3D morphometric quantification of maxillae and defects for patients with unilateral cleft palate via deep learning-based CBCT image auto-segmentation

Artificial Intelligence in Rhinology

Rhinology, allergy, and skull base surgery are fields primed for the integration and implementation of artificial intelligence (AI). The heterogeneity of the disease processes within these fields highlights the opportunity for AI to augment clinical care and promote personalized medicine. Numerous research studies have been published demonstrating the development and clinical potential of AI models within the field. Most describe in silico evaluation models without direct clinical implementation. The major themes of existing studies include diagnostic or clinical decisions support, clustering patients into specific phenotypes or endotypes, predicting post-treatment outcomes, and surgical planning.

Harnessing the Power of Artificial Intelligence in Cleft Lip and Palate: An In-Depth Analysis from Diagnosis to Treatment, a Comprehensive Review

Cleft lip and palate (CLP) is the most common craniofacial malformation, with a range of physical, psychological, and aesthetic consequences. In this comprehensive review, our main objective is to thoroughly examine the relationship between CLP anomalies and the use of artificial intelligence (AI) in children. Additionally, we aim to explore how the integration of AI technology can bring about significant advancements in the fields of diagnosis, treatment methods, and predictive outcomes. By analyzing the existing evidence, we will highlight state-of-the-art algorithms and predictive AI models that play a crucial role in achieving precise diagnosis, susceptibility assessment, and treatment planning for children with CLP anomalies. Our focus will specifically be on the efficacy of alveolar bone graft and orthodontic interventions. The findings of this review showed that deep learning (DL) models revolutionize the diagnostic process, predict susceptibility to CLP, and enhance alveolar bone grafts and orthodontic treatment. DL models surpass human capabilities in terms of precision, and AI algorithms applied to large datasets can uncover the intricate genetic and environmental factors contributing to CLP. Additionally, Machine learning aids in preoperative planning for alveolar bone grafts and provides personalized treatment plans in orthodontic treatment. In conclusion, these advancements inspire optimism for a future where AI seamlessly integrates with CLP management, augmenting its analytical capabilities.

Interpretable artificial intelligence for classification of alveolar bone defect in patients with cleft lip and palate

Cleft lip and/or palate (CLP) is the most common congenital craniofacial anomaly and requires bone grafting of the alveolar cleft. This study aimed to develop a novel classification algorithm to assess the severity of alveolar bone defects in patients with CLP using three-dimensional (3D) surface models and to demonstrate through an interpretable artificial intelligence (AI)-based algorithm the decisions provided by the classifier. Cone-beam computed tomography scans of 194 patients with CLP were used to train and test the performance of an automatic classification of the severity of alveolar bone defect. The shape, height, and width of the alveolar bone defect were assessed in automatically segmented maxillary 3D surface models to determine the ground truth classification index of its severity. The novel classifier algorithm renders the 3D surface models from different viewpoints and captures 2D image snapshots fed into a 2D Convolutional Neural Network. An interpretable AI algorithm was developed that uses features from each view and aggregated via Attention Layers to explain the classification. The precision, recall and F-1 score were 0.823, 0.816, and 0.817, respectively, with agreement ranging from 97.4 to 100% on the severity index within 1 group difference. The new classifier and interpretable AI algorithm presented satisfactory accuracy to classify the severity of alveolar bone defect morphology using 3D surface models of patients with CLP and graphically displaying the features that were considered during the deep learning model's classification decision.

