Automatic Vertebral Body Segmentation Based on Deep Learning of Dixon Images for Bone Marrow Fat Fraction Quantification

A novel deep learning method for large-scale analysis of bone marrow adiposity using UK Biobank Dixon MRI data

Background

Bone marrow adipose tissue (BMAT) represents > 10% fat mass in healthy humans and can be measured by magnetic resonance imaging (MRI) as the bone marrow fat fraction (BMFF). Human MRI studies have identified several diseases associated with BMFF but have been relatively small scale. Population-scale studies therefore have huge potential to reveal BMAT's true clinical relevance. The UK Biobank (UKBB) is undertaking MRI of 100,000 participants, providing the ideal opportunity for such advances.

Objective

To establish deep learning for high-throughput multi-site BMFF analysis from UKBB MRI data.

Materials and methods

We studied males and females aged 60-69. Bone marrow (BM) segmentation was automated using a new lightweight attention-based 3D U-Net convolutional neural network that improved segmentation of small structures from large volumetric data. Using manual segmentations from 61-64 subjects, the models were trained to segment four BM regions of interest: the spine (thoracic and lumbar vertebrae), femoral head, total hip and femoral diaphysis. Models were tested using a further 10-12 datasets per region and validated using datasets from 729 UKBB participants. BMFF was then quantified and pathophysiological characteristics assessed, including site- and sex-dependent differences and the relationships with age, BMI, bone mineral density, peripheral adiposity, and osteoporosis.

Results

Model accuracy matched or exceeded that for conventional U-Nets, yielding Dice scores of 91.2% (spine), 94.5% (femoral head), 91.2% (total hip) and 86.6% (femoral diaphysis). One case of severe scoliosis prevented segmentation of the spine, while one case of Non-Hodgkin Lymphoma prevented segmentation of the spine, femoral head and total hip because of T2 signal depletion; however, successful segmentation was not disrupted by any other pathophysiological variables. The resulting BMFF measurements confirmed expected relationships between BMFF and age, sex and bone density, and identified new site- and sex-specific characteristics.

Conclusions

We have established a new deep learning method for accurate segmentation of small structures from large volumetric data, allowing high-throughput multi-site BMFF measurement in the UKBB. Our findings reveal new pathophysiological insights, highlighting the potential of BMFF as a novel clinical biomarker. Applying our method across the full UKBB cohort will help to reveal the impact of BMAT on human health and disease.

Multi-Modal Modality-Masked Diffusion Network for Brain MRI Synthesis With Random Modality Missing

Synthesis of unavailable imaging modalities from available ones can generate modality-specific complementary information and enable multi-modality based medical images diagnosis or treatment. Existing generative methods for medical image synthesis are usually based on cross-modal translation between acquired and missing modalities. These methods are usually dedicated to specific missing modality and perform synthesis in one shot, which cannot deal with varying number of missing modalities flexibly and construct the mapping across modalities effectively. To address the above issues, in this paper, we propose a unified Multi-modal Modality-masked Diffusion Network (M2DN), tackling multi-modal synthesis from the perspective of "progressive whole-modality inpainting", instead of "cross-modal translation". Specifically, our M2DN considers the missing modalities as random noise and takes all the modalities as a unity in each reverse diffusion step. The proposed joint synthesis scheme performs synthesis for the missing modalities and self-reconstruction for the available ones, which not only enables synthesis for arbitrary missing scenarios, but also facilitates the construction of common latent space and enhances the model representation ability. Besides, we introduce a modality-mask scheme to encode availability status of each incoming modality explicitly in a binary mask, which is adopted as condition for the diffusion model to further enhance the synthesis performance of our M2DN for arbitrary missing scenarios. We carry out experiments on two public brain MRI datasets for synthesis and downstream segmentation tasks. Experimental results demonstrate that our M2DN outperforms the state-of-the-art models significantly and shows great generalizability for arbitrary missing modalities.

Cracking the Chronic Pain code: A scoping review of Artificial Intelligence in Chronic Pain research

OBJECTIVE

The aim of this review is to identify gaps and provide a direction for future research in the utilization of Artificial Intelligence (AI) in chronic pain (CP) management.

