An unsupervised two-step training framework for low-dose computed tomography denoising.

BACKGROUND: Although low-dose computed tomography (CT) imaging has been more widely adopted in clinical practice to reduce radiation exposure to patients, the reconstructed CT images tend to have more noise, which impedes accurate diagnosis. Recently, deep neural networks using convolutional neural networks to reduce noise in the reconstructed low-dose CT images have shown considerable improvement. However, they need a large number of paired normal- and low-dose CT images to fully train the network via supervised learning methods. PURPOSE: To propose an unsupervised two-step training framework for image denoising that uses low-dose CT images of one dataset and unpaired high-dose CT images from another dataset. METHODS: Our proposed framework trains the denoising network in two steps. In the first training step, we train the network using 3D volumes of CT images and predict the center CT slice from them. This pre-trained network is used in the second training step to train the denoising network and is combined with the memory-efficient denoising generative adversarial network (DenoisingGAN), which further enhances both objective and perceptual quality. RESULTS: The experimental results on phantom and clinical datasets show superior performance over the existing traditional machine learning and self-supervised deep learning methods, and the results are comparable to the fully supervised learning methods. CONCLUSIONS: We proposed a new unsupervised learning framework for low-dose CT denoising, convincingly improving noisy CT images from both objective and perceptual quality perspectives. Because our denoising framework does not require physics-based noise models or system-dependent assumptions, our proposed method can be easily reproduced; consequently, it can also be generally applicable to various CT scanners or dose levels.

Advancing diabetes prediction with a progressive self-transfer learning framework for discrete time series data.

Although diabetes mellitus is a complex and pervasive disease, most studies to date have focused on individual features, rather than considering the complexities of multivariate, multi-instance, and time-series data. In this study, we developed a novel diabetes prediction model that incorporates these complex data types. We applied advanced techniques of data imputation (bidirectional recurrent imputation for time series; BRITS) and feature selection (the least absolute shrinkage and selection operator; LASSO). Additionally, we utilized self-supervised algorithms and transfer learning to address the common issues with medical datasets, such as irregular data collection and sparsity. We also proposed a novel approach for discrete time-series data preprocessing, utilizing both shifting and rolling time windows and modifying time resolution. Our study evaluated the performance of a progressive self-transfer network for predicting diabetes, which demonstrated a significant improvement in metrics compared to non-progressive and single self-transfer prediction tasks, particularly in AUC, recall, and F1 score. These findings suggest that the proposed approach can mitigate accumulated errors and reflect temporal information, making it an effective tool for accurate diagnosis and disease management. In summary, our study highlights the importance of considering the complexities of multivariate, multi-instance, and time-series data in diabetes prediction.

Annotation-Efficient Deep Learning Model for Pancreatic Cancer Diagnosis and Classification Using CT Images: A Retrospective Diagnostic Study.

The aim of this study was to develop a novel deep learning (DL) model without requiring large-annotated training datasets for detecting pancreatic cancer (PC) using computed tomography (CT) images. This retrospective diagnostic study was conducted using CT images collected from 2004 and 2019 from 4287 patients diagnosed with PC. We proposed a self-supervised learning algorithm (pseudo-lesion segmentation (PS)) for PC classification, which was trained with and without PS and validated on randomly divided training and validation sets. We further performed cross-racial external validation using open-access CT images from 361 patients. For internal validation, the accuracy and sensitivity for PC classification were 94.3% (92.8-95.4%) and 92.5% (90.0-94.4%), and 95.7% (94.5-96.7%) and 99.3 (98.4-99.7%) for the convolutional neural network (CNN) and transformer-based DL models (both with PS), respectively. Implementing PS on a small-sized training dataset (randomly sampled 10%) increased accuracy by 20.5% and sensitivity by 37.0%. For external validation, the accuracy and sensitivity were 82.5% (78.3-86.1%) and 81.7% (77.3-85.4%) and 87.8% (84.0-90.8%) and 86.5% (82.3-89.8%) for the CNN and transformer-based DL models (both with PS), respectively. PS self-supervised learning can increase DL-based PC classification performance, reliability, and robustness of the model for unseen, and even small, datasets. The proposed DL model is potentially useful for PC diagnosis.

