Segmentation and root localization for analysis of dental radiographs

Gumus, Ergun

doi:10.1007/s11760-016-0861-1

Cited by 4 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Harandi et al [23] applied morphology transform and modified geodesic active contour on panoramic X-rays to achieve better separation and subtraction. Gumus [24] employed the discrete wavelet transform for better location of the ROI and adopted polynomial regression to form a smooth separation line with absent teeth.…”

Section: Related Workmentioning

confidence: 99%

“…Nevertheless, the shape and position of the maxillofacial region are considerably variable in practice, which limits the application of the static window. The dynamic method employs manual threshold selection [22], morphological transformation [23], or wavelet variation [24] to extract the separation line of the upper and lower jaws for correcting the anchor point. Then, the modified anchor point and rectangular, trapezoidal [25] or oval window [26] are combined to capture the maxillofacial region.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Maxillofacial Segmentation in Panoramic Dental X-Ray Images Using an Efficient Encoder-Decoder Network

et al. 2020

View full text Add to dashboard Cite

The panoramic dental X-ray images are an essential diagnostic tool used by dentists to detect the symptoms in an early stage and develop appropriate treatment plans. In recent years, deep learning methods have been applied to achieve tooth segmentation of dental X-rays, which aims to assist dentists in making clinical decisions. Because the original images contain plenty of useless information, it is necessary to extract the region-of-interest (ROI) to obtain more accurate results by focusing on the maxillofacial region. However, a fast and accurate maxillofacial segmentation without hand-crafted features is challenging due to the poor image quality. In this study, we create a large maxillofacial dataset and propose an efficient encoder-decoder network model named EED-Net to solve this problem. This dataset consists of 2602 panoramic dental X-ray images and corresponding segmentation masks annotated by the trained experts. Based on the original structure of U-Net, our model structure contains three major modules: a feature encoder, a corresponding decoder, and a multipath feature extractor that connects the encoding path and the decoding path. In order to obtain more semantic features from the depth and breadth, we replace the convolution layer with the residual block in the encoder and adopt Inception-ResNet block in the multipath feature extractor. Inspired by the skip connection in FCN-8s, the lightweight decoder has the same channel dimension as the number of segmented objects. Besides, a weighted loss function is used to enhance segmentation accuracy. The comprehensive experimental results on the new dataset demonstrate that our model achieves better accuracy and speed trade-offs for maxillofacial segmentation than the latest methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automated Maxillofacial Segmentation in Panoramic Dental X-Ray Images Using an Efficient Encoder-Decoder Network

et al. 2020

View full text Add to dashboard Cite

show abstract

“…As shown in Figure 4. is the image rotation coordinate system, and its rotation center is the 2 O point which is set up by myself. Therefore, it is need for us to realize the conversion between the two coordinate systems, and the rotation center of the processed image is (m, n), then the formula of the coordinate system transformation is represented by the formula (3) and the formula (4): …”

Section: Image Rotation Projectionmentioning

confidence: 99%

“…According to the formula (3), we can convert the coordinate system 1 O into coordinate system 2 O , according to the formula (4), we can convert the coordinate system 2 O into coordinate system 1 O . Assuming that in the new coordinate system, we define that the coordinate of the left upper corner of new image as the origin, the center coordinate of the image that not be rotated as (a, b), and the center coordinate of the image that is rotated as (c, d), then the pixel point of the rotation transformation matrix is shown as formula (5) Our method is based on this theory.…”

Section: Image Rotation Projectionmentioning

confidence: 99%

“…In this paper, the method of 360 degrees rotation projection histogram is proposed, according to the characteristics of circular, the rotating projection can reflect the information of the wheel farthest in the projection histogram and use this histogram can segment the ROI better. Researchers in the field of rotation projection also put forward different methods of application according to the direction of their research [1][2][3] . Besides,L.Liu et al analyse the rotation motion of circular feature based on the principle of perspective, and the method of calculating the rotation angle had been proposed.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation