Accurate detection of cephalometric landmarks is crucial for orthodontic diagnosis and treatment planning. Current landmark detection methods are mainly divided into heatmap-based and regression-based approaches. However, these methods often rely on parallel computation of multiple models to improve accuracy, significantly increasing the complexity of training and deployment. This paper presented a novel regression method that can simultaneously detect all cephalometric landmarks in high-resolution X-ray images. By leveraging the encoder module of Transformer, a dual-encoder model was designed to achieve coarse-to-fine localization of cephalometric landmarks. The entire model consisted of three main components: a feature extraction module, a reference encoder module, and a fine-tuning encoder module, responsible for feature extraction and fusion of X-ray images, coarse localization of cephalometric landmarks, and fine localization of landmarks, respectively. The model was fully end-to-end differentiable and could learn the intercorrelation relationships between cephalometric landmarks. Experimental results showed that the successful detection rate (SDR) of our algorithm was superior to other existing methods. It attained the highest 2 mm SDR of 89.51% on test set 1 of the ISBI2015 dataset and 90.68% on the test set of the ISBI2023 dataset. Meanwhile, it reduces memory consumption and enhances the model's popularity and applicability, providing more reliable technical support for orthodontic diagnosis and treatment plan formulation.
Cephalometry/methods* ; Humans ; Algorithms ; Anatomic Landmarks/diagnostic imaging* ; Image Processing, Computer-Assisted/methods* ; X-Rays

OBJECTIVE: To explore the anatomical parameters of the cervical uncinate process "inflection point" through cervical CT angiography (CTA) and MRI measurements, offering a reliable and safe anatomical landmark for anterior cervical decompression surgery. METHODS: A retrospective analysis was conducted on the cervical CTA and MRI imaging data of normal adults who met the selection criteria between January 2020 and January 2024. The CTA dataset included 326 cases, with 200 males and 126 females, aged 22-55 years (mean, 46.7 years). The MRI dataset included 300 cases, with 200 males and 100 females, aged 18-55 years (mean, 43.7 years). Based on the CTA data, three-dimensional models of C ₃-C ₇ were constructed, and the following measurements were obtained from the superior view: uncinate process "inflection point" to vertebral artery distance (UIVD), uncinate process tip to vertebral artery distance (UTVD), uncinate process "inflection point" to "inflection point" distance (UID), uncinate process long-axis to sagittal angle (ULSA), and uncinate process "inflection point" to transverse foramen-sagittal angle (UITSA). From the anterior view, the anterior uncinate process to sagittal angle (AUSA) was measured. From the posterior view, the posterior uncinate process to sagittal angle (PUSA) was measured. Based on the MRI data, uncinate process "inflection point" to dural sac distance (UIDD) and dural sac width (DSW) were measured. The trends in measurement parameters of C ₃-C ₇ were observed, and the differences in measurement parameters between genders and between the left and right sides of the same segment were compared, as well as the difference in UID and DSW within the same segment was compared. RESULTS: The measurement parameters from C ₃ to C ₇ in the CTA data showed a general increasing trend, with no significant difference between the left and right sides within the same segment ( P>0.05). The UIVD, UTVD, and UID were greater in males than in females, with significant differences observed in the UIVD and UTVD at C ₃ and C ₆ and UID at C ₃, C ₆, and C ₇ ( P<0.05). The MRI measured DSW showed a general increasing trend from C ₃ to C ₇, and the DSW at C ₆ was greater in females than in males, with a significant difference ( P<0.05). The UIDD showed a gradual decreasing trend, with the smallest value at C ₆. There was no significant difference between males and females or between the left and right sides within the same segment ( P>0.05). The UID was greater than the DSW at C ₃-C ₇, and the differences were significant ( P<0.05). CONCLUSION The uncinate process "inflection point" is a constant anatomical structure located at the anteromedial aspect of the uncinate process tip and laterally to the dural sac. It maintains a certain safe distance from the vertebral artery. As a decompression landmark in anterior cervical spine surgery, it not only ensures surgical safety but also guarantees complete decompression.
Humans ; Adult ; Male ; Female ; Middle Aged ; Retrospective Studies ; Cervical Vertebrae/surgery* ; Magnetic Resonance Imaging ; Decompression, Surgical/methods* ; Young Adult ; Adolescent ; Computed Tomography Angiography ; Imaging, Three-Dimensional ; Vertebral Artery/anatomy & histology* ; Anatomic Landmarks/diagnostic imaging*

