Deep Radiomics-based Approach to the Diagnosis of Osteoporosis Using Hip Radiographs

Diagnostic performance of radiomics for predicting osteoporosis in adults: a systematic review and meta-analysis

This study aimed to assess the diagnostic accuracy of radiomics for predicting osteoporosis and the quality of radiomic studies. The study protocol was prospectively registered on PROSPERO (CRD42023425058). We searched PubMed, EMBASE, Web of Science, and Cochrane Library databases from inception to June 1, 2023, for eligible articles that applied radiomic techniques to diagnosing osteoporosis or abnormal bone mass. Quality and risk of bias of the included studies were evaluated with radiomics quality score (RQS), METhodological RadiomICs Score (METRICS), and Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tools. The data analysis utilized the R program with mada, metafor, and meta packages. Ten retrospective studies with 5926 participants were included in the systematic review and meta-analysis. The overall risk of bias and applicability concerns for each domain of the studies were rated as low, except for one study which was considered to have a high risk of flow and time bias. The mean METRICS score was 70.1% (range 49.6-83.2%). There was moderate heterogeneity across studies and meta-regression identified sources of heterogeneity in the data, including imaging modality, feature selection method, and classifier. The pooled diagnostic odds ratio (DOR) under the bivariate random effects model across the studies was 57.22 (95% CI 27.62-118.52). The pooled sensitivity and specificity were 87% (95% CI 81-92%) and 87% (95% CI 77-93%), respectively. The area under the summary receiver operating characteristic curve (AUC) of the radiomic models was 0.94 (range 0.8 to 0.98). The results supported that the radiomic techniques had good accuracy in diagnosing osteoporosis or abnormal bone mass. The application of radiomics in osteoporosis diagnosis needs to be further confirmed by more prospective studies with rigorous adherence to existing guidelines and multicenter validation.

A comprehensive predictive model for postoperative joint function in robot-assisted total hip arthroplasty patients: combining radiomics and clinical indicators

Total hip arthroplasty (THA) effectively treats various end-stage hip conditions, offering pain relief and improved joint function. However, surgical outcomes are influenced by multifaceted factors. This research aims to create a predictive model, incorporating radiomic and clinical information, to forecast post-surgery joint function in robot-assisted THA (RA-THA) patients. The study set comprised 136 patients who underwent unilateral RA-THA, which were subsequently partitioned into a training set (n = 95) and a test set (n = 41) for analysis. Preoperative CT imaging was employed to derive 851 radiomic characteristics, selecting those with an intra-class correlation coefficient > 0.75 for analysis. Least absolute shrinkage and selection operator regression reduced redundancy to six significant radiomic features. Clinical data including preoperative Visual Analog Scale (VAS), Harris Hip Score (HHS), and Western Ontario and McMaster University Osteoarthritis Index (WOMAC) score were collected. Logistic regression identified significant predictors, and three models were developed. Receiver operating characteristic and decision curves evaluated the models. Preoperative VAS, HHS, WOMAC score, and radiomics feature scores were significant predictors. In the training set, the AUCs were 0.835 (clinical model), 0.757 (radiomic model), and 0.891 (combined model). In the test set, the AUCs were 0.777 (clinical model), 0.824 (radiomic model), and 0.881 (combined model). The constructed nomogram prediction model combines radiological features with relevant clinical data to accurately predict functional outcomes 3 years after RA-THA. This model has significant prediction accuracy and broad clinical application prospects and can provide a valuable reference for formulating personalized treatment plans and optimizing patient management strategies.

Deep learning for osteoporosis screening using an anteroposterior hip radiograph image

PURPOSE

Osteoporosis is a common bone disorder characterized by decreased bone mineral density (BMD) and increased bone fragility, which can lead to fractures and eventually cause morbidity and mortality. It is of great concern that the one-year mortality rate for osteoporotic hip fractures could be as high as 22%, regardless of the treatment. Currently, BMD measurement is the standard method for osteoporosis diagnosis, but it is costly and requires special equipment. While a plain radiograph can be obtained more simply and inexpensively, it is not used for diagnosis. Deep learning technologies had been applied to various medical contexts, yet few to osteoporosis unless they were trained on the advanced investigative images, such as computed tomography. The purpose of this study was to develop a deep learning model using the anteroposterior hip radiograph images and measure its diagnostic accuracy for osteoporosis.