A multi-kernel and multi-scale learning based deep ensemble model for predicting recurrence of non-small cell lung cancer.

Predicting recurrence in patients with non-small cell lung cancer (NSCLC) before treatment is vital for guiding personalized medicine. Deep learning techniques have revolutionized the application of cancer informatics, including lung cancer time-to-event prediction. Most existing convolutional neural network (CNN) models are based on a single two-dimensional (2D) computational tomography (CT) image or three-dimensional (3D) CT volume. However, studies have shown that using multi-scale input and fusing multiple networks provide promising performance. This study proposes a deep learning-based ensemble network for recurrence prediction using a dataset of 530 patients with NSCLC. This network assembles 2D CNN models of various input slices, scales, and convolutional kernels, using a deep learning-based feature fusion model as an ensemble strategy. The proposed framework is uniquely designed to benefit from (i) multiple 2D in-plane slices to provide more information than a single central slice, (ii) multi-scale networks and multi-kernel networks to capture the local and peritumoral features, (iii) ensemble design to integrate features from various inputs and model architectures for final prediction. The ensemble of five 2D-CNN models, three slices, and two multi-kernel networks, using 5 × 5 and 6 × 6 convolutional kernels, achieved the best performance with an accuracy of 69.62%, area under the curve (AUC) of 72.5%, F1 score of 70.12%, and recall of 70.81%. Furthermore, the proposed method achieved competitive results compared with the 2D and 3D-CNN models for cancer outcome prediction in the benchmark studies. Our model is also a potential adjuvant treatment tool for identifying NSCLC patients with a high risk of recurrence.

Unsupervised Visual Representation Learning Based on Segmentation of Geometric Pseudo-Shapes for Transformer-Based Medical Tasks.

Recently, transformer-based architectures have been shown to outperform classic convolutional architectures and have rapidly been established as state-of-the-art models for many medical vision tasks. Their superior performance can be explained by their ability to capture long-range dependencies of their multi-head self-attention mechanism. However, they tend to overfit on small- or even medium-sized datasets because of their weak inductive bias. As a result, they require massive, labeled datasets, which are expensive to obtain, especially in the medical domain. This motivated us to explore unsupervised semantic feature learning without any form of annotation. In this work, we aimed to learn semantic features in a self-supervised manner by training transformer-based models to segment the numerical signals of geometric shapes inserted on original computed tomography (CT) images. Moreover, we developed a Convolutional Pyramid vision Transformer (CPT) that leverages multi-kernel convolutional patch embedding and local spatial reduction in each of its layer to generate multi-scale features, capture local information, and reduce computational cost. Using these approaches, we were able to noticeably outperformed state-of-the-art deep learning-based segmentation or classification models of liver cancer CT datasets of 5,237 patients, the pancreatic cancer CT datasets of 6,063 patients, and breast cancer MRI dataset of 127 patients.

Intra-person multi-task learning method for chronic-disease prediction.

In the medical field, various clinical information has been accumulated to help clinicians provide personalized medicine and make better diagnoses. As chronic diseases share similar characteristics, it is possible to predict multiple chronic diseases using the accumulated data of each patient. Thus, we propose an intra-person multi-task learning framework that jointly predicts the status of correlated chronic diseases and improves the model performance. Because chronic diseases occur over a long period and are affected by various factors, we considered features related to each chronic disease and the temporal relationship of the time-series data for accurate prediction. The study was carried out in three stages: (1) data preprocessing and feature selection using bidirectional recurrent imputation for time series (BRITS) and the least absolute shrinkage and selection operator (LASSO); (2) a convolutional neural network and long short-term memory (CNN-LSTM) for single-task models; and (3) a novel intra-person multi-task learning CNN-LSTM framework developed to predict multiple chronic diseases simultaneously. Our multi-task learning method between correlated chronic diseases produced a more stable and accurate system than single-task models and other baseline recurrent networks. Furthermore, the proposed model was tested using different time steps to illustrate its flexibility and generalization across multiple time steps.

