A quantitative and non-invasive vibrational method to assess bone fracture healing: a clinical case study

Application of stacked autoencoder for identification of bone fracture

This study presents a stacked autoencoder (SAE)-based assessment method which is one of the unsupervised learning schemes for the investigation of bone fracture. Relatively accurate health monitoring of bone fracture requires considering physical interactions among tissue, muscle, wave propagation and boundary conditions inside the human body. Furthermore, the investigation of fracture, crack and healing process without state-of-the-art medical devices such as CT, X-ray and MRI systems is challenging. To address these issues, this study presents the SAE method that incorporates bilateral symmetry of the human legs and low-frequency transverse vibration. To verify the presented method, several examples are employed with plastic pipes, cadaver legs and human legs. Virtual spectrograms, created by applying a short-time Fourier transform to the differences in vibration responses, are employed for image-based training in SAE. The virtual spectrograms are then classified and the fine-tuning is also carried out to increase the accuracy. Moreover, a confusion matrix is employed to evaluate classification accuracy and training validity.

Assessment of Bone Healing: Opportunities to Improve the Standard of Care

➤ Bone healing is commonly evaluated by clinical examination and serial radiographic evaluation. Physicians should be mindful that personal and cultural differences in pain perception may affect the clinical examination. Radiographic assessment, even with the Radiographic Union Score, is qualitative, with limited interobserver agreement.➤ Physicians may use serial clinical and radiographical examinations to assess bone healing in most patients, but in ambiguous and complicated cases, they may require other methods to provide assistance in decision-making.➤ In complicated instances, clinically available biomarkers, ultrasound, and magnetic resonance imaging may determine initial callus development. Quantitative computed tomography and finite element analysis can estimate bone strength in later callus consolidation phases.➤ As a future direction, quantitative rigidity assessments for bone healing may help patients to return to function earlier by increasing a clinician's confidence in successful progressive healing.

Modal Frequencies Associations with Musculoskeletal Components of Human Legs for Extracorporeal Bone Healing Assessment Based on a Vibration Analysis Approach

Reliable and quantitative assessments of bone quality and fracture healing prompt well-optimised patient healthcare management and earlier surgical intervention prior to complications of nonunion and malunion. This study presents a clinical investigation on modal frequencies associations with musculoskeletal components of human legs by using a prototype device based on a vibration analysis method. The findings indicated that the first out-of-plane and coupled modes in the frequency range from 60 to 110 Hz are associated with the femur length, suggesting these modes are suitable quantitative measures for bone evaluation. Furthermore, higher-order modes are shown to be associated with the muscle and fat mass of the leg. In addition, mathematical models are formulated via a stepwise regression approach to determine the modal frequencies using the measured leg components as variables. The optimal models of the first modes consist of only femur length as the independent variable and explain approximately 43% of the variation of the modal frequencies. The subsequent findings provide insights for further development on utilising vibration-based methods for practical bone and fracture healing monitoring.