radiology technician in ten minutes and does not require additional equipment beyond a step and stool. The image analysis can be performed by a computer onboard the upgraded c-arm or in the cloud, before loading the examination results into the Picture Archiving and Communication System and Electronic Medical Record systems. Weight-bearing kinematics affects knee function pre- and post-TKA. It has long been exclusively the domain of researchers to make such measurements. We present an approach that leverages common, but digitally upgraded, imaging hardware and software to implement an efficient examination protocol for accurately assessing 3D knee kinematics. With these capabilities, it will be possible to include dynamic 3D knee kinematics as a component of the routine clinical workup for patients who have diseased or replaced knees.

To assess the performance of a newly introduced deep learning-based reconstruction algorithm, namely the artificial intelligence iterative reconstruction (AIIR), in reducing the dose of pediatric chest CT by using the image data of below 3-year-old patients with congenital heart disease (CHD). The lung image available from routine-dose cardiac CT angiography (CTA) on below 3 years patients with CHD was employed as a reference for evaluating the paired low-dose chest CT. A total of 191 subjects were prospectively enrolled, where the dose for chest CT was reduced to ~0.1 mSv while the cardiac CTA protocol was kept unchanged. The low-dose chest CT images, obtained with the AIIR and the hybrid iterative reconstruction (HIR), were compared in image quality, ie, overall image quality and lung structure depiction, and in diagnostic performance, ie, severity assessment of pneumonia and airway stenosis. Compared with the reference, lung image quality was not found significantly different on low-dose AIIR images (all P >0.05) but obviously inferior with the HIR (all P <0.05). Compared with the HIR, low-dose AIIR images also achieved a closer pneumonia severity index (AIIR 4.32±3.82 vs. Ref 4.37±3.84, P >0.05; HIR 5.12±4.06 vs. Ref 4.37±3.84, P <0.05) and airway stenosis grading (consistently graded: AIIR 88.5% vs. HIR 56.5% ) to the reference. AIIR has the potential for large dose reduction in chest CT of patients below 3 years of age while preserving image quality and achieving diagnostic results nearly equivalent to routine dose scans.

Widely used in oncology PET, 2-deoxy-2-18F-FDG PET is more accessible and affordable than amyloid PET, which is a crucial tool to determine amyloid positivity in diagnosis of Alzheimer disease (AD). This study aimed to leverage deep learning with residual 3D convolutional neural networks (3DCNN) to develop a robust model that predicts amyloid-β positivity by using FDG-PET. In this study, a cohort of 187 patients was used for model development. It consisted of patients ranging from cognitively normal to those with dementia and other cognitive impairments who underwent T1-weighted MRI, 18F-FDG, and 11C-Pittsburgh compound B (PiB) PET scans. A residual 3DCNN model was configured using nonexhaustive grid search and trained on repeated random splits of our development data set. We evaluated the performance of our model, and particularly its robustness, using a multisite data set of 99 patients of different ethnicities with images at different site harmonization levels. Our model achieved mean AUC scores of 0.815 and 0.840 on images without and with site harmonization correspondingly. Respectively, it achieved higher AUC scores of 0.801 and 0.834 in the cognitively normal (CN) group compared with 0.777 and 0.745 in the dementia group. As for F1 score, the corresponding mean scores were 0.770 and 0.810 on images without and with site harmonization. In the CN group, it achieved lower F1 scores of 0.580 and 0.658 compared with 0.907 and 0.931 in the dementia group. We demonstrated that residual 3DCNN can learn complex 3D spatial patterns in FDG-PET images and robustly predict amyloid-β positivity with significantly less reliance on site harmonization preprocessing.

