BM-BronchoLC - A rich bronchoscopy dataset for anatomical landmarks and lung cancer lesion recognition.

Flexible bronchoscopy has revolutionized respiratory disease diagnosis. It offers direct visualization and detection of airway abnormalities, including lung cancer lesions. Accurate identification of airway lesions during flexible bronchoscopy plays an important role in the lung cancer diagnosis. The application of artificial intelligence (AI) aims to support physicians in recognizing anatomical landmarks and lung cancer lesions within bronchoscopic imagery. This work described the development of BM-BronchoLC, a rich bronchoscopy dataset encompassing 106 lung cancer and 102 non-lung cancer patients. The dataset incorporates detailed localization and categorical annotations for both anatomical landmarks and lesions, meticulously conducted by senior doctors at Bach Mai Hospital, Vietnam. To assess the dataset's quality, we evaluate two prevalent AI backbone models, namely UNet++ and ESFPNet, on the image segmentation and classification tasks with single-task and multi-task learning paradigms. We present BM-BronchoLC as a reference dataset in developing AI models to assist diagnostic accuracy for anatomical landmarks and lung cancer lesions in bronchoscopy data.

Fully automated landmarking and facial segmentation on 3D photographs.

Three-dimensional facial stereophotogrammetry provides a detailed representation of craniofacial soft tissue without the use of ionizing radiation. While manual annotation of landmarks serves as the current gold standard for cephalometric analysis, it is a time-consuming process and is prone to human error. The aim in this study was to develop and evaluate an automated cephalometric annotation method using a deep learning-based approach. Ten landmarks were manually annotated on 2897 3D facial photographs. The automated landmarking workflow involved two successive DiffusionNet models. The dataset was randomly divided into a training and test dataset. The precision of the workflow was evaluated by calculating the Euclidean distances between the automated and manual landmarks and compared to the intra-observer and inter-observer variability of manual annotation and a semi-automated landmarking method. The workflow was successful in 98.6% of all test cases. The deep learning-based landmarking method achieved precise and consistent landmark annotation. The mean precision of 1.69 ± 1.15 mm was comparable to the inter-observer variability (1.31 ± 0.91 mm) of manual annotation. Automated landmark annotation on 3D photographs was achieved with the DiffusionNet-based approach. The proposed method allows quantitative analysis of large datasets and may be used in diagnosis, follow-up, and virtual surgical planning.

Automated localization of mandibular landmarks in the construction of mandibular median sagittal plane.

OBJECTIVE: To use deep learning to segment the mandible and identify three-dimensional (3D) anatomical landmarks from cone-beam computed tomography (CBCT) images, the planes constructed from the mandibular midline landmarks were compared and analyzed to find the best mandibular midsagittal plane (MMSP). METHODS: A total of 400 participants were randomly divided into a training group (n = 360) and a validation group (n = 40). Normal individuals were used as the test group (n = 50). The PointRend deep learning mechanism segmented the mandible from CBCT images and accurately identified 27 anatomic landmarks via PoseNet. 3D coordinates of 5 central landmarks and 2 pairs of side landmarks were obtained for the test group. Every 35 combinations of 3 midline landmarks were screened using the template mapping technique. The asymmetry index (AI) was calculated for each of the 35 mirror planes. The template mapping technique plane was used as the reference plane; the top four planes with the smallest AIs were compared through distance, volume difference, and similarity index to find the plane with the fewest errors. RESULTS: The mandible was segmented automatically in 10 ± 1.5 s with a 0.98 Dice similarity coefficient. The mean landmark localization error for the 27 landmarks was 1.04 ± 0.28 mm. MMSP should use the plane made by B (supramentale), Gn (gnathion), and F (mandibular foramen). The average AI grade was 1.6 (min-max: 0.59-3.61). There was no significant difference in distance or volume (P > 0.05); however, the similarity index was significantly different (P < 0.01). CONCLUSION: Deep learning can automatically segment the mandible, identify anatomic landmarks, and address medicinal demands in people without mandibular deformities. The most accurate MMSP was the B-Gn-F plane.

