Pathological Image Analysis Using the GPU: Stroma Classification for Neuroblastoma

Mathur, Sachin; Dinakarpandian, Deendayal

doi:10.1109/bibm.2007.15

Cited by 20 publications

(22 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many other methods collect features from either the original RGB image, a converted image to other non-biologically based color spaces (e.g., Lab or HSL), or from a grayscale version of that same image (Al-Kadi, 2010;Basavanhally et al, 2010;Dundar et al, 2011Dundar et al, , 2010Esgiar et al, 2002;Farjam et al, 2007;Glotsos et al, 2008;Huang and Lee, 2009;Jafari-Khouzani and SoltanianZadeh, 2003;Kong et al, 2009;Ozolek et al, 2014;Petushi et al, 2006;Qureshi et al, 2008;Ruiz et al, 2007;Schnorrenberg et al, 1997;Tabesh et al, 2005;Tabesh and Teverovskiy, 2006;Tahir and Bouridane, 2006;Thiran and Macq, 1996;Tuzel et al, 2007;Wang et al, 2010;Wetzel et al, 1999;Weyn et al, 1998;Xu et al 2014aXu et al , 2014b. Since hematoxylin binds to nucleic acids and eosin binds to protein, unmixing the stains allows the feature extraction to directly probe the state of these important biological molecules, whereas features from the mixed image may either miss this signal or be unable to probe them independently.…”

Section: Discussionmentioning

confidence: 99%

“…This enables a strong consensus for the entire tissue, even if the tumor represents only a small portion of the tissue; the impact of the relevant area is not diluted by the effect of the less important tissue surrounding it. While other methods (Kong et al, 2013Ruiz et al, 2007;Sertel et al, 2009) have used tiling, they make their final decision based on the proportion of tiles assigned to a particular disease type. These previous methods have been limited to identifying diseases defined by their preponderance of particular tissue types, as they are unable to evaluate diseases where local features are key in determining a diagnosis.…”

Section: Discussionmentioning

confidence: 99%

“…In order to characterize the oligodendroglioma versus astrocytoma components of 117 GBM samples, Kong et al (2013) segmented and classified over 200 million nuclei. Based on this high computational complexity, it is easy to understand why Ruiz et al (2007) focused their work on using a GPU to reduce the execution time of their stromal classification in neuroblastoma. An alternative approach to reduce computational load while still examining the entire WSI is to reduce the image resolution.…”

Section: Image Tiling Methodsmentioning

confidence: 99%

“…A second approach to tackling the challenges to computerized analysis of WSI uses tiling to break the image into small, manageable pieces (Kong et al, 2013Ruiz et al, 2007;Sertel et al, 2009), analyzing each image piece, as opposed to just examining a few selected regions. However this increase in data means an increase in computation complexity.…”

Section: Image Tiling Methodsmentioning

confidence: 99%

See 3 more Smart Citations

Automated classification of brain tumor type in whole-slide digital pathology images using local representative tiles

Barker

Hoogi

Depeursinge

et al. 2016

Medical Image Analysis

184

110

View full text Add to dashboard Cite

a b s t r a c tComputerized analysis of digital pathology images offers the potential of improving clinical care (e.g. automated diagnosis) and catalyzing research (e.g. discovering disease subtypes). There are two key challenges thwarting computerized analysis of digital pathology images: first, whole slide pathology images are massive, making computerized analysis inefficient, and second, diverse tissue regions in whole slide images that are not directly relevant to the disease may mislead computerized diagnosis algorithms. We propose a method to overcome both of these challenges that utilizes a coarse-to-fine analysis of the localized characteristics in pathology images. An initial surveying stage analyzes the diversity of coarse regions in the whole slide image. This includes extraction of spatially localized features of shape, color and texture from tiled regions covering the slide. Dimensionality reduction of the features assesses the image diversity in the tiled regions and clustering creates representative groups. A second stage provides a detailed analysis of a single representative tile from each group. An Elastic Net classifier produces a diagnostic decision value for each representative tile. A weighted voting scheme aggregates the decision values from these tiles to obtain a diagnosis at the whole slide level. We evaluated our method by automatically classifying 302 brain cancer cases into two possible diagnoses (glioblastoma multiforme (N = 182) versus lower grade glioma (N = 120)) with an accuracy of 93.1 % (p << 0.001). We also evaluated our method in the dataset provided for the 2014 MICCAI Pathology Classification Challenge, in which our method, trained and tested using 5-fold cross validation, produced a classification accuracy of 100% (p << 0.001). Our method showed high stability and robustness to parameter variation, with accuracy varying between 95.5% and 100% when evaluated for a wide range of parameters. Our approach may be useful to automatically differentiate between the two cancer subtypes.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Image Tiling Methodsmentioning