The new artificial intelligence-based software, Roadmap (HeartFlow), may assist in evaluating coronary artery stenosis during cardiac computed tomography (CT) for transcatheter aortic valve replacement (TAVR). Consecutive TAVR candidates who underwent both cardiac CT angiography (CTA) and invasive coronary angiography were enrolled. We evaluated the ability of three methods to predict obstructive coronary artery disease (CAD), defined as ≥50 ​% stenosis on quantitative coronary angiography (QCA), and the need for percutaneous coronary intervention (PCI) within one year: Roadmap, clinician CT specialists with Roadmap, and CT specialists alone. The area under the curve (AUC) for predicting QCA ≥50 ​% stenosis was similar for CT specialists with or without Roadmap (0.93 [0.85-0.97] vs. 0.94 [0.88-0.98], p ​= ​0.82), both significantly higher than Roadmap alone (all p ​< ​0.05). For PCI prediction, no significant differences were found between QCA and CT specialists, with or without Roadmap, while Roadmap's AUC was lower (all p ​< ​0.05). The negative predictive value (NPV) of CT specialists with Roadmap for ≥50 ​% stenosis was 97 ​%, and for PCI prediction, the NPV was comparable to QCA (p ​= ​1.00). In contrast, the positive predictive value (PPV) of Roadmap alone for ≥50 ​% stenosis was 49 ​%, the lowest among all approaches, with a similar trend observed for PCI prediction. While Roadmap alone is insufficient for clinical decision-making due to low PPV, Roadmap may serve as a "second observer", providing a supportive tool for CT specialists by flagging lesions for careful review, thereby enhancing workflow efficiency and maintaining high diagnostic accuracy with excellent NPV.

BackgroundGadolinium-based Contrast Agents (GBCAs) are used in brain MRI exams to improve the visualization of pathology and improve the delineation of lesions. Higher doses of GBCAs can improve lesion sensitivity but involve substantial deviation from standard-of-care procedures and may have safety implications, particularly in the light of recent findings on gadolinium retention and deposition. PurposeTo evaluate the clinical performance of an FDA cleared deep-learning (DL) based contrast boosting algorithm in routine clinical brain MRI exams. MethodsA multi-center retrospective database of contrast-enhanced brain MRI images (obtained from April 2017 to December 2023) was used to evaluate a DL-based contrast boosting algorithm. Pre-contrast and standard post-contrast (SC) images were processed with the algorithm to obtain contrast boosted (CB) images. Quantitative performance of CB images in comparison to SC images was compared using contrast-to-noise ratio (CNR), lesion-to-brain ratio (LBR) and contrast enhancement percentage (CEP). Three board-certified radiologists reviewed CB and SC images side-by-side for qualitative evaluation and rated them on a 4-point Likert scale for lesion contrast enhancement, border delineation, internal morphology, overall image quality, presence of artefacts, and changes in vessel conspicuity. The presence, cause, and severity of any false lesions was recorded. CB results were compared to SC using Wilcoxon signed rank test for statistical significance. ResultsBrain MRI images from 110 patients (47 {+/-} 22 years; 52 Females, 47 Males, 11 N/A) were evaluated. CB images had superior quantitative performance than SC images in terms of CNR (+634%), LBR (+70%) and CEP (+150%). In the qualitative assessment CB images showed better lesion visualization (3.73 vs 3.16) and had better image quality (3.55 vs 3.07). Readers were able to rule out all false lesions on CB by using SC for comparison. ConclusionsDeep learning based contrast boosting improves lesion visualization and image quality without increasing contrast dosage. Key ResultsO_LIIn a retrospective study of 110 patients, deep-learning based contrast boosted (CB) images showed better lesion visualization than standard post-contrast (SC) brain MRI images (3.73 vs 3.16; mean reader scores [4-point Likert scale]) C_LIO_LICB images had better overall image quality than SC images (3.55 vs 3.07) C_LIO_LIContrast-to-noise ratio, Lesion-to-brain Ratio and Contrast Enhancement Percentage for CB images were significantly higher than SC images (+729%, +88% and +165%; p < 0.001) C_LI Summary StatementDeep-learning based contrast boosting achieves better lesion visualization and overall image quality and provides more contrast information, without increasing the contrast dosage in contrast-enhanced brain MR protocols.