Machine Learning-Based Measurement of Regional and Global Spinal Parameters Using the Concept of Incidence Angle of Inflection Points.

This study delves into the application of convolutional neural networks (CNNs) in evaluating spinal sagittal alignment, introducing the innovative concept of incidence angles of inflection points (IAIPs) as intuitive parameters to capture the interplay between pelvic and spinal alignment. Pioneering the fusion of IAIPs with machine learning for sagittal alignment analysis, this research scrutinized whole-spine lateral radiographs from hundreds of patients who visited a single institution, utilizing high-quality images for parameter assessments. Noteworthy findings revealed robust success rates for certain parameters, including pelvic and C2 incidence angles, but comparatively lower rates for sacral slope and L1 incidence. The proposed CNN-based machine learning method demonstrated remarkable efficiency, achieving an impressive 80 percent detection rate for various spinal angles, such as lumbar lordosis and thoracic kyphosis, with a precise error threshold of 3.5°. Further bolstering the study's credibility, measurements derived from the novel formula closely aligned with those directly extracted from the CNN model. In conclusion, this research underscores the utility of the CNN-based deep learning algorithm in delivering precise measurements of spinal sagittal parameters, and highlights the potential for integrating machine learning with the IAIP concept for comprehensive data accumulation in the domain of sagittal spinal alignment analysis, thus advancing our understanding of spinal health.

Quantitative Augmented Reality-Assisted Free-Hand Orthognathic Surgery Using Electromagnetic Tracking and Skin-Attached Dynamic Reference.

The purpose of this study was to develop a quantitative AR-assisted free-hand orthognathic surgery method using electromagnetic (EM) tracking and skin-attached dynamic reference. The authors proposed a novel, simplified, and convenient workflow for augmented reality (AR)-assisted orthognathic surgery based on optical marker-less tracking, a comfortable display, and a non-invasive, skin-attached dynamic reference frame. The 2 registrations between the physical (EM tracking) and CT image spaces and between the physical and AR camera spaces, essential processes in AR-assisted surgery, were pre-operatively performed using the registration body complex and 3D depth camera. The intraoperative model of the maxillary bone segment (MBS) was superimposed on the real patient image with the simulated goal model on a flat-panel display, and the MBS was freely handled for repositioning with respect to the skin-attached dynamic reference tool (SRT) with quantitative visualization of landmarks of interest using only EM tracking. To evaluate the accuracy of AR-assisted Le Fort I surgery, the MBS of the phantom was simulated and repositioned by 6 translational and three rotational movements. The mean absolute deviations (MADs) between the simulation and post-operative positions of MBS landmarks by the SRT were 0.20, 0.34, 0.29, and 0.55 mm in x- (left lateral, right lateral), y- (setback, advance), and z- (impaction, elongation) directions, and RMS, respectively, while those by the BRT were 0.23, 0.37, 0.30, and 0.60 mm. There were no significant differences between the translation and rotation surgeries or among surgeries in the x-, y-, and z-axes for the SRT. The MADs in the x-, y-, and z-axes exhibited no significant differences between the SRT and BRT. The developed method showed high accuracy and reliability in free-hand orthognathic surgery using EM tracking and skin-attached dynamic reference.

Direct and continuous localization of anatomical landmarks for image-guided orthognathic surgery.

OBJECTIVE: The accuracy and consistency of a new image-guided method for orthognathic surgery using direct and continuous landmark localization was compared with that of a conventional method. STUDY DESIGN: Maxillary and mandibular dental casts mounted on an articulator were used as a surgery phantom. We planned six types of surgeries including translations and rotations. The sequential positions of the landmarks determined before surgery could be traced and the difference between planned and actual positions of the landmarks could be visualized during surgery. The final deviation errors were determined with and without applying the pointing instrument to the landmarks. RESULTS: The mean RMS accuracy of 0.47 ± 0.22 mm by direct localization was significantly higher than that of 1.06 ± 0.49 mm by the manual localization. There were no significant differences in accuracies for surgeries using the direct localization method. CONCLUSION: The direct and continuous localization method showed higher accuracy and consistency than conventional manual localization in all phantom surgeries.

Giant plunging ranula: a case report.

A ranula is a bluish, transparent, and thin-walled swelling in the floor of the mouth. They originate from the extravasation and subsequent accumulation of saliva from the sublingual gland. Ranulas are usually limited to the sublingual space but they sometimes extend to the submandibular space and parapharyngeal space, which is defined as a plunging ranula. A 21-year-old woman presented with a complaint of a large swelling in the left submandibular region. On contrast-enhanced CT images, it dissected across the midline, and extended to the parapharyngeal space posteriorly and to the submandibular space inferiorly. Several septa and a fluid-fluid level within the lesion were also demonstrated. We diagnosed this lesion as a ranula rather than cystic hygroma due to the location of its center and its sublingual tail sign. As plunging ranula and cystic hygroma are managed with different surgical approaches, it is important to differentiate them radiologically.

Principal direction of inertia for 3D trajectories from patient-specific TMJ movement.

Accurate simulation and evaluation of mandibular movement is fundamental for the analysis of functional changes and effects of the mandible and maxilla before and after surgical treatments. We applied principal axes of inertia to the three-dimensional (3D) trajectories generated by patient-specific simulations of TMJ movements for the functional evaluations of mandible movement. Three-dimensional movements of the mandible and the maxilla were tracked based on a patient-specific splint and an optical tracking system. The dental occlusion recorded on the sprint provided synchronization for initial movement in the tracking and the simulation phases. The translation and rotation recorded during movement tracking was applied sequentially to the mandibular model in relation to a fixed maxilla model. The sequential 3D positions of selected landmarks on the mandible were calculated based on the reference coordinate system. The landmarks selected for analysis were bilateral condyles and pogonion points. The moment of inertia tensor was calculated with respect to the 3D trajectory points. Using the unit vectors along the principal axes derived from the tensor matrix, α, ß and γ rotations around z-, y- and x-axes were determined to represent the principal directions as principal rotations respectively. The γ direction showed the higher standard deviation, variation of directions, than other directions at all the landmarks. The mandible movement has larger kinematic redundancy in the γ direction than α and ß during mouth opening and closing. Principal directions of inertia would be applied to analyzing the changes in angular motion of trajectories introduced by mandibular shape changes from surgical treatments and also to the analysis of the influence of skeletal deformities on mandibular movement asymmetry.