List of reviewers who served JMI in 2020.

Thanks to AEs who served JMI in 2020.

Purpose: Deep learning has achieved major breakthroughs during the past decade in almost every field. There are plenty of publicly available algorithms, each designed to address a different task of computer vision in general. However, most of these algorithms cannot be directly applied to images in the medical domain. Herein, we are focused on the required preprocessing steps that should be applied to medical images prior to deep neural networks.

Approach: To be able to employ the publicly available algorithms for clinical purposes, we must make a meaningful pixel/voxel representation from medical images which facilitates the learning process. Based on the ultimate goal expected from an algorithm (classification, detection, or segmentation), one may infer the required pre-processing steps that can ideally improve the performance of that algorithm. Required pre-processing steps for computed tomography (CT) and magnetic resonance (MR) images in their correct order are discussed in detail. We further supported our discussion by relevant experiments to investigate the efficiency of the listed preprocessing steps.

Results: Our experiments confirmed how using appropriate image pre-processing in the right order can improve the performance of deep neural networks in terms of better classification and segmentation.

Conclusions: This work investigates the appropriate pre-processing steps for CT and MR images of prostate cancer patients, supported by several experiments that can be useful for educating those new to the field (https://github.com/NIH-MIP/Radiology_Image_Preprocessing_for_Deep_Learning).

Purpose: Quantifying stenosis in cardiac computed tomography angiography (CTA) images remains a difficult task, as image noise and cardiac motion can degrade image quality and distort underlying anatomic information. The purpose of this study was to develop a computational framework to objectively assess the precision of quantifying coronary stenosis in cardiac CTA.

Approach: The framework used models of coronary vessels and plaques, asymmetric motion point spread functions, CT image blur (task-based modulation transfer functions) and noise (noise-power spectrums), and an automated maximum-likelihood estimator implemented as a matched template squared-difference operator. These factors were integrated into an estimability index (e^′) as a task-based measure of image quality in cardiac CTA. The e^′ index was applied to assess how well it can to predict the quality of 132 clinical cases selected from the Prospective Multicenter Imaging Study for Evaluation of Chest Pain trial. The cases were divided into two cohorts, high quality and low quality, based on clinical scores and the concordance of clinical evaluations of cases by experienced cardiac imagers. The framework was also used to ascertain protocol factors for CTA Biomarker initiative of the Quantitative Imaging Biomarker Alliance (QIBA).

Results: The e^′ index categorized the patient datasets with an area under the curve of 0.985, an accuracy of 0.977, and an optimal e^′ threshold of 25.58 corresponding to a stenosis estimation precision (standard deviation) of 3.91%. Data resampling and training–test validation methods demonstrated stable classifier thresholds and receiver operating curve performance. The framework was successfully applicable to the QIBA objective.

Conclusions: A computational framework to objectively quantify stenosis estimation task performance was successfully implemented and was reflective of clinical results in the context of a prominent clinical trial with diverse sites, readers, scanners, acquisition protocols, and patients. It also demonstrated the potential for prospective optimization of imaging protocols toward targeted precision and measurement consistency in cardiac CT images.

Purpose: We investigated the performance of a neural network (NN) material decomposition method under varying pileup conditions.

Approach: Experiments were performed at tube current settings that provided count rates incident on the detector through air equal to 9%, 14%, 27%, 40%, and 54% of the maximum detector count rate. An NN was trained for each count-rate level using transmission measurements through known thicknesses of basis materials (PMMA and aluminum). The NN trained for each count-rate level was applied to x-ray transmission measurements through test materials and to CT data of a rod phantom. Material decomposition error was evaluated as the distance in basis material space between the estimated thicknesses and ground truth.

