Restoring Skeletal Marker Points for Severe Maxillary and Mandibular Jaw Defects Using a Linear Regression Approach

A Stage-Wise Residual Attention Generation Adversarial Network for Mandibular Defect Repairing and Reconstruction

Surgical reconstruction of mandibular defects is a clinical routine manner for the rehabilitation of patients with deformities. The mandible plays a crucial role in maintaining the facial contour and ensuring the speech and mastication functions. The repairing and reconstruction of mandible defects is a significant yet challenging task in oral-maxillofacial surgery. Currently, the mainly available methods are traditional digitalized design methods that suffer from substantial artificial operations, limited applicability and high reconstruction error rates. An automated, precise, and individualized method is imperative for maxillofacial surgeons. In this paper, we propose a Stage-wise Residual Attention Generative Adversarial Network (SRA-GAN) for mandibular defect reconstruction. Specifically, we design a stage-wise residual attention mechanism for generator to enhance the extraction capability of mandibular remote spatial information, making it adaptable to various defects. For the discriminator, we propose a multi-field perceptual network, consisting of two parallel discriminators with different perceptual fields, to reduce the cumulative reconstruction errors. Furthermore, we design a self-encoder perceptual loss function to ensure the correctness of mandibular anatomical structures. The experimental results on a novel custom-built mandibular defect dataset demonstrate that our method has a promising prospect in clinical application, achieving the best Dice Similarity Coefficient (DSC) of 94.238% and 95% Hausdorff Distance (HD95) of 4.787.

Machine learning algorithm based on jaw feature points assist complex maxillary and mandibular reconstruction

PURPOSES

Large-scale jaw reconstruction can hardly achieve satisfactory results only by relying on doctors' experience. In this study, we assessed a new approach using a machine learning algorithm based on jaw feature points to assist complex jaw reconstruction in patients with maxillary and mandibular defects.

METHODS

One hundred and two computed tomography (CT) data on the jaw were collected and 16 skeletal marker points on the jaw were selected. The machine learning algorithm learned the positional relationship between points and built a model, which was used to predict the coordinate position of an unknown point. Then the model was used for a surgical plan in clinical cases.

RESULTS

The linear regression model based on machine learning can control the error within 3 mm. In linear models, Lasso has a slight advantage over the others. We used Lasso to predict the missing points for two patients with maxillary and mandibular defect, respectively. The operation was carried out as planned, and the defects were successfully repaired.

CONCLUSIONS

The restoration of jaw feature points based on a machine learning algorithm is expected to solve large-scale jaw defects without contralateral reference.