A Novel Algorithm for Breast Lesion Detection Using Textons and Local Configuration Pattern Features With Ultrasound Imagery

Acharya, U. Rajendra; Meiburger, Kristen M.; Koh, Joel En Wei; Ciaccio, Edward J.; Arunkumar, N.; See, Mee-Hoong; Taib, Nur Aishah Mohd; Vijayananthan, Anushya; Rahmat, Kartini; Fadzli, Farhana; Leong, Sook Sam; Westerhout, Caroline Judy; Chantre-Astaiza, Ángela; Ramírez-González, Gustavo

doi:10.1109/access.2019.2898121

Cited by 18 publications

(9 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, the texton-based approach to texture segmentation was implemented, since the given method has repeatedly demonstrated its effectiveness and scalability [74][75][76][77][78]. The texton-based segmentation utilizes Leung-Malik (LM) filters [74,79] (Figure 8) which work as visual cortex cells and allow the segmentation of an image into channels of coherent brightness and texture in a natural manner, where the texture originates from the spatial variation of surface normal and reflectance.…”

Section: Local Texture Analysismentioning

confidence: 99%

Open source computer vision-based layer-wise 3D printing analysis

Petsiuk

Pearce

2020

Additive Manufacturing

View full text Add to dashboard Cite

Section: Local Texture Analysismentioning

confidence: 99%

Open source computer vision-based layer-wise 3D printing analysis

Petsiuk

Pearce

2020

Additive Manufacturing

View full text Add to dashboard Cite

“…It is reported that when breast cancer is diagnosed early, its prognosis is good, and the survival rate increases significantly [8]. In recent years, computer-aided diagnosis (CAD) systems have been actively researched to enable fast diagnosis and feature detection [9]- [10][11] [12]. Machine learning-based methods have been proposed to expedite diagnosis and reduce the probability of misdiagnosis by medical doctors.…”

Section: Introductionmentioning

confidence: 99%

Breast Mass Classification Using eLFA Algorithm Based on CRNN Deep Learning Model

2020

View full text Add to dashboard Cite

Breast cancer is known to be common in many developed countries. It is reported as the most common type of cancer in the US, affecting one in eight women. In Korea, thyroid cancer is the most common type of cancer, followed by breast cancer in women. Considering this, early detection and accurate diagnosis of breast cancer are crucial for reducing the associated death rate. Recently, cancer diagnosis systems using medical images have attracted significant attention. Medical imaging methods, such as computed tomography and magnetic resonance imaging, can reveal the overall shape, heterogeneity, and growth speed of carcinoma and are, thus, more commonly employed for diagnoses. Medical imaging has gained popularity since a recent study identified that it could reflect the gene phenotype of a patient. However, an aided diagnosis system based on medical images requires high-specification equipment to analyze high-resolution data. Therefore, this paper proposes an edge extraction algorithm and a modified convolutional recurrent neural network (CRNN) model to accurately assess breast cancer based on medical imaging. The proposed algorithm extracts line-segment information from a breast mass image. The extracted line segments were classified into 16 types. Each type was uniquely labeled and compressed. The image compressed in this process was used as the input for the modified CRNN model. Traditional deep learning models were used to evaluate the performance of the proposed algorithm. The results show that the proposed model had the highest accuracy and lowest loss (99.75% and 0.0257, respectively).

show abstract

“…Textons are image micro-structures serving as building blocks that play a key role in the visual perception of texture by humans. The periodic repetition of textons with well-defined spacing and relative positioning imparts distinct textural characteristics to different regions within a digital image [16]. The aim is to identify statistical properties of the local image regions that, in turn, can be leveraged to evaluate differential maxima in the feature euclidean vector space.…”

Section: Introductionmentioning

confidence: 99%

Texture Representation Through Overlapped Multi-Oriented Tri-Scale Local Binary Pattern

et al. 2019

View full text Add to dashboard Cite

This paper ideates a novel texture descriptor that retains its classification accuracy under varying conditions of image orientation, scale, and illumination. The proposed Overlapped Multi-oriented Tri-scale Local Binary Pattern (OMTLBP) texture descriptor also remains insensitive to additive white Gaussian noise. The wavelet decomposition stage of the OMTLBP provides robustness to photometric variations, while the two subsequent stages -overlapped multi-oriented fusion and multi-scale fusionprovide resilience against geometric transformations within an image. Isolated encoding of constituent pixels along each scale in the joint histogram enables the proposed descriptor to capture both micro and macro structures within the texture. Performance of the OMTLBP is evaluated by classifying a variety of textured images belonging to Outex, KTH-TIPS, Brodatz, CUReT, and UIUC datasets. The experimental results validate the superiority of the proposed method in terms of classification accuracy when compared with the state-of-the-art texture descriptors for noisy images.

show abstract

A Novel Algorithm for Breast Lesion Detection Using Textons and Local Configuration Pattern Features With Ultrasound Imagery

Cited by 18 publications

References 33 publications

Open source computer vision-based layer-wise 3D printing analysis

Open source computer vision-based layer-wise 3D printing analysis

Breast Mass Classification Using eLFA Algorithm Based on CRNN Deep Learning Model

Texture Representation Through Overlapped Multi-Oriented Tri-Scale Local Binary Pattern

Contact Info

Product

Resources

About