Automated bony region identification using artificial neural networks: reliability and validation measurements

A review on the application of deep learning for CT reconstruction, bone segmentation and surgical planning in oral and maxillofacial surgery

Computer-assisted surgery (CAS) allows clinicians to personalize treatments and surgical interventions and has therefore become an increasingly popular treatment modality in maxillofacial surgery. The current maxillofacial CAS consists of three main steps: (1) CT image reconstruction, (2) bone segmentation, and (3) surgical planning. However, each of these three steps can introduce errors that can heavily affect the treatment outcome. As a consequence, tedious and time-consuming manual post-processing is often necessary to ensure that each step is performed adequately. One way to overcome this issue is by developing and implementing neural networks (NNs) within the maxillofacial CAS workflow. These learning algorithms can be trained to perform specific tasks without the need for explicitly defined rules. In recent years, an extremely large number of novel NN approaches have been proposed for a wide variety of applications, which makes it a difficult task to keep up with all relevant developments. This study therefore aimed to summarize and review all relevant NN approaches applied for CT image reconstruction, bone segmentation, and surgical planning. After full text screening, 76 publications were identified: 32 focusing on CT image reconstruction, 33 focusing on bone segmentation and 11 focusing on surgical planning. Generally, convolutional NNs were most widely used in the identified studies, although the multilayer perceptron was most commonly applied in surgical planning tasks. Moreover, the drawbacks of current approaches and promising research avenues are discussed.

The accuracy of clinical 3D printing in reconstructive surgery: literature review and in vivo validation study

A growing number of studies demonstrate the benefits of 3D printing in improving surgical efficiency and subsequently clinical outcomes. However, the number of studies evaluating the accuracy of 3D printing techniques remains scarce. All publications appraising the accuracy of 3D printing between 1950 and 2018 were reviewed using well-established databases, including PubMed, Medline, Web of Science and Embase. An in vivo validation study of our 3D printing technique was undertaken using unprocessed chicken radius bones (Gallus gallus domesticus). Calculating its maximum length, we compared the measurements from computed tomography (CT) scans (CT group), image segmentation (SEG group) and 3D-printed (3DP) models (3DP group). Twenty-eight comparison studies in 19 papers have been identified. Published mean error of CT-based 3D printing techniques were 0.46 mm (1.06%) in stereolithography, 1.05 mm (1.78%) in binder jet technology, 0.72 mm (0.82%) in PolyJet technique, 0.20 mm (0.95%) in fused filament fabrication (FFF) and 0.72 mm (1.25%) in selective laser sintering (SLS). In the current in vivo validation study, mean errors were 0.34 mm (0.86%) in CT group, 1.02 mm (2.51%) in SEG group and 1.16 mm (2.84%) in 3DP group. Our Peninsula 3D printing technique using a FFF 3D printer thus produced accuracy similar to the published studies (1.16 mm, 2.84%). There was a statistically significant difference (P<10-4) between the CT group and the latter SEG and 3DP groups indicating that most of the error is introduced during image segmentation stage.

Artificial Intelligence in Musculoskeletal Imaging: Current Status and Future Directions

OBJECTIVE. The objective of this article is to show how artificial intelligence (AI) has impacted different components of the imaging value chain thus far as well as to describe its potential future uses. CONCLUSION. The use of AI has the potential to greatly enhance every component of the imaging value chain. From assessing the appropriateness of imaging orders to helping predict patients at risk for fracture, AI can increase the value that musculoskeletal imagers provide to their patients and to referring clinicians by improving image quality, patient centricity, imaging efficiency, and diagnostic accuracy.

Texture analysis of paraspinal musculature in MRI of the lumbar spine: analysis of the lumbar stenosis outcome study (LSOS) data

OBJECTIVE

To evaluate association of fatty infiltration in paraspinal musculature with clinical outcomes in patients suffering from lumbar spinal stenosis (LSS) using qualitative and quantitative grading in magnetic resonance imaging (MRI).

MATERIALS AND METHODS

In this retrospective study, texture analysis (TA) was performed on postprocessed axial T2 weighted (w) MR images at level L3/4 using dedicated software (MaZda) in 62 patients with LSS. Associations in fatty infiltration between qualitative Goutallier and quantitative TA findings with two clinical outcome measures, Spinal stenosis measure (SSM) score and walking distance, at baseline and regarding change over time were assessed using machine learning algorithms and multiple logistic regression models.

RESULTS

Quantitative assessment of fatty infiltration using the histogram TA feature "mean" showed higher interreader reliability (ICC 0.83-0.97) compared to the Goutallier staging (κ = 0.69-0.93). No correlation between Goutallier staging and clinical outcome measures was observed. Among 151 TA features, only TA feature "mean" of the spinotransverse group showed a significant but weak correlation with worsened SSM (p = 0.046). TA feature "S(3,3) entropy" showed a significant but weak association with worsened WD over 12 months (p = 0.046).

CONCLUSION

MR TA is a reproducible tool to quantitatively assess paraspinal fatty infiltration, but there is no clear association with the clinical outcome in asymptomatic LSS patients.

Automated Bone Segmentation and Surface Evaluation of a Small Animal Model of Post-Traumatic Osteoarthritis

MicroCT imaging allows for noninvasive microstructural evaluation of mineralized bone tissue, and is essential in studies of small animal models of bone and joint diseases. Automatic segmentation and evaluation of articular surfaces is challenging. Here, we present a novel method to create knee joint surface models, for the evaluation of PTOA-related joint changes in the rat using an atlas-based diffeomorphic registration to automatically isolate bone from surrounding tissues. As validation, two independent raters manually segment datasets and the resulting segmentations were compared to our novel automatic segmentation process. Data were evaluated using label map volumes, overlap metrics, Euclidean distance mapping, and a time trial. Intraclass correlation coefficients were calculated to compare methods, and were greater than 0.90. Total overlap, union overlap, and mean overlap were calculated to compare the automatic and manual methods and ranged from 0.85 to 0.99. A Euclidean distance comparison was also performed and showed no measurable difference between manual and automatic segmentations. Furthermore, our new method was 18 times faster than manual segmentation. Overall, this study describes a reliable, accurate, and automatic segmentation method for mineralized knee structures from microCT images, and will allow for efficient assessment of bony changes in small animal models of PTOA.

