Multiscale Texture Descriptors for Automatic Small Bowel Tumors Detection in Capsule Endoscopy

Barbosa, Daniel; Roupar, Dalila; Lima, C. S.

doi:10.5772/19391

Cited by 6 publications

(5 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This pill-like camera takes about 60 000 images during an 8-hour journey through the gastrointestinal tract. Algorithms have been proposed for the detection of tumors [7], bleeding [8], ulcers [9], or abnormal patterns in general [10]. Similar systems have also been proposed for standard video endoscopy [11,12], with varying success rates.…”

Section: Discussionmentioning

confidence: 99%

Computer-aided detection of early neoplastic lesions in Barrett’s esophagus

et al. 2016

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

Computer-aided detection of early neoplastic lesions in Barrett’s esophagus

et al. 2016

View full text Add to dashboard Cite

show abstract

“…Since the first works of Daubechies [22] and Mallat [31], the WT plays a crucial role in image processing, namely in compression of medical images, image denoising, image enhancement, tomographic reconstruction, and feature extraction for image classification [32]. The Discrete Wavelet Transform (DWT) allows the decomposition of the information within an image/signal into different scales with distinct frequency content, by using different versions of a dilated/contracted and translated/shifted basis function called the mother wavelet.…”

Section: Wavelet Transformmentioning

confidence: 99%

Detection of bladder cancer with feature fusion, transfer learning and CapsNets

Freitas

Vieira

Cordeiro

et al. 2022

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

“…Analogously, a signal can be recovered from its wavelet coefficients through the inverse transform (ICWT). By varying both the scale s and the translation shift parameter τ it is possible to obtain a family of daughter wavelets from the mother wavelet function ψ (Barbosa et al 2011):…”

Section: Texture Characterizationmentioning

confidence: 99%

“…The DWT is suitable for dealing with singularities, and extracting details in horizontal, vertical, and diagonal directions. The image or signal to be analyzed is passed through filters with different cut-off frequencies at different scales, allowing a better decomposition of the patterns within an image (Barbosa et al 2011).…”

Section: Automatic T1 Bladder Tumor Detection By Using Wavelet Analys...mentioning

confidence: 99%

“…The DWT introduced a significant change in the direction of the research done on biomedical signal/image processing and allows a spatial/frequency representation by decomposing the image at different scales with different frequency content. It has also been vastly explored for several problems, such as compression of medical images, image denoising, image enhancement, tomographic reconstruction, and feature extraction for image classification (Barbosa et al 2011). Large wavelet coefficients are located in the neighborhood of edges and irregular textures (Mallat 2008).…”

Section: Texture Characterizationmentioning

confidence: 99%

See 1 more Smart Citation

Automatic T1 bladder tumor detection by using wavelet analysis in cystoscopy images

Freitas¹,

Vieira²,

Lima³

et al. 2018

Phys. Med. Biol.

View full text Add to dashboard Cite

Correct classification of cystoscopy images depends on the interpreter's experience. Bladder cancer is a common lesion that can only be confirmed by biopsying the tissue, therefore, the automatic identification of tumors plays a significant role in early stage diagnosis and its accuracy. To our best knowledge, the use of white light cystoscopy images for bladder tumor diagnosis has not been reported so far. In this paper, a texture analysis based approach is proposed for bladder tumor diagnosis presuming that tumors change in tissue texture. As is well accepted by the scientific community, texture information is more present in the medium to high frequency range which can be selected by using a discrete wavelet transform (DWT). Tumor enhancement can be improved by using automatic segmentation, since a mixing with normal tissue is avoided under ideal conditions. The segmentation module proposed in this paper takes advantage of the wavelet decomposition tree to discard poor texture information in such a way that both steps of the proposed algorithm segmentation and classification share the same focus on texture. Multilayer perceptron and a support vector machine with a stratified ten-fold cross-validation procedure were used for classification purposes by using the hue-saturation-value (HSV), red-green-blue, and CIELab color spaces. Performances of 91% in sensitivity and 92.9% in specificity were obtained regarding HSV color by using both preprocessing and classification steps based on the DWT. The proposed method can achieve good performance on identifying bladder tumor frames. These promising results open the path towards a deeper study regarding the applicability of this algorithm in computer aided diagnosis.

show abstract

Multiscale Texture Descriptors for Automatic Small Bowel Tumors Detection in Capsule Endoscopy

Cited by 6 publications

References 34 publications

Computer-aided detection of early neoplastic lesions in Barrett’s esophagus

Computer-aided detection of early neoplastic lesions in Barrett’s esophagus

Detection of bladder cancer with feature fusion, transfer learning and CapsNets

Automatic T1 bladder tumor detection by using wavelet analysis in cystoscopy images

Contact Info

Product

Resources

About