Landmark annotation through feature combinations: a comparative study on cephalometric images with in-depth analysis of model's explainability.

OBJECTIVES: The objectives of this study are to explore and evaluate the automation of anatomical landmark localization in cephalometric images using machine learning techniques, with a focus on feature extraction and combinations, contextual analysis, and model interpretability through Shapley Additive exPlanations (SHAP) values. METHODS: We conducted extensive experimentation on a private dataset of 300 lateral cephalograms to thoroughly study the annotation results obtained using pixel feature descriptors including raw pixel, gradient magnitude, gradient direction, and histogram-oriented gradient (HOG) values. The study includes evaluation and comparison of these feature descriptions calculated at different contexts namely local, pyramid, and global. The feature descriptor obtained using individual combinations is used to discern between landmark and nonlandmark pixels using classification method. Additionally, this study addresses the opacity of LGBM ensemble tree models across landmarks, introducing SHAP values to enhance interpretability. RESULTS: The performance of feature combinations was assessed using metrics like mean radial error, standard deviation, success detection rate (SDR) (2 mm), and test time. Remarkably, among all the combinations explored, both the HOG and gradient direction operations demonstrated significant performance across all context combinations. At the contextual level, the global texture outperformed the others, although it came with the trade-off of increased test time. The HOG in the local context emerged as the top performer with an SDR of 75.84% compared to others. CONCLUSIONS: The presented analysis enhances the understanding of the significance of different features and their combinations in the realm of landmark annotation but also paves the way for further exploration of landmark-specific feature combination methods, facilitated by explainability.

The accuracy and reliability of different midsagittal planes in the symmetry assessment using cone-beam computed tomography.

Symmetry is an essential component of esthetic assessment. Accurate assessment of facial symmetry is critical to the treatment plan of orthognathic surgery and orthodontic treatment. However, there is no internationally accepted midsagittal plane (MSP) for orthodontists and orthognathic surgeons. The purpose of this study was to explore a clinically friendly MSP, which is more accurate and reliable than what is commonly used in symmetry assessment. Forty patients with symmetric craniofacial structures were analyzed on cone-beam computed tomography (CBCT) scans. The CBCT data were exported to the Simplant Pro software to build four reference planes that were constructed by nasion (N), basion (Ba), sella (S), odontoid (Dent), or incisive foramen (IF). A total of 31 landmarks were located to determine which reference plane is the most optimal MSP by comparing the asymmetry index (AI). The mean value of AI showed a significant difference (p < 0.05) among four reference planes. Also, the mean value of AI for all landmarks showed that Plane 2 (consisting of N, Ba, and IF) and Plane 4 (consisting of N, IF, and Dent) were more accurate and stable. In conclusion, the MSP consisting of N, Dent, and IF shows more accuracy and reliability than the other planes. Further, it is more clinically friendly because of its significant advantage in landmarking.

Identifying anatomic landmarks and median nerve characteristics for the analysis of persistent carpal tunnel syndrome using magnetic resonance imaging (MRI).

OBJECTIVE: Carpal tunnel syndrome (CTS) is the most common nerve entrapment neuropathy in the USA. In this study, we define anatomical landmarks to assess symptomatic and asymptomatic cohorts with persistent CTS using MRI imaging. MATERIALS AND METHODS: Distal vs proximal incomplete release was determined using the distal most aspect of the hook of hamate and the distal wrist crease. An incomplete release showed the transverse carpal ligament (TCL) intact at either boundary. Twenty-one patients with persistent CTS were analyzed for incomplete release, median nerve enlargement and T2 signal hyperintensity, and flattening ratio using postoperative wrist MRI. These findings were compared to a ten-patient asymptomatic persistent CTS control group. Fisher's exact and a Student's two-tailed t-tests were used to determine statistical significance. RESULTS: In the symptomatic persistent CTS group, 13 (61.9%) incomplete releases were identified, 5 (38.5%) incomplete distally, and 1 (7.7%) incomplete proximally. There was no statistical significance in the rate of incomplete releases when compared to the asymptomatic group (p = 1.00). T2 signal hyperintensity and enlargement at the site of release showed no statistical significance, (p = 0.319 and p = 0.999, respectively). The mean flattening ratio at the site of release in the symptomatic group (2.45 ± 0.7) was statistically significant compared to the asymptomatic group (1.48 ± 0.46), (p = 0.007). CONCLUSION: Utilizing the established landmarks, the full length of the TCL can be assessed via MRI. Additionally, evaluation of the median nerve flattening ratio at the level of the incomplete release may be utilized as an aid to the clinical management of persistent CTS.