METHODS

A comprehensive literature search was conducted using various databases, including Ovid MEDLINE, Web of Science Core Collection, IEEE Xplore, and ACM Digital Library. The search was limited to studies on AI in CP research, focusing on diagnosis, prognosis, clinical decision support, self-management, and rehabilitation. The studies were evaluated based on predefined inclusion criteria, including the reporting quality of AI algorithms used.

RESULTS

After the screening process, 60 studies were reviewed, highlighting AI's effectiveness in diagnosing and classifying CP while revealing gaps in the attention given to treatment and rehabilitation. It was found that the most commonly used algorithms in CP research were support vector machines, logistic regression and random forest classifiers. The review also pointed out that attention to CP mechanisms is negligible despite being the most effective way to treat CP.

CONCLUSION

The review concludes that to achieve more effective outcomes in CP management, future research should prioritize identifying CP mechanisms, CP management, and rehabilitation while leveraging a wider range of algorithms and architectures.

SIGNIFICANCE

This review highlights the potential of AI in improving the management of CP, which is a significant personal and economic burden affecting more than 30% of the world's population. The identified gaps and future research directions provide valuable insights to researchers and practitioners in the field, with the potential to improve healthcare utilization.

Deep Learning Model for Grading and Localization of Lumbar Disc Herniation on Magnetic Resonance Imaging

BACKGROUND

Methods for grading and localization of lumbar disc herniation (LDH) on MRI are complex, time-consuming, and subjective. Utilizing deep learning (DL) models as assistance would mitigate such complexities.

PURPOSE

To develop an interpretable DL model capable of grading and localizing LDH.

STUDY TYPE

Retrospective.

SUBJECTS

1496 patients (M/F: 783/713) were evaluated, and randomly divided into training (70%), validation (10%), and test (20%) sets.

FIELD STRENGTH/SEQUENCE

1.5T MRI for axial T2-weighted sequences (spin echo).

ASSESSMENT

The training set was annotated by three spinal surgeons using the Michigan State University classification to train the DL model. The test set was annotated by a spinal surgery expert (as ground truth labels), and two spinal surgeons (comparison with the trained model). An external test set was employed to evaluate the generalizability of the DL model.

STATISTICAL TESTS

Calculated intersection over union (IoU) for detection consistency, utilized Gwet's AC1 to assess interobserver agreement, and evaluated model performance based on sensitivity and specificity, with statistical significance set at P < 0.05.

RESULTS

The DL model achieved high detection consistency in both the internal test dataset (grading: mean IoU 0.84, recall 99.6%; localization: IoU 0.82, recall 99.5%) and external test dataset (grading: 0.72, 98.0%; localization: 0.71, 97.6%). For internal testing, the DL model (grading: 0.81; localization: 0.76), Rater 1 (0.88; 0.82), and Rater 2 (0.86; 0.83) demonstrated results highly consistent with the ground truth labels. The overall sensitivity of the DL model was 87.0% for grading and 84.0% for localization, while the specificity was 95.5% and 94.4%. For external testing, the DL model showed an appreciable decrease in consistency (grading: 0.69; localization: 0.66), sensitivity (77.2%; 76.7%), and specificity (92.3%; 91.8%).

DATA CONCLUSION

The classification capabilities of the DL model closely resemble those of spinal surgeons. For future improvement, enriching the diversity of cases could enhance the model's generalization.

LEVEL OF EVIDENCE: 4

TECHNICAL EFFICACY

Stage 2.

The use of deep learning in medical imaging to improve spine care: A scoping review of current literature and clinical applications

Background

Artificial intelligence is a revolutionary technology that promises to assist clinicians in improving patient care. In radiology, deep learning (DL) is widely used in clinical decision aids due to its ability to analyze complex patterns and images. It allows for rapid, enhanced data, and imaging analysis, from diagnosis to outcome prediction. The purpose of this study was to evaluate the current literature and clinical utilization of DL in spine imaging.

Methods

This study is a scoping review and utilized the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology to review the scientific literature from 2012 to 2021. A search in PubMed, Web of Science, Embased, and IEEE Xplore databases with syntax specific for DL and medical imaging in spine care applications was conducted to collect all original publications on the subject. Specific data was extracted from the available literature, including algorithm application, algorithms tested, database type and size, algorithm training method, and outcome of interest.

