Development of an open-source measurement system to assess the areal bone mineral density of the proximal femur from clinical CT images

Monte Carlo-based in-depth morphological analysis of medullary cavity for designing personalized femoral stem

Background

The design of femoral stem prostheses requires a precise understanding of the femoral marrow cavity. Traditional measurements of morphological parameters in the upper femur, particularly the medullary cavity and cortical region, are primarily based on coronal and sagittal axes, which may not fully capture the true three-dimensional structure of the femur.

Methods

Propose a Monte Carlo-based method for a more comprehensive analysis of the femoral marrow cavity, using CT scans of femurs from a selected group of patients. The study aimed to define and calculate anatomically semantic morphological parameters to enhance the understanding of the femoral marrow cavity's anatomical morphological changes, ultimately improving the design and clinical selection of femoral stem prostheses. To enhance the accuracy of femoral stem prosthesis design, this study aims to develop a Monte Carlo-based method for a more comprehensive analysis of the femoral marrow cavity. The proposed method transforms the non-random problem of determining cross-sectional size into a random issue, allowing for the calculation of the size of the medullary cavity and cortical region. Anatomically semantic morphological parameters are then defined, calculated, and analyzed.

Results

The experimental results indicate that the newly defined parameters complement existing ones, providing a more rational scientific basis for understanding the anatomical morphological changes of the femoral marrow cavity.

Conclusion

This research offers essential scientific theoretical support for improved morphologic research, design, and clinical selection of femoral stem prostheses. It holds significant importance and application value in clinical practice, contributing to a more accurate and comprehensive understanding of femoral anatomy for prosthetic design.

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.

Automated entry of paper-based patient-reported outcomes: Applying deep learning to the Japanese orthopaedic association back pain evaluation questionnaire

BACKGROUND

Health-related patient-reported outcomes (HR-PROs) are crucial for assessing the quality of life among individuals experiencing low back pain. However, manual data entry from paper forms, while convenient for patients, imposes a considerable tallying burden on collectors. In this study, we developed a deep learning (DL) model capable of automatically reading these paper forms.

METHODS

We employed the Japanese Orthopaedic Association Back Pain Evaluation Questionnaire, a globally recognized assessment tool for low back pain. The questionnaire comprised 25 low back pain-related multiple-choice questions and three pain-related visual analog scales (VASs). We collected 1305 forms from an academic medical center as the training set, and 483 forms from a community medical center as the test set. The performance of our DL model for multiple-choice questions was evaluated using accuracy as a categorical classification task. The performance for VASs was evaluated using the correlation coefficient and absolute error as regression tasks.

RESULT

In external validation, the mean accuracy of the categorical questions was 0.997. When outputs for categorical questions with low probability (threshold: 0.9996) were excluded, the accuracy reached 1.000 for the remaining 65 % of questions. Regarding the VASs, the average of the correlation coefficients was 0.989, with the mean absolute error being 0.25.

CONCLUSION

Our DL model demonstrated remarkable accuracy and correlation coefficients when automatic reading paper-based HR-PROs during external validation.

The effect of forearm rotation on the bone mineral density measurements of the distal radius

INTRODUCTION

Forearm dual-energy X-ray absorptiometry (DXA) is often performed in clinics where central DXA is unavailable. Accurate bone mineral density (BMD) measurement is crucial for clinical assessment. Forearm rotation can affect BMD measurements, but this effect remains uncertain. Thus, we aimed to conduct a simulation study using CT images to clarify the effect of forearm rotation on BMD measurements.

MATERIALS AND METHODS

Forearm CT images of 60 women were analyzed. BMD was measured at the total, ultra-distal (UD), mid-distal (MD), and distal 33% radius regions with the radius located at the neutral position using digitally reconstructed radiographs generated from CT images. Then, the rotation was altered from - 30° to 30° (supination set as positive) with a one-degree increment, and the percent BMD changes from the neutral position were quantified for all regions at each angle for each patient.