Global facial soft tissue thicknesses for craniofacial identification (2023): a review of 140 years of data since Welcker's first study.

This year (2023) marks 140 years since the first publication of a facial soft tissue thickness (FSTT) study. Since 1883, a total of 139 studies have been published, collectively tallying > 220,000 tissue thickness measurements of > 19,500 adults. In just the last 5-years, 33 FSTT studies have been conducted. Herein, we add these data (plus an additional 20 studies) to the 2018 T-Table to provide an update of > 81,000 new datapoints to the global tallied facial soft tissue depths table. In contrast to the original 2008 T-Table, some notable changes are as follows: increased FSTTs by 3 mm at infra second molar (ecm2-iM2'), 2.5 mm at gonion (go-go'), 2 mm at mid-ramus (mr-mr'), and 1.5 mm at zygion (zy-zy'). Rolling grand means indicate that stable values have been attained for all nine median FSTT landmarks, while six out of nine bilateral landmarks continue to show ongoing fluctuations, indicating further data collection at these landmarks holds value. When used as point estimators for individuals with known values across 24 landmarks (i.e., C-Table data), the updated grand means produce slightly less estimation error than the 2018 T-Table means (3.5 mm versus 3.6 mm, respectively). Future efforts to produce less noisy datasets (i.e., reduce measurement and sampling errors as much as possible between studies) would be useful.

The relationship between biological parameters and facial soft tissue thickness measured by ultrasound and its forensic implications.

Facial soft tissue thickness (FSTT) data are currently widely used in forensic and medical science. In the forensic sciences, they form the basis for craniofacial reconstruction and identification methods. Since there are few FSTT data in the Slovak population, this study aims to enrich the data in well-defined age categories, taking into account differences between sexes and body mass index (BMI). The sample consisted of 127 participants aged 17 to 86 years from Slovakia. In addition to biological sex and age information, stature and body weight were recorded to calculate BMI. Subsequently, 17 facial anthropometric landmarks were used to measure FSTT using a noninvasive General Electric LOGIQe R7 ultrasound device. The mean values of FSTT were greater in the mouth region in males and in the zygomatic and eye regions in females. Differences between males and females, regardless of sex and BMI, were significant only at two landmarks. When BMI and age were taken into account, there were differences in 12 of 17 landmarks. Linear regression results showed the strongest correlation of most landmarks with BMI, followed by age and sex. When the FSTT was estimated in association with sex/age/BMI, landmarks in the zygomatic, mandibular, and frontal regions were the best regressors. The results of the present study demonstrate that B-mode ultrasound measurements of FSTT can be used in facial reconstruction as a function of BMI, age, and sex of the subject. Furthermore, the present regression equations can help practitioners in the forensic/medical field to calculate individual tissue thickness.

Positioning errors of anatomical landmarks identified by fixed vertices in homologous meshes.