Results

A total of 365 studies (total sample of 232,394 patients) were included and grouped into 4 general applications: diagnostic tools, clinical decision support tools, automated clinical/instrumentation assessment, and clinical outcome prediction. Notable disparities exist in the selected algorithms and the training across multiple disparate databases. The most frequently used algorithms were U-Net and ResNet. A DL model was developed and validated in 92% of included studies, while a pre-existing DL model was investigated in 8%. Of all developed models, only 15% of them have been externally validated.

Conclusions

Based on this scoping review, DL in spine imaging is used in a broad range of clinical applications, particularly for diagnosing spinal conditions. There is a wide variety of DL algorithms, database characteristics, and training methods. Future studies should focus on external validation of existing models before bringing them into clinical use.

One Model to Synthesize Them All: Multi-Contrast Multi-Scale Transformer for Missing Data Imputation

Multi-contrast magnetic resonance imaging (MRI) is widely used in clinical practice as each contrast provides complementary information. However, the availability of each imaging contrast may vary amongst patients, which poses challenges to radiologists and automated image analysis algorithms. A general approach for tackling this problem is missing data imputation, which aims to synthesize the missing contrasts from existing ones. While several convolutional neural networks (CNN) based algorithms have been proposed, they suffer from the fundamental limitations of CNN models, such as the requirement for fixed numbers of input and output channels, the inability to capture long-range dependencies, and the lack of interpretability. In this work, we formulate missing data imputation as a sequence-to-sequence learning problem and propose a multi-contrast multi-scale Transformer (MMT), which can take any subset of input contrasts and synthesize those that are missing. MMT consists of a multi-scale Transformer encoder that builds hierarchical representations of inputs combined with a multi-scale Transformer decoder that generates the outputs in a coarse-to-fine fashion. The proposed multi-contrast Swin Transformer blocks can efficiently capture intra- and inter-contrast dependencies for accurate image synthesis. Moreover, MMT is inherently interpretable as it allows us to understand the importance of each input contrast in different regions by analyzing the in-built attention maps of Transformer blocks in the decoder. Extensive experiments on two large-scale multi-contrast MRI datasets demonstrate that MMT outperforms the state-of-the-art methods quantitatively and qualitatively.

Deep Learning for Multi-Tissue Segmentation and Fully Automatic Personalized Biomechanical Models from BACPAC Clinical Lumbar Spine MRI

STUDY DESIGN

In vivo retrospective study of fully automatic quantitative imaging feature extraction from clinically acquired lumbar spine magnetic resonance imaging (MRI).

OBJECTIVE

To demonstrate the feasibility of substituting automatic for human-demarcated segmentation of major anatomic structures in clinical lumbar spine MRI to generate quantitative image-based features and biomechanical models.

SETTING

Previous studies have demonstrated the viability of automatic segmentation applied to medical images; however, the feasibility of these networks to segment clinically acquired images has not yet been demonstrated, as they largely rely on specialized sequences or strict quality of imaging data to achieve good performance.

METHODS

Convolutional neural networks were trained to demarcate vertebral bodies, intervertebral disc, and paraspinous muscles from sagittal and axial T1-weighted MRIs. Intervertebral disc height, muscle cross-sectional area, and subject-specific musculoskeletal models of tissue loading in the lumbar spine were then computed from these segmentations and compared against those computed from human-demarcated masks.

RESULTS

Segmentation masks, as well as the morphological metrics and biomechanical models computed from those masks, were highly similar between human- and computer-generated methods. Segmentations were similar, with Dice similarity coefficients of 0.77 or greater across networks, and morphological metrics and biomechanical models were similar, with Pearson R correlation coefficients of 0.69 or greater when significant.

CONCLUSIONS

This study demonstrates the feasibility of substituting computer-generated for human-generated segmentations of major anatomic structures in lumbar spine MRI to compute quantitative image-based morphological metrics and subject-specific musculoskeletal models of tissue loading quickly, efficiently, and at scale without interrupting routine clinical care.

