Intertrochanteric (IT) femur fractures are the most common fractures in elderly people, and they lead to significant morbidity, mortality, and reduced quality of life. The different types of fractures require a careful definition to ensure accurate surgical planning and reduce the operation time, healing time, and number of surgical failures. In this study, a deep learning-based automatic multi-class IT fracture detection model was developed using computed tomography (CT) images and based on the AO/OTA classification method. The original CT image was resized and rearranged according to the fracture location and an unsharp masking filter was applied. A multi-class classification of nine different types of IT fractures and no fracture was performed using the faster regional-convolutional neural network (R-CNN). Bayesian optimization was also implemented to determine the optimal hyperparameter values for the faster R-CNN algorithm. In our proposed model, IT fractures classified into two classes showed an average accuracy of 0.97 ± 0.02, which was 0.90 ± 0.02 when classified into ten classes. Additionally, the detected region of interest from our proposed model showed minimum root mean square error and intersection over union values of 16.34 ± 47.01 pixels and 0.87 ± 0.12, respectively. In the future, our proposed automatic multi-class IT femur fracture detection model could allow clinicians to identify the fracture region and diagnose different types of femur fractures faster and more accurately. This will increase the probability of correct surgical treatment and minimize postoperative complications.
- MeSH
- deep learning MeSH
- fraktury kyčle * diagnostické zobrazování klasifikace MeSH
- lidé MeSH
- neuronové sítě (počítačové) MeSH
- počítačová rentgenová tomografie * metody MeSH
- statistika jako téma MeSH
- Check Tag
- lidé MeSH
- mužské pohlaví MeSH
- ženské pohlaví MeSH
- Publikační typ
- klinická studie MeSH
- práce podpořená grantem MeSH
This study proposes a method to measure the twisting angle of a rod during a spinal correction surgery in real-time without performing an alignment procedure by using the six-axis data (tri-axis acceleration, tri-axis rate gyro) of the IMU and a Tait-Bryan Euler angle algorithm. To determine whether the twisting angle calculation algorithm offered an improvement, typical procedures described in existing studies were implemented using the same experimental data and were then validated using a three-dimensional motion analysis system (Vicon 460 motion analysis system). The correlation coefficients and the RMSE of the proposed method were 0.904 and 0.680° in the servo-motor experiment, and 0.988 and 0.691° in the mock surgery experiment, respectively, and these values were not significantly different from those calculated through other methods in previous studies. Therefore, if the proposed method is used during surgery, an alignment procedure and the assumptions following the morphology of body, which are limitations of prior research, are not necessary. Also the twisting angle of the rod can be observed without using magnetic data of IMU in real time during surgery. It is expected that the correction loss, which is a serious problem that can occur in patients after spinal correction, could be prevented.
- Klíčová slova
- derotační chirurgie páteře u pacientů s idiopatickou skoliózou,
- MeSH
- chirurgické nástroje využití MeSH
- diagnostické techniky a postupy přístrojové vybavení trendy využití MeSH
- lidé MeSH
- nemoci páteře diagnóza etiologie chirurgie MeSH
- ortopedické výkony * metody využití MeSH
- respirační insuficience diagnóza etiologie terapie MeSH
- rotace * škodlivé účinky MeSH
- skolióza * diagnóza chirurgie terapie MeSH
- srdeční selhání diagnóza etiologie terapie MeSH
- statistika jako téma MeSH
- torze mechanická MeSH
- zakřivení páteře chirurgie terapie MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- práce podpořená grantem MeSH