BACKGROUND: Human movement analysis is usually achieved by tracking markers attached to anatomical landmarks with photogrammetry. Such marker-based systems have disadvantages that have led to the development of markerless procedures, although their accuracy is not usually comparable to that of manual palpation procedures. New motion acquisition systems, such as 3D temporal scanners, provide homologous meshes that can be exploited for this purpose. RESEARCH QUESTION: Can fixed vertices of a homologous mesh be used to identify anatomical landmarks with an accuracy equivalent to that of manual palpation? METHODS: We used 3165 human shape scans from the CAESAR dataset, with labelled locations of anatomical landmarks. First, we fitted a template mesh to the scans, and assigned a vertex of that mesh to 53 anatomical landmarks in all subjects. Then we defined a nominal vertex for each landmark, as the more centred vertex out of the set assigned for that landmark. We calculated the errors of the template-fitting and the nominal vertex determination procedures, and analysed their relationship to subject's sex, height and body mass index, as well as their size compared to manual palpation errors. RESULTS: The template-fitting errors were below 5 mm, and the nominal vertex determination errors reached maximum values of 24 mm. Except for the trochanter, those errors were the same order of magnitude or smaller than inter-examiner errors of lower limb landmarks. Errors increased with height and body mass index, and were smaller for men than for women of the same height and body mass index. SIGNIFICANCE: We defined a set of vertices for 53 anatomical landmarks in a homologous mesh, which yields location errors comparable to those obtained by manual palpation for the majority of landmarks. We also quantified how the subject's sex and anthropometric features can affect the size of those errors.

Angle Evaluation of Possible Routes that Can Be Used to Reach the Foramen Ovale in the Anterior Approach / Evaluación Angular de Posibles Rutas que se Pueden Utilizar para Alcanzar el Foramen Oval en el Abordaje Anterior

SUMMARY: For the treatment of trigeminal neuralgia, the foramen ovale is reached by entering the cheek with a needle. Thermocoagulation is performed with balloon compression, administration of alcohol or radiofrequency. Apart from the classical method, it is theoretically possible to reach the foramen ovale through the mouth with the anterior approach. In our study, it was aimed to examine horizontally and vertically the angular values that must be given to the needle to reach the foramen ovale in the anterior approach. Three landmark points were determined on both right and left sides of 25 dry skulls. A rod was inserted starting from these landmark points and passing through the center of the foramen ovale. The vertical and horizontal angular values of this bar were measured. For each foramen ovale, 3 vertical angles, 3 horizontal angles and 4 distance measurements were made. There was a significant difference between the right and left sides in terms of horizontal angular values. Average values of horizontal angles (in degrees); on the right, 7.29 for H1, 12.15 for H2, 32.29 for H3; 1.26 for H1, 9.46 for H2, and 30.56 for H3 on the left side (p<0.005). The angle value was measured as 0 or negative value in 5 (20 %) of the H1 angle measurements made on the right side and 14 (56 %) on the left side. The H2 angle value was found to be smaller than the H1 angle in the skull 2 (8 %) on the right and 3 (12 %) on the left. There was no difference between the right and left sides in terms of vertical angular values. A significant difference was found between the right and left sides in the D1, D2, D4 distances (p<0.005). Six important anatomical features affecting angular values were encountered.

Para el tratamiento de la neuralgia del trigémino, se alcanza el foramen oval introduciendo una aguja en la mejilla. La termocoagulación se realiza con compresión con balón, administración de alcohol o radiofrecuencia. Aparte del método clásico, en teoría es posible alcanzar el foramen oval a través de la cavidad oral mediante el abordaje anterior. En nuestro estudio se tuvo como objetivo examinar horizontal y verticalmente los valores angulares que se deben dar a la aguja para alcanzar el foramen oval en el abordaje anterior. Se determinaron tres puntos de referencia en los lados derecho e izquierdo de 25 cráneos secos. Se insertó una varilla comenzando desde estos puntos de referencia y pasando por el centro del foramen oval. Se midieron los valores angulares verticales y horizontales de esta barra. Para cada foramen oval se realizaron mediciones de 3 ángulos verticales, 3 ángulos horizontales y 4 distancias. Hubo una diferencia significativa entre los lados derecho e izquierdo en términos de valores angulares horizontales. Valores medios de ángulos horizontales (en grados); a la derecha, 7,29 para H1, 12,15 para H2, 32,29 para H3; 1,26 para H1, 9,46 para H2 y 30,56 para H3 en el lado izquierdo (p<0,005). El valor del ángulo se midió como 0 o valor negativo en 5 (20 %) de las mediciones del ángulo H1 realizadas en el lado derecho y 14 (56 %) en el lado izquierdo. Se encontró que el valor del ángulo H2 era menor que el ángulo H1 en el cráneo 2 (8 %) a la derecha y 3 (12 %) a la izquierda. No hubo diferencia entre los lados derecho e izquierdo en términos de valores angulares verticales. Se encontró diferencia significativa entre el lado derecho e izquierdo en las distancias D1, D2, D4 (p<0,005). Se encontraron seis características anatómicas importantes que afectan los valores angulares.

