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

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.

Predicting osteoporosis from kidney-ureter-bladder radiographs utilizing deep convolutional neural networks

Osteoporosis is a common condition that can lead to fractures, mobility issues, and death. Although dual-energy X-ray absorptiometry (DXA) is the gold standard for osteoporosis, it is expensive and not widely available. In contrast, kidney-ureter-bladder (KUB) radiographs are inexpensive and frequently ordered in clinical practice. Thus, it is a potential screening tool for osteoporosis. In this study, we explored the possibility of predicting the bone mineral density (BMD) and classifying high-risk patient groups using KUB radiographs. We proposed DeepDXA-KUB, a deep learning model that predicts the BMD values of the left hip and lumbar vertebrae from an input KUB image. The datasets were obtained from Taiwanese medical centers between 2006 and 2019, using 8913 pairs of KUB radiographs and DXA examinations performed within 6 months. The images were randomly divided into training and validation sets in a 4:1 ratio. To evaluate the model's performance, we computed a confusion matrix and evaluated the sensitivity, specificity, accuracy, precision, positive predictive value, negative predictive value, F1 score, and area under the receiver operating curve (AUROC). Moderate correlations were observed between the predicted and DXA-measured BMD values, with a correlation coefficient of 0.858 for the lumbar vertebrae and 0.87 for the left hip. The model demonstrated an osteoporosis detection accuracy, sensitivity, and specificity of 84.7 %, 81.6 %, and 86.6 % for the lumbar vertebrae and 84.2 %, 91.2 %, and 81 % for the left hip, respectively. The AUROC was 0.939 for the lumbar vertebrae and 0.947 for the left hip, indicating a satisfactory performance in osteoporosis screening. The present study is the first to develop a deep learning model based on KUB radiographs to predict lumbar spine and femoral BMD. Our model demonstrated a promising correlation between the predicted and DXA-measured BMD in both the lumbar vertebrae and hip, showing great potential for the opportunistic screening of osteoporosis.

Application of Artificial Intelligence Methods on Osteoporosis Classification with Radiographs-A Systematic Review

Osteoporosis is a complex endocrine disease characterized by a decline in bone mass and microstructural integrity. It constitutes a major global health problem. Recent progress in the field of artificial intelligence (AI) has opened new avenues for the effective diagnosis of osteoporosis via radiographs. This review investigates the application of AI classification of osteoporosis in radiographs. A comprehensive exploration of electronic repositories (ClinicalTrials.gov, Web of Science, PubMed, MEDLINE) was carried out in adherence to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses 2020 statement (PRISMA). A collection of 31 articles was extracted from these repositories and their significant outcomes were consolidated and outlined. This encompassed insights into anatomical regions, the specific machine learning methods employed, the effectiveness in predicting BMD, and categorizing osteoporosis. Through analyzing the respective studies, we evaluated the effectiveness and limitations of AI osteoporosis classification in radiographs. The pooled reported accuracy, sensitivity, and specificity of osteoporosis classification ranges from 66.1% to 97.9%, 67.4% to 100.0%, and 60.0% to 97.5% respectively. This review underscores the potential of AI osteoporosis classification and offers valuable insights for future research endeavors, which should focus on addressing the challenges in technical and clinical integration to facilitate practical implementation of this technology.

Deep learning in the radiologic diagnosis of osteoporosis: a literature review

OBJECTIVE

Osteoporosis is a systemic bone disease characterized by low bone mass, damaged bone microstructure, increased bone fragility, and susceptibility to fractures. With the rapid development of artificial intelligence, a series of studies have reported deep learning applications in the screening and diagnosis of osteoporosis. The aim of this review was to summary the application of deep learning methods in the radiologic diagnosis of osteoporosis.

METHODS

We conducted a two-step literature search using the PubMed and Web of Science databases. In this review, we focused on routine radiologic methods, such as X-ray, computed tomography, and magnetic resonance imaging, used to opportunistically screen for osteoporosis.

RESULTS

A total of 40 studies were included in this review. These studies were divided into three categories: osteoporosis screening (n = 20), bone mineral density prediction (n = 13), and osteoporotic fracture risk prediction and detection (n = 7).

