Classification of human teeth caries using custom non-invasive optical imaging system

Gawad, Ahmed L. Abdel; El-Sharkawy, Yasser H.; El-Sherif, Ashraf F.

doi:10.1007/s41547-017-0008-x

Cited by 10 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The reflectance mode involved placing source-detector separations (SDSs) at three distinct distances, namely 250 µm, 750 µm, and 1.5 mm. Commercial DOS systems used in dental detection use various probe sizes such as 50 µm, 100 µm, 200 µm, and 400 µm [17,30]. While smaller probe sizes are suitable to detect very fine details and small irregularities, larger probe sizes are typically used for initial screenings.…”

Section: Resultsmentioning

confidence: 99%

Monte Carlo Simulation of Diffuse Optical Spectroscopy for 3D Modeling of Dental Tissues

Moradi

Chen

2023

Sensors

View full text Add to dashboard Cite

Three-dimensional precise models of teeth are critical for a variety of dental procedures, including orthodontics, prosthodontics, and implantology. While X-ray-based imaging devices are commonly used to obtain anatomical information about teeth, optical devices offer a promising alternative for acquiring 3D data of teeth without exposing patients to harmful radiation. Previous research has not examined the optical interactions with all dental tissue compartments nor provided a thorough analysis of detected signals at various boundary conditions for both transmittance and reflectance modes. To address this gap, a GPU-based Monte Carlo (MC) method has been utilized to assess the feasibility of diffuse optical spectroscopy (DOS) systems operating at 633 nm and 1310 nm wavelengths for simulating light-tissue interactions in a 3D tooth model. The results show that the system’s sensitivity to detect pulp signals at both 633 nm and 1310 nm wavelengths is higher in the transmittance compared with that in the reflectance mode. Analyzing the recorded absorbance, reflectance, and transmittance data verified that surface reflection at boundaries can improve the detected signal, especially from the pulp region in both reflectance and transmittance DOS systems. These findings could ultimately lead to more accurate and effective dental diagnosis and treatment.

show abstract

Section: Resultsmentioning

confidence: 99%

Monte Carlo Simulation of Diffuse Optical Spectroscopy for 3D Modeling of Dental Tissues

Moradi

Chen

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Anyway, all checking modalities have their issues to give an exact proclamation about the achievement of the ablation. On the other side hyperspectral imaging (HSI) method provides specific wavelengths (spectral image) across the electromagnetic spectrum as it collects spatial and spectral information for the specimen under investigation [39], [40].…”

Section: Discussionmentioning

confidence: 99%

“…Recently, many researchers have developed several imaging methods to guarantee suitable removal of liver malignant and metastases utilizing non-intrusive or negligibly obtrusive systems with respect to the conventional excisional biopsy. Of these imaging techniques, infrared thermography monitoring [33], [34],contrast-enhanced ultrasound [35], real-time ultrasound elastography ,high resolution US [36], [37] and electrode vibration elastography [38].This exploratory investigation was the leading at the attainability of HSI observing in RFA .On the other side hyperspectral imaging (HSI) method provides a specific wavelengths (spectral image) across the electromagnetic spectrum as it collects spatial and spectral information for the specimen under investigation [39], [40].…”

mentioning

confidence: 99%

Spatiotemporal Thermal Contours mapping of ex-vivo Bovine Liver Radiofrequency Thermal Ablation utilizing Hyperspectral Image and its Associated K-Mean Clustering Algorithm