Analysis of the Asterion Morphology in Relation to Its Clinical Significance / Análisis de la Morfología del Asterion en Relación con su Importancia Clínica

SUMMARY: The asterion presents a significant anthropological marking and meeting point between three sutures. It is a surface landmark for the transverse-sigmoid venous sinus complex and is also a surgical landmark for access to the posterior cranial fossa, giving it clinical importance. The aim of this research was to analyze the shape of the asterion and to set the measurement methods that will determine distance between the asterion and surrounding features. The study sample, as a part of the Osteological collection of the Department of Anatomy, Faculty of Medicine Novi Sad, consisted of 43 skulls. Morphometric analysis was related to the measurement of the defined parameters and descriptive analysis presented the classification of asterion in relation to the presence of sutural bones, as well as the determination of the position of the asterion according to the transverse-sigmoid venous complex. There was a statistically significant difference between male and female skulls for all the measured parameters. The results show that 34.88 % were type 1 (one or more sutural bones are present) and 65.12 % were type 2 asteria (no sutural bones are present). More frequent occurrence of asteria type 2 was seen on both, male and female skulls. The most frequent position of the asteria on both sides of the skull was in the transverse- sigmoid venous complex (76.92 % on the right side vs. 72.22 % on the left cranial side). Clinical significance of knowing the area of asterion is reflected in order to make the surgical, as well as diagnostic procedures, as successful as possible.

El asterion presenta una importante marca antropológica y punto de encuentro entre tres suturas. Es un punto de referencia de superficie para el complejo del seno venoso sigmoideo transverso y también es un punto de referencia quirúrgico para el acceso a la fosa craneal posterior, lo que le confiere importancia clínica. El objetivo de esta investigación fue analizar la forma del asterión y establecer los métodos de medición que determinarán la distancia entre el asterión y las características circundantes. La muestra del estudio, que forma parte de la colección osteológica del Departamento de Anatomía de la Facultad de Medicina de Novi Sad, estuvo compuesta por 43 cráneos. El análisis morfométrico se relacionó con la medición de los parámetros definidos y el análisis descriptivo presentó la clasificación del asterion en relación a la presencia de huesos suturales, así como la determinación de la posición del asterion según el complejo venoso transverso-sigmoideo. Hubo una diferencia estadísticamente significativa entre los cráneos masculinos y femeninos para todos los parámetros medidos. Los resultados muestran que el 34,88 % eran tipo 1 (hay uno o más huesos suturales presentes) y el 65,12 % eran asteria tipo 2 (no hay huesos suturales presentes). Se observó una aparición más frecuente de asteria tipo 2 en cráneos tanto masculinos como femeninos. La posición más frecuente de la asteria en ambos lados del cráneo fue en el complejo venoso sigmoideo transverso (76,92 % en el lado derecho vs. 72,22 % en el lado craneal izquierdo). La importancia clínica de conocer el área de asterion se refleja en que los procedimientos quirúrgicos y de diagnóstico tengan el mejor resultado posible.

Ceph-Net: automatic detection of cephalometric landmarks on scanned lateral cephalograms from children and adolescents using an attention-based stacked regression network.