Results: There was no clear trend between count-rate level and material decomposition error for all test materials except neoprene. As an example result, Teflon error was 0.33 cm at the 9% count-rate level and 0.12 cm at the 54% count-rate level for the x-ray transmission experiments. Decomposition error increased with count-rate level for the neoprene test case, with 0.65-cm error at 9% count-rate level and 1.14-cm error at the 54% count-rate level. In the CT study, material decomposition error decreased with increasing incident count rate. For example, the material decomposition error for Teflon was 0.089, 0.066, 0.054 at count-rate levels of 14%, 27%, and 40%, respectively.

Conclusions: Results demonstrate over a range of incident count-rate levels that an NN trained at a specific count-rate level can learn the relationship between photon-counting spectral measurements and basis material thicknesses.

Purpose: Brain image volumetric measurements (BVM) methods have been used to quantify brain tissue volumes using magnetic resonance imaging (MRI) when investigating abnormalities. Although BVM methods are widely used, they need to be evaluated to quantify their reliability. Currently, the gold-standard reference to evaluate a BVM is usually manual labeling measurement. Manual volume labeling is a time-consuming and expensive task, but the confidence level ascribed to this method is not absolute. We describe and evaluate a biomimetic brain phantom as an alternative for the manual validation of BVM.

Methods: We printed a three-dimensional (3D) brain mold using an MRI of a three-year-old boy diagnosed with Sturge-Weber syndrome. Then we prepared three different mixtures of styrene-ethylene/butylene-styrene gel and paraffin to mimic white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). The mold was filled by these three mixtures with known volumes. We scanned the brain phantom using two MRI scanners, 1.5 and 3.0 Tesla. Our suggestion is a new challenging model to evaluate the BVM which includes the measured volumes of the phantom compartments and its MRI. We investigated the performance of an automatic BVM, i.e., the expectation–maximization (EM) method, to estimate its accuracy in BVM.

Results: The automatic BVM results using the EM method showed a relative error (regarding the phantom volume) of 0.08, 0.03, and 0.13 (±0.03 uncertainty) percentages of the GM, CSF, and WM volume, respectively, which was in good agreement with the results reported using manual segmentation.

Conclusions: The phantom can be a potential quantifier for a wide range of segmentation methods.

Purpose: Automatic instance segmentation of glomeruli within kidney whole slide imaging (WSI) is essential for clinical research in renal pathology. In computer vision, the end-to-end instance segmentation methods (e.g., Mask-RCNN) have shown their advantages relative to detect-then-segment approaches by performing complementary detection and segmentation tasks simultaneously. As a result, the end-to-end Mask-RCNN approach has been the de facto standard method in recent glomerular segmentation studies, where downsampling and patch-based techniques are used to properly evaluate the high-resolution images from WSI (e.g., >10,000  ×  10,000  pixels on 40  ×  ). However, in high-resolution WSI, a single glomerulus itself can be more than 1000  ×  1000  pixels in original resolution which yields significant information loss when the corresponding features maps are downsampled to the 28  ×  28 resolution via the end-to-end Mask-RCNN pipeline.

Approach: We assess if the end-to-end instance segmentation framework is optimal for high-resolution WSI objects by comparing Mask-RCNN with our proposed detect-then-segment framework. Beyond such a comparison, we also comprehensively evaluate the performance of our detect-then-segment pipeline through: (1) two of the most prevalent segmentation backbones (U-Net and DeepLab_v3); (2) six different image resolutions (512  ×  512, 256  ×  256, 128  ×  128, 64  ×  64, 32  ×  32, and 28  ×  28); and (3) two different color spaces (RGB and LAB).

Results: Our detect-then-segment pipeline, with the DeepLab_v3 segmentation framework operating on previously detected glomeruli of 512  ×  512 resolution, achieved a 0.953 Dice similarity coefficient (DSC), compared with a 0.902 DSC from the end-to-end Mask-RCNN pipeline. Further, we found that neither RGB nor LAB color spaces yield better performance when compared against each other in the context of a detect-then-segment framework.