Aref¹,

Aboughaleb²,

Rabie³

et al. 2020

BRCR

Self Cite

View full text Add to dashboard Cite

Significance: Hepatocellular carcinoma (HCC) is considered as worldwide health problem with a poor diagnosis due to limited detection techniques. Thermal ablation is the dominant modality to treat liver tumors for discriminating patients who are not allowed to have surgical intervention. Knowing that, observing or foreseeing the size of the subsequent tissue putrefaction during the Thermal Ablation techniques is a difficult undertaking. Aim: To examine the impacts of ablation zone volume following Radiofrequency ablation (RFA) of an ex-vivo bovine liver to correlate the impacts of thermal ablation with target organ perfusion; by exploiting the unique properties of Hyperspectral Imaging (HSI).where, Vessels may source cooling in the adjacent tumor target (heat‑sink‑effect) with risk of cancer recurrence and the infiltration profundity estimations consider the lessening of the tissue. Materials and Methods: Radiofrequency ablation was perfused on ex-vivo bovine livers at peripheral and central‑vessel‑adjacent locations, and monitored by HSI with a spectral range from 400 to 1000 nm. The system contains k-means clustering (K=8) algorithms combining spectral and spatial information. Labeled spectral signatures datasets were used as training data. Statistical analysis (10 samples) was computed to calculate the highest variance between six spectral images for determining the optimum wavelength for discrimination between the affected regions after thermal ablation (normal, thermal, and ablated liver tissue regions). Results: The change of the optical properties of ex-vivo liver tissues provides different responses to light transmission, scattering, absorption and particularly the reflection over the spectrum range. The spectral reflectance signatures were measured and evaluated using designed K-mean clustering algorithm after image reconstructed. Trials showed that spectral region 650~650 nm was proposed as optimum spectral range. Where, these results successfully distinguishes the Surface Thermal ablation region (x,y-axis),as well as the Thermal penetration Depth (z-axis) for Tissue characterization and Contour mapping for the unwanted thermal damage. Conclusions: Hyperspectral imaging is a powerful tool in real-time monitoring the thermal ablation and more accurate compared to the conventional imaging modality.

show abstract

“…Feature space is reduced using a heuristic approach based on the information gain ratio method. Gawad et al [ 38 ] formulated a caries status detection and classification model based on a low-powered and less hazardous 635 nm He-Ne laser–tissue interaction mechanism to characterize human teeth into regular, moderate, and severe caries degree status.…”

Section: Related Workmentioning

confidence: 99%

Teeth Lesion Detection Using Deep Learning and the Internet of Things Post-COVID-19

Shafi,

Sajad,

Fatima

et al. 2023

Sensors

View full text Add to dashboard Cite

With a view of the post-COVID-19 world and probable future pandemics, this paper presents an Internet of Things (IoT)-based automated healthcare diagnosis model that employs a mixed approach using data augmentation, transfer learning, and deep learning techniques and does not require physical interaction between the patient and physician. Through a user-friendly graphic user interface and availability of suitable computing power on smart devices, the embedded artificial intelligence allows the proposed model to be effectively used by a layperson without the need for a dental expert by indicating any issues with the teeth and subsequent treatment options. The proposed method involves multiple processes, including data acquisition using IoT devices, data preprocessing, deep learning-based feature extraction, and classification through an unsupervised neural network. The dataset contains multiple periapical X-rays of five different types of lesions obtained through an IoT device mounted within the mouth guard. A pretrained AlexNet, a fast GPU implementation of a convolutional neural network (CNN), is fine-tuned using data augmentation and transfer learning and employed to extract the suitable feature set. The data augmentation avoids overtraining, whereas accuracy is improved by transfer learning. Later, support vector machine (SVM) and the K-nearest neighbors (KNN) classifiers are trained for lesion classification. It was found that the proposed automated model based on the AlexNet extraction mechanism followed by the SVM classifier achieved an accuracy of 98%, showing the effectiveness of the presented approach.

show abstract

Classification of human teeth caries using custom non-invasive optical imaging system

Cited by 10 publications

References 25 publications

Monte Carlo Simulation of Diffuse Optical Spectroscopy for 3D Modeling of Dental Tissues

Monte Carlo Simulation of Diffuse Optical Spectroscopy for 3D Modeling of Dental Tissues

Spatiotemporal Thermal Contours mapping of ex-vivo Bovine Liver Radiofrequency Thermal Ablation utilizing Hyperspectral Image and its Associated K-Mean Clustering Algorithm

Teeth Lesion Detection Using Deep Learning and the Internet of Things Post-COVID-19

Contact Info

Product

Resources

About