AFFnet - a deep convolutional neural network for the detection of atypical femur fractures from anteriorposterior radiographs.

Despite well-defined criteria for radiographic diagnosis of atypical femur fractures (AFFs), missed and delayed diagnosis is common. An AFF diagnostic software could provide timely AFF detection to prevent progression of incomplete or development of contralateral AFFs. In this study, we investigated the ability for an artificial intelligence (AI)-based application, using deep learning models (DLMs), particularly convolutional neural networks (CNNs), to detect AFFs from femoral radiographs. A labelled Australian dataset of pre-operative complete AFF (cAFF), incomplete AFF (iAFF), typical femoral shaft fracture (TFF), and non-fractured femoral (NFF) X-ray images in anterior-posterior view were used for training (N = 213, 49, 394, 1359, respectively). An AFFnet model was developed using a pretrained (ImageNet dataset) ResNet-50 backbone, and a novel Box Attention Guide (BAG) module to guide the model's scanning patterns to enhance its learning. All images were used to train and internally test the model using a 5-fold cross validation approach, and further validated by an external dataset. External validation of the model's performance was conducted on a Sweden dataset comprising 733 TFF and 290 AFF images. Precision, sensitivity, specificity, F1-score and AUC were measured and compared between AFFnet and a global approach with ResNet-50. Excellent diagnostic performance was recorded in both models (all AUC >0.97), however AFFnet recorded lower number of prediction errors, and improved sensitivity, F1-score and precision compared to ResNet-50 in both internal and external testing. Sensitivity in the detection of iAFF was higher for AFFnet than ResNet-50 (82 % vs 56 %). In conclusion, AFFnet achieved excellent diagnostic performance on internal and external validation, which was superior to a pre-existing model. Accurate AI-based AFF diagnostic software has the potential to improve AFF diagnosis, reduce radiologist error, and allow urgent intervention, thus improving patient outcomes.

Denosumab Prevents Bone Loss and Microarchitectural Deterioration in Premenopausal Women With Breast Cancer Receiving Estradiol Suppression Therapy: A Randomized Controlled Trial.

PURPOSE: Suppression of ovarian function and aromatase inhibition (AI) increases disease-free survival in premenopausal women with estrogen receptor (ER)-positive early-stage breast cancer but accelerates bone loss. We therefore hypothesized that suppressing bone remodeling using denosumab (DMAB) would prevent bone loss in these women. METHODS: In a 12-month double-blind randomized trial, 68 women with ER-positive early-stage breast cancer commencing ovarian function suppression and AI were randomly assigned to 60 mg DMAB (n = 34) or placebo (PBO; n = 34) once every 6 months (at 0 and 6 months). Volumetric bone mineral density (BMD), microarchitecture, and estimated bone strength of the distal tibia and distal radius were measured using high-resolution peripheral quantitative computed tomography, and spine and hip BMD were measured using dual-energy X-ray absorptiometry at 0, 6, and 12 months. The primary end point and treatment effect was the mean adjusted between group difference (MAD; [95% CI]) in distal tibial total volumetric BMD over 12 months, with a single P value tested over all time points. The study is registered with the Australian New Zealand Clinical Trials Registry (anzctr.org.au; identifier: ACTRN12616001051437). RESULTS: Intention-to-treat analysis included all 68 randomly assigned women. Over 12 months, compared with PBO, DMAB prevented the decrease in distal tibial total BMD (MAD, 20.8 mg HA/cm3 [95% CI, 17.3 to 24.2]), cortical BMD (42.9 mg HA/cm3 [95% CI, 32.1 to 53.9]), trabecular BMD (3.32 mg HA/cm3 [95% CI, 1.45 to 5.20], P = .004), estimated stiffness (11.6 kN/m [95% CI, 7.6 to 15.6]), and failure load (563 N [95% CI, 388 to 736]). Findings were similar at the distal radius. Decreases in BMD at the lumbar spine (MAD, 0.13 g/cm2 [95% CI, 0.11 to 0.15]), total hip (0.08 g/cm2 [95% CI, 0.07 to 0.09], and femoral neck (0.06 g/cm2 [95% CI, 0.05 to 0.07]) were also prevented. All P < .001 unless otherwise noted. CONCLUSION: Treatment with DMAB at commencement of estradiol suppression therapy preserves BMD, bone microarchitecture, and estimated strength, and is likely to increase fracture-free survival.

A Novel RUNX1 Genetic Variant Identified in a Young Male with Severe Osteoporosis.

This case describes a young man with an unusual cause of severe osteoporosis and markedly deranged bone microarchitecture resulting in multiple fractures. A potentially pathogenic germline variant in the runt-related transcription factor 1 (RUNX1) gene was discovered by a focused 51-gene myeloid malignancy panel during investigation for his unexplained normochromic normocytic anemia. Further bone-specific genetic testing and a pedigree analysis were declined by the patient. Recent experimental evidence demonstrates that RUNX1 plays a key role in the regulation of osteogenesis and bone homeostasis during skeletal development, mediated by the bone morphogenic protein and Wnt signaling pathways. Therefore, rarer causes of osteoporosis, including those affecting bone formation, should be considered in young patients with multiple unexpected minimal trauma fractures. © 2023 The Authors. JBMR Plus published by Wiley Periodicals LLC on behalf of American Society for Bone and Mineral Research.