Conclusions: The detect-then-segment pipeline achieved better segmentation performance compared with the end-to-end method. Our study provides an extensive quantitative reference for other researchers to select the optimized and most accurate segmentation approach for glomeruli, or other biological objects of similar character, on high-resolution WSI.

Purpose: Image registration is an important aspect of medical image analysis and a key component in many analysis concepts. Applications include fusion of multimodal images, multi-atlas segmentation, and whole-body analysis. Deformable image registration is often computationally expensive, and the need for efficient registration methods is highlighted by the emergence of large-scale image databases, e.g., the UK Biobank, providing imaging from 100,000 participants.

Approach: We present a heterogeneous computing approach, utilizing both the CPU and the graphics processing unit (GPU), to accelerate a previously proposed image registration method. The parallelizable task of computing the matching criterion is offloaded to the GPU, where it can be computed efficiently, while the more complex optimization task is performed on the CPU. To lessen the impact of data synchronization between the CPU and GPU, we propose a pipeline model, effectively overlapping computational tasks with data synchronization. The performance is evaluated on a brain labeling task and compared with a CPU implementation of the same method and the popular advanced normalization tools (ANTs) software.

Results: The proposed method presents a speed-up by factors of 4 and 8 against the CPU implementation and the ANTs software, respectively. A significant improvement in labeling quality was also observed, with measured mean Dice overlaps of 0.712 and 0.701 for our method and ANTs, respectively.

Conclusions: We showed that the proposed method compares favorably to the ANTs software yielding both a significant speed-up and an improvement in labeling quality. The registration method together with the proposed parallelization strategy is implemented as an open-source software package, deform.

Purpose: A brain tumor is deadly as its exact extraction is tricky. However, at times, its removal is the only way to save a patient, leaving very little room for the doctors to make a mistake. Image segmentation algorithms can be used to detect tumor in magnetic resonance imaging (MRI). Irregularity in size, location, and shape of tumor in brain with imbalanced distribution of classes in the dataset make this a challenging task. To deal with these challenges, a region of interest (ROI) is extracted from images by removing redundant information.

Approach: We present a process to extract ROIs by converting images into neutrosophic domain. Two modalities FLAIR and T2 were diffused to reduce inhomogeneity in nontumorous regions and then anisotropic diffusion is applied to reduce the noise. The ROIs, which are tumorous regions, were extracted using neutrosophic technique based on the modified S-function. The extracted ROIs were refined by applying the morphological operations in the end.

Results: We evaluated our proposed method using three datasets including BraTS 2019 and compared the results with state-of-the-art methods. The parameters sensitivity, false negative rate, and ratio of ROI area to slice area were calculated to evaluate the proposed method. These parameters indicate that the proposed method achieved more than 98% sensitivity, 1.5% false negative rate, and removed more than 80% redundancy.

Conclusions: Evaluating parameters indicate that the method proposed has removed most of the redundant data from MRI images and extracted ROIs are composed of tumorous region.

Purpose: Deep learning is a promising technique for spleen segmentation. Our study aims to validate the reproducibility of deep learning-based spleen volume estimation by performing spleen segmentation on clinically acquired computed tomography (CT) scans from patients with myeloproliferative neoplasms.

Approach: As approved by the institutional review board, we obtained 138 de-identified abdominal CT scans. A sum of voxel volume on an expert annotator’s segmentations establishes the ground truth (estimation 1). We used our deep convolutional neural network (estimation 2) alongside traditional linear estimations (estimation 3 and 4) to estimate spleen volumes independently. Dice coefficient, Hausdorff distance, R² coefficient, Pearson R coefficient, the absolute difference in volume, and the relative difference in volume were calculated for 2 to 4 against the ground truth to compare and assess methods’ performances. We re-labeled on scan–rescan on a subset of 40 studies to evaluate method reproducibility.