Automated shape-independent assessment of the spatial distribution of proton density fat fraction in vertebral bone marrow

This work proposes a method for automatic standardized assessment of bone marrow volume and spatial distribution of the proton density fat fraction (PDFF) in vertebral bodies. Intra- and interindividual variability in size and shape of vertebral bodies is a challenge for comparable interindividual evaluation and monitoring of changes in the composition and distribution of bone marrow due to aging and/or intervention. Based on deep learning image segmentation, bone marrow PDFF of single vertebral bodies is mapped to a cylindrical template and corrected for the inclination with respect to the horizontal plane. The proposed technique was applied and tested in a cohort of 60 healthy (30 males, 30 females) individuals. Obtained bone marrow volumes and mean PDFF values are comparable to former manual and (semi-)automatic approaches. Moreover, the proposed method allows shape-independent characterization of the spatial PDFF distribution inside vertebral bodies.

Detection of sarcopenia using deep learning-based artificial intelligence body part measure system (AIBMS)

Background: Sarcopenia is an aging syndrome that increases the risks of various adverse outcomes, including falls, fractures, physical disability, and death. Sarcopenia can be diagnosed through medical images-based body part analysis, which requires laborious and time-consuming outlining of irregular contours of abdominal body parts. Therefore, it is critical to develop an efficient computational method for automatically segmenting body parts and predicting diseases. Methods: In this study, we designed an Artificial Intelligence Body Part Measure System (AIBMS) based on deep learning to automate body parts segmentation from abdominal CT scans and quantification of body part areas and volumes. The system was developed using three network models, including SEG-NET, U-NET, and Attention U-NET, and trained on abdominal CT plain scan data. Results: This segmentation model was evaluated using multi-device developmental and independent test datasets and demonstrated a high level of accuracy with over 0.9 DSC score in segment body parts. Based on the characteristics of the three network models, we gave recommendations for the appropriate model selection in various clinical scenarios. We constructed a sarcopenia classification model based on cutoff values (Auto SMI model), which demonstrated high accuracy in predicting sarcopenia with an AUC of 0.874. We used Youden index to optimize the Auto SMI model and found a better threshold of 40.69. Conclusion: We developed an AI system to segment body parts in abdominal CT images and constructed a model based on cutoff value to achieve the prediction of sarcopenia with high accuracy.

Deep Learning-Based Medical Images Segmentation of Musculoskeletal Anatomical Structures: A Survey of Bottlenecks and Strategies

By leveraging the recent development of artificial intelligence algorithms, several medical sectors have benefited from using automatic segmentation tools from bioimaging to segment anatomical structures. Segmentation of the musculoskeletal system is key for studying alterations in anatomical tissue and supporting medical interventions. The clinical use of such tools requires an understanding of the proper method for interpreting data and evaluating their performance. The current systematic review aims to present the common bottlenecks for musculoskeletal structures analysis (e.g., small sample size, data inhomogeneity) and the related strategies utilized by different authors. A search was performed using the PUBMED database with the following keywords: deep learning, musculoskeletal system, segmentation. A total of 140 articles published up until February 2022 were obtained and analyzed according to the PRISMA framework in terms of anatomical structures, bioimaging techniques, pre/post-processing operations, training/validation/testing subset creation, network architecture, loss functions, performance indicators and so on. Several common trends emerged from this survey; however, the different methods need to be compared and discussed based on each specific case study (anatomical region, medical imaging acquisition setting, study population, etc.). These findings can be used to guide clinicians (as end users) to better understand the potential benefits and limitations of these tools.

Spinopelvic measurements of sagittal balance with deep learning: systematic review and critical evaluation

PURPOSE

To summarize and critically evaluate the existing studies for spinopelvic measurements of sagittal balance that are based on deep learning (DL).

METHODS

Three databases (PubMed, WoS and Scopus) were queried for records using keywords related to DL and measurement of sagittal balance. After screening the resulting 529 records that were augmented with specific web search, 34 studies published between 2017 and 2022 were included in the final review, and evaluated from the perspective of the observed sagittal spinopelvic parameters, properties of spine image datasets, applied DL methodology and resulting measurement performance.

RESULTS

Studies reported DL measurement of up to 18 different spinopelvic parameters, but the actual number depended on the image field of view. Image datasets were composed of lateral lumbar spine and whole spine X-rays, biplanar whole spine X-rays and lumbar spine magnetic resonance cross sections, and were increasing in size or enriched by augmentation techniques. Spinopelvic parameter measurement was approached either by landmark detection or structure segmentation, and U-Net was the most frequently applied DL architecture. The latest DL methods achieved excellent performance in terms of mean absolute error against reference manual measurements (~ 2° or ~ 1 mm).

