Deep learning in the diagnosis of maxillary sinus diseases: A systematic review.

OBJECTIVES: To assess the performance of deep learning (DL) in the detection, classification, and segmentation of maxillary sinus diseases. MATERIALS AND METHODS: An electronic search was conducted by two reviewers on databases including PubMed, Scopus, Cochrane, and IEEE. All English papers published no later than February 7, 2024, were evaluated. Studies related to DL for diagnosing maxillary sinus diseases were also searched in journals manually. RESULTS: 14 of 1167 studies were eligible according to the inclusion criteria. All studies trained DL models based on radiographic images. Six studies applied to detection tasks, one focused on classification, two segmented lesions, and five studies made a combination of 2 types of DL models. The accuracy of the DL algorithms ranged from 75.7% to 99.7%, and the area under curves (AUC) varied between 0.7 and 0.997. CONCLUSION: DL can accurately deal with the tasks of diagnosing maxillary sinus diseases. Students, residents, and dentists could be assisted by DL algorithms to diagnose and make rational decisions on implant treatment related to maxillary sinuses.

A hybrid robotic system for zygomatic implant placement based on mixed reality navigation.

BACKGROUNDS: Zygomatic implant (ZI) placement surgery is a viable surgical option for patients with severe maxillary atrophy and insufficient residual maxillary bone. Still, it is difficult and risky due to the long path of ZI placement and the narrow field of vision. Dynamic navigation is a superior solution, but it presents challenges such as requiring operators to have advanced skills and experience. Moreover, the precision and stability of manual implantation remain inadequate. These issues are anticipated to be addressed by implementing robot-assisted surgery and achieved by introducing a mixed reality (MR) navigation-guided hybrid robotic system for ZI placement surgery. METHODS: This study utilized a hybrid robotic system to perform the ZI placement surgery. Our first step was to reconstruct a virtual 3D model from preoperative cone-beam CT (CBCT) images. We proposed a series of algorithms based on coordinate transformation, which includes image-phantom registration, HoloLens-tracker registration, drill-phantom calibration, and robot-implant calibration, to unify all objects within the same coordinate system. These algorithms enable real-time tracking of the surgical drill's position and orientation relative to the patient phantom. Subsequently, the surgical drill is directed to the entry position, and the planned implantation paths are superimposed on the patient phantom using HoloLens 2 for visualization. Finally, the hybrid robot system performs the processed of drilling, expansion, and placement of ZIs under the guidance of the MR navigation system. RESULTS: Phantom experiments of ZI placement were conducted using 10 patient phantoms, with a total of 40 ZIs inserted. Out of these, 20 were manually implanted, and the remaining 20 were robotically implanted. Comparisons between the actual implanted ZI paths and the preoperatively planned ZI paths showed that our MR navigation-guided hybrid robotic system achieved a coronal deviation of 0.887 ± 0.213 mm, an apical deviation of 1.201 ± 0.318 mm, and an angular deviation of 3.468 ± 0.339° This demonstrates significantly better accuracy and stability than manual implantation. CONCLUSION: Our proposed hybrid robotic system enables automated ZI placement surgery guided by MR navigation, achieving greater accuracy and stability compared to manual operations in phantom experiments. Furthermore, this system is expected to apply to animal and cadaveric experiments, to get a good ready for clinical studies.

Comparison of the accuracy of dental implant placement using dynamic and augmented reality-based dynamic navigation: An in vitro study.