Why Aboriginal and Torres Strait Islander Australians fall and fracture: the codesigned Study of Indigenous Muscle and Bone Ageing (SIMBA) protocol.

OBJECTIVES: Aboriginal and Torres Strait Islander Australians have a substantially greater fracture risk, where men are 50% and women are 26% more likely to experience a hip fracture compared with non-Indigenous Australians. Fall-related injuries in this population have also increased by 10%/year compared with 4.3%/year in non-Indigenous Australians. This study aims to determine why falls and fracture risk are higher in Aboriginal and Torres Strait Islander Australians. SETTING: All clinical assessments will be performed at one centre in Melbourne, Australia. At baseline, participants will have clinical assessments, including questionnaires, anthropometry, bone structure, body composition and physical performance tests. These assessments will be repeated at follow-up 1 and follow-up 2, with an interval of 12 months between each clinical visit. PARTICIPANTS: This codesigned prospective observational study aims to recruit a total of 298 adults who identify as Aboriginal and Torres Strait Islander and reside within Victoria, Australia. Stratified sampling by age and sex will be used to ensure equitable distribution of men and women across four age-bands (35-44, 45-54, 55-64 and 65+ years). PRIMARY AND SECONDARY OUTCOME MEASURES: The primary outcome is within-individual yearly change in areal bone mineral density at the total hip, femoral neck and lumbar spine assessed by dual energy X-ray absorptiometry. Within-individual change in cortical and trabecular volumetric bone mineral density at the radius and tibia using high-resolution peripheral quantitative computed tomography will be determined. Secondary outcomes include yearly differences in physical performance and body composition. ETHICAL APPROVAL: Ethics approval for this study has been granted by the Monash Health Human Research Ethics Committee (project number: RES-19-0000374A). TRIAL REGISTRATION NUMBER: ACTRN12620000161921.

Effects of estradiol on bone in men undergoing androgen deprivation therapy: a randomized placebo-controlled trial.

Objective: In men, many effects of testosterone (T) on the skeleton are thought to be mediated by estradiol (E2), but trial evidence is largely lacking. This study aimed to determine the effects of E2 on bone health in men in the absence of endogenous T. Design: This study is a 6-month randomized, placebo-controlled trial with the hypothesis that E2 would slow the decline of volumetric bone mineral density (vBMD) and bone microstructure, maintain areal bone mineral density (aBMD), and reduce bone remodelling. Methods: 78 participants receiving androgen deprivation therapy for prostate cancer were randomized to 0.9 mg of 0.1% E2 gel daily or matched placebo. The outcome measures were vBMD and microarchitecture at the distal tibia and distal radius by high-resolution peripheral quantitative CT, aBMD at the spine and hip by dual-energy x-ray absorptiometry, and serum bone remodelling markers. Results: For the primary endpoint, total vBMD at the distal tibia, there was no significant difference between groups, mean adjusted difference (MAD) 2.0 mgHA/cm3 (95% CI: -0.8 to 4.8), P = 0.17. Cortical vBMD at the distal radius increased in the E2 group relative to placebo, MAD 14.8 mgHA/cm3 (95% CI: 4.5 to 25.0), P = 0.005. Relative to placebo, E2 increased estimated failure load at tibia, MAD 250 N (95% CI: 36 to 465), P = 0.02, and radius, MAD 193 N (95% CI: 65 to 320), P = 0.003. Relative to placebo, E2 increased aBMD at the lumbar spine, MAD 0.02 g/cm2 (95% CI: 0.01 to 0.03), P = 0.01, and ultra-distal radius, MAD 0.01 g/cm2 (95% CI: 0.00 to 0.02), P = 0.01, and reduced serum bone remodelling markers. Conclusion: Relative to placebo, E2 treatment increases some measures of bone density and bone strength in men and reduces bone remodelling, effects that occur in the absence of endogenous T.

Associations of Serum 25-Hydroxyvitamin D with Physical Performance and Bone Health in Overweight and Obese Older Adults.

Low vitamin D status commonly accompanies obesity, and both vitamin D deficiency and obesity have been associated with falls and fracture risk in older adults. We aimed to determine the associations of serum 25-hydroxyvitamin D (25(OH)D) concentrations with physical performance and bone health in community-dwelling, overweight and obese older men and women. Serum 25(OH)D concentrations were measured in 84 participants with body mass index ≥25 kg/m² (mean ± SD age 62.4 ± 7.9 years; 55% women). Physical function was determined by short physical performance battery, hand grip and quadriceps strength, and stair climb power tests. Body composition and bone structure were assessed by dual-energy X-ray absorptiometry and peripheral quantitative computed tomography, respectively. Mean ± SD 25(OH)D was 49.6 ± 17.7 nmol/L, and 50% of participants had low 25(OH)D (<50 nmol/L) levels. 25(OH)D concentrations were positively associated with quadricep strength and stair climb power in women (B = 0.15; 95% CI 0.02⁻0.27 kg and B = 1.07; 95% CI 0.12⁻2.03 W, respectively) but not in men. There were no associations between 25(OH)D and bone parameters in either sex after multivariable adjustment (all p > 0.05). Lower 25(OH)D concentrations are associated with poorer quadricep strength and muscle power in overweight and obese older women but not men.