Objective: To explore an automatic landmarking method for anatomical landmarks in the three-dimensional (3D) data of the maxillary complex and preliminarily evaluate its reproducibility and accuracy. Methods: From June 2021 to December 2022, spiral CT data of 31 patients with relatively normal craniofacial morphology were selected from those who visited the Department of Oral and Maxillofacial Surgery, Peking University School and Hospital of Stomatology. The sample included 15 males and 16 females, with the age of (33.3±8.3) years. The maxillary complex was reconstructed in 3D using Mimics software, and the resulting 3D data of the maxillary complex was mesh-refined using Geomagic software. Two attending physicians and one associate chief physician manually landmarked the 31 maxillary complex datasets, determining 24 anatomical landmarks. The average values of the three expert landmarking results were used as the expert-defined landmarks. One case that conformed to the average 3D morphological characteristics of healthy individuals' craniofacial bones was selected as the template data, while the remaining 30 cases were used as target data. The open-source MeshMonk program (a non-rigid registration algorithm) was used to perform an initial alignment of the template and target data based on 4 landmarks (nasion, left and right zygomatic arch prominence, and anterior nasal spine). The template data was then deformed to the shape of the target data using a non-rigid registration algorithm, resulting in the deformed template data. Based on the unchanged index property of homonymous landmarks before and after deformation of the template data, the coordinates of each landmark in the deformed template data were automatically retrieved as the automatic landmarking coordinates of the homonymous landmarks in the target data, thus completing the automatic landmarking process. The automatic landmarking process for the 30 target data was repeated three times. The root-mean-square distance (RMSD) of the dense corresponding point pairs (approximately 25 000 pairs) between the deformed template data and the target data was calculated as the deformation error of the non-rigid registration algorithm, and the intra-class correlation coefficient (ICC) of the deformation error in the three repetitions was analyzed. The linear distances between the automatic landmarking results and the expert-defined landmarks for the 24 anatomical landmarks were calculated as the automatic landmarking errors, and the ICC values of the 3D coordinates in the three automatic landmarking repetitions were analyzed. Results: The average three-dimensional deviation (RMSD) between the deformed template data and the corresponding target data for the 30 cases was (0.70±0.09) mm, with an ICC value of 1.00 for the deformation error in the three repetitions of the non-rigid registration algorithm. The average automatic landmarking error for the 24 anatomical landmarks was (1.86±0.30) mm, with the smallest error at the anterior nasal spine (0.65±0.24) mm and the largest error at the left oribital (3.27±2.28) mm. The ICC values for the 3D coordinates in the three automatic landmarking repetitions were all 1.00. Conclusions: This study established an automatic landmarking method for three-dimensional data of the maxillary complex based on a non-rigid registration algorithm. The accuracy and repeatability of this method for landmarking normal maxillary complex 3D data were relatively good.
Male ; Female ; Humans ; Adult ; Imaging, Three-Dimensional/methods* ; Reproducibility of Results ; Algorithms ; Software ; Tomography, Spiral Computed ; Anatomic Landmarks/anatomy & histology*

