Improvement of the in vitro Pig Mandible Periodontal Tissue Images Quality Recorded by an OCT Handheld in 1200–1400 nm Infrared Domain: A Preliminary Study

Toadere, Florin; Toşa, Nicoleta; Badea, Mîndra Eugenia; Miron, Andreea; Cebotari, Victor; Toşa, V.; Turcu, Ioan; Chifor, Radu

doi:10.1007/978-3-030-93564-1_16

Cited by 3 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The software described in this paper consists of the fallowing filters: nimble, un-sharpening mask, homomorphic, coherence shock and region of interest. The mathematical theory behind un-sharpening mask, homomorphic and coherence shock filters is presented on references [2][3][4]7]. Un-sharpening mask filter first applies a low pass filter to the original images and then the blurred image is subtracted from the original image.…”

Section: Image Processing Algorithmmentioning

confidence: 99%

“…All of these parts introduce blur in the process of capture and rendering images [1]. Image sharpening may be performed by employing various filters: Laplacian and Sobel filters, [1,4], un sharpening masking filter [2][3][4], shock filter [2][3][4]7], fuzzy [5], wavelet [6] and Nimble Filter [4]. It is a desire and a challenge to have better perception of the biomedical images content.…”

Section: Introductionmentioning

confidence: 99%

“…The main advantage of this software consists of the fact that in the output images pixels are square in all biomedical filtered images. A previous version of the software was tested on pig mandible image [2] acquired using an OCT system and then on SEM images [3]. Thus, in time, this own made software requested updates and modifications in order to be employed in biomedical image processing.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improvement of biomedical images for better outcomes

Toadere

2023

Advanced Topics in Optoelectronics, Microelectronics, and Nanotechnologies XI

View full text Add to dashboard Cite

An algorithm which restores pixels from blurred MM (mammography), RMN (resonance magnetic image), CT (Computer Tomography) and OCT (Optical Coherence Tomography) biomedical images is presented. Improvement of the image having static blur is performed using an image processing algorithm consisting of following filters: nimble, sharpening, homomorphic, coherence shock and region of interest. Then, the contrast and the intensity of the image are enhanced. Once the algorithm applies, the display image has square pixels well defined. This achievement allows better view of details which were previously blurred. Prove of concept is illustrate with a set of demonstrative biomedical images. Pictures are rendered as pairs images in which one is blurred and the other one is filtered.

show abstract

Section: Image Processing Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improvement of biomedical images for better outcomes

Toadere

2023

Advanced Topics in Optoelectronics, Microelectronics, and Nanotechnologies XI

View full text Add to dashboard Cite

show abstract

“…Due to the evolution of technology, periodontal tissue imaging has started to play a key role in periodontal disease diagnosis. Previous studies showed efficiency for non-invasive periodontal imaging investigations using optical coherence tomography [ 15 , 16 , 17 ] and periodontal ultrasonography [ 18 , 19 ]. The main inconvenience for non-invasive or X-ray imaging technologies is the operator dependence and time-consuming interpretation process.…”

Section: Introductionmentioning

confidence: 99%

Automatic Segmentation of Periodontal Tissue Ultrasound Images with Artificial Intelligence: A Novel Method for Improving Dataset Quality

Chifor

Hotoleanu

Mariţa

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

This research aimed to evaluate Mask R-CNN and U-Net convolutional neural network models for pixel-level classification in order to perform the automatic segmentation of bi-dimensional images of US dental arches, identifying anatomical elements required for periodontal diagnosis. A secondary aim was to evaluate the efficiency of a correction method of the ground truth masks segmented by an operator, for improving the quality of the datasets used for training the neural network models, by 3D ultrasound reconstructions of the examined periodontal tissue. Methods: Ultrasound periodontal investigations were performed for 52 teeth of 11 patients using a 3D ultrasound scanner prototype. The original ultrasound images were segmented by a low experienced operator using region growing-based segmentation algorithms. Three-dimensional ultrasound reconstructions were used for the quality check and correction of the segmentation. Mask R-CNN and U-NET were trained and used for prediction of periodontal tissue’s elements identification. Results: The average Intersection over Union ranged between 10% for the periodontal pocket and 75.6% for gingiva. Even though the original dataset contained 3417 images from 11 patients, and the corrected dataset only 2135 images from 5 patients, the prediction’s accuracy is significantly better for the models trained with the corrected dataset. Conclusions: The proposed quality check and correction method by evaluating in the 3D space the operator’s ground truth segmentation had a positive impact on the quality of the datasets demonstrated through higher IoU after retraining the models using the corrected dataset.

show abstract