scholarly journals Fully Automatic Knee Bone Detection and Segmentation on Three-Dimensional MRI

Diagnostics ◽  
2022 ◽  
Vol 12 (1) ◽  
pp. 123
Author(s):  
Rania Almajalid ◽  
Ming Zhang ◽  
Juan Shan

In the medical sector, three-dimensional (3D) images are commonly used like computed tomography (CT) and magnetic resonance imaging (MRI). The 3D MRI is a non-invasive method of studying the soft-tissue structures in a knee joint for osteoarthritis studies. It can greatly improve the accuracy of segmenting structures such as cartilage, bone marrow lesion, and meniscus by identifying the bone structure first. U-net is a convolutional neural network that was originally designed to segment the biological images with limited training data. The input of the original U-net is a single 2D image and the output is a binary 2D image. In this study, we modified the U-net model to identify the knee bone structures using 3D MRI, which is a sequence of 2D slices. A fully automatic model has been proposed to detect and segment knee bones. The proposed model was trained, tested, and validated using 99 knee MRI cases where each case consists of 160 2D slices for a single knee scan. To evaluate the model’s performance, the similarity, dice coefficient (DICE), and area error metrics were calculated. Separate models were trained using different knee bone components including tibia, femur, patella, as well as a combined model for segmenting all the knee bones. Using the whole MRI sequence (160 slices), the method was able to detect the beginning and ending bone slices first, and then segment the bone structures for all the slices in between. On the testing set, the detection model accomplished 98.79% accuracy and the segmentation model achieved DICE 96.94% and similarity 93.98%. The proposed method outperforms several state-of-the-art methods, i.e., it outperforms U-net by 3.68%, SegNet by 14.45%, and FCN-8 by 2.34%, in terms of DICE score using the same dataset.

Author(s):  
Praneet C. Bala ◽  
Benjamin R. Eisenreich ◽  
Seng Bum Michael Yoo ◽  
Benjamin Y. Hayden ◽  
Hyun Soo Park ◽  
...  

The rhesus macaque is an important model species in several branches of science, including neuroscience, psychology, ethology, and several fields of medicine. The utility of the macaque model would be greatly enhanced by the ability to precisely measure its behavior, specifically, its pose (position of multiple major body landmarks) in freely moving conditions. Existing approaches do not provide sufficient tracking. Here, we describe OpenMonkeyStudio, a novel deep learning-based markerless motion capture system for estimating 3D pose in freely moving macaques in large unconstrained environments. Our system makes use of 62 precisely calibrated and synchronized machine vision cameras that encircle an open 2.45m×2.45m×2.75m enclosure. The resulting multiview image streams allow for novel data augmentation via 3D reconstruction of hand-annotated images that in turn train a robust view-invariant deep neural network model. This view invariance represents an important advance over previous markerless 2D tracking approaches, and allows fully automatic pose inference on unconstrained natural motion. We show that OpenMonkeyStudio can be used to accurately recognize actions and track two monkey social interactions without human intervention. We also make the training data (195,228 images) and trained detection model publicly available.


2021 ◽  
Vol 25 (03) ◽  
pp. 488-500
Author(s):  
Oganes Ashikyan ◽  
Joel Wells ◽  
Avneesh Chhabra

AbstractMagnetic resonance imaging (MRI) is a common choice among various imaging modalities for the evaluation of hip conditions. Conventional MRI with two-dimensional acquisitions requires a significant amount of time and is limited by partial-volume artifacts and suboptimal fluid-to-cartilage contrast. Recent hardware and software advances have resulted in development of novel isotropic three-dimensional (3D) single-acquisition protocols that cover the volume of the entire hip and can be reconstructed in arbitrary planes for submillimeter assessment of bony and labro-cartilaginous structures in their planes of orientation. This technique facilitates superior identification of small labral tears and other hip lesions with better correlations with arthroscopy. In this review, we discuss technical details related to 3D MRI of the hip, its advantages, and its role in commonly encountered painful conditions that can be evaluated with great precision using this technology. The entities described are femoroacetabular impingement with acetabular labral tears, acetabular dysplasia, avascular necrosis, regional tendinopathies and tendon tears, bursitis, and other conditions.


