Automatic brain tissue segmentation based on graph filter

Kong, Yaguang; Chen, Xiaopeng; Wu, Jiasong; Zhang, Pinzheng; Chen, Yang; Hu, Shu

doi:10.1186/s12880-018-0252-x

Cited by 14 publications

(7 citation statements)

References 43 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, Numerous methods and algorithms have been proposed to reduce metal artifacts in CT and CBCT images [23–26]. Y. Chen et al, [23] showed that A discriminative dictionary representation method was developed to mitigate CT truncation artifacts directly in the DICOM image domain. Both phantom and human subject studies demonstrated that the proposed method can effectively reduce truncation artifacts without access to projection data.…”

Section: Discussionmentioning

confidence: 99%

Effect of exposure parameters of cone beam computed tomography on metal artifact reduction around the dental implants in various bone densities

et al. 2019

View full text Add to dashboard Cite

Background This study aimed to assess the effect of exposure parameters such as milliampere (mA) and field of view (FOV) of cone beam computed tomography (CBCT) on a metal artifact of dental implants placed in different bone densities. Methods A total of 27 bone blocks with different densities (nine were type 1, nine were types 2 and 3, and nine were type 4) were used in this in vitro, experimental study. These blocks were placed in mandibular wax models. The blocks were scanned after drilling (hole preparation) and after implant placement using Cranex3D imaging system with a 4 × 6 cm 2 and 6 × 8 cm 2 FOV and 4 and 10 mA. Gray value of the bone blocks was recorded before and after placement of implants. Results In general, irrespective of bone density, the amount of artifacts was lower in small FOV compared to large FOV ( P < 0.05). Change of mA had no effect on metal artifacts ( P > 0.05). Artifacts in type 4 bone were greater than in other bone types ( P < 0.05). Difference between type 1 and types 2 and 3 was not significant ( P > 0.05). Conclusion According to the results of this study , Peri-implant artifacts were seen in all bone types; the amount of artifacts in type 4 bone was higher than that in other types. Size of FOV and bone density affect the metal artifacts around dental implants; so that a smaller FOV can be used to decrease metal artifacts.

show abstract

Section: Discussionmentioning

confidence: 99%

Effect of exposure parameters of cone beam computed tomography on metal artifact reduction around the dental implants in various bone densities

et al. 2019

View full text Add to dashboard Cite

show abstract

“…These models divided the brain image into multiple regions. For example, [40,41] divided the brain into eight regions), whereas [42,43] divided the brain into three regions. Dolz et al [44] proposed 3D and fully CN N for the segmentation of the subcortical brain structure.…”

Section: Brain Segmentationmentioning

confidence: 99%

Learning to Detect Boundary Information for Brain Image Segmentation

Khaled

Han

Ghaleb

2022

Preprint

View full text Add to dashboard Cite

MRI brain images are always of low contrast, which makes it difficult to identify to which area the information at the boundary of brain images belongs. This can make the extraction of features at the boundary more challenging, since those features can be misleading as they might mix properties of different brain regions. Hence, to alleviate such a problem, image boundary detection plays a vital role in medical image segmentation, and brain segmentation in particular, as unclear boundaries can worsen brain segmentation results. Yet, given the low quality of brain images, boundary detection in the context of brain image segmentation remains challenging. Despite the research invested to improve boundary detection and brain segmentation, these two problems were addressed independently, i.e., little attention was paid to applying boundary detection to brain segmentation tasks. Therefore, in this paper, we propose a boundary detection-based model for brain image segmentation. To this end, we first design a boundary segmentation network for detecting and segmenting images brain tissues. Then, we design a boundary information module (BIM) to distinguish boundaries from the three different brain tissues. After that, we add a boundary attention gate (BAG) to the encoder output layers of our transformer to capture more informative local details. We evaluate our proposed model on two datasets of brain tissue images, including infant and adult brains. The extensive evaluation experiments of our model show better performance (a Dice Coefficient (DC) accuracy of up to 5.3% compared to the state-of-the-art models) in detecting and segmenting brain tissue images.

show abstract

“…The used BrainWeb data set consists of artificially simulated MRI data and was originally designed to validate various segmentation algorithms as a known basic truth [20]. It exhibits similarity of image morphological structures to in vivo acquired MRI data [20,38] and is used frequently in studies for verification purposes [1,16,19].…”

Section: Limitations Of the Studymentioning

confidence: 99%

Semantic segmentation of cerebrospinal fluid and brain volume with a convolutional neural network in pediatric hydrocephalus—transfer learning from existing algorithms

et al. 2020

View full text Add to dashboard Cite

Background For the segmentation of medical imaging data, a multitude of precise but very specific algorithms exist. In previous studies, we investigated the possibility of segmenting MRI data to determine cerebrospinal fluid and brain volume using a classical machine learning algorithm. It demonstrated good clinical usability and a very accurate correlation of the volumes to the single area determination in a reproducible axial layer. This study aims to investigate whether these established segmentation algorithms can be transferred to new, more generalizable deep learning algorithms employing an extended transfer learning procedure and whether medically meaningful segmentation is possible. Methods Ninety-five routinely performed true FISP MRI sequences were retrospectively analyzed in 43 patients with pediatric hydrocephalus. Using a freely available and clinically established segmentation algorithm based on a hidden Markov random field model, four classes of segmentation (brain, cerebrospinal fluid (CSF), background, and tissue) were generated. Fifty-nine randomly selected data sets (10,432 slices) were used as a training data set. Images were augmented for contrast, brightness, and random left/right and X/Y translation. A convolutional neural network (CNN) for semantic image segmentation composed of an encoder and corresponding decoder subnetwork was set up. The network was pre-initialized with layers and weights from a pre-trained VGG 16 model. Following the network was trained with the labeled image data set. A validation data set of 18 scans (3289 slices) was used to monitor the performance as the deep CNN trained. The classification results were tested on 18 randomly allocated labeled data sets (3319 slices) and on a T2-weighted BrainWeb data set with known ground truth. Results The segmentation of clinical test data provided reliable results (global accuracy 0.90, Dice coefficient 0.86), while the CNN segmentation of data from the BrainWeb data set showed comparable results (global accuracy 0.89, Dice coefficient 0.84). The segmentation of the BrainWeb data set with the classical FAST algorithm produced consistent findings (global accuracy 0.90, Dice coefficient 0.87). Likewise, the area development of brain and CSF in the long-term clinical course of three patients was presented. Conclusion Using the presented methods, we showed that conventional segmentation algorithms can be transferred to new advances in deep learning with comparable accuracy, generating a large number of training data sets with relatively little effort. A clinically meaningful segmentation possibility was demonstrated.

show abstract

Automatic brain tissue segmentation based on graph filter

Cited by 14 publications

References 43 publications

Effect of exposure parameters of cone beam computed tomography on metal artifact reduction around the dental implants in various bone densities

Effect of exposure parameters of cone beam computed tomography on metal artifact reduction around the dental implants in various bone densities

Learning to Detect Boundary Information for Brain Image Segmentation

Semantic segmentation of cerebrospinal fluid and brain volume with a convolutional neural network in pediatric hydrocephalus—transfer learning from existing algorithms

Contact Info

Product

Resources

About