Botulinum neurotoxin type A improves vasti muscle balance, patellar tracking, and pain in patients with chronic patellofemoral pain.

The purpose of this study was to determine the effects of botulinum neurotoxin type A (BoNT-A) on vastus lateralis:vastus medialis (VL:VM) muscle balance, patellar tracking, and pain in patients with chronic patellofemoral (PF) pain. We recruited 13 participants (9 females, 4 males) with recalcitrant PF pain who underwent ultrasound-guided BoNT-A injections into the distal third of the VL muscle, followed by a 6-week home exercise program to strengthen their VM muscle. We imaged the participants in a C-arm computed tomography (CT) scanner before and after the intervention. We calculated VL:VM ratios from CT images from a supine, nonweight-bearing condition. We obtained patellar tilt and bisect offset values from CT images from an upright, weight-bearing condition. We recorded functional pain scores before, immediately after, and 2-4 years after the intervention. We classified the participants into normal tracking and maltracking groups based on their patellar tilt and bisect offset values. BoNT-A with home exercise reduced VL:VM ratio (18%; p < 0.001), patellar tilt (19%; p = 0.020), and bisect offset (5%; p = 0.025). Four participants classified as maltrackers before the intervention transitioned to normal tracking after the intervention. Functional pain scores improved immediately after the intervention (13%, p < 0.001) and remained improved at 2-year follow-up (12%, p = 0.011). Statement of Clinical Significance: This study provides new evidence in support of BoNT-A for treatment of PF pain. Classification of patients under weight-bearing conditions may identify individuals who will most benefit from a BoNT-A treatment.

Acquisition of a single grid-based phase-contrast X-ray image using instantaneous frequency and noise filtering.

BACKGROUND: To obtain phase-contrast X-ray images, single-grid imaging systems are effective, but Moire artifacts remain a significant issue. The solution for removing Moire artifacts from an image is grid rotation, which can distinguish between these artifacts and sample information within the Fourier space. However, the mechanical movement of grid rotation is slower than the real-time change in Moire artifacts. Thus, Moire artifacts generated during real-time imaging cannot be removed using grid rotation. To overcome this problem, we propose an effective method to obtain phase-contrast X-ray images using instantaneous frequency and noise filtering. RESULT: The proposed phase-contrast X-ray image using instantaneous frequency and noise filtering effectively suppressed noise with Moire patterns. The proposed method also preserved the clear edge of the inner and outer boundaries and internal anatomical information from the biological sample, outperforming conventional Fourier analysis-based methods, including absorption, scattering, and phase-contrast X-ray images. In particular, when comparing the phase information for the proposed method with the x-axis gradient image from the absorption image, the proposed method correctly distinguished two different types of soft tissue and the detailed information, while the latter method did not. CONCLUSION: This study successfully achieved a significant improvement in image quality for phase-contrast X-ray images using instantaneous frequency and noise filtering. This study can provide a foundation for real-time bio-imaging research using three-dimensional computed tomography.

Wavelet subband-specific learning for low-dose computed tomography denoising.

Deep neural networks have shown great improvements in low-dose computed tomography (CT) denoising. Early algorithms were primarily optimized to obtain an accurate image with low distortion between the denoised image and reference full-dose image at the cost of yielding an overly smoothed unrealistic CT image. Recent research has sought to preserve the fine details of denoised images with high perceptual quality, which has been accompanied by a decrease in objective quality due to a trade-off between perceptual quality and distortion. We pursue a network that can generate accurate and realistic CT images with high objective and perceptual quality within one network, achieving a better perception-distortion trade-off. To achieve this goal, we propose a stationary wavelet transform-assisted network employing the characteristics of high- and low-frequency domains of the wavelet transform and frequency subband-specific losses defined in the wavelet domain. We first introduce a stationary wavelet transform for the network training procedure. Then, we train the network using objective loss functions defined for high- and low-frequency domains to enhance the objective quality of the denoised CT image. With this network design, we train the network again after replacing the objective loss functions with perceptual loss functions in high- and low-frequency domains. As a result, we acquired denoised CT images with high perceptual quality using this strategy while minimizing the objective quality loss. We evaluated our algorithms on the phantom and clinical images, and the quantitative and qualitative results indicate that ours outperform the existing state-of-the-art algorithms in terms of objective and perceptual quality.