Deep Learning in Diagnosis of Dental Anomalies and Diseases: A Systematic Review

Deep learning and diagnostic applications in oral and dental health have received significant attention recently. In this review, studies applying deep learning to diagnose anomalies and diseases in dental image material were systematically compiled, and their datasets, methodologies, test processes, explainable artificial intelligence methods, and findings were analyzed. Tests and results in studies involving human-artificial intelligence comparisons are discussed in detail to draw attention to the clinical importance of deep learning. In addition, the review critically evaluates the literature to guide and further develop future studies in this field. An extensive literature search was conducted for the 2019-May 2023 range using the Medline (PubMed) and Google Scholar databases to identify eligible articles, and 101 studies were shortlisted, including applications for diagnosing dental anomalies (n = 22) and diseases (n = 79) using deep learning for classification, object detection, and segmentation tasks. According to the results, the most commonly used task type was classification (n = 51), the most commonly used dental image material was panoramic radiographs (n = 55), and the most frequently used performance metric was sensitivity/recall/true positive rate (n = 87) and accuracy (n = 69). Dataset sizes ranged from 60 to 12,179 images. Although deep learning algorithms are used as individual or at least individualized architectures, standardized architectures such as pre-trained CNNs, Faster R-CNN, YOLO, and U-Net have been used in most studies. Few studies have used the explainable AI method (n = 22) and applied tests comparing human and artificial intelligence (n = 21). Deep learning is promising for better diagnosis and treatment planning in dentistry based on the high-performance results reported by the studies. For all that, their safety should be demonstrated using a more reproducible and comparable methodology, including tests with information about their clinical applicability, by defining a standard set of tests and performance metrics.

Unilateral Cleft Lip and Palate Has Asymmetry of Bony Orbits: A Retrospective Study

Facial asymmetry is common in unilateral clefts. Since virtual surgical planning (VSP) is becoming more common and automated segmentation is utilized more often, the position and asymmetry of the orbits can affect the design outcome. The aim of this study is to evaluate whether non-syndromic unilateral cleft lip and palate (UCLP) patients requiring orthognathic surgery have asymmetry of the bony orbits. Retrospectively, we analyzed the preoperative cone-beam computed tomography (CBCT) or computed tomography (CT) data of UCLP (n = 15) patients scheduled for a Le Fort 1 (n = 10) or bimaxillary osteotomy (n = 5) with VSP at the Cleft Palate and Craniofacial Center, Helsinki University Hospital. The width, height, and depth of the bony orbit and the distance between the sella turcica and infraorbital canal were measured. A volumetric analysis of the orbits was also performed. The measurements were tested for distribution, and the cleft side and the contralateral side were compared statistically with a two-sided paired t-test. To assess asymmetry in the non-cleft population, we performed the same measurements of skeletal class III patients undergoing orthognathic surgery at Päijät-Häme Central Hospital (n = 16). The volume of bony orbit was statistically significantly smaller (p = 0.014), the distance from the infraorbital canal to sella turcica was shorter (p = 0.019), and the anatomical location of the orbit was more medio-posterior on the cleft side than on the contralateral side. The non-cleft group showed no statistically significant asymmetry in any measurements. According to these preliminary results, UCLP patients undergoing orthognathic surgery show asymmetry of the bony orbit not seen in skeletal class III patients without a cleft. This should be considered in VSP for the correction of maxillary hypoplasia and facial asymmetry in patients with UCLP.

A deep learning-based automatic segmentation of zygomatic bones from cone-beam computed tomography images: A proof of concept

OBJECTIVES

To investigate the efficiency and accuracy of a deep learning-based automatic segmentation method for zygomatic bones from cone-beam computed tomography (CBCT) images.

METHODS

One hundred thirty CBCT scans were included and randomly divided into three subsets (training, validation, and test) in a 6:2:2 ratio. A deep learning-based model was developed, and it included a classification network and a segmentation network, where an edge supervision module was added to increase the attention of the edges of zygomatic bones. Attention maps were generated by the Grad-CAM and Guided Grad-CAM algorithms to improve the interpretability of the model. The performance of the model was then compared with that of four dentists on 10 CBCT scans from the test dataset. A p value <.05 was considered statistically significant.

RESULTS

The accuracy of the classification network was 99.64%. The Dice coefficient (Dice) of the deep learning-based model for the test dataset was 92.34 ± 2.04%, the average surface distance (ASD) was 0.1 ± 0.15 mm, and the 95% Hausdorff distance (HD) was 0.98 ± 0.42 mm. The model required 17.03 seconds on average to segment zygomatic bones, whereas this task took 49.3 minutes for dentists to complete. The Dice score of the model for the 10 CBCT scans was 93.2 ± 1.3%, while that of the dentists was 90.37 ± 3.32%.