CONCLUSION

Although the application of relatively complex DL architectures resulted in an improved measurement accuracy of sagittal spinopelvic parameters, future methods should focus on multi-institution and multi-observer analyses as well as uncertainty estimation and error handling implementations for integration into the clinical workflow. Further advances will enhance the predictive analytics of DL methods for spinopelvic parameter measurement.

LEVEL OF EVIDENCE I

Diagnostic: individual cross-sectional studies with the consistently applied reference standard and blinding.

Current development and prospects of deep learning in spine image analysis: a literature review

BACKGROUND AND OBJECTIVE

As the spine is pivotal in the support and protection of human bodies, much attention is given to the understanding of spinal diseases. Quick, accurate, and automatic analysis of a spine image greatly enhances the efficiency with which spine conditions can be diagnosed. Deep learning (DL) is a representative artificial intelligence technology that has made encouraging progress in the last 6 years. However, it is still difficult for clinicians and technicians to fully understand this rapidly evolving field due to the diversity of applications, network structures, and evaluation criteria. This study aimed to provide clinicians and technicians with a comprehensive understanding of the development and prospects of DL spine image analysis by reviewing published literature.

METHODS

A systematic literature search was conducted in the PubMed and Web of Science databases using the keywords "deep learning" and "spine". Date ranges used to conduct the search were from 1 January, 2015 to 20 March, 2021. A total of 79 English articles were reviewed.

KEY CONTENT AND FINDINGS

The DL technology has been applied extensively to the segmentation, detection, diagnosis, and quantitative evaluation of spine images. It uses static or dynamic image information, as well as local or non-local information. The high accuracy of analysis is comparable to that achieved manually by doctors. However, further exploration is needed in terms of data sharing, functional information, and network interpretability.

CONCLUSIONS

The DL technique is a powerful method for spine image analysis. We believe that, with the joint efforts of researchers and clinicians, intelligent, interpretable, and reliable DL spine analysis methods will be widely applied in clinical practice in the future.

Automatic segmentation model of intercondylar fossa based on deep learning: a novel and effective assessment method for the notch volume

Background

Notch volume is associated with anterior cruciate ligament (ACL) injury. Manual tracking of intercondylar notch on MR images is time-consuming and laborious. Deep learning has become a powerful tool for processing medical images. This study aims to develop an MRI segmentation model of intercondylar fossa based on deep learning to automatically measure notch volume, and explore its correlation with ACL injury.

Methods

The MRI data of 363 subjects (311 males and 52 females) with ACL injuries incurred during non-contact sports and 232 subjects (147 males and 85 females) with intact ACL were retrospectively analyzed. Each layer of intercondylar fossa was manually traced by radiologists on axial MR images. Notch volume was then calculated. We constructed an automatic segmentation system based on the architecture of Res-UNet for intercondylar fossa and used dice similarity coefficient (DSC) to compare the performance of segmentation systems by different networks. Unpaired t-test was performed to determine differences in notch volume between ACL-injured and intact groups, and between males and females.

Results

The DSCs of intercondylar fossa based on different networks were all more than 0.90, and Res-UNet showed the best performance. The notch volume was significantly lower in the ACL-injured group than in the control group (6.12 ± 1.34 cm³ vs. 6.95 ± 1.75 cm³, P < 0.001). Females had lower notch volume than males (5.41 ± 1.30 cm³ vs. 6.76 ± 1.51 cm³, P < 0.001). Males and females who had ACL injuries had smaller notch than those with intact ACL (p < 0.001 and p < 0.005). Men had larger notches than women, regardless of the ACL injuries (p < 0.001).

Conclusion

Using a deep neural network to segment intercondylar fossa automatically provides a technical support for the clinical prediction and prevention of ACL injury and re-injury after surgery.

The contributions of cartilage endplate composition and vertebral bone marrow fat to intervertebral disc degeneration in patients with chronic low back pain

Purpose

The composition of the subchondral bone marrow and cartilage endplate (CEP) could affect intervertebral disc health by influencing vertebral perfusion and nutrient diffusion. However, the relative contributions of these factors to disc degeneration in patients with chronic low back pain (cLBP) have not been quantified. The goal of this study was to use compositional biomarkers derived from quantitative MRI to establish how CEP composition (surrogate for permeability) and vertebral bone marrow fat fraction (BMFF, surrogate for perfusion) relate to disc degeneration.