2021 ◽  
Vol 25 (03) ◽  
pp. 418-424
Author(s):  
Blake C. Jones ◽  
Shivani Ahlawat ◽  
Laura M. Fayad

AbstractAdvances in magnetic resonance imaging (MRI) technology now enable the feasible three-dimensional (3D) acquisition of images. With respect to the imaging of musculoskeletal (MSK) tumors, literature is beginning to accumulate on the use of 3D MRI acquisition for tumor detection and characterization. The benefits of 3D MRI, including general advantages, such as decreased acquisition time, isotropic resolution, and increased image quality, are not only inherently useful for tumor imaging, but they also contribute to the feasibility of more specialized tumor-imaging techniques, such as whole-body MRI, and are reviewed here. Disadvantages of 3D acquisition, such as motion artifact and equipment requirements, do exist and are also discussed. Although further study is needed, 3D MRI acquisition will likely prove increasingly useful in the evaluation of patients with tumors of the MSK system.


2021 ◽  
Vol 25 (03) ◽  
pp. 455-467
Author(s):  
Faysal Altahawi ◽  
Jason Pierce ◽  
Mercan Aslan ◽  
Xiaojuan Li ◽  
Carl S. Winalski ◽  
...  

AbstractThree-dimensional (3D) magnetic resonance imaging (MRI) of the knee is widely used in musculoskeletal (MSK) imaging. Currently, 3D sequences are most commonly used for morphological imaging. Isotropic 3D MRI provides higher out-of-plane resolution than standard two-dimensional (2D) MRI, leading to reduced partial volume averaging artifacts and allowing for multiplanar reconstructions in any plane with any thickness from a single high-resolution isotropic acquisition. Specifically, isotropic 3D fast spin-echo imaging, with options for tissue weighting similar to those used in multiplanar 2D FSE imaging, is of particular interest to MSK radiologists. New applications for 3D spatially encoded sequences are also increasingly available for clinical use. These applications offer advantages over standard 2D techniques for metal artifact reduction, quantitative cartilage imaging, nerve imaging, and bone shape analysis. Emerging fast imaging techniques can be used to overcome the long acquisition times that have limited the adoption of 3D imaging in clinical protocols.


2013 ◽  
Vol 633 ◽  
pp. 3-14 ◽  
Author(s):  
Yan Rui ◽  
Aleksandar Subic ◽  
Monir Takla ◽  
Chun H. Wang ◽  
Anja Niehoff ◽  
...  

This paper presents a comprehensive biomimetic design approach to developing novel load bearing lightweight vehicle structures inspired by the structural properties of animal bones. Lightweight vehicle structures developed in this way would have increased stiffness at significantly reduced weight. In this research, trabecular (cancellous) bone was analyzed at the metaphyses of four different species including rat, rabbit, chicken, and sheep. Three-dimensional models of bone structures were reconstructed from micro-CT scanned images using the computer aided design software Mimics. Force resistance and energy absorption properties of relevant bone structures subjected to quasi-static compression loads were investigated and analysed using the Finite Element (FE) method. Based on the obtained results, the paper discusses the effects of load directions, bone structure allocation and model thickness on the energy absorption and force resistance of the bone structures. The simulation results obtained in this research were compared to the results of conventional vehicle side intrusion bars.


2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Kenneth W. Dunn ◽  
Chichen Fu ◽  
David Joon Ho ◽  
Soonam Lee ◽  
Shuo Han ◽  
...  

AbstractThe scale of biological microscopy has increased dramatically over the past ten years, with the development of new modalities supporting collection of high-resolution fluorescence image volumes spanning hundreds of microns if not millimeters. The size and complexity of these volumes is such that quantitative analysis requires automated methods of image processing to identify and characterize individual cells. For many workflows, this process starts with segmentation of nuclei that, due to their ubiquity, ease-of-labeling and relatively simple structure, make them appealing targets for automated detection of individual cells. However, in the context of large, three-dimensional image volumes, nuclei present many challenges to automated segmentation, such that conventional approaches are seldom effective and/or robust. Techniques based upon deep-learning have shown great promise, but enthusiasm for applying these techniques is tempered by the need to generate training data, an arduous task, particularly in three dimensions. Here we present results of a new technique of nuclear segmentation using neural networks trained on synthetic data. Comparisons with results obtained using commonly-used image processing packages demonstrate that DeepSynth provides the superior results associated with deep-learning techniques without the need for manual annotation.