Background/purpose: Augmented reality has been gradually applied in dental implant surgery. However, whether the dynamic navigation system integrated with augmented reality technology will further improve the accuracy is still unknown. The purpose of this study is to investigate the accuracy of dental implant placement using dynamic navigation and augmented reality-based dynamic navigation systems. Materials and methods: Thirty-two cone-beam CT (CBCT) scans from clinical patients were collected and used to generate 64 phantoms that were allocated to the augmented reality-based dynamic navigation (ARDN) group or the conventional dynamic navigation (DN) group. The primary outcomes were global coronal, apical and angular deviations, and they were measured after image fusion. A linear mixed model with a random intercept was used. A P value < 0.05 was considered to indicate statistical significance. Results: A total of 242 dental implants were placed in two groups. The global coronal, apical and angular deviations of the ARDN and DN groups were 1.31 ± 0.67 mm vs. 1.18 ± 0.59 mm, 1.36 ± 0.67 mm vs. 1.39 ± 0.55 mm, and 3.72 ± 2.13° vs. 3.1 ± 1.56°, respectively. No significant differences were found with regard to coronal and apical deviations (P = 0.16 and 0.6, respectively), but the DN group had a significantly lower angular deviation than the ARDN group (P = 0.02). Conclusion: The augmented reality-based dynamic navigation system yielded a similar accuracy to the conventional dynamic navigation system for dental implant placement in coronal and apical points, but the augmented reality-based dynamic navigation system yielded a higher angular deviation.

The combined effects of azoxystrobin and different aged polyethylene microplastics on earthworms (Eisenia fetida): A systematic evaluation based on oxidative damage and intestinal function.

Pesticides and microplastics are common pollutants in soil environments, adversely affecting soil organisms. However, the combined toxicological effects of aged microplastics and pesticides on soil organisms are still unclear. In this study, we systematically studied the toxicological effects of azoxystrobin and four different aged polyethylene (PE) microplastics on earthworms (Eisenia fetida). The purpose was to evaluate the effects of aging microplastics on the toxicity of microplastics-pesticides combinations on earthworms. The results showed that different-aged PE microplastics promoted azoxystrobin accumulation in earthworms. Meanwhile, combined exposure to azoxystrobin and aged PE microplastics decreased the body weight of earthworms. Besides, both single and combined exposure to azoxystrobin and aged PE microplastics could lead to oxidative damage in earthworms. Further studies revealed that azoxystrobin and aged PE microplastics damage the intestinal structure and function of earthworms. Additionally, the combination of different aged PE microplastics and azoxystrobin was more toxic on earthworms than single exposures. The PE microplastics subjected to mechanical wear, ultraviolet radiation, and acid aging exhibited the strongest toxicity enhancement effects on earthworms. This high toxicity may be related to the modification of PE microplastics caused by aging. In summary, these results demonstrated the enhancing effects of aged PE microplastics on the toxicity of pesticides to earthworms. More importantly, aged PE microplastics exhibited stronger toxicity-enhancing effects in the early exposure stages. This study provides important data supporting the impact of different aged PE microplastics on the environmental risks of pesticides.

Microplastics derived from plastic mulch films and their carrier function effect on the environmental risk of pesticides.

Plastic film mulching can maintain soil water and heat conditions, promote plant growth and thus generate considerable economic benefits in agriculture. However, as they age, these plastics degrade and form microplastics (MPs). Additionally, pesticides are widely utilized to control organisms that harm plants, and they can ultimately enter and remain in the environment after use. Pesticides can also be sorbed by MPs, and the sorption kinetics and isotherms explain the three stages of pesticide sorption: rapid sorption, slow sorption and sorption equilibrium. In this process, hydrophobic and partition interactions, electrostatic interactions and valence bond interactions are the main sorption mechanisms. Additionally, small MPs, biodegradable MPs and aged conventional MPs often exhibit stronger pesticide sorption capacity. As environmental conditions change, especially in simulated biological media, pesticides can desorb from MPs. The utilization of pesticides by environmental microorganisms is the main factor controlling the degradation rate of pesticides in the presence of MPs. Pesticide sorption by MPs and size effects of MPs on pesticides are related to the internal exposure level of biological pesticides and changes in pesticide toxicity in the presence of MPs. Most studies have suggested that MPs exacerbate the toxicological effects of pesticides on sentinel species. Hence, the environmental risks of pesticides are altered by MPs and the carrier function of MPs. Based on this, research on the affinity between MPs and various pesticides should be systematically conducted. During agricultural production, pesticides should be cautiously selected and used plastic film to ensure human health and ecological security.

OrthoCalc: The six degrees of freedom measurement workflow of rotational and displacement changes for maxilla positioning evaluation.

