Automatic lower limb bone segmentation in radiographs with different orientations and fields of view based on a contextual network.

PURPOSE: Bone identification and segmentation in X-ray images are crucial in orthopedics for the automation of clinical procedures, but it often involves some manual operations. In this work, using a modified SegNet neural network, we automatically identify and segment lower limb bone structures on radiographs presenting various fields of view and different patient orientations. METHODS: A wide contextual neural network architecture is proposed to perform a high-quality pixel-wise semantic segmentation on X-ray images presenting structures with a similar appearance and strong superposition. The proposed architecture is based on the premise that every output pixel on the label map has a wide receptive field. This allows the network to capture both global and local contextual information. The overlapping between structures is handled with additional labels. RESULTS: The proposed approach was evaluated on a test dataset composed of 70 radiographs with entire and partial bones. We obtained an average detection rate of 98.00% and an average Dice coefficient of 95.25 ± 9.02% across all classes. For the challenging subset of images with high superposition, we obtained an average detection rate of 96.36% and an average Dice coefficient of 93.81 ± 10.03% across all classes. CONCLUSION: The results show the effectiveness of the proposed approach in segmenting and identifying lower limb bone structures and overlapping structures in radiographs with strong bone superposition and highly variable configurations, as well as in radiographs containing only small pieces of bone structures.

Do postoperative antibiotics influence one-year peri-implant crestal bone remodelling and morbidity? A double-blinded randomized clinical trial.

OBJECTIVES: The primary objective of this study was to assess whether giving postoperative antibiotics to healthy patients after straightforward platform-switched implant placement would influence peri-implant crestal bone levels and postoperative morbidity after 1 year. METHODS: Thirty-eight healthy individuals were recruited in this pilot, randomized, double-blinded, placebo-controlled clinical trial. The intervention group (n = 18) received two grams of amoxicillin one hour before implant placement followed by a 7 days postoperative regimen (500 mg tid). The control group (n = 20) took the same preoperative dose of amoxicillin and an identical placebo postoperatively. Mesial and distal peri-implant crestal bone levels were measured at baseline, four months and one year later with standardized periapical radiographs. Postoperative pain severity was assessed through self-administered questionnaires for 7 days. Surgery-associated morbidities were evaluated after one, three, 16 weeks and 1 year. Descriptive and bivariate analyses were used. RESULTS: Thirty-seven participants completed the trial. At the one-year follow-up, the mean combined peri-implant crestal bone changes for the intervention (n = 18) and control (n = 19) groups were - 0.44 ± 0.41 mm and - 0.27 ± 0.56 mm, respectively. The difference between the groups (intervention-control) for mean combined crestal bone level changes was not statistically significant. There were no significant differences in surgery-associated morbidities between the intervention and control groups. The one-year implant survival rate was 100% in both groups. CONCLUSIONS: Study results suggest that a routine postoperative antibiotic regimen for healthy patients undergoing straightforward platform-switched implant placement might not be necessary to prevent postoperative peri-implant bone loss and complications.

Tibial Tunnel Placement in ACL Reconstruction Using a Novel Grid and Biplanar Stereoradiographic Imaging.

BACKGROUND: Nonanatomic graft placement is a frequent cause of anterior cruciate ligament reconstruction (ACLR) failure, and it can be attributed to either tibial or femoral tunnel malposition. To describe tibial tunnel placement in ACLR, we used EOS, a low-dose biplanar stereoradiographic imaging modality, to create a comprehensive grid that combines anteroposterior (AP) and mediolateral (ML) coordinates. PURPOSE: To (1) validate the automated grid generated from EOS imaging and (2) compare the results with optimal tibial tunnel placement. STUDY DESIGN: Descriptive laboratory study. METHODS: Using EOS, 3-dimensional models were created of the knees of 37 patients who had undergone ACLR. From the most medial, lateral, anterior, and posterior points on the tibial plateau of the EOS 3-dimensional model for each patient, an automated and personalized grid was generated from 2 independent observers' series of reconstructions. To validate this grid, each observer also manually measured the ML and AP distances, the medial proximal tibial angle (MPTA), and the tibial slope for each patient. The ideal tibial tunnel placement, as described in the literature, was compared with the actual tibial tunnel grid coordinates of each patient. RESULTS: The automated grid metrics for observer 1 gave a mean (95% CI) AP depth of 54.7 mm (53.4-55.9), ML width of 75.0 mm (73.3-76.6), MPTA of 84.9° (83.7-86.0), and slope of 7.2° (5.4-9.0). The differences with corresponding manual measurements were means (95% CIs) of 2.4 mm (1.4-3.4 mm), 0.5 mm (-1.3 to 2.2 mm), 1.2° (-0.4° to 2.9°), and -0.4° (-2.1° to 1.2°), respectively. The correlation between automated and manual measurements was r = 0.78 for the AP depth, r = 0.68 for the ML width, r = 0.18 for the MPTA, and r = 0.44 for the slope. The center of the actual tibial aperture on the plateau was a mean of 5.5 mm (95% CI, 4.8-6.1 mm) away from the referenced anatomic position, with a tendency toward more medial placement. CONCLUSION: The automated grid created using biplanar stereoradiographic imaging provided a novel, precise, and reproducible description of the tibial tunnel placement in ACLR. CLINICAL RELEVANCE: This technique can be used during preoperative planning, intraoperative guidance, and postoperative evaluation of tibial tunnel placement in ACLR.