Results: Calculated against the ground truth, the R² coefficients for our method (estimation 2) and linear method (estimation 3 and 4) are 0.998, 0.954, and 0.973, respectively. The Pearson R coefficients for the estimations against the ground truth are 0.999, 0.963, and 0.978, respectively (paired t-tests produced p  <  0.05 between 2 and 3, and 2 and 4).

Conclusion: The deep convolutional neural network algorithm shows excellent potential in rendering more precise spleen volume estimations. Our computer-aided segmentation exhibits reasonable improvements in splenic volume estimation accuracy.

Purpose: Repeated injections of linear gadolinium-based contrast agent (GBCA) have shown correlations with increased signal intensities (SI) on unenhanced T1-weighted (T1w) images. Assessment is usually performed manually on a single slice and the SI as an average of a freehand region-of-interest is reported. We aim to develop a fully automated software that segments and computes SI ratio of dentate nucleus (DN) to pons (DN/P) and globus pallidus (GP) to thalamus (GP/T) for the assessment of gadolinium presence in the brain after a serial GBCA administrations.

Approach: All patients (N  =  113) underwent at least eight GBCA enhanced scans. The modal SI in the DN, GP, pons, and thalamus were measured volumetrically on unenhanced T1w images and corrected based on the reference protocol (measurement 1) and compared to the SI-uncorrected-modal-volume (measurement 2), SI-corrected-mean-volume (measurement 3), as well as SI-corrected-modal-single slice (measurement 4) approaches.

Results: Automatic processing worked on all 2119 studies (1150 at 1.5 T and 969 at 3 T). DN/P were 1.085  ±  0.048 (1.5 T) and 0.979  ±  0.061 (3 T). GP/T were 1.084  ±  0.039 (1.5 T) and 1.069  ±  0.042 (3 T). Modal DN/P ratios from volumetric assessment at 1.5 T failed to show a statistical difference with or without SI corrections (p  =  0.71). All other t-tests demonstrated significant differences (measurement 2, 3, 4 compared to 1, p  <  0.001).

Conclusion: The fully automatic method is an effective powerful tool to streamline the analysis of SI ratios in the deep brain tissues. Divergent SI ratios using different approaches reinforces the need to standardize the measurement for the research in this field.

Purpose: Intracerebral hemorrhage (ICH) is a common disease that is known for its high morbidity, high mortality, and high disability. The fast and accurate detection of ICH is essential for the acute care of patients. Electrical impedance tomography (EIT) offers an alternative with which pathological tissues can be detected by reconstructing conductivity variation. Nevertheless, the sensitive field of EIT is greatly affected by medium distribution, which is referred to as soft-field effect. In addition, the image reconstruction is a severely ill-posed inverse problem. Furthermore, due to the low conductivity of skull, the sensitivity in the sensing area is extremely low. Therefore, the reconstruction of ICH with EIT is great challenge.

Approach: A sparse image reconstruction method is proposed for EIT to visualize the conductivity variation caused by ICH. To reduce the impact of soft-field effect, the normalization of sensitivity distribution is conducted for monolayer and three-layer head model. In addition, a constrained sparse L₁-norm minimization model is developed for the image reconstruction. Augmented Lagrangian multiplier method and alternating minimization scheme are adopted to solve the proposed model.

Results: The results show that the sensitivity in the sensing area is largely enhanced. Numerical simulation based on monolayer head model and three-layer head model is respectively carried out. Both the reconstructed images and the quantitative evaluations show that image reconstructed by the proposed method is much better than that reconstructed by traditional Tikhonov method. The reconstructions evaluated under the impact of noise also show that the proposed method has superior anti-noise performance.

Conclusions: With the proposed method, the quality of the reconstructed image would be greatly improved. It is an effective approach for imaging ICH with EIT technique.

Purpose: To assess whether the three-dimensional reconstructions of preoperative computed tomography (CT) scans are helpful for establishing extranodal extension (ENE) in head and neck carcinoma.

