On the other hand, CNN networks tend to develop from shallow layer networks to broader or problem-specific self-made or complicated networks.
Many studies that used pre-trained networks like Alexnet, VGG, GoogLeNet, and Inception v3 found that they performed well in general.
Deep learning frameworks, well-known as convolutional neural networks (CNNs), are primarily employed for processing large and complex image datasets because they can obtain multiple features from obfuscated layers ( Schmidhuber, 2015 Hwang et al., 2019). Also, various studies revealed that analysis of dental imaging modalities is beneficial in applications like human identification, age estimation, and biometrics ( Nomir & Abdel-Mottaleb, 2007 Caruso, Silvestri & Sconfienza, 2013).Īt present, deep learning (DL) and machine learning (ML) techniques have gained huge momentum in the field of DXRI analysis. Dental image examination involved various stages consisting of image enhancement, segmentation, feature extractions, and identification of regions, which are subsequently valuable for detecting cavities, tooth fractures, cysts or tumors, root canal length, and teeth growth in children ( Kutsch, 2011 Purnama et al., 2015). In most cases, the automatic computerized tool that can help the investigation process would be highly beneficial ( Abdi, Kasaei & Mehdizadeh, 2015 Jain & Chauhan, 2017).
#Dental xray vision manual#
Image segmentation is the most widely used image-processing technique to analyze medical images and help improve computer-aided medical diagnosis systems ( Li et al., 2006 Shah et al., 2006).įurthermore, manual examination of a large collection of X-ray images can be time-consuming because visual inspection and tooth structure analysis have an abysmal sensitive rate therefore, human screening may not identify a high proportion of caries ( Olsen et al., 2009). However, to analyze a dental X-ray image, researchers primarily use image processing methods to extract the relevant information. For dentists, radiography imparts a significant role in assisting imaging assessment in providing a thorough clinical diagnosis and dental structures preventive examinations ( Molteni, 1993). The survey presents extensive details of the state-of-the-art methods, including image modalities, pre-processing applied for image enhancement, performance measures, and datasets utilized.ĭental X-ray imaging (DXRI) has been developed as the foundation for dental professionals across the world because of the assistance provided in detecting the abnormalities present in the teeth structures ( Oprea et al., 2008). Overall state-of-the-art research works have been classified into three major categories, i.e., image processing, machine learning, and deep learning approaches, and their respective advantages and limitations are identified and discussed. In this article, we have provided a comprehensive survey of dental image segmentation and analysis by investigating more than 130 research works conducted through various dental imaging modalities, such as various modes of X-ray, CT (Computed Tomography), CBCT (Cone Beam Computed Tomography), etc. However, automation in the domain of dental image segmentation and examination is essentially the need of the hour in order to ensure error-free diagnosis and better treatment planning. Human dental image analysis is a challenging and time-consuming process due to the unspecified and uneven structures of various teeth, and hence the manual investigation of dental abnormalities is at par excellence. Another aspect of dental imaging is that it can be helpful in the field of biometrics. In dentistry, practitioners interpret various dental X-ray imaging modalities to identify tooth-related problems, abnormalities, or teeth structure changes.
0 kommentar(er)