CONCLUSIONS

Deep learning has demonstrated a remarkable capacity for osteoporosis screening. However, clinical commercialization of a diagnostic model for osteoporosis remains a challenge.

Assessment of Osteoporosis at the Lumbar Spine Using Ultrashort Echo Time Magnetization Transfer (UTE-MT) MRI

BACKGROUND

Bone collagen-matrix contributes to the mechanical properties of bone by imparting tensile strength and elasticity, which can be indirectly quantified by ultrashort echo time magnetization transfer ratio (UTE-MTR) to assess osteoporosis.

PURPOSE

To evaluate osteoporosis at the human lumbar spine using UTE-MTR.

STUDY TYPE

Prospective.

POPULATION

One hundred forty-eight-volunteers (age-range, 50-85; females, N = 90), including 81-normal bone density, 35-osteopenic, and 32-osteoporotic subjects. Ten additional healthy volunteers were recruited to study the intrasession reproducibility of the UTE-MT.

FIELD STRENGTH/SEQUENCE

3T/UTE-MT, short repetition-time adiabatic inversion recovery prepared UTE (STAIR-UTE), and iterative decomposition of water-and-fat with echo-asymmetry and least-squares estimation (IDEAL-IQ).

ASSESSMENT

Fracture risk was calculated using Fracture-Risk-Assessment-Tool (FRAX). Region-of-interests (ROIs) were delineated on the trabecular area in the maps of bone-mineral-density, UTE-MTR, collagen-bound water proton-fraction (CBWPF), and bone-marrow fat fraction (BMFF).

STATISTICAL TESTS

Linear-regression and Bland-Altman analysis were performed to assess the reproducibility of UTE-MTR measurements in the different scans. UTE-MTR and BMFF were correlated with bone-mineral-density using Pearson's regression and with FRAX scores using nonlinear regression. The abilities of UTE-MTR, CBWPF, and BMFF to discriminate between the three patient subgroups were evaluated using receiver-operator-characteristic (ROC) analysis and area-under-the-curve (AUC). Decision-curve-analysis (DCA) and clinical-impact curves were used to evaluate the value of UTE-MTR in clinical diagnosis. The DeLong test was used to compare the ROC curves. P-value <0.05 was considered statistically significant.

RESULTS

Excellent reproducibility was obtained for the UTE-MT measurements. UTE-MTR strongly correlated with bone-mineral-density (r = 0.76) and FRAX scores (r = -0.77). UTE-MTR exhibited higher AUCs (≥0.723) than BMFF, indicating its superior ability to distinguish between the three patient subgroups. The DCA and clinical-impact curves confirmed the diagnostic value of UTE-MTR. UTE-MTR and CBWPF showed similar performance in correlation with bone-mineral-density and cohort classification.

DATA CONCLUSION

UTE-MTR strongly correlates with bone-mineral-density and FRAX and shows great potential in distinguishing between normal, osteopenic, and osteoporotic subjects.

EVIDENCE LEVEL

1 TECHNICAL EFFICACY: Stage 2.

Automated graded prognostic assessment for patients with hepatocellular carcinoma using machine learning

BACKGROUND

Accurate mortality risk quantification is crucial for the management of hepatocellular carcinoma (HCC); however, most scoring systems are subjective.

PURPOSE

To develop and independently validate a machine learning mortality risk quantification method for HCC patients using standard-of-care clinical data and liver radiomics on baseline magnetic resonance imaging (MRI).

METHODS

This retrospective study included all patients with multiphasic contrast-enhanced MRI at the time of diagnosis treated at our institution. Patients were censored at their last date of follow-up, end-of-observation, or liver transplantation date. The data were randomly sampled into independent cohorts, with 85% for development and 15% for independent validation. An automated liver segmentation framework was adopted for radiomic feature extraction. A random survival forest combined clinical and radiomic variables to predict overall survival (OS), and performance was evaluated using Harrell's C-index.