EM segmentation of the distal femur and proximal tibia: a high-throughput approach to anatomic surface generation

Fully automated segmentation of computed tomography (CT) images remains a challenge for musculoskeletal researchers. The surfaces generated from image segmentations are valuable for surgical evaluation and planning. Previously, we demonstrated the expectation maximization (EM) algorithm as a semi-automated method of bone segmentation from CT images. In this work, we improve upon the methodology of probability map generation and demonstrate extended applicability of EM-based segmentation to the distal femur and proximal tibia using 72 CT image sets. We also compare the resulting EM segmentations to manual tracings using overlap metrics and time. In the case of the distal femur, the resulting quality metrics had mean values of 0.91 and 0.95 for the Jaccard and Dice metrics, respectively. For the proximal tibia, the Jaccard and Dice metrics were 0.90 and 0.95, respectively. The EM segmentation method was 8 times faster than the average manual segmentation and required less than 4% of the human rater time. Overall, the EM algorithm offers reliable image segmentations with an increased efficiency in comparison to manual segmentation techniques.

Toward the development of virtual surgical tools to aid orthopaedic FE analyses

Computational models of joint anatomy and function provide a means for biomechanists, physicians, and physical therapists to understand the effects of repetitive motion, acute injury, and degenerative diseases. Finite element models, for example, may be used to predict the outcome of a surgical intervention or to improve the design of prosthetic implants. Countless models have been developed over the years to address a myriad of orthopaedic procedures. Unfortunately, few studies have incorporated patient-specific models. Historically, baseline anatomic models have been used due to the demands associated with model development. Moreover, surgical simulations impose additional modeling challenges. Current meshing practices do not readily accommodate the inclusion of implants. Our goal is to develop a suite of tools (virtual instruments and guides) which enable surgical procedures to be readily simulated and to facilitate the development of all-hexahedral finite element mesh definitions.

Current progress in patient-specific modeling

We present a survey of recent advancements in the emerging field of patient-specific modeling (PSM). Researchers in this field are currently simulating a wide variety of tissue and organ dynamics to address challenges in various clinical domains. The majority of this research employs three-dimensional, image-based modeling techniques. Recent PSM publications mostly represent feasibility or preliminary validation studies on modeling technologies, and these systems will require further clinical validation and usability testing before they can become a standard of care. We anticipate that with further testing and research, PSM-derived technologies will eventually become valuable, versatile clinical tools.

An interactive multiblock approach to meshing the spine

Finite element (FE) analysis is a useful tool to study spine biomechanics as a complement to laboratory-driven experimental studies. Although individualized models have the potential to yield clinically relevant results, the demands associated with modeling the geometric complexity of the spine often limit its utility. Existing spine FE models share similar characteristics and are often based on similar assumptions, but vary in geometric fidelity due to the mesh generation techniques that were used. Using existing multiblock techniques, we propose mesh generation methods that ease the effort and reduce the time required to create subject-specific allhexahedral finite element models of the spine. We have demonstrated the meshing techniques by creating a C4-C5 functional spinal unit and validated it by comparing the resultant motions and vertebral strains with data reported in the literature.

IA-FEMesh: an open-source, interactive, multiblock approach to anatomic finite element model development

Finite element (FE) analysis is a valuable tool in musculoskeletal research. The demands associated with mesh development, however, often prove daunting. In an effort to facilitate anatomic FE model development we have developed an open-source software toolkit (IA-FEMesh). IA-FEMesh employs a multiblock meshing scheme aimed at hexahedral mesh generation. An emphasis has been placed on making the tools interactive, in an effort to create a user friendly environment. The goal is to provide an efficient and reliable method for model development, visualization, and mesh quality evaluation. While these tools have been developed, initially, in the context of skeletal structures they can be applied to countless applications.

Semi-automated phalanx bone segmentation using the expectation maximization algorithm

Medical imaging technologies have allowed for in vivo exploration and evaluation of the human musculoskeletal system. Three-dimensional bone models generated using image-segmentation techniques provide a means to optimize individualized orthopedic surgical procedures using engineering analyses. However, many of the current segmentation techniques are not clinically practical due to the required time and human intervention. As a proof of concept, we demonstrate the use of an expectation maximization (EM) algorithm to segment the hand phalanx bones, and hypothesize that this semi-automated technique will improve the efficiency while providing similar definitions as compared to a manual rater. Our results show a relative overlap of the proximal, middle, and distal phalanx bones of 0.83, 0.79, and 0.72 for the EM technique when compared to validated manual segmentations. The EM segmentations were also compared to 3D surface scans of the cadaveric specimens, which resulted in distance maps showing an average distance for the proximal, middle, and distal phalanx bones of 0.45, 0.46, and 0.51 mm, respectively. The EM segmentation improved on the segmentation speed of the manual techniques by a factor of eight. Overall, the manual segmentations had greater relative overlap metric values, which suggests that the manual segmentations are a better fit to the actual surface of the bone. As shown by the comparison to the bone surface scans, the EM technique provides a similar representation of the anatomic structure and offers an increase in efficiency that could help to reduce the time needed for defining anatomical structures from CT scans.