MFA-net: Object detection for complex X-ray cargo and baggage security imagery.

Deep convolutional networks have been developed to detect prohibited items for automated inspection of X-ray screening systems in the transport security system. To our knowledge, the existing frameworks were developed to recognize threats using only baggage security X-ray scans. Therefore, the detection accuracy in other domains of security X-ray scans, such as cargo X-ray scans, cannot be ensured. We propose an object detection method for efficiently detecting contraband items in both cargo and baggage for X-ray security scans. The proposed network, MFA-net, consists of three plug-and-play modules, including the multiscale dilated convolutional module, fusion feature pyramid network, and auxiliary point detection head. First, the multiscale dilated convolutional module converts the standard convolution of the detector backbone to a conditional convolution by aggregating the features from multiple dilated convolutions using dynamic feature selection to overcome the object-scale variant issue. Second, the fusion feature pyramid network combines the proposed attention and fusion modules to enhance multiscale object recognition and alleviate the object and occlusion problem. Third, the auxiliary point detection head adopts an auxiliary head to predict the new keypoints of the bounding box to emphasize the localizability without requiring further ground-truth information. We tested the performance of the MFA-net on two large-scale X-ray security image datasets from different domains: a Security Inspection X-ray (SIXray) dataset in the baggage domain and our dataset, named CargoX, in the cargo domain. Moreover, MFA-net outperformed state-of-the-art object detectors in both domains. Thus, adopting the proposed modules can further increase the detection capability of the current object detectors on X-ray security images.

Deep Learning with Multimodal Integration for Predicting Recurrence in Patients with Non-Small Cell Lung Cancer.

Due to high recurrence rates in patients with non-small cell lung cancer (NSCLC), medical professionals need extremely accurate diagnostic methods to prevent bleak prognoses. However, even the most commonly used diagnostic method, the TNM staging system, which describes the tumor-size, nodal-involvement, and presence of metastasis, is often inaccurate in predicting NSCLC recurrence. These limitations make it difficult for clinicians to tailor treatments to individual patients. Here, we propose a novel approach, which applies deep learning to an ensemble-based method that exploits patient-derived, multi-modal data. This will aid clinicians in successfully identifying patients at high risk of recurrence and improve treatment planning.

Object detectors involving a NAS-gate convolutional module and capsule attention module.

Several state-of-the-art object detectors have demonstrated outstanding performances by optimizing feature representation through modification of the backbone architecture and exploitation of a feature pyramid. To determine the effectiveness of this approach, we explore the modification of object detectors' backbone and feature pyramid by utilizing Neural Architecture Search (NAS) and Capsule Network. We introduce two modules, namely, NAS-gate convolutional module and Capsule Attention module. The NAS-gate convolutional module optimizes standard convolution in a backbone network based on differentiable architecture search cooperation with multiple convolution conditions to overcome object scale variation problems. The Capsule Attention module exploits the strong spatial relationship encoding ability of the capsule network to generate a spatial attention mask, which emphasizes important features and suppresses unnecessary features in the feature pyramid, in order to optimize the feature representation and localization capability of the detectors. Experimental results indicate that the NAS-gate convolutional module can alleviate the object scale variation problem and the Capsule Attention network can help to avoid inaccurate localization. Next, we introduce NASGC-CapANet, which incorporates the two modules, i.e., a NAS-gate convolutional module and capsule attention module. Results of comparisons against state-of-the-art object detectors on the MS COCO val-2017 dataset demonstrate that NASGC-CapANet-based Faster R-CNN significantly outperforms the baseline Faster R-CNN with a ResNet-50 backbone and a ResNet-101 backbone by mAPs of 2.7% and 2.0%, respectively. Furthermore, the NASGC-CapANet-based Cascade R-CNN achieves a box mAP of 43.8% on the MS COCO test-dev dataset.