confidence: 99%

Section: Image Tiling Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Automated classification of brain tumor type in whole-slide digital pathology images using local representative tiles

Barker

Hoogi

Depeursinge

et al. 2016

Medical Image Analysis

184

110

View full text Add to dashboard Cite

show abstract

“…Thus, linear algebra operations [11,6], medical image processing [10,15], or database querying [8] are just a few examples of different arenas in which GPU computation has been successfully applied. Also, [13] presents an extensive survey of the non-graphical applications where the use of GPU delivers good results.…”

Section: Attaining High Performance In General-purpose Computations Omentioning

confidence: 99%

Attaining High Performance in General-Purpose Computations on Current Graphics Processors

Igual

Mayo

Quintana–Ort́ı

2008

High Performance Computing for Computational Science - VECPAR 2008

View full text Add to dashboard Cite

Abstract:The increase in performance of the last generations of graphics processors (GPUs) has made this class of hardware a coprocessing platform of remarkable success in certain types of operations. In this paper we evaluate the performance of linear algebra and image processing routines, both on classical and unified GPU architectures and traditional processors (CPUs). From this study, we gain insights on the properties that make an algorithm likely to deliver high performance on a GPU. Keywords:Graphics processors (GPUs), general purpose computing on GPU, linear algebra, image processing, high performance. Resumen:El aumento de prestaciones de lasúltimas generaciones de procesadores gráficos (GPUs) ha convertido a este tipo de hardware en una plataforma de coprocesamiento de considerableéxito para cierto tipo de aplicaciones.En el presente artículo, se evalua el rendimiento de rutinas deálgebra lineal y procesamiento de imágenes, tanto en arquitecuturas gráficas clásicas como unificadas, así como sobre procesadores de carácter general (CPUs).A partir de dicho estudio, se extraen las propiedades que hacen de un algoritmo candidato a obtener elevado rendimiento al ser ejecutado sobre una GPU. Palabras clave:Procesadores gráficos (GPUs), procesamiento de carácter general sobre GPUs, algebra lineal, procesamiento de imágenes, altas prestaciones. Spain, {figual,mayo,quintana}@icc.uji.es Abstract. The increase in performance of the last generations of graphics processors (GPUs) has made this class of hardware a coprocessing platform of remarkable success in certain types of operations. In this paper we evaluate the performance of linear algebra and image processing routines, both on classical and unified GPU architectures and traditional processors (CPUs). From this study, we gain insights on the properties that make an algorithm likely to deliver high performance on a GPU.

show abstract

Efficient Region-based Classification for Whole Slide Images

Apou

Naegel

Forestier

et al. 2015

Communications in Computer and Information Science

View full text Add to dashboard Cite

Pathological Image Analysis Using the GPU: Stroma Classification for Neuroblastoma

Cited by 20 publications

References 9 publications

Automated classification of brain tumor type in whole-slide digital pathology images using local representative tiles

Automated classification of brain tumor type in whole-slide digital pathology images using local representative tiles

Attaining High Performance in General-Purpose Computations on Current Graphics Processors

Efficient Region-based Classification for Whole Slide Images

Contact Info

Product

Resources

About