Search

Advanced mathematical and deep learning (DL) algorithms have recently played a crucial role in diagnosing medical parameters and diseases. One of these areas that need to be more focused on is dentistry. This is why creating digital twins of dental issues in the metaverse is a practical and effective technique to benefit from the immersive characteristics of this technology and adapt the real world of dentistry to the virtual world. These technologies can create virtual facilities and environments for patients, physicians, and researchers to access a variety of medical services. Experiencing an immersive interaction between doctors and patients can be another considerable advantage of these technologies, which can dramatically improve the efficiency of the healthcare system. In addition, offering these amenities through a blockchain system enhances reliability, safety, openness, and the ability to trace data exchange. It also brings about cost savings through improved efficiencies. In this paper, a digital twin of cervical vertebral maturation (CVM), which is a critical factor in a wide range of dental surgery, within a blockchain-based metaverse platform is designed and implemented. A DL method has been used to create an automated diagnosis process for the upcoming CVM images in the proposed platform. This method includes MobileNetV2, a mobile architecture that improves the performance of mobile models in multiple tasks and benchmarks. The proposed technique of digital twinning is simple, fast, and suitable for physicians and medical specialists, as well as for adapting to the Internet of Medical Things (IoMT) due to its low latency and computing costs. One of the important contributions of the current study is to use of DL-based computer vision as a real-time measurement method so that the proposed digital twin does not require additional sensors. Furthermore, a comprehensive conceptual framework for creating digital twins of CVM based on MobileNetV2 within a blockchain ecosystem has been designed and implemented, showing the applicability and suitability of the introduced approach. The high performance of the proposed model on a collected small dataset demonstrates that low-cost deep learning can be used for diagnosis, anomaly detection, better design, and many more applications of the upcoming digital representations. In addition, this study shows how digital twins can be performed and developed for dental issues with the lowest hardware infrastructures, reducing the costs of diagnosis and treatment for patients.

In our study, the effect of the use of autofluorescence (Visually Enhanced Lesion Scope—VELscope) on increasing the success rate of surgical treatment in oral squamous carcinoma (OSCC) was investigated. Our hypothesis was tested on a group of 122 patients suffering from OSCC, randomized into a study and a control group enrolled in our study after meeting the inclusion criteria. The preoperative checkup via VELscope, accompanied by the marking of the range of a loss of fluorescence in the study group, was performed before the surgery. We developed a unique mucosal tattoo marking technique for this purpose. The histopathological results after surgical treatment, i.e., the margin status, were then compared. In the study group, we achieved pathological free margin (pFM) in 55 patients, pathological close margin (pCM) in 6 cases, and we encountered no cases of pathological positive margin (pPM) in the mucosal layer. In comparison, the control group results revealed pPM in 7 cases, pCM in 14 cases, and pFM in 40 of all cases in the mucosal layer. This study demonstrated that preoperative autofluorescence assessment of the mucosal surroundings of OSCC increased the ability to achieve pFM resection 4.8 times in terms of lateral margins.