2019 ◽  
Vol 25 (13) ◽  
pp. 1700-1709
Author(s):  
Xun Yang Hu ◽  
Luckshi Rajendran ◽  
Emmanuelle Lapointe ◽  
Roger Tam ◽  
David Li ◽  
...  

The most recent guidelines for magnetic resonance imaging (MRI) in multiple sclerosis (MS) recommend three-dimensional (3D) MRI sequences over their two-dimensional (2D) counterparts. This development has been made possible by advances in MRI scanner hardware and software. In this article, we review the 3D versions of conventional sequences, including T1-weighted, T2-weighted and fluid-attenuated inversion recovery (FLAIR), as well as more advanced scans, including double inversion recovery (DIR), FLAIR2, FLAIR*, phase-sensitive inversion recovery, and susceptibility weighted imaging (SWI).


2021 ◽  
Vol 25 (03) ◽  
pp. 425-432
Author(s):  
Fatemeh Ezzati ◽  
Majid Chalian ◽  
Parham Pezeshk

AbstractMagnetic resonance imaging (MRI) is commonly used to evaluate musculoskeletal pathologies due to its high spatial resolution and excellent tissue contrast. The diagnosis of rheumatic diseases can often be challenging. Investigation with conventional two-dimensional MRI is helpful for diagnosis and monitoring treatment. In the past few years, three-dimensional (3D) MRI has been more commonly used to assess joint pathologies including inflammatory and rheumatic diseases. This review discusses the techniques and protocols of 3D MRI and its diagnostic yield in the assessment of rheumatic diseases, along with different examples.


2021 ◽  
Vol 25 (03) ◽  
pp. 388-396
Author(s):  
Mohammad Samim

AbstractComputed tomography (CT) is most commonly used to produce three-dimensional (3D) models for evaluating bone and joint morphology in clinical practice. However, 3D models created from magnetic resonance imaging (MRI) data can be equally effective for comprehensive and accurate assessment of osseous and soft tissue structure morphology and pathology. The quality of 3D MRI models has steadily increased over time, with growing potential to replace 3D CT models in various musculoskeletal (MSK) applications. In practice, a single MRI examination for two-dimensional and 3D assessments can increase the value of MRI and simplify the pre- and postoperative imaging work-up. Multiple studies have shown excellent performance of 3D MRI models in shoulder injuries, in the hip in the setting of femoroacetabular impingement, and in the knee for the creation of bone surface models. Therefore, the utility of 3D MRI postprocessed models is expected to continue to rise and broaden in applications. Computer-based and artificial intelligence–assisted postprocessing techniques have tremendous potential to improve the efficiency of 3D model creation, opening many research avenues to validate the applicability of 3D MRI and establish 3D-specific quantitative assessment criteria. We provide a practice-focused overview of 3D MRI acquisition strategies, postprocessing techniques for 3D model creation, MSK applications of 3D MRI models, and an illustration of cases from our daily clinical practice.


2019 ◽  
Vol 2019 ◽  
pp. 1-13 ◽  
Author(s):  
Zuying Feng ◽  
Yan Li ◽  
Liang Hao ◽  
Yihu Yang ◽  
Tian Tang ◽  
...  

A biodegradable UV-cured resin has been fabricated via stereolithography apparatus (SLA). The formulation consists of a commercial polyurethane resin as an oligomer, trimethylolpropane trimethacrylate (TEGDMA) as a reactive diluent and phenylbis (2, 4, 6-trimethylbenzoyl)-phosphine oxide (Irgacure 819) as a photoinitiator. The tensile strength of the three-dimensional (3D) printed specimens is 68 MPa, 62% higher than that of the reference specimens (produced by direct casting). The flexural strength and modulus can reach 115 MPa and 5.8 GPa, respectively. A solvent-free method is applied to fabricate graphene-reinforced nanocomposite. Porous bone structures (a jawbone with a square architecture and a sternum with a round architecture) and gyroid scaffold of graphene-reinforced nanocomposite for bone tissue engineering have been 3D printed via SLA. The UV-crosslinkable graphene-reinforced biodegradable nanocomposite using SLA 3D printing technology can potentially remove important cost barriers for personalized biological tissue engineering as compared to the traditional mould-based multistep methods.


Sign in / Sign up

Export Citation Format

Share Document