A 3D active model framework for segmentation of proximal femur in MR images

A Two stage deep learning network for automated femoral segmentation in bilateral lower limb CT scans

This study presents the development of a deep learning-based two-stage network designed for the efficient and precise segmentation of the femur in full lower limb CT images. The proposed network incorporates a dual-phase approach: rapid delineation of regions of interest followed by semantic segmentation of the femur. The experimental dataset comprises 100 samples obtained from a hospital, partitioned into 85 for training, 8 for validation, and 7 for testing. In the first stage, the model achieves an average Intersection over Union of 0.9671 and a mean Average Precision of 0.9656, effectively delineating the femoral region with high accuracy. During the second stage, the network attains an average Dice coefficient of 0.953, sensitivity of 0.965, specificity of 0.998, and pixel accuracy of 0.996, ensuring precise segmentation of the femur. When compared to the single-stage SegResNet architecture, the proposed two-stage model demonstrates faster convergence during training, reduced inference times, higher segmentation accuracy, and overall superior performance. Comparative evaluations against the TransUnet model further highlight the network's notable advantages in accuracy and robustness. In summary, the proposed two-stage network offers an efficient, accurate, and autonomous solution for femur segmentation in large-scale and complex medical imaging datasets. Requiring relatively modest training and computational resources, the model exhibits significant potential for scalability and clinical applicability, making it a valuable tool for advancing femoral image segmentation and supporting diagnostic workflows.

Noninvasive shape-fitting method quantifies cam morphology in femoroacetabular impingement syndrome: Implications for diagnosis and surgical planning

There are considerable limitations associated with the standard 2D imaging currently used for the diagnosis and surgical planning of cam-type femoroacetabular impingement syndrome (FAIS). The aim of this study was to determine the accuracy of a new patient-specific shape-fitting method that quantifies cam morphology in 3D based solely on preoperative MRI imaging. Preoperative and postoperative 1.5T MRI scans were performed on n = 15 patients to generate 3D models of the proximal femur, in turn used to create the actual and the virtual cam. The actual cams were reconstructed by subtracting the postoperative from the preoperative 3D model and used as reference, while the virtual cams were generated by subtracting the preoperative 3D model from the virtual shape template produced with the shape-fitting method based solely on preoperative MRI scans. The accuracy of the shape-fitting method was tested on all patients by evaluating the agreement between the metrics of height, surface area, and volume that quantified virtual and actual cams. Accuracy of the shape-fitting method was demonstrated obtaining a 97.8% average level of agreement between these metrics. In conclusion, the shape-fitting technique is a noninvasive and patient-specific tool for the quantification and localization of cam morphology. Future studies will include the implementation of the technique within a clinically based software for diagnosis and surgical planning for cam-type FAIS.

MRI-- and CT--based metrics for the quantification of arthroscopic bone resections in femoroacetabular impingement syndrome

The purpose of this in vitro study was to quantify the bone resected from the proximal femur during hip arthroscopy using metrics generated from magnetic resonance imaging (MRI) and computed tomography (CT) reconstructed three-dimensional (3D) bone models. Seven cadaveric hemi-pelvises underwent both a 1.5 T MRI and CT scan before and following an arthroscopic proximal femoral osteochondroplasty. The images from MRI and CT were segmented to generate 3D proximal femoral surface models. A validated 3D--3D registration method was used to compare surface--to--surface distances between the 3D models before and following surgery. The new metrics of maximum height, mean height, surface area and volume, were computed to quantify bone resected during osteochondroplasty. Stability of the metrics across imaging modalities was established through paired sample t--tests and bivariate correlation. Bivariate correlation analyses indicated strong correlations between all metrics (r = 0.728--0.878) computed from MRI and CT derived models. There were no differences in the MRI- and CT-based metrics used to quantify bone resected during femoral osteochondroplasty. Preoperative- and postoperative MRI and CT derived 3D bone models can be used to quantify bone resected during femoral osteochondroplasty, without significant differences between the imaging modalities.

A deep learning-based approach to automatic proximal femur segmentation in quantitative CT images

Automatic CT segmentation of proximal femur has a great potential for use in orthopedic diseases, especially in the imaging-based assessments of hip fracture risk. In this study, we proposed an approach based on deep learning for the fast and automatic extraction of the periosteal and endosteal contours of proximal femur in order to differentiate cortical and trabecular bone compartments. A three-dimensional (3D) end-to-end fully convolutional neural network (CNN), which can better combine the information among neighbor slices and get more accurate segmentation results by 3D CNN, was developed for our segmentation task. The separation of cortical and trabecular bones derived from the QCT software MIAF-Femur was used as the segmentation reference. Two models with the same network structures were trained, and they achieved a dice similarity coefficient (DSC) of 97.82% and 96.53% for the periosteal and endosteal contours, respectively. Compared with MIAF-Femur, it takes half an hour to segment a case, and our CNN model takes a few minutes. To verify the excellent performance of our model for proximal femoral segmentation, we measured the volumes of different parts of the proximal femur and compared it with the ground truth, and the relative errors of femur volume between predicted result and ground truth are all less than 5%. This approach will be expected helpful to measure the bone mineral densities of cortical and trabecular bones, and to evaluate the bone strength based on FEA.