Approach: Patients with a histological diagnosis of ENE (pENE  +  ) were considered “cases” and patients with negative histological examination for ENE (pENE  −  ) were considered “controls.” Cases and controls were divided into two groups: a major nodes (MaN) group (lymph nodes on CT  >  15  mm) and a minor nodes (MiN) group (lymph nodes on CT  ≤  15  mm). The preoperative CT scans were uploaded to the Anatomage Table and were randomly and blindly provided to the radiologist for assessment. The findings at the Anatomage Table were compared with those of CT and magnetic resonance imaging (MRI) scans.

Results: Analysis of data from the MaN group showed that the Anatomage Table had a higher percentage of concordance with histopathological examination (90%) than the CT and MRI scans. The Anatomage Table had 100% sensitivity in identifying all pENE  +   patients, associated with a lower specificity. The negative predictive value of 100% allowed identification of pENE  −   patients. In the MiN group, on the other hand, sensitivity was lower, related to a high number of false-negative results.

Conclusions: The Anatomage Table could represent a useful tool for preoperatively establishing the extranodal extension of cervical lymph node metastasis.

Purpose: Mesenchymal stem cells (MSCs) have demonstrated clinically relevant therapeutic effects for treatment of trauma and chronic diseases. The proliferative potential, immunomodulatory characteristics, and multipotentiality of MSCs in monolayer culture is reflected by their morphological phenotype. Standard techniques to evaluate culture viability are subjective, destructive, or time-consuming. We present an image analysis approach to objectively determine morphological phenotype of MSCs for prediction of culture efficacy.

Approach: The algorithm was trained using phase-contrast micrographs acquired during the early and mid-logarithmic stages of MSC expansion. Cell regions are localized using edge detection, thresholding, and morphological operations, followed by cell marker identification using H-minima transform within each region to differentiate individual cells from cell clusters. Clusters are segmented using marker-controlled watershed to obtain single cells. Morphometric and textural features are extracted to classify cells based on phenotype using machine learning.

Results: Algorithm performance was validated using an independent test dataset of 186 MSCs in 36 culture images. Results show 88% sensitivity and 86% precision for overall cell detection and a mean Sorensen–Dice coefficient of 0.849  ±  0.106 for segmentation per image. The algorithm exhibited an area under the curve of 0.816 (CI₉₅  =  0.769 to 0.886) and 0.787 (CI₉₅  =  0.716 to 0.851) for classifying MSCs according to their phenotype at early and mid-logarithmic expansion, respectively.

Conclusions: The proposed method shows potential to segment and classify low and moderately dense MSCs based on phenotype with high accuracy and robustness. It enables quantifiable and consistent morphology-based quality assessment for various culture protocols to facilitate cytotherapy development.

Purpose: The automatic segmentation of multiple sclerosis lesions in magnetic resonance imaging has the potential to reduce radiologists’ efforts on a daily time-consuming task and to bring more reproducibility. Almost all new segmentation techniques make use of convolutional neural networks with their own different architecture. Architectural choices are rarely explained. We aimed at presenting the relevance of a U-net-like architecture for our specific task and at building an efficient and simple model.

Approach: An experimental study was performed by observing the impact of applying different mutations and deletions to a simple U-net-like architecture.

Results: The power of the U-net architecture is explained by the joint benefits of using an encoder–decoder architecture and by linking them with long skip connections. Augmenting the number of convolutional layers and decreasing the number of feature maps allowed us to build an exceptionally light and competitive architecture, the minimally parameterized U-net (MPU-net), with only ∼30,000 parameters.

Conclusion: The empirical study of the U-net has led to a better understanding of its architecture. It has guided the building of the MPU-net, a model far less parameterized than others (at least by a factor of seven). This neural network achieves a human-level segmentation of multiple sclerosis lesions on fluid-attenuated inversion recovery images only. It shows that this segmentation task does not necessitate overly complicated models to be achieved. This gives the opportunity to build more explainable models that can help such methods to be adopted in a clinical environment.