Femoral Tunnel Placement Analysis in ACL Reconstruction Through Use of a Novel 3-Dimensional Reference With Biplanar Stereoradiographic Imaging.

BACKGROUND: The femoral-sided anatomic footprint of the anterior cruciate ligament (ACL) has been widely studied during the past decades. Nonanatomic placement is an important cause of ACL reconstruction (ACLR) failure. PURPOSE: To describe femoral tunnel placement in ACLR through use of a comprehensive 3-dimensional (3D) cylindrical coordinate system combining both the traditional clockface technique and the quadrant method. Our objective was to validate this technique and evaluate its reproducibility. STUDY DESIGN: Descriptive laboratory study. METHODS: The EOS Imaging System was used to make 3D models of the knee for 37 patients who had undergone ACLR. We designed an automated cylindrical reference software program individualized to the distal femoral morphology of each patient. Cylinder parameters were collected from 2 observers' series of 3D models. Each independent observer also manually measured the corresponding parameters using a lateral view of the 3D contours and a 2-dimensional stereoradiographic image for the corresponding patient. RESULTS: The average cylinder produced from the first observer's EOS 3D models had a 30.0° orientation (95% CI, 28.4°-31.5°), 40.4 mm length (95% CI, 39.3-41.4 mm), and 19.3 mm diameter (95% CI, 18.6-20.0 mm). For the second observer, these measurements were 29.7° (95% CI, 28.1°-31.3°), 40.7 mm (95% CI, 39.7-41.8 mm), and 19.7 mm (95% CI, 18.8-20.6 mm), respectively. Our method showed moderate intertest intraclass correlation among all 3 measuring techniques for both length (r = 0.68) and diameter (r = 0.63) but poor correlation for orientation (r = 0.44). In terms of interobserver reproducibility of the automated EOS 3D method, similar results were obtained: moderate to excellent correlations for length (r = 0.95; P < .001) and diameter (r = 0.66; P < .001) but poor correlation for orientation (r = 0.29; P < .08). With this reference system, we were able to describe the placement of each individual femoral tunnel aperture, averaging a difference of less than 10 mm from the historical anatomic description by Bernard et al. CONCLUSION: This novel 3D cylindrical coordinate system using biplanar, stereoradiographic, low-irradiation imaging showed a precision comparable with standard manual measurements for ACLR femoral tunnel placement. Our results also suggest that automated cylinders issued from EOS 3D models show adequate accuracy and reproducibility. CLINICAL RELEVANCE: This technique will open multiple possibilities in ACLR femoral tunnel placement in terms of preoperative planning, postoperative feedback, and even intraoperative guidance with augmented reality.

Shape, Pose and Density Statistical Model for 3D Reconstruction of Articulated Structures from X-Ray Images.

This article proposes a joint statistical model, to describe the volumetric shape + pose + density information, and a reconstruction algorithm to simultaneously recover the volumetric information of several anatomical structures from biplanar radiographs. A PCA-based representation is proposed as compact model representation and a hybrid AAM search and genetic optimization is used to perform the reconstruction. A study was conducted to recover a 3D volume grid containing a human knee mesh from 2 orthogonal simulated radiographs. The model was computed on a data set of 200 subjects and the reconstruction test was performed on 18 subjects, leading to a surface distance RMSE of 0.7 ± 0.31 mm for the distal femur, 0.9 ± 0.3 mm for the proximal tibia and 0.8 ± 0.3 mm for the fibula. These results demonstrate the feasibility and the pertinence of the proposed approach, the next step being its application in a clinical context.