RESULTS

A total of 555 treatment-naïve HCC patients (mean age, 63.8 years ± 8.9 [standard deviation]; 118 females) with MRI at the time of diagnosis were included, of which 287 (51.7%) died after a median time of 14.40 (interquartile range, 22.23) months, and had median followed up of 32.47 (interquartile range, 61.5) months. The developed risk prediction framework required 1.11 min on average and yielded C-indices of 0.8503 and 0.8234 in the development and independent validation cohorts, respectively, outperforming conventional clinical staging systems. Predicted risk scores were significantly associated with OS (p < .00001 in both cohorts).

CONCLUSIONS

Machine learning reliably, rapidly, and reproducibly predicts mortality risk in patients with hepatocellular carcinoma from data routinely acquired in clinical practice.

CLINICAL RELEVANCE STATEMENT

Precision mortality risk prediction using routinely available standard-of-care clinical data and automated MRI radiomic features could enable personalized follow-up strategies, guide management decisions, and improve clinical workflow efficiency in tumor boards.

KEY POINTS

• Machine learning enables hepatocellular carcinoma mortality risk prediction using standard-of-care clinical data and automated radiomic features from multiphasic contrast-enhanced MRI. • Automated mortality risk prediction achieved state-of-the-art performances for mortality risk quantification and outperformed conventional clinical staging systems. • Patients were stratified into low, intermediate, and high-risk groups with significantly different survival times, generalizable to an independent evaluation cohort.

Development and Validation of a Feature-Based Broad-Learning System for Opportunistic Osteoporosis Screening Using Lumbar Spine Radiographs

RATIONALE AND OBJECTIVES

Osteoporosis is primarily diagnosed using dual-energy X-ray absorptiometry (DXA); yet, DXA is significantly underutilized, causing osteoporosis, an underdiagnosed condition. We aimed to provide an opportunistic approach to screen for osteoporosis using artificial intelligence based on lumbar spine X-ray radiographs.

MATERIALS AND METHODS

In this institutional review board-approved retrospective study, female patients aged ≥50 years who received both X-ray scans and DXA of the lumbar vertebrae, in three centers, were included. A total of 1180 cases were used for training and 145 cases were used for testing. We proposed a novel broad-learning system (BLS) and then compared the performance of BLS models using radiomic features and deep features as a source of input. The deep features were extracted using ResNet18 and VGG11, respectively. The diagnostic performances of these BLS models were evaluated with the area under the curve (AUC), sensitivity, and specificity.

RESULTS

The incidence rate of osteoporosis in the training and test sets was 35.9% and 37.9%, respectively. The radiomic feature-based BLS model achieved higher testing AUC (0.802 vs. 0.654 vs. 0.632, both P = .002), sensitivity (78.2% vs. 56.4% vs. 50.9%), and specificity (82.2% vs. 74,4% vs. 75.6%) than the two deep feature-based BLS models.

CONCLUSION

Our proposed radiomic feature-based BLS model has the potential to expand osteoporosis screening to a broader population by identifying osteoporosis on lumbar spine X-ray radiographs.

Machine Learning and Radiomics of Bone Scintigraphy: Their Role in Predicting Recurrence of Localized or Locally Advanced Prostate Cancer

BACKGROUND

Machine-learning (ML) and radiomics features have been utilized for survival outcome analysis in various cancers. This study aims to investigate the application of ML based on patients' clinical features and radiomics features derived from bone scintigraphy (BS) and to evaluate recurrence-free survival in local or locally advanced prostate cancer (PCa) patients after the initial treatment.

METHODS

A total of 354 patients who met the eligibility criteria were analyzed and used to train the model. Clinical information and radiomics features of BS were obtained. Survival-related clinical features and radiomics features were included in the ML model training. Using the pyradiomics software, 128 radiomics features from each BS image's region of interest, validated by experts, were extracted. Four textural matrices were also calculated: GLCM, NGLDM, GLRLM, and GLSZM. Five training models (Logistic Regression, Naive Bayes, Random Forest, Support Vector Classification, and XGBoost) were applied using K-fold cross-validation. Recurrence was defined as either a rise in PSA levels, radiographic progression, or death. To assess the classifier's effectiveness, the ROC curve area and confusion matrix were employed.