BACKGROUND: This study is undertaken to establish the accuracy and reliability of OrthoCalc, a 3D application designed for the evaluation of maxillary positioning. METHODS: We registered target virtual planned models, maxillary models from pre-operative and post-operative CT scans, and post-operative intra-oral scans to a common reference system, allowing for digital evaluation. To assess rotational changes, we introduced a novel measurement method based on virtual cuboid models. Displacement errors were calculated based on proposed registration matrices. We also compared OrthoCalc to established commercial medical software as a benchmark. RESULTS: Statistical significance calculated showed no significant differences between OrthoCalc and commercial software. the biggest error of 0.04 degree in rotation change was found in the yaw. A maximum displacement change of 0.75 mm was found in the X direction. CONCLUSIONS: Our study validates OrthoCalc as a precise and reliable tool for assessing maxillary position changes with six degrees of freedom in orthognathic surgery, endorsing its clinical utility.

Morphological and quantitative study of the inferior alveolar nerve canal in hemifacial microsomia.

This study aimed to probe into the anatomic course of inferior alveolar nerve canal (IANC) in hemifacial microsomia (HFM) on a large scale, morphological observations and further quantitative study were performed. Patients were classified by Pruzansky-Kaban classification. The anatomic course of IANC was analyzed morphologically with three-dimensional (3D) imaging software among 248 patients. Seven distances between fixed landmarks on both sides were measured for 236 patients. The differences between affected and unaffected sides were compared. Significant differences were found in the entrance (P < 0.001), route (P < 0.001), and exit (P < 0.05) of IANC in type IIb and III HFM. The higher the degree of mandibular deformity was, the higher the incidence of IANC variation was (P < 0.05). The distances in the horizontal aspect of IANC including from mandibular foramen to mental foramen (P < 0.05) and from mental foramen to gonion (P < 0.05) were significantly shorter on the affected side. Abnormalities of the anatomical course of IANC exist in patients with Pruzansky-Kaban type IIb and type III HFM. The reduction of IANC on the affected side in the horizontal distance is more obvious. Three-dimensional imaging assessment is recommended before surgery.

Efficacy of navigation system-assisted distraction osteogenesis for hemifacial microsomia based on artificial intelligence for 3 to 18 years old: study protocol for a randomized controlled single-blind trial.

BACKGROUND: Mandibular distraction osteogenesis (MDO) is a major part of the treatment for hemifacial microsomia patients. Due to the narrow surgical field of the intraoral approach, osteotomy accuracy is highly dependent on the surgeons' experience. Electromagnetic (EM) tracking systems can achieve satisfying accuracy to provide helpful real-time surgical navigation. Our research team developed an EM navigation system based on artificial intelligence, which has been justified in improving the accuracy of osteotomy in the MDO in animal experiments. This study aims to clarify the effect of the EM navigation system in improving the MDO accuracy for hemifacial microsomia patients. METHODS: This study is designed as a single-centered and randomized controlled trial. Altogether, 22 hemifacial microsomia patients are randomly assigned to the experiment and control groups. All patients receive three-dimensional CT scans and preoperative surgical plans. The EM navigation system will be set up for those in the experiment group, and the control group will undergo traditional surgery. The primary outcome is the surgical precision by comparing the osteotomy position of pre- and postoperative CT scan images through the Geomagic Control software. The secondary outcomes include mandibular symmetry (occlusal plane deviation angle, mandibular ramus height, and body length), pain scale, and complications. Other indications, such as the adverse events of the system and the satisfactory score from patients and their families, will be recorded. DISCUSSION: This small sample randomized controlled trial intends to explore the application of an EM navigation system in MDO for patients, which has been adopted in other surgeries such as orthognathic procedures. Because of the delicate structures of children and the narrow surgical view, accurate osteotomy and protection of nearby tissue from injury are essential for successful treatment. The EM navigation system based on artificial intelligence adopted in this trial is hypothesized to provide precise real-time navigation for surgeons and optimally improve patient outcomes, including function and aesthetic results. The results of this trial will extend the application of new navigation technology in pediatric plastic surgery. TRIAL REGISTRATION: Chinese Clinical Trial Registry ChiCTR2200061565. Registered on 29 June 2022.