BACKGROUND: The success of cephalometric analysis depends on the accurate detection of cephalometric landmarks on scanned lateral cephalograms. However, manual cephalometric analysis is time-consuming and can cause inter- and intra-observer variability. The purpose of this study was to automatically detect cephalometric landmarks on scanned lateral cephalograms with low contrast and resolution using an attention-based stacked regression network (Ceph-Net). METHODS: The main body of Ceph-Net compromised stacked fully convolutional networks (FCN) which progressively refined the detection of cephalometric landmarks on each FCN. By embedding dual attention and multi-path convolution modules in Ceph-Net, the network learned local and global context and semantic relationships between cephalometric landmarks. Additionally, the intermediate deep supervision in each FCN further boosted the training stability and the detection performance of cephalometric landmarks. RESULTS: Ceph-Net showed a superior detection performance in mean radial error and successful detection rate, including accuracy improvements in cephalometric landmark detection located in low-contrast soft tissues compared with other detection networks. Moreover, Ceph-Net presented superior detection performance on the test dataset split by age from 8 to 16 years old. CONCLUSIONS: Ceph-Net demonstrated an automatic and superior detection of cephalometric landmarks by successfully learning local and global context and semantic relationships between cephalometric landmarks in scanned lateral cephalograms with low contrast and resolutions.

An artificial intelligence study: automatic description of anatomic landmarks on panoramic radiographs in the pediatric population.

BACKGROUND: Panoramic radiographs, in which anatomic landmarks can be observed, are used to detect cases closely related to pediatric dentistry. The purpose of the study is to investigate the success and reliability of the detection of maxillary and mandibular anatomic structures observed on panoramic radiographs in children using artificial intelligence. METHODS: A total of 981 mixed images of pediatric patients for 9 different pediatric anatomic landmarks including maxillary sinus, orbita, mandibular canal, mental foramen, foramen mandible, incisura mandible, articular eminence, condylar and coronoid processes were labelled, the training was carried out using 2D convolutional neural networks (CNN) architectures, by giving 500 training epochs and Pytorch-implemented YOLO-v5 models were produced. The success rate of the AI model prediction was tested on a 10% test data set. RESULTS: A total of 14,804 labels including maxillary sinus (1922), orbita (1944), mandibular canal (1879), mental foramen (884), foramen mandible (1885), incisura mandible (1922), articular eminence (1645), condylar (1733) and coronoid (990) processes were made. The most successful F1 Scores were obtained from orbita (1), incisura mandible (0.99), maxillary sinus (0.98), and mandibular canal (0.97). The best sensitivity values were obtained from orbita, maxillary sinus, mandibular canal, incisura mandible, and condylar process. The worst sensitivity values were obtained from mental foramen (0.92) and articular eminence (0.92). CONCLUSIONS: The regular and standardized labelling, the relatively larger areas, and the success of the YOLO-v5 algorithm contributed to obtaining these successful results. Automatic segmentation of these structures will save time for physicians in clinical diagnosis and will increase the visibility of pathologies related to structures and the awareness of physicians.

Personalization of thoracoabdominal CT examinations using scanner integrated clinical decision support systems - Impact on the acquisition technique, scan range, and reconstruction type.

OBJECTIVES: This study evaluates the impact of a scanner-integrated, customized clinical decision support system (CDSS) on the acquisition technique, scan range, and reconstruction in thoracoabdominal CT. MATERIALS AND METHODS: We applied CDSS in contrast-enhanced examinations of the trunk with various clinical indications on a recent scanner with the capability of dual-energy CT (DECT), anatomic landmark detection (ALD), and iterative metal-artifact reduction (MAR). Simple and comprehensive questions about the patient's breath hold capability, the anatomical region of interest, and metal implants can be answered after the localizer. The acquisition technique (single energy, SECT, or dual energy), scan range (chest-abdomen-pelvis or chest-abdomen), and reconstruction technique (with or without MAR) were then automatically adapted in the examination protocols in coherence with these selections. Retrospectively, we compared the usage rates for these techniques in 624 examinations on the study scanner with 740 examinations on a comparable scanner without CDSS. Subgroup analysis of effective dose (ED), scan duration, and image quality (IQ) was performed in the study group. RESULTS: CDSS leads to an increased usage rate of DECT (64.4% vs. 2.8%) and MAR (75.4% vs. 44.0%). All scan range adaptations by ALD were successful. The resulting subjective IQ between single energy and DECT acquisitions was comparable (all p > 0.05). Scan duration was significantly longer in DECT than in SECT (16.9 s vs. 6.5 s; p < 0.001). However, the objective IQ was significantly higher in DECT (CNRD 2.1 vs. 1.8; p < 0.01), and the ED significantly lower (6.7 mSv vs. 7.6 mSv; p = 0.004). CONCLUSION: CDSS for thoracoabdominal CT leads to a substantially increased usage rate of innovative techniques during acquisition and reconstruction. Patients with adapted protocols benefit from improved image quality and increased post-processing options at lower radiation doses.