OBJECTIVE: To explore an efficient and automatic method for determining the anatomical landmarks of three-dimensional(3D) mandibular data, and to preliminarily evaluate the performance of the method. METHODS: The CT data of 40 patients with normal craniofacial morphology were collected (among them, 30 cases were used to establish the 3D mandibular average model, and 10 cases were used as test datasets to validate the performance of this method in determining the mandibular landmarks), and the 3D mandibular data were reconstructed in Mimics software. Among the 40 cases of mandibular data after the 3D reconstruction, 30 cases that were more similar to the mean value of Chinese mandibular features were selected, and the size of the mandibular data of 30 cases was normalized based on the Procrustes analysis algorithm in MATLAB software. Then, in the Geomagic Wrap software, the 3D mandibular average shape model of the above 30 mandibular data was constructed. Through symmetry processing, curvature sampling, index marking and other processing procedures, a 3D mandible structured template with 18 996 semi-landmarks and 19 indexed mandibular anatomical landmarks were constructed. The open source non-rigid registration algorithm program Meshmonk was used to match the 3D mandible template constructed above with the tested patient's 3D mandible data through non-rigid deformation, and 19 anatomical landmark positions of the patient's 3D mandible data were obtained. The accuracy of the research method was evaluated by comparing the distance error of the landmarks manually marked by stomatological experts with the landmarks marked by the method of this research. RESULTS: The method of this study was applied to the data of 10 patients with normal mandibular morphology. The average distance error of 19 landmarks was 1.42 mm, of which the minimum errors were the apex of the coracoid process [right: (1.01±0.44) mm; left: (0.56±0.14) mm] and maximum errors were the anterior edge of the lowest point of anterior ramus [right: (2.52±0.95) mm; left: (2.57±1.10) mm], the average distance error of the midline landmarks was (1.15±0.60) mm, and the average distance error of the bilateral landmarks was (1.51±0.67) mm. CONCLUSION The automatic determination method of 3D mandibular anatomical landmarks based on 3D mandibular average shape model and non-rigid registration algorithm established in this study can effectively improve the efficiency of automatic labeling of 3D mandibular data features. The automatic determination of anatomical landmarks can basically meet the needs of oral clinical applications, and the labeling effect of deformed mandible data needs to be further tested.
Humans ; Imaging, Three-Dimensional/methods* ; Mandible/diagnostic imaging* ; Software ; Algorithms ; Anatomic Landmarks/anatomy & histology*

Objective: To explore the establishment of an efficient and automatic method to determine anatomical landmarks in three-dimensional (3D) facial data, and to evaluate the effectiveness of this method in determining landmarks. Methods: A total of 30 male patients with tooth defect or dentition defect (with good facial symmetry) who visited the Department of Prosthodontics, Peking University School and Hospital of Stomatology from June to August 2021 were selected, and these participants' age was between 18-45 years. 3D facial data of patients was collected and the size normalization and overlap alignment were performed based on the Procrustes analysis algorithm. A 3D face average model was built in Geomagic Studio 2013 software, and a 3D face template was built through parametric processing. MeshLab 2020 software was used to determine the serial number information of 32 facial anatomical landmarks (10 midline landmarks and 22 bilateral landmarks). Five male patients with no mandibular deviation and 5 with mild mandibular deviation were selected from the Department of Orthodontics or Oral and Maxillofacial Surgery, Peking University School and Hospital of Stomatology from June to August 2021. 3D facial data of patients was collected as test data. Based on the 3D face template and the serial number information of the facial anatomical landmarks, the coordinates of 32 facial anatomical landmarks on the test data were automatically determined with the help of the MeshMonk non-rigid registration algorithm program, as the data for the template method to determine the landmarks. The positions of 32 facial anatomical landmarks on the test data were manually determined by the same attending physician, and the coordinates of the landmarks were recorded as the data for determining landmarks by the expert method. Calculated the distance value of the coordinates of facial anatomical landmarks between the template method and the expert method, as the landmark localization error, and evaluated the effect of the template method in determining the landmarks. Results: For 5 patients with no mandibular deviation, the landmark localization error of all facial anatomical landmarks by template method was (1.65±1.19) mm, the landmark localization error of the midline facial anatomical landmarks was (1.19±0.45) mm, the landmark localization error of bilateral facial anatomical landmarks was (1.85±1.33) mm. For 5 patients with mild mandibular deviation, the landmark localization error of all facial anatomical landmarks by template method was (2.55±2.22) mm, the landmark localization error of the midline facial anatomical landmarks was (1.85±1.13) mm, the landmark localization error of bilateral facial anatomical landmarks was (2.87±2.45) mm. Conclusions: The automatic determination method of facial anatomical landmarks proposed in this study has certain feasibility, and the determination effect of midline facial anatomical landmarks is better than that of bilateral facial anatomical landmarks. The effect of determining facial anatomical landmarks in patients without mandibular deviation is better than that in patients with mild mandibular deviation.
Adolescent ; Adult ; Algorithms ; Anatomic Landmarks ; Cephalometry/methods* ; Face/anatomy & histology* ; Female ; Humans ; Imaging, Three-Dimensional/methods* ; Male ; Malocclusion ; Middle Aged ; Orthodontics ; Software ; Young Adult