Liver Segmentation on CT and MR Using Laplacian Mesh Optimization.

OBJECTIVE: The purpose of this paper is to describe a semiautomated segmentation method for the liver and evaluate its performance on CT-scan and MR images. METHODS: First, an approximate 3-D model of the liver is initialized from a few user-generated contours to globally outline the liver shape. The model is then automatically deformed by a Laplacian mesh optimization scheme until it precisely delineates the patient's liver. A correction tool was implemented to allow the user to improve the segmentation until satisfaction. RESULTS: The proposed method was tested against 30 CT-scans from the SLIVER07 challenge repository and 20 MR studies from the Montreal University Hospital Center, covering a wide spectrum of liver morphologies and pathologies. The average volumetric overlap error was 5.1% for CT and 7.6% for MRI and the average segmentation time was 6 min. CONCLUSION: The obtained results show that the proposed method is efficient, reliable, and could effectively be used routinely in the clinical setting. SIGNIFICANCE: The proposed approach can alleviate the cumbersome and tedious process of slice-wise segmentation required for precise hepatic volumetry, virtual surgery, and treatment planning.

Investigation of 3D glenohumeral displacements from 3D reconstruction using biplane X-ray images: Accuracy and reproducibility of the technique and preliminary analysis in rotator cuff tear patients.

Rotator cuff (RC) tears may be associated with increased glenohumeral instability; however, this instability is difficult to quantify using currently available diagnostic tools. Recently, the three-dimensional (3D) reconstruction and registration method of the scapula and humeral head, based on sequences of low-dose biplane X-ray images, has been proposed for glenohumeral displacement assessment. This research aimed to evaluate the accuracy and reproducibility of this technique and to investigate its potential with a preliminary application comparing RC tear patients and asymptomatic volunteers. Accuracy was assessed using CT scan model registration on biplane X-ray images for five cadaveric shoulder specimens and showed differences ranging from 0.6 to 1.4mm depending on the direction of interest. Intra- and interobserver reproducibility was assessed through two operators who repeated the reconstruction of five subjects three times, allowing defining 95% confidence interval ranging from ±1.8 to ±3.6mm. Intraclass correlation coefficient varied between 0.84 and 0.98. Comparison between RC tear patients and asymptomatic volunteers showed differences of glenohumeral displacements, especially in the superoinferior direction when shoulder was abducted at 20° and 45°. This study thus assessed the accuracy of the low-dose 3D biplane X-ray reconstruction technique for glenohumeral displacement assessment and showed potential in biomechanical and clinical research.

A multi-criteria evaluation platform for segmentation algorithms.

The purpose of this paper is to present a platform for evaluating segmentation algorithms that detect anatomical structures in medical images. Structure detection being subject to human interpretation, we first describe a method to define a ground truth model, i.e. a generated bronze standard, that will be the reference for subsequent analysis. This bronze standard will be characterized in order to retrieve its confidence level that will later be used to normalize the algorithm evaluation. We then describe how the developed platform helps in evaluating algorithm performances described using five evaluation criteria: accuracy, reliability, robustness, under/over segmentation sensitivity and outlier sensitivity. First, we explain how to extract those evaluation criteria using specific normalized metrics commonly found in the literature, then we present how to combine all the information in order to get a global evaluation of segmentation algorithms. Lastly, a radar-style graph analysis is presented for easy multi-criteria interpretation.

Performing accurate joint kinematics from 3-D in vivo image sequences through consensus-driven simultaneous registration.

This paper addresses the problem of the robust registration of multiple observations of the same object. Such a problem typically arises whenever it becomes necessary to recover the trajectory of an evolving object observed through standard 3-D medical imaging techniques. The instances of the tracked object are assumed to be variously truncated, locally subject to morphological evolutions throughout the sequence, and imprinted with significant segmentation errors as well as significant noise perturbations. The algorithm operates through the robust and simultaneous registration of all surface instances of a given object through median consensus. This operation consists of two interwoven processes set up to work in close collaboration. The first one progressively generates a median and implicit shape computed with respect to current estimations of the registration transformations, while the other refines these transformations with respect to the current estimation of their median shape. When compared with standard robust techniques, tests reveal significant improvements, both in robustness and precision. The algorithm is based on widely-used techniques, and proves highly effective while offering great flexibility of utilization.