METHODS

We retrospectively collected all anteroposterior hip radiograph images of patients from 2013 to 2021 at a tertiary care hospital. The BMD measurements of the included patients were reviewed, and the radiograph images that had a time interval of more than two years from the measurements were excluded. All images were randomized using a computer-generated unequal allocation into two datasets, i.e., 80% of images were used for the training dataset and the remaining 20% for the test dataset. The T score of BMD obtained from the ipsilateral femoral neck of the same patient closest to the date of the performed radiograph was chosen. The T score cutoff value of - 2.5 was used to diagnose osteoporosis. Five deep learning models were trained on the training dataset, and their diagnostic performances were evaluated using the test dataset. Finally, the best model was determined by the area under the curves (AUC).

RESULTS

A total of 363 anteroposterior hip radiograph images were identified. The average time interval between the performed radiograph and the BMD measurement was 6.6 months. Two-hundred-thirteen images were labeled as non-osteoporosis (T score >  - 2.5), and the other 150 images as osteoporosis (T score ≤  - 2.5). The best-selected deep learning model achieved an AUC of 0.91 and accuracy of 0.82.

CONCLUSIONS

This study demonstrates the potential of deep learning for osteoporosis screening using anteroposterior hip radiographs. The results suggest that the deep learning model might potentially be used as a screening tool to find patients at risk for osteoporosis to perform further BMD measurement.

Clinical Validation of a Deep Learning-Based Software for Lumbar Bone Mineral Density and T-Score Prediction from Chest X-ray Images

Screening for osteoporosis is crucial for early detection and prevention, yet it faces challenges due to the low accuracy of calcaneal quantitative ultrasound (QUS) and limited access to dual-energy X-ray absorptiometry (DXA) scans. Recent advances in AI offer a promising solution through opportunistic screening using existing medical images. This study aims to utilize deep learning techniques to develop a model that analyzes chest X-ray (CXR) images for osteoporosis screening. This study included the AI model development stage and the clinical validation stage. In the AI model development stage, the combined dataset of 5122 paired CXR images and DXA reports from the patients aged 20 to 98 years at a medical center was collected. The images were enhanced and filtered for hardware retention such as pedicle screws, bone cement, artificial intervertebral discs or severe deformity in target level of T12 and L1. The dataset was then separated into training, validating, and testing datasets for model training and performance validation. In the clinical validation stage, we collected 440 paired CXR images and DXA reports from both the TCVGH and Joy Clinic, including 304 pared data from TCVGH and 136 paired data from Joy Clinic. The pre-clinical test yielded an area under the curve (AUC) of 0.940, while the clinical validation showed an AUC of 0.946. Pearson's correlation coefficient was 0.88. The model demonstrated an overall accuracy, sensitivity, and specificity of 89.0%, 88.7%, and 89.4%, respectively. This study proposes an AI model for opportunistic osteoporosis screening through CXR, demonstrating good performance and suggesting its potential for broad adoption in preliminary screening among high-risk populations.

Automated osteoporosis classification and T-score prediction using hip radiographs via deep learning algorithm

Background

Despite being the gold standard for diagnosing osteoporosis, dual-energy X-ray absorptiometry (DXA) is an underutilized screening tool for osteoporosis.

Objectives

This study proposed and validated a controllable feature layer of a convolutional neural network (CNN) model with a preprocessing image algorithm to classify osteoporosis and predict T-score on the proximal hip region via simple hip radiographs.

Design

This was a single-center, retrospective study.