Body landmarks and genetic algorithm-based approach for non-contact detection of head forward posture among Chinese adolescents: revitalizing machine learning in medicine.

Addressing the current complexities, costs, and adherence issues in the detection of forward head posture (FHP), our study conducted an exhaustive epidemiologic investigation, incorporating a comprehensive posture screening process for each participant in China. This research introduces an avant-garde, machine learning-based non-contact method for the accurate discernment of FHP. Our approach elevates detection accuracy by leveraging body landmarks identified from human images, followed by the application of a genetic algorithm for precise feature identification and posture estimation. Observational data corroborates the superior efficacy of the Extra Tree Classifier technique in FHP detection, attaining an accuracy of 82.4%, a specificity of 85.5%, and a positive predictive value of 90.2%. Our model affords a rapid, effective solution for FHP identification, spotlighting the transformative potential of the convergence of feature point recognition and genetic algorithms in non-contact posture detection. The expansive potential and paramount importance of these applications in this niche field are therefore underscored.

[Effect of alar base cinch suture based on anatomic landmarks on the morphology of nasolabial region in patients after orthognathic surgery].

OBJECTIVE: To study the effect of a modified alar base cinch suture (ABCS) based on nasal musculature anatomy on the three-dimensional morphology of nasolabial region in patients after Le Fort Ⅰ osteotomy. METHODS: In the study, 30 patients[11 males and 19 females, with an average age of (23.23±2.98) years]with skeletal Class Ⅲ malocclusion underwent orthognathic surgery between August, 2019 and January, 2020 to have the maxilla advanced no more than 4 mm in the Department of Oral and Maxillofacial Surgery, Peking University School and Hospital of Stomatology were involved and were divided into the test and control groups based on the random number table.In the test group, the nasal musculature was identified and labeled before dissection and the ABCS was according to the label, while in the control group, the nasal musculature was directly sutured and knotted in the midline of nose without prepend labeling.All the patients underwent three-dimensional facial photos preoperatively and 6 months postoperatively by using 3dMD face system.On the three dimensional image, soft tissue landmarks of nasolabial region was identified by the same examiner.Fourteen measurements including straight distance, curve distance, angle and ratio were measured.Statistical analysis was done by using SPSS 22.0. RESULTS: There were significant differences between the two groups in cutaneous height of upper lip (P=0.023) and in nasal tip protrusion-alar width (P=0.012).The increase rate of cutaneous height of upper lip and the decrease rate of nasal tip protrusion-alar width in the control group were significantly higher than that in the test group.The alar width and alar base width of the both groups were significantly increased compared with the preoperative level (P < 0.05).The nasolabial angle in the control group was significantly higher compared with the normal value, while there was no significant difference between the test group and the normal value. CONCLUSION: Compared with the conventional suture method, this modified alar base cinch suture is more favorable for the postoperative nasal coordination and nasolabial morphology in patients who need mild to moderate maxillary advancement, and it has certain advantages in operability and objective accuracy.So it could become a modified and accurate method of alar base cinch suture and be widely applied in clinical practice.

Systematic review on forensic craniofacial reconstruction. I. facial soft-tissue thickness.