RESULTS

The maximum mean BMD changes were 5.8%, 7.0%, 6.2%, and 7.2% for the total, UD, MD, and distal 33% radius regions, respectively. The analysis of the absolute values of the percent BMD changes from the neutral position showed that BMD changes of all patients remained within 2% when the rotation was between - 5° and 7° for the total region, between - 3° and 2° for the UD region, between - 4° and 3° for the MD region, and between - 3° and 1° for the distal 33% radius region.

CONCLUSION

Subtle rotational changes affected the BMD measurement of each region. The results showed the importance of forearm positioning when measuring the distal radius BMD.

Bone mineral density estimation from a plain X-ray image by learning decomposition into projections of bone-segmented computed tomography

Osteoporosis is a prevalent bone disease that causes fractures in fragile bones, leading to a decline in daily living activities. Dual-energy X-ray absorptiometry (DXA) and quantitative computed tomography (QCT) are highly accurate for diagnosing osteoporosis; however, these modalities require special equipment and scan protocols. To frequently monitor bone health, low-cost, low-dose, and ubiquitously available diagnostic methods are highly anticipated. In this study, we aim to perform bone mineral density (BMD) estimation from a plain X-ray image for opportunistic screening, which is potentially useful for early diagnosis. Existing methods have used multi-stage approaches consisting of extraction of the region of interest and simple regression to estimate BMD, which require a large amount of training data. Therefore, we propose an efficient method that learns decomposition into projections of bone-segmented QCT for BMD estimation under limited datasets. The proposed method achieved high accuracy in BMD estimation, where Pearson correlation coefficients of 0.880 and 0.920 were observed for DXA-measured BMD and QCT-measured BMD estimation tasks, respectively, and the root mean square of the coefficient of variation values were 3.27 to 3.79% for four measurements with different poses. Furthermore, we conducted extensive validation experiments, including multi-pose, uncalibrated-CT, and compression experiments toward actual application in routine clinical practice.

Improved distinct bone segmentation in upper-body CT through multi-resolution networks

PURPOSE

Automated distinct bone segmentation from CT scans is widely used in planning and navigation workflows. U-Net variants are known to provide excellent results in supervised semantic segmentation. However, in distinct bone segmentation from upper-body CTs a large field of view and a computationally taxing 3D architecture are required. This leads to low-resolution results lacking detail or localisation errors due to missing spatial context when using high-resolution inputs.

METHODS

We propose to solve this problem by using end-to-end trainable segmentation networks that combine several 3D U-Nets working at different resolutions. Our approach, which extends and generalizes HookNet and MRN, captures spatial information at a lower resolution and skips the encoded information to the target network, which operates on smaller high-resolution inputs. We evaluated our proposed architecture against single-resolution networks and performed an ablation study on information concatenation and the number of context networks.

RESULTS

Our proposed best network achieves a median DSC of 0.86 taken over all 125 segmented bone classes and reduces the confusion among similar-looking bones in different locations. These results outperform our previously published 3D U-Net baseline results on the task and distinct bone segmentation results reported by other groups.

CONCLUSION

The presented multi-resolution 3D U-Nets address current shortcomings in bone segmentation from upper-body CT scans by allowing for capturing a larger field of view while avoiding the cubic growth of the input pixels and intermediate computations that quickly outgrow the computational capacities in 3D. The approach thus improves the accuracy and efficiency of distinct bone segmentation from upper-body CT.

Development and validation of an open-source tool for opportunistic screening of osteoporosis from hip CT images

Aims

This study aimed to develop and validate a fully automated system that quantifies proximal femoral bone mineral density (BMD) from CT images.

Methods

The study analyzed 978 pairs of hip CT and dual-energy X-ray absorptiometry (DXA) measurements of the proximal femur (DXA-BMD) collected from three institutions. From the CT images, the femur and a calibration phantom were automatically segmented using previously trained deep-learning models. The Hounsfield units of each voxel were converted into density (mg/cm3). Then, a deep-learning model trained by manual landmark selection of 315 cases was developed to select the landmarks at the proximal femur to rotate the CT volume to the neutral position. Finally, the CT volume of the femur was projected onto the coronal plane, and the areal BMD of the proximal femur (CT-aBMD) was quantified. CT-aBMD correlated to DXA-BMD, and a receiver operating characteristic (ROC) analysis quantified the accuracy in diagnosing osteoporosis.

