Recognition and Segmentation of Individual Bone Fragments with a Deep Learning Approach in CT Scans of Complex Intertrochanteric Fractures: A Retrospective Study

[Research progress on weak state of lateral wall in intertrochanteric fractures]

Objective

To review the research progress of the weak state of the lateral wall in intertrochanteric fracture, in order to provide clinical references.

Methods

The relevant research literature on the lateral wall of intertrochanteric fracture at home and abroad in recent years was summarized and analyzed in terms of morphology, fracture line in coronal plane, and bone density.

Results

Assessment of weak state of the lateral wall is particularly important in the treatment of intertrochanteric fractures. Lateral wall thickness is the main way to assess the weak state of the lateral wall, but there are still problems. Many scholars at home and abroad have studied various aspects such as width, height, and length of the anterior cortex, but there is a lack of a comprehensive assessment method. Coronal fractures affect lateral wall morphology and are difficult to detect on X-ray films, requiring vigilance on the part of the clinician. Further research is needed to clarify the correlation between bone density and the weak state of the lateral wall. The femur lesser trochanter fractures interacts with the latertal wall, and the lesser trochanter fracture exacerbates the weak state. The soft tissue around the lateral wall also affects the weak state, so attention must be paid to protecting the soft tissues during operation.

Conclusion

There are more methods for assessing the weak state of the lateral wall, but none of them has formed a unified standard. Most of the current studies assess the weak state from a single perspective and lack a comprehensive assessment of all aspects affecting the lateral wall. Fewer studies have been conducted to assess the residual lateral wall function after a partial fracture of the lateral wall, and further research is needed.

Hybrid SFNet Model for Bone Fracture Detection and Classification Using ML/DL

An expert performs bone fracture diagnosis using an X-ray image manually, which is a time-consuming process. The development of machine learning (ML), as well as deep learning (DL), has set a new path in medical image diagnosis. In this study, we proposed a novel multi-scale feature fusion of a convolution neural network (CNN) and an improved canny edge algorithm that segregate fracture and healthy bone image. The hybrid scale fracture network (SFNet) is a novel two-scale sequential DL model. This model is highly efficient for bone fracture diagnosis and takes less computation time compared to other state-of-the-art deep CNN models. The innovation behind this research is that it works with an improved canny edge algorithm to obtain edges in the images that localize the fracture region. After that, grey images and their corresponding canny edge images are fed to the proposed hybrid SFNet for training and evaluation. Furthermore, the performance is also compared with the state-of-the-art deep CNN models on a bone image dataset. Our results showed that SFNet with canny (SFNet + canny) achieved the highest accuracy, F1-score and recall of 99.12%, 99% and 100%, respectively, for bone fracture diagnosis. It showed that using a canny edge algorithm improves the performance of CNN.