Forensic anthropologists are traditionally interested in facial approximations and reconstruction of physiognomies of individuals from past populations and creation of lifelike features onto unknown skulls retrieved from forensic or bioarchaeological contexts. Present review article examines the significance of facial soft-tissue thickness (FSTT) in craniofacial reconstruction by revisiting the studies published in the recent past decade (2010-21). The searches for published articles mentioning the FSTT and related topics over these years were performed using the following search engines: PubMed, ScienceDirect, Web of Science, and Scopus. A total of 325 research articles were identified using different keywords, out of which 84 studies were found relevant for systematic review presented in this article. The selected studies were further analyzed based on the adopted study design, radiographic modality used for estimating FSTT, and generated databases and their advantages and limitations. Out of 84 relevant articles, 30 articles presented databases for sex, age, and ethnicity-dependent variations in soft tissue thickness measurements. Finally, 17 studies reporting sexual dimorphic variations in FSTT values estimated in supine or upright postured individuals (aged 18-90 years and above) were considered for meta-analysis. This article gives a decisive outlook on research trends in FSTT estimations, its contributions in refining craniofacial reconstruction technology, and identifying where we lack and where we can improve.

Using a New Deep Learning Method for 3D Cephalometry in Patients With Hemifacial Microsomia.

ABSTRACT: Deep learning algorithms based on automatic 3D cephalometric marking points about people without craniomaxillofacial deformities have achieved good results. However, there has been no previous report about hemifacial microsomia (HFM). The purpose of this study is to apply a new deep learning method based on a 3D point cloud graph convolutional neural network to predict and locate landmarks in patients with HFM based on the relationships between points. The authors used a PointNet++ model to investigate the automatic 3D cephalometry. And the mean distance error (MDE) of the center coordinate position and the success detection rate (SDR) were used to evaluate the accuracy of systematic labeling. A total of 135 patients were enrolled. The MDE for all 32 landmarks was 1.46 ± 1.308 mm, and 10 landmarks showed SDRs at 2 mm over 90%, and only 4 landmarks showed SDRs at 2 mm under 60%. Compared with the manual reproducibility, the standard distance deviation and coefficient of variation values for the MDE of the artificial intelligence system was 0.67 and 0.43, respectively. In summary, our training sets were derived from HFM computed tomography to achieve accurate results. The 3D cephalometry system based on the graph convolutional network algorithm may be suitable for the 3D cephalometry system in HFM cases. More accurate results may be obtained if the HFM training set is expanded in the future.

Automated detection of cephalometric landmarks using deep neural patchworks.

OBJECTIVES: This study evaluated the accuracy of deep neural patchworks (DNPs), a deep learning-based segmentation framework, for automated identification of 60 cephalometric landmarks (bone-, soft tissue- and tooth-landmarks) on CT scans. The aim was to determine whether DNP could be used for routine three-dimensional cephalometric analysis in diagnostics and treatment planning in orthognathic surgery and orthodontics. METHODS: Full skull CT scans of 30 adult patients (18 female, 12 male, mean age 35.6 years) were randomly divided into a training and test data set (each n = 15). Clinician A annotated 60 landmarks in all 30 CT scans. Clinician B annotated 60 landmarks in the test data set only. The DNP was trained using spherical segmentations of the adjacent tissue for each landmark. Automated landmark predictions in the separate test data set were created by calculating the center of mass of the predictions. The accuracy of the method was evaluated by comparing these annotations to the manual annotations. RESULTS: The DNP was successfully trained to identify all 60 landmarks. The mean error of our method was 1.94 mm (SD 1.45 mm) compared to a mean error of 1.32 mm (SD 1.08 mm) for manual annotations. The minimum error was found for landmarks ANS 1.11 mm, SN 1.2 mm, and CP_R 1.25 mm. CONCLUSION: The DNP-algorithm was able to accurately identify cephalometric landmarks with mean errors <2 mm. This method could improve the workflow of cephalometric analysis in orthodontics and orthognathic surgery. Low training requirements while still accomplishing high precision make this method particularly promising for clinical use.

[Study on the method of automatically determining maxillary complex landmarks based on non-rigid registration algorithms].

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.