Results

CT-aBMD was successfully measured in 976/978 hips (99.8%). A significant correlation was found between CT-aBMD and DXA-BMD (r = 0.941; p < 0.001). In the ROC analysis, the area under the curve to diagnose osteoporosis was 0.976. The diagnostic sensitivity and specificity were 88.9% and 96%, respectively, with the cutoff set at 0.625 g/cm2.

Conclusion

Accurate DXA-BMD measurements and diagnosis of osteoporosis were performed from CT images using the system developed herein. As the models are open-source, clinicians can use the proposed system to screen osteoporosis and determine the surgical strategy for hip surgery.

Feasibility of Bone Mineral Density and Bone Microarchitecture Assessment Using Deep Learning With a Convolutional Neural Network

OBJECTIVES

We evaluated the feasibility of using deep learning with a convolutional neural network for predicting bone mineral density (BMD) and bone microarchitecture from conventional computed tomography (CT) images acquired by multivendor scanners.

METHODS

We enrolled 402 patients who underwent noncontrast CT examinations, including L1-L4 vertebrae, and dual-energy x-ray absorptiometry (DXA) examination. Among these, 280 patients (3360 sagittal vertebral images), 70 patients (280 sagittal vertebral images), and 52 patients (208 sagittal vertebral images) were assigned to the training data set for deep learning model development, the validation, and the test data set, respectively. Bone mineral density and the trabecular bone score (TBS), an index of bone microarchitecture, were assessed by DXA. BMDDL and TBSDL were predicted by deep learning with a convolutional neural network (ResNet50). Pearson correlation tests assessed the correlation between BMDDL and BMD, and TBSDL and TBS. The diagnostic performance of BMDDL for osteopenia/osteoporosis and that of TBSDL for bone microarchitecture impairment were evaluated using receiver operating characteristic curve analysis.

RESULTS

BMDDL and BMD correlated strongly (r = 0.81, P < 0.01), whereas TBSDL and TBS correlated moderately (r = 0.54, P < 0.01). The sensitivity and specificity of BMDDL for identifying osteopenia or osteoporosis were 93% and 90%, and 100% and 94%, respectively. The sensitivity and specificity of TBSDL for identifying patients with bone microarchitecture impairment were 73% for all values.

CONCLUSIONS

The BMDDL and TBSDL derived from conventional CT images could identify patients who should undergo DXA, which could be a gatekeeper tool for detecting latent osteoporosis/osteopenia or bone microarchitecture impairment.

The effect of patient positioning on measurements of bone mineral density of the proximal femur: a simulation study using computed tomographic images

The patient's position may affect the bone mineral density (BMD) measurements; however, the extent of this effect is undefined. This CT image-based simulation study quantified changes in BMD induced by hip flexion, adduction, and rotations to recommend appropriate patient positioning when acquiring dual-energy x-ray absorptiometry images.

PURPOSE

Several studies have analyzed the effect of hip rotation on the measurement of bone mineral density (BMD) of the proximal femur by dual-energy x-ray absorptiometry (DXA). However, as the effects of hip flexion and abduction on BMD measurements remain uncertain, a computational simulation study using CT images was performed in this study.

METHODS

Hip CT images of 120 patients (33 men and 87 women; mean age, 82.1 ± 9.4 years) were used for analysis. Digitally reconstructed radiographs of the proximal femur region were generated from CT images to calculate the BMD of the proximal femur region. BMD at the neutral position was quantified, and the percent changes in BMD when hip internal rotation was altered from -30° to 15°, when hip flexion was altered from 0° to 30°, and when hip abduction was altered from -15° to 30° were quantified. Analyses were automatically performed with a 1° increment in each direction using computer programming.

RESULTS

The alteration of hip angles in each direction affected BMD measurements, with the largest changes found for hip flexion (maximum change of 17.7% at 30° flexion) and the smallest changes found for hip rotation (maximum change of 2.2% at 15° internal rotation). The BMD measurements increased by 0.34% for each 1° of hip abduction, and the maximum change was 12.3% at 30° abduction.

