Clinical applications of machine learning in predicting 3D shapes of the human body: a systematic review

Corrective Osteotomy in a Patient With Congenital Absence of Pronation Based on Three-Dimensional Statistical Shape Modeling

We present a new indication of a three-dimensional statistical shape model (SSM): a patient with bilateral impaired forearm rotation due to a congenital variance in bone shape. A corrective osteotomy was planned and performed to best match the SSM created by computed tomography (CT) scans of 18 peers. Postoperatively, pronation increased by 70°, and the patient was pain-free. A CT scan showed accurate correction of the deformity and union of all osteotomies. This technique offers opportunities for patients with bilateral nontraumatic osseous forearm pathology.

Deep Learning-Based Facial and Skeletal Transformations for Surgical Planning

The increasing application of virtual surgical planning (VSP) in orthognathic surgery implies a critical need for accurate prediction of facial and skeletal shapes. The craniofacial relationship in patients with dentofacial deformities is still not understood, and transformations between facial and skeletal shapes remain a challenging task due to intricate anatomical structures and nonlinear relationships between the facial soft tissue and bones. In this study, a novel bidirectional 3-dimensional (3D) deep learning framework, named P2P-ConvGC, was developed and validated based on a large-scale data set for accurate subject-specific transformations between facial and skeletal shapes. Specifically, the 2-stage point-sampling strategy was used to generate multiple nonoverlapping point subsets to represent high-resolution facial and skeletal shapes. Facial and skeletal point subsets were separately input into the prediction system to predict the corresponding skeletal and facial point subsets via the skeletal prediction subnetwork and facial prediction subnetwork. For quantitative evaluation, the accuracy was calculated with shape errors and landmark errors between the predicted skeleton or face with corresponding ground truths. The shape error was calculated by comparing the predicted point sets with the ground truths, with P2P-ConvGC outperforming existing state-of-the-art algorithms including P2P-Net, P2P-ASNL, and P2P-Conv. The total landmark errors (Euclidean distances of craniomaxillofacial landmarks) of P2P-ConvGC in the upper skull, mandible, and facial soft tissues were 1.964 ± 0.904 mm, 2.398 ± 1.174 mm, and 2.226 ± 0.774 mm, respectively. Furthermore, the clinical feasibility of the bidirectional model was validated using a clinical cohort. The result demonstrated its prediction ability with average surface deviation errors of 0.895 ± 0.175 mm for facial prediction and 0.906 ± 0.082 mm for skeletal prediction. To conclude, our proposed model achieved good performance on the subject-specific prediction of facial and skeletal shapes and showed clinical application potential in postoperative facial prediction and VSP for orthognathic surgery.

Comparison of three-dimensional imaging of the nose using three different 3D-photography systems: an observational study

BACKGROUND

New 3D technologies for superficial soft tissue changes, especially in plastic and reconstructive surgical procedures, can improve the planning and documentation of facial surgeries. The purpose of this study was to compare and determine the applicability and feasibility of three different 3D-photography systems in clinical practice imaging the nose.

METHODS

A total of 16 healthy non-operated noses were included in this prospective study. A plaster model of each nose was produced, digitized, and converted to a .stl mesh (= ground truth model). Three-dimensional images of each nose were then taken using Artec Space Spider (gold standard), Planmeca ProFace®, and the Bellus3D Dental Pro application. All resulting .stl files were aligned to the ground truth model using MeshLab software, and the root mean square error (RMSE), mean surface distance (MSD), and Hausdorff distance (HD) were calculated.

RESULTS

The Artec Space Spider 3D-photography system showed significantly better results compared to the two other systems in regard to RMSE, MSD, and HD (each p < 0.001). There was no significant difference between Planmeca ProFace® and Bellus3D Dental Pro in terms of RMSE, MSD, and HD. Overall, all three camera systems showed a clinically acceptable deviation to the reference model (range: -1.23-1.57 mm).

CONCLUSIONS

The three evaluated 3D-photography systems were suitable for nose imaging in the clinical routine. While Artec Space Spider showed the highest accuracy, the Bellus3D Dental Pro app may be the most feasible option for everyday clinical use due to its portability, ease of use, and low cost. This study presents three different systems, allowing readers to extrapolate to other systems when planning to introduce 3D photography in the clinical routine.

Drug-target interaction prediction based on spatial consistency constraint and graph convolutional autoencoder

BACKGROUND

Drug-target interaction (DTI) prediction plays an important role in drug discovery and repositioning. However, most of the computational methods used for identifying relevant DTIs do not consider the invariance of the nearest neighbour relationships between drugs or targets. In other words, they do not take into account the invariance of the topological relationships between nodes during representation learning. It may limit the performance of the DTI prediction methods.

RESULTS

Here, we propose a novel graph convolutional autoencoder-based model, named SDGAE, to predict DTIs. As the graph convolutional network cannot handle isolated nodes in a network, a pre-processing step was applied to reduce the number of isolated nodes in the heterogeneous network and facilitate effective exploitation of the graph convolutional network. By maintaining the graph structure during representation learning, the nearest neighbour relationships between nodes in the embedding space remained as close as possible to the original space.

CONCLUSIONS

Overall, we demonstrated that SDGAE can automatically learn more informative and robust feature vectors of drugs and targets, thus exhibiting significantly improved predictive accuracy for DTIs.