Purpose: To assess acute ischemic stroke (AIS) severity, infarct is segmented using computed tomography perfusion (CTP) software, such as RAPID, Sphere, and Vitrea, relying on contralateral hemisphere thresholds. Since this approach is potentially patient dependent, we investigated whether convolutional neural networks (CNNs) could achieve better performances without the need for contralateral hemisphere thresholds.

Approach: CTP and diffusion-weighted imaging (DWI) data were retrospectively collected for 63 AIS patients. Cerebral blood flow (CBF), cerebral blood volume (CBV), time-to-peak, mean-transit-time (MTT), and delay time maps were generated using Vitrea CTP software. U-net shaped CNNs were developed, trained, and tested for 26 different input CTP parameter combinations. Infarct labels were segmented from DWI volumes registered with CTP volumes. Infarct volumes were reconstructed from two-dimensional CTP infarct segmentations. To remove erroneous segmentations, conditional random field (CRF) postprocessing was applied and compared with prior results. Spatial and volumetric infarct agreement was assessed between DWI and CTP (CNNs and commercial software) using median infarct difference, median absolute error, dice coefficient, positive predictive value.

Results: The most accurate combination of parameters for CNN segmenting infarct using CRF postprocessing was CBF, CBV, and MTT (4.83 mL, 10.14 mL, 0.66, 0.73). Commercial software results are: RAPID = (2.25 mL, 21.48 mL, 0.63, 0.70), Sphere = (7.57 mL, 17.74 mL, 0.64, 0.70), Vitrea = (6.79 mL, 15.28 mL, 0.63, 0.72).

Conclusions: Use of CNNs with multiple input perfusion parameters has shown to be accurate in segmenting infarcts and has the ability to improve clinical workflow by eliminating the need for contralateral hemisphere comparisons.

Purpose: Current skin cancer detection relies on dermatologists’ visual assessments of moles directly or dermoscopically. Our goal is to show that our similarity assessment algorithm on dermoscopic images can perform as well as a dermatologist’s assessment.

Approach: Given one target mole and two other moles from the same patient, our model determines which mole is more similar to the target mole. Similarity was quantified as the Euclidean distance in a feature space designed to capture mole properties such as size, shape, and color. We tested our model on 18 patients, each of whom had at least five moles, and compared the model assessments of mole similarity with that of three dermatologists. Fleiss’ Kappa agreement coefficients and iteration tests were used to evaluate the agreement in similarity assessment among dermatologists and our model.

Results: With the selected features of size, entropy (color variation), and cluster prominence (asymmetry), our algorithm’s similarity assessments agreed moderately with the similarity assessments of dermatologists. The mean Kappa of 1000 iteration tests was 0.49 (confidence interval   (  CI  )    =    [  0.23  ,  0.74  ]  ) when comparing three dermatologists and our model, which is comparable to the agreement in similarity assessment among the dermatologists themselves (the mean Kappa of 1000 iteration tests for three dermatologists was 0.48, CI  =    [  0.19  ,  0.77  ]  .) By contrast, the mean Kappa was 0.22 (CI  =    [    −  0.00  ,  0.43  ]  ) when comparing the similarity assessments of three dermatologists and random guesses.

Conclusions: Our study showed that our image feature-engineering-based algorithm can effectively assess the similarity of moles as dermatologists do. Such a similarity assessment could serve as the foundation for computer-assisted intra-patient evaluation of moles.

Purpose: The purpose of this work was to develop a new method of tracking a laparoscopic ultrasound (LUS) transducer in laparoscopic video by combining the hardware [e.g., electromagnetic (EM)] and the computer vision-based (e.g., ArUco) tracking methods.

