Distal radius fracture is common in the general population. Fracture management includes a plaster cast, splint and synthetic material cast to immobilise the injured arm. Casting complications are common in those conventional casting technologies. 3D printing technology is a rapidly increasing application in rehabilitation. However, there is no clinical study investigating the application of a 3D–printed orthopaedic cast for the treatment of bone fractures. We have developed a patient-specific casting technology fabricated by 3D printing. This pioneering study aims to use 3D–printed casts we developed for the treatment of distal radius fractures, to provide the foundation for conducting additional clinical trials, and to perform clinical assessments. Ten patients with ages between 5 and 78 years are involved in the clinical trial. Patients are applied 3D–printed casts we developed. Orthopaedic surgeons carried out a six-week follow-up to examine clinical outcomes. Two questionnaires were developed for the assessment of clinical efficacy and patients’ satisfaction. These questionnaires are completed by physicians and participating patients. A 3D–printed cast creates a custom-fitted design to maintain the fractured bone alignment. No loss of reduction is found in all patients. Compartment syndrome and pressure sores are not present. Patient comfort gets positive scores on the questionnaire. All (100%) of the patients opt for the 3D–printed cast instead of the conventional plaster cast. A patient-specific, 3D–printed cast offers a proper fit to immobilise an injured arm and holds the fracture reduction appropriately. A custom-fitted structure reduces the risk of pressure-related complications due to the high and concentrated local stress. The ventilated and lightweight design minimises interference with a patient’s daily activities and reduces the risk of cutaneous complications. Patients express a strong preference for using a 3D–printed cast instead of a plaster cast. Limitations of the novel cast include a slight odour after heavy sweating and the relatively high cost due to the limitations of current 3D printing technologies. This pioneering study is the first clinical trial on the application of a 3D–printed cast for the treatment of forearm fractures. The novel casting technology heals the fracture effectively without casting complications. The 3D–printed cast is patient-specific and ventilated as well as lightweight, and it features both increased patient comfort and satisfaction.

Background: No investigations have thoroughly explored the feasibility of combining magnetic resonance (MR) images and deep-learning methods for predicting the progression of knee osteoarthritis (KOA). We thus aimed to develop a potential deep-learning model for predicting OA progression based on MR images for the clinical setting. Methods: A longitudinal case-control study was performed using data from the Foundation for the National Institutes of Health (FNIH), composed of progressive cases [182 osteoarthritis (OA) knees with both radiographic and pain progression for 24–48 months] and matched controls (182 OA knees not meeting the case definition). DeepKOA was developed through 3-dimensional (3D) DenseNet169 to predict KOA progression over 24–48 months based on sagittal intermediate-weighted turbo-spin echo sequences with fat-suppression (SAG-IW-TSE-FS), sagittal 3D dual-echo steady-state water excitation (SAG-3D-DESS-WE) and its axial and coronal multiplanar reformation, and their combined MR images with patient-level labels at baseline, 12, and 24 months to eventually determine the probability of progression. The classification performance of the DeepKOA was evaluated using 5-fold cross-validation. An X-ray-based model and traditional models that used clinical variables via multilayer perceptron were built. Combined models were also constructed, which integrated clinical variables with DeepKOA. The area under the curve (AUC) was used as the evaluation metric. Results: The performance of SAG-IW-TSE-FS in predicting OA progression was similar or higher to that of other single and combined sequences. The DeepKOA based on SAG-IW-TSE-FS achieved an AUC of 0.664 (95% CI: 0.585–0.743) at baseline, 0.739 (95% CI: 0.703–0.775) at 12 months, and 0.775 (95% CI: 0.686–0.865) at 24 months. The X-ray-based model achieved an AUC ranging from 0.573 to 0.613 at 3 time points. However, adding clinical variables to DeepKOA did not improve performance (P>0.05). Initial visualizations from gradient-weighted class activation mapping (Grad-CAM) indicated that the frequency with which the patellofemoral joint was highlighted increased as time progressed, which contrasted the trend observed in the tibiofemoral joint. The meniscus, the infrapatellar fat pad, and muscles posterior to the knee were highlighted to varying degrees. Conclusions: This study initially demonstrated the feasibility of DeepKOA in the prediction of KOA progression and identified the potential responsible structures which may enlighten the future development of more clinically practical methods.

Fully automated radiomic screening pipeline for osteoporosis and abnormal bone density with a deep learning-based segmentation using a short lumbar mDixon sequence Yinxia Zhao, Tianyun Zhao, Shenglan Chen, Xintao Zhang, Mario Serrano Sosa, Jin Liu, Xianfu Mo, Xiaojun Chen, Mingqian Huang, Shaolin Li, Xiaodong Zhang, Chuan Huang