Texture in Biomedical Images

Petrou, Maria

doi:10.1007/978-3-642-15816-2_6

Cited by 11 publications

(13 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the literature, different parameter settings have been suggested, and filter banks created by these parameter settings work well in general. Details for the derivation of Gabor wavelets and parameter selection can be found in [113,148,180]. Invariant Gabor representations can be accessed in [78].…”

Section: Dense Texture Descriptorsmentioning

confidence: 99%

From BoW to CNN: Two Decades of Texture Representation for Texture Classification

et al. 2018

View full text Add to dashboard Cite

Texture is a fundamental characteristic of many types of images, and texture representation is one of the essential and challenging problems in computer vision and pattern recognition which has attracted extensive research attention over several decades. Since 2000, texture representations based on Bag of Words (BoW) and on Convolutional Neural Networks (CNNs) have been extensively studied with impressive performance. Given this period of remarkable evolution, this paper aims to present a comprehensive survey of advances in texture representation over the last two decades. More than 250 major publications are cited in this survey covering different aspects of the research, including benchmark datasets and state of the art results. In retrospect of what has been achieved so far, the survey discusses open challenges and directions for future research.

show abstract

Section: Dense Texture Descriptorsmentioning

confidence: 99%

From BoW to CNN: Two Decades of Texture Representation for Texture Classification

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Although the concept of texture is widely used in image analysis, there is still no exact definition of texture, and researchers from different domains define texture from different perspectives. One definition describes texture as a property intrinsic to the imaged object, not something that (like noise) is caused by the imaging instrument . Under this definition, multimodal image registration can be theoretically treated as monomodal image registration if we can robustly extract the real texture from different images.…”

Section: Discussionmentioning

confidence: 99%

“…One definition describes texture as a property intrinsic to the imaged object, not something that (like noise) is caused by the imaging instrument. 35 Under this definition, multimodal image registration can be theoretically treated as monomodal image registration if we can robustly extract the real texture from different images. However, the difficulty is that different medical images encode the imaged object in different ways, and at the same time, the resulting images usually suffer from high levels of noise and intensity nonuniformity.…”

Section: Discussionmentioning

confidence: 99%

Fast and robust multimodal image registration using a local derivative pattern

et al. 2017

View full text Add to dashboard Cite

Purpose: Deformable multimodal image registration, which can benefit radiotherapy and image guided surgery by providing complementary information, remains a challenging task in the medical image analysis field due to the difficulty of defining a proper similarity measure. This article presents a novel, robust and fast binary descriptor, the discriminative local derivative pattern (dLDP), which is able to encode images of different modalities into similar image representations. Methods: dLDP calculates a binary string for each voxel according to the pattern of intensity derivatives in its neighborhood. The descriptor similarity is evaluated using the Hamming distance, which can be efficiently computed, instead of conventional L1 or L2 norms. For the first time, we validated the effectiveness and feasibility of the local derivative pattern for multimodal deformable image registration with several multi-modal registration applications. Results: dLDP was compared with three state-of-the-art methods in artificial image and clinical settings. In the experiments of deformable registration between different magnetic resonance imaging (MRI) modalities from BrainWeb, between computed tomography and MRI images from patient data, and between MRI and ultrasound images from BITE database, we show our method outperforms localized mutual information and entropy images in terms of both accuracy and time efficiency. We have further validated dLDP for the deformable registration of preoperative MRI and three-dimensional intraoperative ultrasound images. Our results indicate that dLDP reduces the average mean target registration error from 4.12 mm to 2.30 mm. This accuracy is statistically equivalent to the accuracy of the state-of-the-art methods in the study; however, in terms of computational complexity, our method significantly outperforms other methods and is even comparable to the sum of the absolute difference. Conclusions: The results reveal that dLDP can achieve superior performance regarding both accuracy and time efficiency in general multimodal image registration. In addition, dLDP also indicates the potential for clinical ultrasound guided intervention.

show abstract

“…Practically it requires careful consideration of the significance of the individual features to achieve high discrimination by reducing the effect of heavily correlated features, and the features with little discriminatory power [20]. The choice of appropriate features depends on the particular image and the application and they should be reliable such that the features of the same class should have similar values, uncorrelated in order to avoid the wasteful in computation [21], and they should be extracted in a reliable way [22,23]. In this study, we concentrate on textural feature because there are no specific size and organized shapes of the brain tumors in addition it may appear in different image intensities [24].…”

Section: Proposed Feature Extraction Methodsmentioning

confidence: 99%

MRI brain scan classification using novel 3-D statistical features

Hasan

Meziane

Aspin

et al. 2017

Proceedings of the Second International Conference on Internet of Things, Data and Cloud Computing

View full text Add to dashboard Cite

The paper presents an automated algorithm for detecting and classifying magnetic resonance brain slices into normal and abnormal based on a novel three-dimensional modified grey level co-occurrence matrix approach that is used for extracting texture features from MRI brain scans. This approach is used to analyze and measure asymmetry between the two brain hemispheres, based on the prior-knowledge that the two hemispheres of a healthy brain have approximately a bilateral symmetry. The experimental results demonstrate the efficacy of our proposed algorithm in detecting brain abnormalities with high accuracy and low computational time. The dataset used in the experiment comprises 165 patients with 88 having different brain abnormalities whilst the remaining do not exhibit any detectable pathology. The algorithm was tested using a ten-fold cross-validation technique with 10 repetitions to avoid the result depending on the sample order. The maximum accuracy achieved for the brain tumors detection was 93.3% using a Multi-Layer Perceptron Neural Network.

show abstract

Texture in Biomedical Images

Cited by 11 publications

References 11 publications

From BoW to CNN: Two Decades of Texture Representation for Texture Classification

From BoW to CNN: Two Decades of Texture Representation for Texture Classification

Fast and robust multimodal image registration using a local derivative pattern

MRI brain scan classification using novel 3-D statistical features

Contact Info

Product

Resources

About