CONCLUSION

This simulation study quantified the amount of BMD change induced by altering the hip position. Based on these results, we recommend that patients be positioned carefully when acquiring DXA images.

Development of a system to assess the two- and three-dimensional bone mineral density of the lumbar vertebrae from clinical quantitative CT images

This study developed a system to quantify the lumbar spine's bone mineral density (BMD) in two and three dimensions for osteoporosis screening using quantitative CT images. Measuring the two-dimensional BMD could reproduce the BMD measurement performed in dual-energy X-ray absorptiometry, and an accurate diagnosis of osteoporosis was possible.

PURPOSE

To date, the assessment of bone mineral density (BMD) using CT images has been made in three dimensions, leading to errors in detecting osteoporosis based on the two-dimensional assessments of BMD using dual-energy X-ray absorptiometry (DXA-BMD). Herein, we aimed to develop a system that measures two- and three-dimensional lumbar BMD from quantitative CT images and validated the accuracy of the system in diagnosing osteoporosis with regard to the DXA classification.

METHODS

Fifty-nine pairs of spinal CT and DXA images were analyzed. First, the three-dimensional BMD was measured at the axial slice of the L1 vertebra on CT images (L1-vBMD). Then, the L1-L4 vertebrae were segmented from the CT images to measure the three-dimensional BMD at the trabecular region of the L1-L4 vertebral bodies (CT-vBMD). Lastly, the segmented vertebrae were projected onto the coronal plane to measure the two-dimensional BMD (CT-aBMD). Each parameter was correlated with DXA-BMD, and the receiver operating characteristic (ROC) curve to diagnose osteoporosis was assessed.

RESULTS

The correlation coefficients of DXA-BMD with L1-vBMD, CT-vBMD, and CT-aBMD were 0.364, 0.456, and 0.911, respectively (all p < 0.01). In the ROC curve analysis to diagnose osteoporosis, the area under the curve for CT-aBMD (0.941) was significantly higher than those for L1-vBMD (0.582) and CT-vBMD (0.657) (both p < 0.01).

CONCLUSION

Compared with L1-vBMD and CT-vBMD, CT-aBMD could accurately predict DXA-BMD and detect patients with osteoporosis. Given that our method can quantify BMD in both two and three dimensions, it could be used to screen for osteoporosis from quantitative CT images.

The Effect of Region of Interest on Measurement of Bone Mineral Density of the Proximal Femur: Simulation Analysis Using CT Images

While accurate measurement of bone mineral density (BMD) is essential in the diagnosis of osteoporosis and in evaluating the treatment of osteoporosis, it is unclear how region of interest (ROI) settings affect measurement of BMD at the total proximal femur region. In this study, we performed a simulation analysis to clarify the effect on BMD measurement of changing the ROI using hip computed tomography (CT) images of 75 females (mean age, 62.4 years). Digitally reconstructed radiographs of the proximal femur region were generated from CT images to calculate the change in BMD when the proximal boundary of the ROI was altered by 0-10 mm, and when the distal boundary of the ROI was altered by 0-30 mm. Further, changes in BMD were compared across BMD classification groups. A mean BMD increase of 0.62% was found for each 1-mm extension of the distal boundary. A mean BMD decrease of 0.18% was found for each 1-mm alteration of the proximal boundary. Comparing BMD classification groups, patients with osteoporosis and osteopenia demonstrated greater BMD changes than patients with normal BMD for the distal boundary (0.68%, 0.64%, and 0.54%, respectively) and patients with osteoporosis demonstrated greater BMD changes than patients with osteoporosis and normal BMD for the proximal boundary (0.37%, 0.13%, and 0.03%, respectively). In conclusion, our study found that a consistent ROI setting, especially on the distal boundary, is necessary for the accurate measurement of total proximal femur BMD. Based on the findings, we recommend confirming that the ROI setting shown on the BMD result form is consistent with changes in serial BMD.