Methods

MRI data from 60 patients with cLBP were included in this prospective observational study (28 female, 32 male; age = 40.0 ± 11.9 years, 19–65 [mean ± SD, min–max]). Ultra-short echo-time MRI was used to calculate CEP T2* relaxation times (reflecting biochemical composition), water-fat MRI was used to calculate vertebral BMFF, and T1ρ MRI was used to calculate T1ρ relaxation times in the nucleus pulposus (NP T1ρ, reflecting proteoglycan content and degenerative grade). Univariate linear regression was used to assess the independent effects of CEP T2* and vertebral BMFF on NP T1ρ. Mixed effects multivariable linear regression accounting for age, sex, and BMI was used to assess the combined relationship between variables.

Results

CEP T2* and vertebral BMFF were independently associated with NP T1ρ (p = 0.003 and 0.0001, respectively). After adjusting for age, sex, and BMI, NP T1ρ remained significantly associated with CEP T2* (p = 0.0001) but not vertebral BMFF (p = 0.43).

Conclusion

Poor CEP composition plays a significant role in disc degeneration severity and can affect disc health both with and without deficits in vertebral perfusion.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00586-022-07206-x.

Multi-scanner and multi-modal lumbar vertebral body and intervertebral disc segmentation database

Magnetic resonance imaging (MRI) is widely utilized for diagnosing and monitoring of spinal disorders. For a number of applications, particularly those related to quantitative MRI, an essential step towards achieving reliable and objective measurements is the segmentation of the examined structures. Performed manually, such process is time-consuming and prone to errors, posing a bottleneck to its clinical applicability. A more efficient analysis would be achieved by automating a segmentation process. However, routine spine MRI acquisitions pose several challenges for achieving robust and accurate segmentations, due to varying MRI acquisition characteristics occurring in data acquired from different sites. Moreover, heterogeneous annotated datasets, collected from multiple scanners with different pulse sequence protocols, are limited. Thus, we present a manually segmented lumbar spine MRI database containing a wide range of data obtained from multiple scanners and pulse sequences, with segmentations of lumbar vertebral bodies and intervertebral discs. The database is intended for the use in developing and testing of automated lumbar spine segmentation algorithms in multi-domain scenarios.

Measurement(s)	Vertebral Body • Intervertebral Disc
Technology Type(s)	Magnetic Resonance Imaging

Fully automated radiomic screening pipeline for osteoporosis and abnormal bone density with a deep learning-based segmentation using a short lumbar mDixon sequence

BACKGROUND

Although lumbar bone marrow fat fraction (BMFF) has been demonstrated to be predictive of osteoporosis, its utility is limited by the requirement of manual segmentation. Additionally, quantitative features beyond simple BMFF average remain to be explored. In this study, we developed a fully automated radiomic pipeline using deep learning-based segmentation to detect osteoporosis and abnormal bone density (ABD) using a <20 s modified Dixon (mDixon) sequence.

METHODS

In total, 222 subjects underwent quantitative computed tomography (QCT) and lower back magnetic resonance imaging (MRI). Bone mineral density (BMD) were extracted from L1-L3 using QCT as the reference standard; 206 subjects (48.8±14.9 years old, 140 females) were included in the final analysis, and were divided temporally into the training/validation set (142/64 subjects). A deep-learning network was developed to perform automated segmentation. Radiomic models were built using the same training set to predict ABD and osteoporosis using the mDixon maps. The performance was evaluated using the temporal validation set comprised of 64 subjects, along with the automated segmentation. Additional 25 subjects (56.1±8.8 years, 14 females) from another site and a different scanner vendor was included as independent validation to evaluate the performance of the pipeline.

RESULTS

The automated segmentation achieved an outstanding mean dice coefficient of 0.912±0.062 compared to manual in the temporal validation. Task-based evaluation was performed in the temporal validation set, for predicting ABD and osteoporosis, the area under the curve, sensitivity, specificity, and accuracy were 0.925/0.899, 0.923/0.667, 0.789/0.873, 0.844/0.844, respectively. These values were comparable to that of manual segmentation. External validation (cross-vendor) was also performed; the area under the curve, sensitivity, specificity, and accuracy were 0.688/0.913, 0.786/0.857, 0.545/0.944, 0.680/0.920 for ABD and osteoporosis prediction, respectively.