Approach: We developed a special tracking mount for the imaging tip of the LUS transducer. The mount incorporated an EM sensor and an ArUco pattern registered to it. The hybrid method used ArUco tracking for ArUco-success frames (i.e., frames where ArUco succeeds in detecting the pattern) and used corrected EM tracking for the ArUco-failure frames. The corrected EM tracking result was obtained by applying correction matrices to the original EM tracking result. The correction matrices were calculated in previous ArUco-success frames by comparing the ArUco result and the original EM tracking result.

Results: We performed phantom and animal studies to evaluate the performance of our hybrid tracking method. The corrected EM tracking results showed significant improvements over the original EM tracking results. In the animal study, 59.2% frames were ArUco-success frames. For the ArUco-failure frames, mean reprojection errors for the original EM tracking method and for the corrected EM tracking method were 30.8 pixel and 10.3 pixel, respectively.

Conclusions: The new hybrid method is more reliable than using ArUco tracking alone and more accurate and practical than using EM tracking alone for tracking the LUS transducer in the laparoscope camera image. The proposed method has the potential to significantly improve tracking performance for LUS-based augmented reality applications.

Purpose: Percutaneous fracture fixation is a challenging procedure that requires accurate interpretation of fluoroscopic images to insert guidewires through narrow bone corridors. We present a guidance system with a video camera mounted onboard the surgical drill to achieve real-time augmentation of the drill trajectory in fluoroscopy and/or CT.

Approach: The camera was mounted on the drill and calibrated with respect to the drill axis. Markers identifiable in both video and fluoroscopy are placed about the surgical field and co-registered by feature correspondences. If available, a preoperative CT can also be co-registered by 3D–2D image registration. Real-time guidance is achieved by virtual overlay of the registered drill axis on fluoroscopy or in CT. Performance was evaluated in terms of target registration error (TRE), conformance within clinically relevant pelvic bone corridors, and runtime.

Results: Registration of the drill axis to fluoroscopy demonstrated median TRE of 0.9 mm and 2.0 deg when solved with two views (e.g., anteroposterior and lateral) and five markers visible in both video and fluoroscopy—more than sufficient to provide Kirschner wire (K-wire) conformance within common pelvic bone corridors. Registration accuracy was reduced when solved with a single fluoroscopic view (TRE  =  3.4  mm and 2.7 deg) but was also sufficient for K-wire conformance within pelvic bone corridors. Registration was robust with as few as four markers visible within the field of view. Runtime of the initial implementation allowed fluoroscopy overlay and/or 3D CT navigation with freehand manipulation of the drill up to 10  frames  /  s.

Conclusions: A drill-mounted video guidance system was developed to assist with K-wire placement. Overall workflow is compatible with fluoroscopically guided orthopaedic trauma surgery and does not require markers to be placed in preoperative CT. The initial prototype demonstrates accuracy and runtime that could improve the accuracy of K-wire placement, motivating future work for translation to clinical studies.

Purpose: We explain our concept for customization of a guidance instrument, present a prototype, and describe a set of experiments to evaluate its positioning and drilling accuracy.

Methods: Our concept is characterized by the use of bone cement, which enables fixation of a specific configuration for each individual surgical template. This well-established medical product was selected to ensure future intraoperative fabrication of the template under sterile conditions. For customization, a manually operated alignment device is proposed that temporarily defines the planned trajectory until the bone cement is hardened. Experiments (n  =  10) with half-skull phantoms were performed. Analysis of accuracy comprises targeting validations and experiments including drilling in bone substitutes.

Results: The resulting mean positioning error was found to be 0.41  ±  0.30  mm at the level of the target point whereas drilling was possible with a mean accuracy of 0.35  ±  0.30  mm.

Conclusion: We proposed a cost-effective, easy-to-use approach for accurate instrument guidance that enables template fabrication under sterile conditions. The utilization of bone cement was proven to fulfill the demands of an easy, quick, and prospectively intraoperatively doable customization. We could demonstrate sufficient accuracy for many surgical applications, e.g., in neurosurgery. The system in this early development stage already outperforms conventional stereotactic frames and image-guided surgery systems in terms of targeting accuracy.