Methods

An image dataset of 3460 unilateral hip images from 1730 patients (age ⩾50 years) was retrospectively collected with matched DXA assessment for T-score for the targeted proximal hip regions to train (2473 unilateral hip images from 1430 patients) and test (497 unilateral hip images from 300 patients) the proposed CNN model. All images were processed with a fully automated CNN model, X1AI-Osteo.

Results

The proposed screening tool illustrated a better performance (sensitivity: 97.2%; specificity: 95.6%; positive predictive value: 95.7%; negative predictive value: 97.1%; area under the curve: 0.96) than the open-sourced CNN models in predicting osteoporosis. Moreover, when combining variables, including age, body mass index, and sex as features in the training metric, there was high consistency in the T-score on the targeted hip regions between the proposed CNN model and the DXA (r = 0.996, p < 0.001).

Conclusion

The proposed CNN model may identify osteoporosis and predict T-scores on the targeted hip regions from simple hip radiographs with high accuracy, highlighting the future application for population-based opportunistic osteoporosis screening with low cost and high adaptability for a broader population at risk.

Trial registration

TMU-JIRB N201909036.

Application of Radiomics to the Differential Diagnosis of Temporal Bone Skull Base Lesions: A Pilot Study

BACKGROUND

Temporal bone skull base pathologies represent a complex differential because they can be radiographically obscure and difficult to diagnose without biopsy. Radiomics involves the use of mathematical quantification of imaging data beyond simple intensity, size, and location to inform diagnosis and prognosis. We examined the feasibility of using radiomic parameters to help predict temporal bone tumor type.

METHODS

A total of 117 radiomic parameters were analyzed from 5 magnetic resonance imaging sequences (T1 without contrast, T1 with contrast, T2, fluid-attenuated inversion recovery, apparent diffusion coefficient [ADC]) for each tumor. Statistical analysis was used to delineate known primary, metastatic/secondary, and lymphoma lesions using radiomics.

RESULTS

The mean tumor volumes for the 14 primary, 12 secondary, and 8 lymphoma lesions were 2.98 ± 2.11, 3.28 ± 2.31, and 12.16 ± 7.1 cm3, respectively (P = 0.2). No significant differences in mean intensity values for any sequence helped distinguish tumors (P > 0.05), but 6 radiomic parameters were significantly correlated with diagnostic accuracy. Discriminant analysis using a stepwise algorithm generated a model where radiomic parameters for T1 cluster prominence, ADC dependence nonuniformity, T1 with contrast zone percentage, and ADC informational measure of correlation 2 achieved the best predictive model (P = 0.0001). These significant characteristics were often indirect measures of tumor heterogeneity on different magnetic resonance imaging sequences.

CONCLUSIONS

These data suggest that quantitative measures of tumor heterogeneity can be discriminatory of pathology and might be integrated into clinical workflow. Although this pilot study requires further validation, these data support the exploration of radiomics in temporal bone radiographic diagnostics.

Deep learning model for analyzing the relationship between mandibular third molar and inferior alveolar nerve in panoramic radiography

In this study, the accuracy of the positional relationship of the contact between the inferior alveolar canal and mandibular third molar was evaluated using deep learning. In contact analysis, we investigated the diagnostic performance of the presence or absence of contact between the mandibular third molar and inferior alveolar canal. We also evaluated the diagnostic performance of bone continuity diagnosed based on computed tomography as a continuity analysis. A dataset of 1279 images of mandibular third molars from digital radiographs taken at the Department of Oral and Maxillofacial Surgery at a general hospital (2014-2021) was used for the validation. The deep learning models were ResNet50 and ResNet50v2, with stochastic gradient descent and sharpness-aware minimization (SAM) as optimizers. The performance metrics were accuracy, precision, recall, specificity, F1 score, and area under the receiver operating characteristic curve (AUC). The results indicated that ResNet50v2 using SAM performed excellently in the contact and continuity analyses. The accuracy and AUC were 0.860 and 0.890 for the contact analyses and 0.766 and 0.843 for the continuity analyses. In the contact analysis, SAM and the deep learning model performed effectively. However, in the continuity analysis, none of the deep learning models demonstrated significant classification performance.