Rigid and Non-Rigid Motion Compensation in Weight-Bearing CBCT of the Knee Using Simulated Inertial Measurements.

OBJECTIVE: Involuntary subject motion is the main source of artifacts in weight-bearing cone-beam CT of the knee. To achieve image quality for clinical diagnosis, the motion needs to be compensated. We propose to use inertial measurement units (IMUs) attached to the leg for motion estimation. METHODS: We perform a simulation study using real motion recorded with an optical tracking system. Three IMU-based correction approaches are evaluated, namely rigid motion correction, non-rigid 2D projection deformation and non-rigid 3D dynamic reconstruction. We present an initialization process based on the system geometry. With an IMU noise simulation, we investigate the applicability of the proposed methods in real applications. RESULTS: All proposed IMU-based approaches correct motion at least as good as a state-of-the-art marker-based approach. The structural similarity index and the root mean squared error between motion-free and motion corrected volumes are improved by 24-35% and 78-85%, respectively, compared with the uncorrected case. The noise analysis shows that the noise levels of commercially available IMUs need to be improved by a factor of 105 which is currently only achieved by specialized hardware not robust enough for the application. CONCLUSION: Our simulation study confirms the feasibility of this novel approach and defines improvements necessary for a real application. SIGNIFICANCE: The presented work lays the foundation for IMU-based motion compensation in cone-beam CT of the knee and creates valuable insights for future developments.

Digital Hologram Watermarking Based on Multiple Deep Neural Networks Training Reconstruction and Attack.

This paper proposes a method to embed and extract a watermark on a digital hologram using a deep neural network. The entire algorithm for watermarking digital holograms consists of three sub-networks. For the robustness of watermarking, an attack simulation is inserted inside the deep neural network. By including attack simulation and holographic reconstruction in the network, the deep neural network for watermarking can simultaneously train invisibility and robustness. We propose a network training method using hologram and reconstruction. After training the proposed network, we analyze the robustness of each attack and perform re-training according to this result to propose a method to improve the robustness. We quantitatively evaluate the results of robustness against various attacks and show the reliability of the proposed technique.

3D Non-Rigid Alignment of Low-Dose Scans Allows to Correct for Saturation in Lower Extremity Cone-Beam CT.

Detector saturation in cone-beam computed tomography occurs when an object of highly varying shape and material composition is imaged using an automatic exposure control (AEC) system. When imaging a subject's knees, high beam energy ensures the visibility of internal structures but leads to overexposure in less dense border regions. In this work, we propose to use an additional low-dose scan to correct the saturation artifacts of AEC scans. Overexposed pixels are identified in the projection images of the AEC scan using histogram-based thresholding. The saturation-free pixels from the AEC scan are combined with the skin border pixels of the low-dose scan prior to volumetric reconstruction. To compensate for patient motion between the two scans, a 3D non-rigid alignment of the projection images in a backward-forward-projection process based on fiducial marker positions is proposed. On numerical simulations, the projection combination improved the structural similarity index measure from 0.883 to 0.999. Further evaluations were performed on two in vivo subject knee acquisitions, one without and one with motion between the AEC and low-dose scans. Saturation-free reference images were acquired using a beam attenuator. The proposed method could qualitatively restore the information of peripheral tissue structures. Applying the 3D non-rigid alignment made it possible to use the projection images with inter-scan subject motion for projection image combination. The increase in radiation exposure due to the additional low-dose scan was found to be negligibly low. The presented methods allow simple but effective correction of saturation artifacts.

The effect of patellofemoral pain syndrome on patellofemoral joint kinematics under upright weight-bearing conditions.