Multi-landmark environment analysis with reinforcement learning for pelvic abnormality detection and quantification

Morphological abnormalities of the femoroacetabular (hip) joint are among the most common human musculoskeletal disorders and often develop asymptomatically at early easily treatable stages. In this paper, we propose an automated framework for landmark-based detection and quantification of hip abnormalities from magnetic resonance (MR) images. The framework relies on a novel idea of multi-landmark environment analysis with reinforcement learning. In particular, we merge the concepts of the graphical lasso and Morris sensitivity analysis with deep neural networks to quantitatively estimate the contribution of individual landmark and landmark subgroup locations to the other landmark locations. Convolutional neural networks for image segmentation are utilized to propose the initial landmark locations, and landmark detection is then formulated as a reinforcement learning (RL) problem, where each landmark-agent can adjust its position by observing the local MR image neighborhood and the locations of the most-contributive landmarks. The framework was validated on T1-, T2- and proton density-weighted MR images of 260 patients with the aim to measure the lateral center-edge angle (LCEA), femoral neck-shaft angle (NSA), and the anterior and posterior acetabular sector angles (AASA and PASA) of the hip, and derive the quantitative abnormality metrics from these angles. The framework was successfully tested using the UNet and feature pyramid network (FPN) segmentation architectures for landmark proposal generation, and the deep Q-network (DeepQN), deep deterministic policy gradient (DDPG), twin delayed deep deterministic policy gradient (TD3), and actor-critic policy gradient (A2C) RL networks for landmark position optimization. The resulting overall landmark detection error of 1.5 mm and angle measurement error of 1.4° indicates a superior performance in comparison to existing methods. Moreover, the automatically estimated abnormality labels were in 95% agreement with those generated by an expert radiologist.

The use of 3D printed models for the pre-operative planning of surgical correction of pediatric hip deformities: a case series and concise review of the literature

BACKGROUND AND AIM

Three-dimensional (3D) printing is prevailing in surgical planning of complex cases. The aim of this study is to describe the use of 3D printed models during the surgical planning for the treatment of four pediatric hip deformity cases. Moreover, pediatric pelvic deformities analyzed by 3D printed models have been object of a concise review.

METHODS

All treated patients were females, with an average age of 5 years old. Patients' dysplastic pelvises were 3D-printed in real scale using processed files from Computed Tomography (CT) or Magnetic Resonance Imaging (MRI). Data about 3D printing, surgery time, blood loss and fluoroscopy have been recorded.

RESULTS

The Zanoli-Pemberton or Ganz-Paley osteotomies were performed on the four 3D printed models, then the real surgery was performed in the operating room. Time and costs to produce 3D printed models were respectively on average 17:26 h and 34.66 €. The surgical duration took about 87.5 min while the blood loss average was 1.9 ml/dl. Fluoroscopy time was 21 sec. MRI model resulted inaccurate and more difficult to produce. 10 papers have been selected for the concise literature review.

CONCLUSIONS

3D printed models have proved themselves useful in the reduction of surgery time, blood loss and ionizing radiation, as well as they have improved surgical outcomes. 3D printed model is a valid tool to deepen the complex anatomy and orientate surgical choices by allowing surgeons to carefully plan the surgery.

Three-Dimensional Magnetic Resonance Imaging Bone Models of the Hip Joint Using Deep Learning: Dynamic Simulation of Hip Impingement for Diagnosis of Intra- and Extra-articular Hip Impingement

Background:

Dynamic 3-dimensional (3D) simulation of hip impingement enables better understanding of complex hip deformities in young adult patients with femoroacetabular impingement (FAI). Deep learning algorithms may improve magnetic resonance imaging (MRI) segmentation.

Purpose:

(1) To evaluate the accuracy of 3D models created using convolutional neural networks (CNNs) for fully automatic MRI bone segmentation of the hip joint, (2) to correlate hip range of motion (ROM) between manual and automatic segmentation, and (3) to compare location of hip impingement in 3D models created using automatic bone segmentation in patients with FAI.

Study Design:

Cohort study (diagnosis); Level of evidence, 3.