Purpose: Prosthetic heart valve designs must be rigorously tested using cardiovascular equipment. The valve orifice area over time constitutes a key quality metric which is typically assessed manually, thus a tedious and error-prone task. From a computer vision viewpoint, a major unsolved issue lies in the orifice being partly occluded by the leaflets’ inner side or inaccurately depicted due to its transparency. Here, we address this issue, which allows us to focus on the accurate and automatic computation of valve orifice areas.

Approach: We propose a segmentation approach based on the detection of the leaflets’ free edges. Using video frames recorded with a high-speed digital camera during in vitro simulations, an initial estimation of the orifice area is first obtained via active contouring and thresholding and then refined to capture the leaflet free edges via a curve transformation mechanism.

Results: Experiments on video data from pulsatile flow testing demonstrate the effectiveness of our approach: a root-mean-square error (RMSE) on the temporal extracted orifice areas between 0.8% and 1.2%, an average Jaccard similarity coefficient between 0.933 and 0.956, and an average Hausdorff distance between 7.2 and 11.9 pixels.

Conclusions: Our approach significantly outperformed a state-of-the-art algorithm in terms of evaluation metrics related to valve design (RMSE) and computer vision (accuracy of the orifice shape). It can also cope with lower quality videos and is better at processing frames showing an almost closed valve, a crucial quality for assessing valve design malfunctions related to their improper closing.

Purpose: Reconstruction of patient anatomy is critical to patient-specific instrument (PSI) design in total joint replacement (TJR). Conventionally, computed tomography (CT) and magnetic resonance imaging (MRI) are used to obtain the patient anatomy as they are accurate imaging modalities. However, computing anatomical landmarks from the patient anatomy for PSIs requires either high-resolution CT, increasing time of scan and radiation exposure to the patient, or longer and more expensive MRI scans. As an alternative, reconstruction from single-plane fluoroscopic x-ray provides a cost-efficient tool to obtain patient anatomical structures while allowing capture of the patient’s joint dynamics, important clinical information for TJR.

Approach: We present a three-dimensional (3D) reconstruction scheme that automatically and accurately reconstructs the 3D knee anatomy from single-plane fluoroscopic x-ray based on a nonlinear statistical shape model called kernel principal component analysis. To increase robustness, we designed a hybrid energy function that integrated feature and intensity information as a similarity measure for the 3D reconstruction.

Results: We evaluated the proposed method on five subjects during deep knee bending: the root-mean-square accuracy is 1.19  ±  0.36  mm for reconstructed femur and 1.15  ±  0.17  mm for reconstructed tibia.

Conclusions: The proposed method demonstrates reliable 3D bone model reconstruction accuracy with successful elimination of prior 3D imaging and reduction of manual labor and radiation dose on patient as well as characterizing joints in motion. This method is promising for applications in medical interventions such as patient-specific arthroplasty design, surgical planning, surgical navigation, and understanding anatomical and dynamic characteristics of joints.

Purpose: Detailed blood flow studies may contribute to improvements in carotid artery stenting. High-frame-rate contrast-enhanced ultrasound followed by particle image velocimetry (PIV), also called echoPIV, is a technique to study blood flow patterns in detail. The performance of echoPIV in presence of a stent has not yet been studied extensively. We compared the performance of echoPIV in stented and nonstented regions in an in vitro flow setup.

Approach: A carotid artery stent was deployed in a vessel-mimicking phantom. High-frame-rate contrast-enhanced ultrasound images were acquired with various settings. Signal intensities of the contrast agent, velocity values, and flow profiles were calculated.

Results: The results showed decreased signal intensities and correlation coefficients inside the stent, however, PIV analysis in the stent still resulted in plausible flow vectors.

Conclusions: Velocity values and laminar flow profiles can be measured in vitro in stented arteries using echoPIV.