Patellofemoral pain (PFP) is commonly caused by abnormal pressure on the knee due to excessive load while standing, squatting, or going up or down stairs. To better understand the pathophysiology of PFP, we conducted a noninvasive patellar tracking study using a C-arm computed tomography (CT) scanner to assess the non-weight-bearing condition at 0° knee flexion (NWB0°) in supine, weight-bearing at 0° (WB0°) when upright, and at 30° (WB30°) in a squat. Three-dimensional (3D) CT images were obtained from patients with PFP (12 women, 6 men; mean age, 31 ± 9 years; mean weight, 68 ± 9 kg) and control subjects (8 women, 10 men; mean age, 39 ± 15 years; mean weight, 71 ± 13 kg). Six 3D-landmarks on the patella and femur were used to establish a joint coordinate system (JCS) and kinematic degrees of freedom (DoF) values on the JCS were obtained: patellar tilt (PT, °), patellar flexion (PF, °), patellar rotation (PR, °), patellar lateral-medial shift (PTx, mm), patellar proximal-distal shift (PTy, mm), and patellar anterior-posterior shift (PTz, mm). Tests for statistical significance (p < 0.05) showed that the PF during WB30°, the PTy during NWB0°, and the PTz during NWB0°, WB0°, and WB30° showed clear differences between the patients with PFP and healthy controls. In particular, the PF during WB30° (17.62°, extension) and the PTz during WB0° (72.5‬0 mm, posterior) had the largest rotational and translational differences (JCS Δ = patients with PFP-controls), respectively. The JCS coordinates with statistically significant difference can serve as key biomarkers of patellar motion when evaluating a patient suspected of having PFP. The proposed method could reveal diagnostic biomarkers for accurately identifying PFP patients and be an effective addition to clinical diagnosis before surgery and to help plan rehabilitation strategies.

Automated stitching of microscope images of fluorescence in cells with minimal overlap.

The morphology of tumor cells is highly related to their phenotype and activity. To verify the drug response of a brain tumor patient, fluorescence microscope images of drug-treated patient-derived cells in each well are analyzed. Due to the limitation of the field of view (FOV), a large number of small FOVs are acquired to compose one complete microscope well. Here, we propose an automated method for accurately stitching tile-scanned fluorescence microscope images, even with noise and a narrow overlapping region between adjacent fields. The proposed method is based on intensity-based normalized cross-correlation (NCC) and a triangular method-based threshold. The proposed method's quantitative accuracy and the sensitivity of the input was compared to other existing stitching tools, MIST and FijiIS, setting manually stitched images as the ground truth. The test images were 20 samples of 3 × 3 grid images in three versions of the fluorescence channel. The distance between the location of each field and number of cells was determined for different input field overlap ranges (1%, 3%, 5%, and 10%), while the actual value was about 1.15%. The proposed method had a distance error of 1.5 pixels at an input overlap of 1%, showing the lowest minimum error at all channels. Regarding the difference in cell numbers, although the number of overlapping cells was always small because of the narrow overlapping range, the proposed method was able to generate the resultant image with the smallest difference. In addition, to confirm the size limitation of the proposed algorithm, the accuracy of stitching images of grid structures 3 × 3, 5 × 5, 10 × 10-20 × 20 was tested, showing consistent results. In conclusion, quantitative evaluation of the performance of the method proved its improved accuracy compared to other current state-of-art techniques, and it showed robust performance even with noise and a narrow overlapping region between adjacent fields.

A learning-based material decomposition pipeline for multi-energy x-ray imaging.

