Automated classification of renal cell carcinoma subtypes using bag-of-features

Raza, S. Hussain; Parry, R. Mitchell; Sharma, Yachna; Chaudry, Qaiser; Moffitt, Richard A.; Young, Andrew N.; Wang, May D.

doi:10.1109/iembs.2010.5626009

Cited by 6 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of pattern recognition models is highly dependent on the features used; therefore picking the right features for a particular problem is the main motivation [8], [30], [31], [69] Texture Haralick [8], [20], [21], [26], [33][34][35] Gabor Filter [5], [8], [45] Co-occurrence texture [24], [52], [73] Haar wavelet coefficients [41], [49] LBP [44], [45] Bag of features [36][37][38][39][40][41][42][43], [74] to provide a review of current representation techniques applied in histopathology domain.…”

Section: Automatic Histopathology Image Analysis Processmentioning

confidence: 99%

“…Each patch can be represented through different descriptors, image representation is built with a frequency histogram where each bin shows how related is the image with each visual word of the dictionary. This model has obtained success results for basal-cell carcinoma detection [36][37][38][39][40], medullobastoma [41] and renal cell carcinoma [42] classification. This kind of representation was used to build a CBIR system using Non Negative Matrix Factorization (NMF) by Vanegas et al [43].…”

Section: Visual Featuresmentioning

confidence: 99%

See 1 more Smart Citation

Representación de imágenes de histopatología utilizada en tareas de análisis automático: estado del arte

Arévalo

Cruz-Roa

2014

Rev. Med.

View full text Add to dashboard Cite

<p>This paper presents a review of the state-of-the-art in histopathology image representation used in automatic image analysis tasks. Automatic analysis of histopathology images is important for building computer-assisted diagnosis tools, automatic image enhancing systems and virtual microscopy systems, among other applications. Histopathology images have a rich mix of visual patterns with particularities that make them difficult to analyze. The paper discusses these particularities, the acquisition process and the challenges found when doing automatic analysis. Second an overview of recent works and methods addressed to deal with visual content representation in different automatic image analysis tasks is presented. Third an overview of applications of image representation methods in several medical domains and tasks is presented. Finally, the paper concludes with current trends of automatic analysis of histopathology images like digital pathology.</p>

show abstract

Section: Automatic Histopathology Image Analysis Processmentioning

confidence: 99%

Section: Visual Featuresmentioning

confidence: 99%

Representación de imágenes de histopatología utilizada en tareas de análisis automático: estado del arte

Arévalo

Cruz-Roa

2014

Rev. Med.

View full text Add to dashboard Cite

show abstract

“…The bag-of-features (BOF) method [9] is one of the popular mid-level image representation methods. This concept is inherited from the bag-of-words (BoW) which is used for textual document analysis in natural language processing [25,41,42].…”

Section: Introductionmentioning

confidence: 99%

Improved bag-of-features using grey relational analysis for classification of histology images

Pal

Saraswat

Mittal

2021

Complex Intell. Syst.

View full text Add to dashboard Cite

An efficient classification method to categorize histopathological images is a challenging research problem. In this paper, an improved bag-of-features approach is presented as an efficient image classification method. In bag-of-features, a large number of keypoints are extracted from histopathological images that increases the computational cost of the codebook construction step. Therefore, to select the a relevant subset of keypoints, a new keypoints selection method is introduced in the bag-of-features method. To validate the performance of the proposed method, an extensive experimental analysis is conducted on two standard histopathological image datasets, namely ADL and Blue histology datasets. The proposed keypoint selection method reduces the extracted high dimensional features by 95% and 68% from the ADL and Blue histology datasets respectively with less computational time. Moreover, the enhanced bag-of-features method increases classification accuracy by from other considered classification methods.

show abstract

“…Recently, the bag-of-features approach has emerged as a useful tool for medical image classification [4–7]. The bag-of-features framework evolved from the bag-of-words model for text documents [8].…”

Section: Introductionmentioning

confidence: 99%

“…Feature vectors are combined into a codebook that represents the characteristic patches in a collection of images. Typically, scale and rotation invariant features or raw pixel intensities are used [4–7]. Depending on the application, scenarios may exist where one or both could help or hurt performance.…”

Section: Introductionmentioning

confidence: 99%

An Analysis of Scale and Rotation Invariance in the Bag-of-Features Method for Histopathological Image Classification

Raza

Parry

Moffitt

et al. 2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The bag-of-features method has emerged as a useful and flexible tool that can capture medically relevant image characteristics. In this paper, we study the effect of scale and rotation invariance in the bag-offeatures framework for Renal Cell Carcinoma subtype classification. We estimated the performance of different features by linear support vector machine over 10 iterations of 3-fold cross validation. For a very heterogeneous dataset labeled by an expert pathologist, we achieve a classification accuracy of 88% with four subtypes. Our study shows that rotation invariance is more important than scale invariance but combining both properties gives better classification performance.

show abstract

Automated classification of renal cell carcinoma subtypes using bag-of-features

Cited by 6 publications

References 16 publications

Representación de imágenes de histopatología utilizada en tareas de análisis automático: estado del arte

Representación de imágenes de histopatología utilizada en tareas de análisis automático: estado del arte

Improved bag-of-features using grey relational analysis for classification of histology images

An Analysis of Scale and Rotation Invariance in the Bag-of-Features Method for Histopathological Image Classification

Contact Info

Product

Resources

About