STUDY DESIGN: Cadaveric, observational study.PURPOSE: Atlantoaxial instability (AAI) is characterized by excessive movement at the C1–C2 junction between the atlas and axis. An anterior surgical approach to expose the upper cervical spine for internal fixation and bone grafting has been developed to fix AAI. Currently, no anatomic information exists on the anterior transarticular atlantoaxial screw or screw and plate fixation between C1 and C2 in the Indian population. The objective of this study is to assess the anatomic landmarks of C1–C2 vertebrae: entry point, trajectory, screw length, and safety of the procedure.OVERVIEW OF LITERATURE: Methods outlined by Magerl and Harms are the optimal approaches among the dorsal techniques. Contraindications for these techniques include aberrant location of vertebral arteries, fractures of C1–C2 posterior structures. In these cases, anterior transarticular fixation is an alternative. Several available screw insertion trajectories have been reported. Biomechanical studies have demonstrated that adequate rigidity of this fixation is comparable with posterior fusion techniques.METHODS: Direct measurements using Vernier calipers and a goniometer were recorded from 30 embalmed human cadavers. The primary parameters measured were the minimum and maximum lateral and posterior angulations of the screw in the sagittal and coronal planes, respectively, and optimum screw length, if it was placed accurately.RESULTS: The posterior and lateral angles of screw placement in the coronal and sagittal planes ranged from 16° to 30° (mean±standard deviation [SD], 23.93°±3.93°) and 8° to 17° (mean±SD, 13.3°±2.26°), respectively. The optimum screw length was 25–38 mm (mean±SD, 28.76±3.69 mm).CONCLUSIONS: If the screw was inserted without lateral angulation, the spinal canal or cord could be violated. If a longer screw was inserted with greater posterior angulation, the vertebral artery at the posterior or posterolateral aspect of the C1 superior facet could be violated. Thus, 26° and 30° of lateral and posterior angulations, respectively, are the maximum angles permissible to avoid injury of the vertebral artery and violations of the spinal canal or atlanto-occipital joint.
Anatomic Landmarks ; Atlanto-Occipital Joint ; Bone Transplantation ; Cadaver ; Humans ; Observational Study ; Spinal Canal ; Spine ; Vertebral Artery

OBJECTIVE: To compare four different three-dimensional horizontal planes and detect anatomical landmarks so as to provide theoretical reference for horizontal reference plane constructed by three-dimensional cephalometry. METHODS: The subjects of this study were 32 facial symmetry patients (menton from midsagittal plane ≤2 mm). Cone-beam computed tomography (CBCT) was obtained before orthodontic treatment, and the data were imported into Dolphin imaging soft in DICOM format. The sagittal plane was passing through the Nasion, Sella and Dent. Four horizontal reference planes were constructed by three points of bilateral porion and bilateral orbitale. Plane 1: horizontal reference plane constructed by right porion and bilateral orbitale. Plane 2: horizontal reference plane constructed by left porion and bilateral orbitale. Plane 3: horizontal reference plane constructed by bilateral porion and right orbitale. Plane 4: horizontal reference plane constructed by bilateral porion and left orbitale. Pitch, yaw, roll for four planes were measured three dimensionally. All the samples were measured two times by one judge at an interval of two weeks. The two times measuring results were evaluated with Intraclass correlation coefficient (ICC) for verifying reliability. The multiple sets of repeated measurement analysis were used to compare the four different planes. Based on ages, the samples were divided into two groups (group 1: ages 13 to 17, group 2: over 18 years), the mean and standard deviation of landmark coordinates measured with Dent as the origin point, the circumference formula was applied to calculate the change of landmark position generated by head rotation. RESULTS: No significant differences of pitch, yaw and roll among the four planes (P=0.196, 0.314, and 0.341). One degree of pitch rotation made changes of porion and orbitale approximate 0.5 mm, and 1.6 mm, respectively. One degree of yaw rotation made changes of porion and orbitale approximate 1.1 mm, and 1.5 mm, respectively. One degree of roll rotation made changes of porion and orbitale approximate 1.2 mm, and 0.7 mm, respectively. CONCLUSION There was no significant difference among the four horizontal planes constructed by any three points of bilateral orbitales and bilateral porions. It has the highest concordance using bilateral orbitales and one porion to construct horizontal plane in this study, probably the best option in clinical practice. Different head rotation generated different distance changes of anatomical landmarks.
Adolescent ; Anatomic Landmarks ; Cephalometry ; Cone-Beam Computed Tomography ; Humans ; Imaging, Three-Dimensional ; Reproducibility of Results

