Three-dimensional cephalometry using individual skeletal laser technology models

Assessment of an Artificial Intelligence Mandibular Osteotomy Design System: A Retrospective Study

BACKGROUND

In this study, an AI osteotomy software was developed to design the presurgical plan of mandibular angle osteotomy, which is followed by the comparison between the software-designed presurgical plan and the traditional manual presurgical plan, thus assessing the practicability of applying the AI osteotomy software in clinical practices.

METHODS

(1) Develop an AI osteotomy software: design an algorithm based on convolutional neural networks capable of learning feature point and processing clustering segmentation; then, select 2296 cases of successful 3D mandibular angle osteotomy presurgical plans, followed by using those 2296 cases to train the deep learning algorithm; (2) compare the osteotomy presurgical plan of AI osteotomy software and that of manual: first step: randomly selecting 80 cases of typical female head 3D CTs, and designing those 80 cases by means of AI osteotomy software designing (group A) and manually designing (group B), respectively; second step: comparing several indexes of group A and those of group B, including the efficiency index (time from input original CT data to osteotomy presurgical plan output), the safety index (the minimum distance from the osteotomy plane to the mandibular canal), the symmetry indexes (bilateral difference of mandibular angle, mandibular ramus height and mandibular valgus angle) and aesthetic indexes (width ratio between middle and lower faces (M/L), mandibular angle and mandibular valgus angle).

RESULTS

The efficiency index: the design time of group A is 1.768 ± 0.768 min and that of group B is 26.108 ± 1.137 min, with P = 0.000; the safety index: The minimum distances from the osteotomy plane to the mandibular canal are 3.908 ± 0.361mm and 3.651 ± 0.437mm, p = 0.117 in groups A and B, respectively; The symmetry indexes: Bilateral differences of mandibular angle are 1.824 ± 1.834° and 1.567 ± 1.059° in groups A and B, respectively, with P = 0.278; bilateral differences of mandibular ramus height are 2.083 ± 1.263 and 2.965 ± 1.433, respectively, with P = 0.119 in groups A and B; Aesthetic indexes: M/L in groups A and B is 1.364 ± 0.074 and 1.371 ± 0.067, respectively, with P = 0.793; mandibular angles in groups A and B are 127.724 ± 5.800° and 127.242 ± 5.545°, respectively, with P = 0.681; Valgus angles in groups A and B are 11.474 ± 5.380 and 9.743 ± 4.620, respectively, with P = 0.273.

CONCLUSIONS

With high efficiency, as well as safety, symmetry and aesthetics equivalent to those of a manual design, the AI osteotomy software designing can be used as an alternative method for manual osteotomy designing.

LEVEL OF EVIDENCE IV

This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266.

Accuracy of using computer-aided rapid prototyping templates for mandible reconstruction with an iliac crest graft

Background

This study aimed to evaluate the accuracy of surgical outcomes in free iliac crest mandibular reconstructions that were carried out with virtual surgical plans and rapid prototyping templates.

Methods

This study evaluated eight patients who underwent mandibular osteotomy and reconstruction with free iliac crest grafts using virtual surgical planning and designed guiding templates. Operations were performed using the prefabricated guiding templates. Postoperative three-dimensional computer models were overlaid and compared with the preoperatively designed models in the same coordinate system.

Results

Compared to the virtual osteotomy, the mean error of distance of the actual mandibular osteotomy was 2.06 ± 0.86 mm. When compared to the virtual harvested grafts, the mean error volume of the actual harvested grafts was 1412.22 ± 439.24 mm³ (9.12% ± 2.84%). The mean error between the volume of the actual harvested grafts and the shaped grafts was 2094.35 ± 929.12 mm³ (12.40% ± 5.50%).

Conclusions

The use of computer-aided rapid prototyping templates for virtual surgical planning appears to positively influence the accuracy of mandibular reconstruction.

Digital surgical templates for managing high-energy zygomaticomaxillary complex injuries associated with orbital volume change: a quantitative assessment

PURPOSE

This study sought to introduce 3-dimensional (3D) virtual surgical planning and digital rapid-prototyping templates for zygomaticomaxillary complex (ZMC) injuries associated with orbital volume change and to evaluate the surgical outcomes quantitatively.

PATIENTS AND METHODS

Eight patients who underwent open reduction and fixation for a ZMC injury with orbital volume change were studied. Computed tomographic (CT) scan of the zygomaticomaxillary area was performed before the operation in each case. Scanned data were converted into 3D models using Mimics software (Materialise, Brussels, Belgium) for surgical designs. Virtual surgical reductions and correlated guiding templates were designed using Mimics and Magics software (Materialise). The operations were performed with the help of prefabricated templates to reduce the fractures. A postoperative CT scan of each patient was obtained within 2 weeks after surgery, and quantitative measurements were made to assess the surgical outcomes. Preoperative volumes of the bilateral orbits were compared, and concordance with postoperative volumes of the bilateral orbits was assessed. Twenty-one pairs of distances from 7 marker points to 3 reference planes were measured to assess postoperative facial symmetry.

RESULTS

Volumes of the injured orbits were significantly different from volumes of the uninjured orbits preoperatively (P < .05), whereas bilateral orbital volumes showed no statistically significant difference postoperatively (P > .05). In addition, 19 of the 21 pairs of bilateral distances showed no significant difference postoperatively (P > .05).

CONCLUSIONS

Quantitative assessment showed that digitally designed, rapid-prototyping templates for ZMC fractures have a positive impact on restoring facial symmetry and concordance of bilateral orbital volumes.

Outcome measurement in the correction of mandibular asymmetry

This study related clinical assessments of the severity of mandibular asymmetry with computerized measurements, obtained by digitizing mandibular outlines from standardized facial photographs. Four ratios were calculated: area (size), compactness (shape), perimeter (length of outline), and moment (center of area). When comparing clinical severity with computer assessment, significant correlations were observed; those for area and compactness were the highest. Sixteen patients subsequently underwent corrective surgery, and their ratios were used to relate the degree of improvement to the original severity of the asymmetry. The posttreatment ratios were also used to audit the outcome, comparing the patients' scores as a group with results previously obtained from patients with normal symmetry and mild asymmetry. Posttreatment outcomes were significantly different from the normal outline group but were comparable with outcomes of patients with mild mandibular asymmetry. The system provided a sensitive, noninvasive method of assessing treatment change and could be useful in providing an objective means of quantifying treatment outcomes.