Automatic Extraction of Femur Contours from Calibrated Fluoroscopic Images

Abstract

Automatic identification and extraction of bone contours from x-ray images is an essential first step task for further medical image analysis. In this paper we propose a 3D statistical model based framework for the proximal femur contour extraction from calibrated x-ray images. The automatic initialization is solved by an Estimation of Bayesian Network Algorithm to fit a multiple component geometrical model to the x-ray data. The contour extraction is accomplished by a non-rigid 2D/3D registration between a 3D statistical model and the x-ray images, in which bone contours are extracted by a graphical model based Bayesian inference. Preliminary experiments on clinical data sets verified its validity. [10] 3D statistical models are used for 2D segmentation and 3D reconstruction from calibrated 2D fluoroscopic images (location and orientation of the fluoroscopic source w.r.t. the image acquisition planes are known). Compared with 2D statistical modes, 3D statistical model usually only contains shape information but not the intensity information on the 2D images. In principle it can be used for segmenting an image taken from an arbitary view direction. 3D statistical model also need an initialization, which is usually manually defined [7][9]. Due to the dense mesh of the 3D statistical model [16], fully automated solutions based on evolutionary algorithm is computational expensive [17]. MotivationIn this paper we propose a 3D statistical model based fully automatic segmentation framework for calibrated fluoroscopic images. In our approach, the initialization is accomplished by an Estimation of Bayesian Network Algorithm on a simplified multiple component model instead of the triangulated surface mesh of the 3D model, which reduces the computational complexity. The statistical model based fine shape extraction is achieved by a Bayesian inference on a Bayesian network, which encodes the shape and texture information of the model and therefore enhances the robustness and accuracy of the contour extraction. Related WorkBayesian network based approach [18][19][20] is used to identify or track object such as human body, which is composed with multiple subparts and among the subparts structral or kinematic constrains exist. The Bayesian network embeds the subparts constraints in a graphical model associated with image observations. Bayesian network is also exploited for finding deformable shapes

A new 2D‐3D registration gold‐standard dataset for the hip joint based on uncertainty modeling

“…Experimental methods for patient-specific QA in advanced radiotherapy are, however, time-consuming in both manpower and accelerator time and have been shown to be unable to detect some unacceptable plans. [6][7][8][9][10][11] Recent studies have demonstrated a sensitivity of only 5% to detect IMRT plan errors using IMRT pretreatment measurements. 12,13 Moreover, as treatment planning becomes more efficient and the number of patients treated with advanced radiotherapy techniques steadily increases, measurement-based verification may result in a continued increase in workload.…”

“… 1 In spine surgery, the registration of single vertebrae is mostly used for pedicle screw placement and cement reinforcement. 2 , 3 , 4 For total hip replacement, the registration is used for intra‐operative positioning of the femoral implant 5 , 6 , 7 and post‐operative analysis of cup placement. 8 , 9 , 10 In orthopedic diagnostics, the 3D curvature of scoliotic spine 11 and the scoliotic rib cage were analyzed.…”

A robust channel network extraction method combining discrete curve evolution and the skeleton construction technique

“…Therefore, the exploration of extracting landform features from CL data is also necessary for hydrological applications. Based on a Delaunay triangulation built from CLs, skeleton construction techniques have been proposed to extract the landform features by using "flat triangles" [41] or "crust and skeleton extraction" [9]. However, the skeleton construction methods usually fail to create topologically correct drainage systems, due to the lack of connectivity.…”

Unsupervised Reconstruction of a Patient-Specific Surface Model of a Proximal Femur from Calibrated Fluoroscopic Images

“…The image-to-model correspondence is established using a non-rigid 2D point matching process, which iteratively uses a symmetric injective nearestneighbor mapping operator and 2D thin-plate splines based deformation to find a fraction of best matched 2D point pairs between features detected from the fluoroscopic images and those extracted from the 3D model. The image contours of the proximal femur are extracted from the input images by a graphical model based Bayesian inference [6] whereas the apparent contours of the 3D model are extracted using an approach described in [7]. The obtained 2D point pairs are then used to set up a set of 3D point pairs such that we turn a 2D-3D reconstruction problem to a 3D-3D one.…”

“…The 3D/3D reconstruction problem is then solved optimally in three sequential stages. For details, we refer to our previous works [4] and [6].…”