CONCLUSIONS

Our work is the first attempt using radiomics to predict osteoporosis with BMFF map, and the deep-learning based segmentation will further facilitate the clinical utility of the pipeline as a screening tool for early detection of ABD.

Artificial Intelligence and Computer Vision in Low Back Pain: A Systematic Review

Chronic Low Back Pain (LBP) is a symptom that may be caused by several diseases, and it is currently the leading cause of disability worldwide. The increased amount of digital images in orthopaedics has led to the development of methods related to artificial intelligence, and to computer vision in particular, which aim to improve diagnosis and treatment of LBP. In this manuscript, we have systematically reviewed the available literature on the use of computer vision in the diagnosis and treatment of LBP. A systematic research of PubMed electronic database was performed. The search strategy was set as the combinations of the following keywords: "Artificial Intelligence", "Feature Extraction", "Segmentation", "Computer Vision", "Machine Learning", "Deep Learning", "Neural Network", "Low Back Pain", "Lumbar". Results: The search returned a total of 558 articles. After careful evaluation of the abstracts, 358 were excluded, whereas 124 papers were excluded after full-text examination, taking the number of eligible articles to 76. The main applications of computer vision in LBP include feature extraction and segmentation, which are usually followed by further tasks. Most recent methods use deep learning models rather than digital image processing techniques. The best performing methods for segmentation of vertebrae, intervertebral discs, spinal canal and lumbar muscles achieve Sørensen-Dice scores greater than 90%, whereas studies focusing on localization and identification of structures collectively showed an accuracy greater than 80%. Future advances in artificial intelligence are expected to increase systems' autonomy and reliability, thus providing even more effective tools for the diagnosis and treatment of LBP.

Texture Analysis Using CT and Chemical Shift Encoding-Based Water-Fat MRI Can Improve Differentiation Between Patients With and Without Osteoporotic Vertebral Fractures

PURPOSE

Osteoporosis is a highly prevalent skeletal disease that frequently entails vertebral fractures. Areal bone mineral density (BMD) derived from dual-energy X-ray absorptiometry (DXA) is the reference standard, but has well-known limitations. Texture analysis can provide surrogate markers of tissue microstructure based on computed tomography (CT) or magnetic resonance imaging (MRI) data of the spine, thus potentially improving fracture risk estimation beyond areal BMD. However, it is largely unknown whether MRI-derived texture analysis can predict volumetric BMD (vBMD), or whether a model incorporating texture analysis based on CT and MRI may be capable of differentiating between patients with and without osteoporotic vertebral fractures.

MATERIALS AND METHODS

Twenty-six patients (15 females, median age: 73 years, 11 patients showing at least one osteoporotic vertebral fracture) who had CT and 3-Tesla chemical shift encoding-based water-fat MRI (CSE-MRI) available were analyzed. In total, 171 vertebral bodies of the thoracolumbar spine were segmented using an automatic convolutional neural network (CNN)-based framework, followed by extraction of integral and trabecular vBMD using CT data. For CSE-MRI, manual segmentation of vertebral bodies and consecutive extraction of the mean proton density fat fraction (PDFF) and T2* was performed. First-order, second-order, and higher-order texture features were derived from texture analysis using CT and CSE-MRI data. Stepwise multivariate linear regression models were computed using integral vBMD and fracture status as dependent variables.

RESULTS

Patients with osteoporotic vertebral fractures showed significantly lower integral and trabecular vBMD when compared to patients without fractures (p<0.001). For the model with integral vBMD as the dependent variable, T2* combined with three PDFF-based texture features explained 40% of the variance (adjusted R²[Ra2] = 0.40; p<0.001). Furthermore, regarding the differentiation between patients with and without osteoporotic vertebral fractures, a model including texture features from CT and CSE-MRI data showed better performance than a model based on integral vBMD and PDFF only ( Ra2 = 0.47 vs. Ra2  = 0.81; included texture features in the final model: integral vBMD, CT_Short-run_emphasis, CT_Varianceglobal, and PDFF_Variance).

CONCLUSION

Using texture analysis for spine CT and CSE-MRI can facilitate the differentiation between patients with and without osteoporotic vertebral fractures, implicating that future fracture prediction in osteoporosis may be improved.