CONCLUSIONS

The proposed deep learning-based model could segment zygomatic bones with high accuracy and efficiency compared with those of dentists.

CLINICAL SIGNIFICANCE

The proposed automatic segmentation model for zygomatic bone could generate an accurate 3D model for the preoperative digital planning of zygoma reconstruction, orbital surgery, zygomatic implant surgery, and orthodontics.

Deep Learning-Based Medical Images Segmentation of Musculoskeletal Anatomical Structures: A Survey of Bottlenecks and Strategies

By leveraging the recent development of artificial intelligence algorithms, several medical sectors have benefited from using automatic segmentation tools from bioimaging to segment anatomical structures. Segmentation of the musculoskeletal system is key for studying alterations in anatomical tissue and supporting medical interventions. The clinical use of such tools requires an understanding of the proper method for interpreting data and evaluating their performance. The current systematic review aims to present the common bottlenecks for musculoskeletal structures analysis (e.g., small sample size, data inhomogeneity) and the related strategies utilized by different authors. A search was performed using the PUBMED database with the following keywords: deep learning, musculoskeletal system, segmentation. A total of 140 articles published up until February 2022 were obtained and analyzed according to the PRISMA framework in terms of anatomical structures, bioimaging techniques, pre/post-processing operations, training/validation/testing subset creation, network architecture, loss functions, performance indicators and so on. Several common trends emerged from this survey; however, the different methods need to be compared and discussed based on each specific case study (anatomical region, medical imaging acquisition setting, study population, etc.). These findings can be used to guide clinicians (as end users) to better understand the potential benefits and limitations of these tools.

Machine learning in 3D auto-filling alveolar cleft of CT images to assess the influence of alveolar bone grafting on the development of maxilla

BACKGROUND

Machine learning based auto-segmentation of 3D images has been developed rapidly in recent years. However, the application of this new method in the research of patients with unilateral cleft lip and palate (UCLP) is very limited. In this study, a machine learning algorithm utilizing 3D U-net was used to automatically segment the maxilla, fill the cleft and evaluate the alveolar bone graft in UCLP patients. Cleft related factors and the surgery impact on the development of maxilla were analyzed.

METHODS

Preoperative and postoperative computed tomography images of 32 patients (64 images) were obtained. The deep-learning-based protocol was used to segment the maxilla and defect, followed by manual refinement. Paired t-tests and Mann-Whitney tests were performed to reveal the changes of the maxilla after surgery. Two-factor, two-level analysis for repeated measurement was used to examine the different trends of growth on the cleft and non-cleft sides of the maxilla. Pearson and Spearman correlations were used to explore the relationship between the defect and the changes of the maxillary cleft side.

RESULTS

One-year after the alveolar bone grafting surgery, different growth amount was found on the cleft and non-cleft sides of maxilla. The maxillary length (from 34.64 ± 2.48 to 35.67 ± 2.45 mm) and the alveolar length (from 36.58 ± 3.21 to 37.63 ± 2.94 mm) increased significantly only on the cleft side while the maxillary anterior width (from 11.61 ± 1.61 to 12.01 ± 1.41 mm) and posterior width (from 29.63 ± 2.25 to 30.74 ± 2.63 mm) increased significantly only on the non-cleft side after surgery. Morphology of the cleft was found to be related to the pre-surgical maxillary dimension on the cleft side, while its correlation with the change of the maxilla after surgery was low or not statistically significant.

CONCLUSION

The auto-segmentation of the maxilla and the cleft could be performed very efficiently and accurately with the machine learning method. Asymmetric growth was found on the cleft and non-cleft sides of the maxilla after alveolar bone graft in UCLP patients. The morphology of the cleft mainly contributed to the pre-operation variance of the maxilla but had little impact on the maxilla growth after surgery.