RESULTS

Of the 354 patients, 101 patients were categorized into the recurrence group with more advanced disease status compared to the non-recurrence group. Key clinical features including tumor stage, radical prostatectomy, initial PSA, Gleason Score primary pattern, and radiotherapy were used for model training. Random Forest (RF) was the best-performing model, with a sensitivity of 0.81, specificity of 0.87, and accuracy of 0.85. The ROC curve analysis showed that predictions from RF outperformed predictions from other ML models with a final AUC of 0.94 and a p-value of <0.001. The other models had accuracy ranges from 0.52 to 0.78 and AUC ranges from 0.67 to 0.84.

CONCLUSIONS

The study showed that ML based on clinical features and radiomics features of BS improves the prediction of PCa recurrence after initial treatment. These findings highlight the added value of ML techniques for risk classification in PCa based on clinical features and radiomics features of BS.

The role of genetic and epigenetic factors in determining the risk of spinal fragility fractures: new insights in the management of spinal osteoporosis

Osteoporosis predisposes patients to spinal fragility fractures. Imaging plays a key role in the diagnosis and prognostication of these osteoporotic vertebral fractures (OVF). However, the current imaging knowledge base for OVF is lacking sufficient standardisation to enable effective risk prognostication. OVF have been shown to be more prevalent in Caucasian patient cohorts in comparison to the Eastern Asian population. These population-based differences in risk for developing OVF suggest that there could be genetic and epigenetic factors that drive the pathogenesis of osteoporosis, low bone mineral density (BMD) and OVF. Several genetic loci have been associated with a higher vertebral fracture risk, although at varying degrees of significance. The present challenge is clarifying whether these associations are specific to vertebral fractures or osteoporosis more generally. Furthermore, these factors could be exploited for diagnostic interpretation as biomarkers [including novel long non-coding (lnc)RNAs, micro (mi)RNAs and circular (circ)RNAs]. The extent of methylation of genes, alongside post-translational histone modifications, have shown to affect several interlinked pathways that converge on the regulation of bone deposition and resorption, partially through their influence on osteoblast and osteoclast differentiation. Lastly, in addition to biomarkers, several exciting new imaging modalities could add to the established dual-energy X-ray absorptiometry (DXA) method used for BMD assessment. New technologies, and novel sequences within existing imaging modalities, may be able to quantify the quality of bone in addition to the BMD and bone structure; these are making progress through various stages of development from the pre-clinical sphere through to deployment in the clinical setting. In this mini review, we explore the literature to clarify the genetic and epigenetic factors associated with spinal fragility fractures and delineate the causal genes, pathways and interactions which could drive different risk profiles. We also outline the cutting-edge imaging modalities which could transform diagnostic protocols for OVF.

New Horizons: Artificial Intelligence Tools for Managing Osteoporosis

Osteoporosis is a disease characterized by low bone mass and microarchitectural deterioration leading to increased bone fragility and fracture risk. Typically, osteoporotic fractures occur at the spine, hip, distal forearm, and proximal humerus, but other skeletal sites may be affected as well. One of the major challenges in the management of osteoporosis lies in the fact that although the operational diagnosis is based on bone mineral density (BMD) as measured by dual x-ray absorptiometry, the majority of fractures occur at nonosteoporotic BMD values. Furthermore, osteoporosis often remains undiagnosed regardless of the low severity of the underlying trauma. Also, there is only weak consensus among the major guidelines worldwide, when to treat, whom to treat, and which drug to use. Against this background, increasing efforts have been undertaken in the past few years by artificial intelligence (AI) developers to support and improve the management of this disease. The performance of many of these newly developed AI algorithms have been shown to be at least comparable to that of physician experts, or even superior. However, even if study results appear promising at a first glance, they should always be interpreted with caution. Use of inadequate reference standards or selection of variables that are of little or no value in clinical practice are limitations not infrequently found. Consequently, there is a clear need for high-quality clinical research in this field of AI. This could, eg, be achieved by establishing an internationally consented "best practice framework" that considers all relevant stakeholders.