Methods:

The authors retrospectively reviewed 31 hip MRI scans from 26 symptomatic patients (mean age, 27 years) with hip pain due to FAI. All patients had matched computed tomography (CT) and MRI scans of the pelvis and the knee. CT- and MRI-based osseous 3D models of the hip joint of the same patients were compared (MRI: T1 volumetric interpolated breath-hold examination high-resolution sequence; 0.8 mm³ isovoxel). CNNs were used to develop fully automatic bone segmentation of the hip joint, and the 3D models created using this method were compared with manual segmentation of CT- and MRI-based 3D models. Impingement-free ROM and location of hip impingement were calculated using previously validated collision detection software.

Results:

The difference between the CT- and MRI-based 3D models was <1 mm, and the difference between fully automatic and manual segmentation of MRI-based 3D models was <1 mm. The correlation of automatic and manual MRI-based 3D models was excellent and significant for impingement-free ROM (r = 0.995; P < .001), flexion (r = 0.953; P < .001), and internal rotation at 90° of flexion (r = 0.982; P < .001). The correlation for impingement-free flexion between automatic MRI-based 3D models and CT-based 3D models was 0.953 (P < .001). The location of impingement was not significantly different between manual and automatic segmentation of MRI-based 3D models, and the location of extra-articular hip impingement was not different between CT- and MRI-based 3D models.

Conclusion:

CNN can potentially be used in clinical practice to provide rapid and accurate 3D MRI hip joint models for young patients. The created models can be used for simulation of impingement during diagnosis of intra- and extra-articular hip impingement to enable radiation-free and patient-specific surgical planning for hip arthroscopy and open hip preservation surgery.

ST-V-Net: incorporating shape prior into convolutional neural networks for proximal femur segmentation

We aim to develop a deep-learning-based method for automatic proximal femur segmentation in quantitative computed tomography (QCT) images. We proposed a spatial transformation V-Net (ST-V-Net), which contains a V-Net and a spatial transform network (STN) to extract the proximal femur from QCT images. The STN incorporates a shape prior into the segmentation network as a constraint and guidance for model training, which improves model performance and accelerates model convergence. Meanwhile, a multi-stage training strategy is adopted to fine-tune the weights of the ST-V-Net. We performed experiments using a QCT dataset which included 397 QCT subjects. During the experiments for the entire cohort and then for male and female subjects separately, 90% of the subjects were used in ten-fold stratified cross-validation for training and the rest of the subjects were used to evaluate the performance of models. In the entire cohort, the proposed model achieved a Dice similarity coefficient (DSC) of 0.9888, a sensitivity of 0.9966 and a specificity of 0.9988. Compared with V-Net, the Hausdorff distance was reduced from 9.144 to 5.917 mm, and the average surface distance was reduced from 0.012 to 0.009 mm using the proposed ST-V-Net. Quantitative evaluation demonstrated excellent performance of the proposed ST-V-Net for automatic proximal femur segmentation in QCT images. In addition, the proposed ST-V-Net sheds light on incorporating shape prior to segmentation to further improve the model performance.

Semantic segmentation of the multiform proximal femur and femoral head bones with the deep convolutional neural networks in low quality MRI sections acquired in different MRI protocols

Medical image segmentation is one of the most crucial issues in medical image processing and analysis. In general, segmentation of the various structures in medical images is performed for the further image analyzes such as quantification, assessment, diagnosis, prognosis and classification. In this paper, a research study for the 2D semantic segmentation of the multiform, both spheric and aspheric, femoral head and proximal femur bones in magnetic resonance imaging (MRI) sections of the patients with Legg-Calve-Perthes disease (LCPD) with the deep convolutional neural networks (CNNs) is presented. In the scope of the proposed study, bilateral hip MRI sections acquired in coronal plane were used. The main characteristic of the MRI sections that were used is to be low quality images which were obtained in different MRI protocols by using 3 different MRI scanners with 1.5 T imaging capability. In performance evaluations, promising segmentation results were achieved with deep CNNs in low quality MRI sections acquired in different MRI protocols. A success rate about 90% was observed in semantic segmentation of the multiform femoral head and proximal femur bones in a total of 194 MRI sections obtained from 33 MRI sequences of 13 patients with deep CNNs.

Osteoporosis Recognition in Rats under Low-Power Lens Based on Convexity Optimization Feature Fusion

Considering the poor medical conditions in some regions of China, this paper attempts to develop a simple and easy way to extract and process the bone features of blurry medical images and improve the diagnosis accuracy of osteoporosis as much as possible. After reviewing the previous studies on osteoporosis, especially those focusing on texture analysis, a convexity optimization model was proposed based on intra-class dispersion, which combines texture features and shape features. Experimental results show that the proposed model boasts a larger application scope than Lasso, a popular feature selection method that only supports generalized linear models. The research findings ensure the accuracy of osteoporosis diagnosis and enjoy good potentials for clinical application.