BACKGROUND: The aim of this study was to develop a formula guiding the peripherally inserted central catheter (PICC) tip placement based on anatomical landmarks such as the upper arm, clavicle, and sternum as well as the patient’s height, weight, and body mass index. METHODS: Fifty-five patients who were scheduled to have PICCs were included in the study. We measured four distances along the passage of the PICC, which were as follows; the tip of the third finger to the middle of the elbow crease (Distance A), the middle of the elbow crease to the acromion process (Distance B), the acromion process to the sternal head of the clavicle (Distance C), and the sternal head of the clavicle to the end of the xiphoid process (Distance D). The lengths from the elbow creases to their carina bifurcations as determined by fluoroscopy during PICC insertions were recorded and used as reference. RESULTS: The formula for determining PICC depth based on the four distances was determined by regression analysis. The optimal formula was determined to be 25.3 + 0.5 × (Distance C) + 0.6 × (Distance D) which yielded an R2 value of 0.3. CONCLUSIONS: The formula proposed for proper depth of the adult, 25.0 + 0.5 × (clavicle length) + 0.6 × (sternum length) for PICC insertion can be used to place the tip at the carina bifurcation level. The distance from elbow crease to catheter insertion point should be added to the length generated by this formula.
Acromion ; Adult ; Anatomic Landmarks ; Arm ; Body Mass Index ; Catheterization, Peripheral ; Catheters* ; Clavicle ; Elbow ; Fingers ; Fluoroscopy ; Head ; Humans ; Regression Analysis ; Sternum

BACKGROUND: Cross-facial nerve graft is considered the treatment of choice for facial reanimation in patients with unilateral facial palsy caused by central facial nerve damage. In most cases, a traditional parotidectomy skin incision is used to locate the buccal and zygomatic branches of the facial nerve. METHODS: In this study, cross-facial nerve graft with the sural nerve was planned for three patients with facial palsy through an intraoral approach. RESULTS: An incision was made on the buccal cheek mucosa, and the dissection was performed to locate the buccal branch of the facial nerve. The parotid papillae and parotid duct were used as anatomic landmarks to locate the buccal branch. CONCLUSIONS: The intraoral approach is more advantageous than the conventional extraoral approach because of clear anatomic marker (parotid papilla), invisible postoperative scar, reduced tissue damage from dissection, and reduced operating time.
Anatomic Landmarks ; Cheek ; Cicatrix ; Facial Nerve ; Facial Paralysis ; Humans ; Mucous Membrane ; Skin ; Sural Nerve ; Transplants

OBJECTIVE: To compare the observer preference of image quality and radiation dose between non-grid, grid-like, and grid images. MATERIALS AND METHODS: Each of the 38 patients underwent bedside chest radiography with and without a grid. A grid-like image was generated from a non-grid image using SimGrid software (Samsung Electronics Co. Ltd.) employing deep-learning-based scatter correction technology. Two readers recorded the preference for 10 anatomic landmarks and the overall appearance on a five-point scale for a pair of non-grid and grid-like images, and a pair of grid-like and grid images, respectively, which were randomly presented. The dose area product (DAP) was also recorded. Wilcoxon's rank sum test was used to assess the significance of preference. RESULTS: Both readers preferred grid-like images to non-grid images significantly (p < 0.001); with a significant difference in terms of the preference for grid images to grid-like images (p = 0.317, 0.034, respectively). In terms of anatomic landmarks, both readers preferred grid-like images to non-grid images (p < 0.05). No significant differences existed between grid-like and grid images except for the preference for grid images in proximal airways by two readers, and in retrocardiac lung and thoracic spine by one reader. The median DAP were 1.48 (range, 1.37–2.17) dGy*cm2 in grid images and 1.22 (range, 1.11–1.78) dGy*cm2 in grid-like images with a significant difference (p < 0.001). CONCLUSION: The SimGrid software significantly improved the image quality of non-grid images to a level comparable to that of grid images with a relatively lower level of radiation exposure.
Anatomic Landmarks ; Humans ; Lung ; Radiation Exposure ; Radiography* ; Spine ; Thorax*