PURPOSE: Benefiting from multi-energy x-ray imaging technology, material decomposition facilitates the characterization of different materials in x-ray imaging. However, the performance of material decomposition is limited by the accuracy of the decomposition model. Due to the presence of nonideal effects in x-ray imaging systems, it is difficult to explicitly build the imaging system models for material decomposition. As an alternative, this paper explores the feasibility of using machine learning approaches for material decomposition tasks. METHODS: In this work, we propose a learning-based pipeline to perform material decomposition. In this pipeline, the step of feature extraction is implemented to integrate more informative features, such as neighboring information, to facilitate material decomposition tasks, and the step of hold-out validation with continuous interleaved sampling is employed to perform model evaluation and selection. We demonstrate the material decomposition capability of our proposed pipeline with promising machine learning algorithms in both simulation and experimentation, the algorithms of which are artificial neural network (ANN), Random Tree, REPTree and Random Forest. The performance was quantitatively evaluated using a simulated XCAT phantom and an anthropomorphic torso phantom. In order to evaluate the proposed method, two measurement-based material decomposition methods were used as the reference methods for comparison studies. In addition, deep learning-based solutions were also investigated to complete this work as a comprehensive comparison of machine learning solution for material decomposition. RESULTS: In both the simulation study and the experimental study, the introduced machine learning algorithms are able to train models for the material decomposition tasks. With the application of neighboring information, the performance of each machine learning algorithm is strongly improved. Compared to the state-of-the-art method, the performance of ANN in the simulation study is an improvement of over 24% in the noiseless scenarios and over 169% in the noisy scenario, while the performance of the Random Forest is an improvement of over 40% and 165%, respectively. Similarly, the performance of ANN in the experimental study is an improvement of over 42% in the denoised scenario and over 45% in the original scenario, while the performance of Random Forest is an improvement by over 33% and 40%, respectively. CONCLUSIONS: The proposed pipeline is able to build generic material decomposition models for different scenarios, and it was validated by quantitative evaluation in both simulation and experimentation. Compared to the reference methods, appropriate features and machine learning algorithms can significantly improve material decomposition performance. The results indicate that it is feasible and promising to perform material decomposition using machine learning methods, and our study will facilitate future efforts toward clinical applications.

Assessment of a photon-counting detector for a dual-energy C-arm angiographic system.

PURPOSE: This article presents the implementation and assessment of photon-counting dual-energy x-ray detector technology for angiographic C-arm systems in interventional radiology. METHODS: A photon-counting detector was successfully integrated into a clinical C-arm CT system. Detector performance was assessed using image uniformity metrics in both 2D projections and 3D cone-beam computed tomography (CBCT) images. Uniform exposure fields were acquired to analyze projection images and scans of a homogeneous cylinder phantom were taken to analyze 3D reconstructions. Image uniformity was assessed over a broad range of imaging parameters. RESULTS: Detector calibration greatly improved image uniformity, reducing image variation from 8.8% to 0.5% in an ideal scenario, but image uniformity degraded when imaging parameters varied strongly from values set at calibration: the tube voltage, low-high energy threshhold, and tube current had the greatest impact. Material discrimination and dynamic angiography capabilities were successfully demonstrated in separate phantom and in vivo experiments. CONCLUSION: The uniformity results identified major factors degrading image quality. The quantitative results will guide selection of calibration points to mitigate the loss of uniformity. The unique combination of dual-energy and fluoroscopy imaging capabilities with a flat-panel photon-counting detector may enable new applications in interventional radiology.

Comparison of Different Approaches for Measuring Tibial Cartilage Thickness.

Osteoarthritis is a degenerative disease affecting bones and cartilage especially in the human knee. In this context, cartilage thickness is an indicator for knee cartilage health. Thickness measurements are performed on medical images acquired in-vivo. Currently, there is no standard method agreed upon that defines a distance measure in articular cartilage. In this work, we present a comparison of different methods commonly used in literature. These methods are based on nearest neighbors, surface normal vectors, local thickness and potential field lines. All approaches were applied to manual segmentations of tibia and lateral and medial tibial cartilage performed by experienced raters. The underlying data were contrast agent-enhanced cone-beam C-arm CT reconstructions of one healthy subject's knee. The subject was scanned three times, once in supine position and two times in a standing weight-bearing position. A comparison of the resulting thickness maps shows similar distributions and high correlation coefficients between the approaches above 0.90. The nearest neighbor method results on average in the lowest cartilage thickness values, while the local thickness approach assigns the highest values. We showed that the different methods agree in their thickness distribution. The results will be used for a future evaluation of cartilage change under weight-bearing conditions.