Segmentation of the proximal femur in radial MR scans using a random forest classifier and deformable model registration

BACKGROUND

Radial 2D MRI scans of the hip are routinely used for the diagnosis of the cam type of femoroacetabular impingement (FAI) and of avascular necrosis (AVN) of the femoral head, both considered causes of hip joint osteoarthritis in young and active patients. A method for automated and accurate segmentation of the proximal femur from radial MRI scans could be very useful in both clinical routine and biomechanical studies. However, to our knowledge, no such method has been published before.

PURPOSE

The aims of this study are the development of a system for the segmentation of the proximal femur from radial MRI scans and the reconstruction of its 3D model that can be used for diagnosis and planning of hip-preserving surgery.

METHODS

The proposed system relies on: (a) a random forest classifier and (b) the registration of a 3D template mesh of the femur to the radial slices based on a physically based deformable model. The input to the system are the radial slices and the manually specified positions of three landmarks. Our dataset consists of the radial MRI scans of 25 patients symptomatic of FAI or AVN and accompanying manual segmentation of the femur, treated as the ground truth.

RESULTS

The achieved segmentation of the proximal femur has an average Dice similarity coefficient (DSC) of 96.37 ± 1.55%, an average symmetric mean absolute distance (SMAD) of 0.94 ± 0.39 mm and an average Hausdorff distance of 2.37 ± 1.14 mm. In the femoral head subregion, the average SMAD is 0.64 ± 0.18 mm and the average Hausdorff distance is 1.41 ± 0.56 mm.

CONCLUSIONS

We validated a semiautomated method for the segmentation of the proximal femur from radial MR scans. A 3D model of the proximal femur is also reconstructed, which can be used for the planning of hip-preserving surgery.

Segmentation of the Proximal Femur from MR Images using Deep Convolutional Neural Networks

Magnetic resonance imaging (MRI) has been proposed as a complimentary method to measure bone quality and assess fracture risk. However, manual segmentation of MR images of bone is time-consuming, limiting the use of MRI measurements in the clinical practice. The purpose of this paper is to present an automatic proximal femur segmentation method that is based on deep convolutional neural networks (CNNs). This study had institutional review board approval and written informed consent was obtained from all subjects. A dataset of volumetric structural MR images of the proximal femur from 86 subjects were manually-segmented by an expert. We performed experiments by training two different CNN architectures with multiple number of initial feature maps, layers and dilation rates, and tested their segmentation performance against the gold standard of manual segmentations using four-fold cross-validation. Automatic segmentation of the proximal femur using CNNs achieved a high dice similarity score of 0.95 ± 0.02 with precision = 0.95 ± 0.02, and recall = 0.95 ± 0.03. The high segmentation accuracy provided by CNNs has the potential to help bring the use of structural MRI measurements of bone quality into clinical practice for management of osteoporosis.

Optimisation of three-dimensional lower jaw resection margin planning using a novel Black Bone magnetic resonance imaging protocol

BACKGROUND

MRI is the optimal method for sensitive detection of tumour tissue and pre-operative staging in oral cancer. When jawbone resections are necessary, the current standard of care for oral tumour surgery in our hospital is 3D virtual planning from CT data. 3D printed jawbone cutting guides are designed from the CT data. The tumour margins are difficult to visualise on CT, whereas they are clearly visible on MRI scans. The aim of this study was to change the conventional CT-based workflow by developing a method for 3D MRI-based lower jaw models. The MRI-based visualisation of the tumour aids in planning bone resection margins.

MATERIALS AND FINDINGS

A workflow for MRI-based 3D surgical planning with bone cutting guides was developed using a four-step approach. Key MRI parameters were defined (phase 1), followed by an application of selected Black Bone MRI sequences on healthy volunteers (phase 2). Three Black Bone MRI sequences were chosen for phase 3: standard, fat saturated, and an out of phase sequence. These protocols were validated by applying them on patients (n = 10) and comparison to corresponding CT data. The mean deviation values between the MRI- and the CT-based models were 0.63, 0.59 and 0.80 mm for the three evaluated Black Bone MRI sequences. Phase 4 entailed examination of the clinical value during surgery, using excellently fitting printed bone cutting guides designed from MRI-based lower jaw models, in two patients with oral cancer. The mean deviation of the resection planes was 2.3 mm, 3.8 mm for the fibula segments, and the mean axis deviation was the fibula segments of 1.9°.

CONCLUSIONS

This study offers a method for 3D virtual resection planning and surgery using cutting guides based solely on MRI imaging. Therefore, no additional CT data are required for 3D virtual planning in oral cancer surgery.