Detecting Prostatic Adenocarcinoma From Digitized Histology Using a Multi-Scale Hierarchical Classification Approach

Doyle, Scott; Rodríguez, Carlos; Madabhushi, Anant; Tomaszeweski, John; Feldman, Michael D.

doi:10.1109/iembs.2006.260188

Cited by 31 publications

(17 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…WSI in particular affords the technologic possibility for "machine learning space" for the development of customized algorithms for various tissues and diseases. Proof of concept for this approach has already been reported for prostate tissue and Gleason pattern recognition (6,9). It is only through the development of tools that marry histopathology with highly quantifiable, automated and reproducible staining that neuropathologists, working on everything from neurodegenerative disease to brain tumors, will be able to support the growing demand associated with clinical trials and animal model systems.…”

Section: Future Applications (Multispectral Analysis and Biorepositormentioning

confidence: 99%

Digital Pathology: A Tool for 21st Century Neuropathology

Guzmán

Judkins

2009

Brain Pathology

View full text Add to dashboard Cite

Digital pathology represents an electronic environment for performing pathologic analysis and managing the information associated with this activity. The technology to create and support digital pathology has largely developed over the last decade. The use of digital pathology tools is essential to adapt and lead in the rapidly changing environment of 21st century neuropathology. The utility of digital pathology has already been demonstrated by pathologists in several areas including consensus reviews, quality assurance (Q/A), tissue microarrays (TMAs), education and proficiency testing. These utilities notwithstanding, interface issues, storage and image formatting all present challenges to the integration of digital pathology into the neuropathology work environment. With continued technologic improvements, as well as the introduction of fluorescent side scanning and multispectral detection, future developments in digital pathology offer the promise of adding powerful analytic tools to the pathology work environment. The integration of digital pathology with biorepositories offers particular promise for neuropathologists engaged in tissue banking. The utilization of these tools will be essential for neuropathologists to continue as leaders in diagnostics, translational research and basic science in the 21st century.

show abstract

Section: Future Applications (Multispectral Analysis and Biorepositormentioning

confidence: 99%

Digital Pathology: A Tool for 21st Century Neuropathology

Guzmán

Judkins

2009

Brain Pathology

View full text Add to dashboard Cite

show abstract

“…There were many studies conducted for automated detection of regions having the characteristics of a specific disease. The diseases taken into consideration in this respect include colorectal dysplasia (Hamilton et al, 1997), breast lesions (Sahiner et al, 1996;Dundar et al, 2010Dundar et al, , 2011, renal cell carcinoma (Waheed et al, 2007), cervical (Hallouche et al, 1992), prostate (Diamond et al, 1982;Pitts et al, 1993;Doyle et al, 2006Doyle et al, , 2007Huang and Lee, 2009), oral cancers (Muthu et al, 2012;Mookiah et al, 2011) and colon cancers (Hamilton et al, 1987;Nasser Esgiar et al, 1998;Rajpoot and Rajpoot, 2004;Masood et al, 2006;Filippas et al, 2003;Nwoye et al, 2006).…”

Section: Introductionmentioning

confidence: 99%

“…Filippas et al (2003) focused on the identification of normal and cancerous colonic mucosa using a genetic algorithm. Doyle et al performed studies for automated detection of prostatic adenocarcinoma and for prostate cancer grading using Adaboost, Decision Trees and SVM classifiers (Doyle et al, 2006(Doyle et al, , 2007. There are other methods applied to the different types of carcinomas.…”

Section: Introductionmentioning

confidence: 99%

Automated labelling of cancer textures in colorectal histopathology slides using quasi-supervised learning

Onder¹,

Sarıoğlu²,

Karaçali³

2013

Micron

View full text Add to dashboard Cite

a b s t r a c tQuasi-supervised learning is a statistical learning algorithm that contrasts two datasets by computing estimate for the posterior probability of each sample in either dataset. This method has not been applied to histopathological images before. The purpose of this study is to evaluate the performance of the method to identify colorectal tissues with or without adenocarcinoma. Light microscopic digital images from histopathological sections were obtained from 30 colorectal radical surgery materials including adenocarcinoma and non-neoplastic regions. The texture features were extracted by using local histograms and co-occurrence matrices. The quasi-supervised learning algorithm operates on two datasets, one containing samples of normal tissues labelled only indirectly, and the other containing an unlabeled collection of samples of both normal and cancer tissues. As such, the algorithm eliminates the need for manually labelled samples of normal and cancer tissues for conventional supervised learning and significantly reduces the expert intervention. Several texture feature vector datasets corresponding to different extraction parameters were tested within the proposed framework. The Independent Component Analysis dimensionality reduction approach was also identified as the one improving the labelling performance evaluated in this series. In this series, the proposed method was applied to the dataset of 22,080 vectors with reduced dimensionality 119 from 132. Regions containing cancer tissue could be identified accurately having false and true positive rates up to 19% and 88% respectively without using manually labelled ground-truth datasets in a quasi-supervised strategy. The resulting labelling performances were compared to that of a conventional powerful supervised classifier using manually labelled ground-truth data. The supervised classifier results were calculated as 3.5% and 95% for the same case. The results in this series in comparison with the benchmark classifier, suggest that quasi-supervised image texture labelling may be a useful method in the analysis and classification of pathological slides but further study is required to improve the results.

show abstract

“…multi-resolution) approaches. [1011] In image processing, multi-scale schemes are often used to interpret contextual information over different image resolutions. [10] Most multi-scale frameworks, which operate by exposing a single FOV to classifiers at multiple image resolutions, perform well when quantifying large-scale image patterns.…”

Section: Introductionmentioning

confidence: 99%

Multi-field-of-view strategy for image-based outcome prediction of multi-parametric estrogen receptor-positive breast cancer histopathology: Comparison to Oncotype DX

Basavanhally

Feldman

Shih

et al. 2012

Journal of Pathology Informatics

Self Cite

View full text Add to dashboard Cite

In this paper, we attempt to quantify the prognostic information embedded in multi-parametric histologic biopsy images to predict disease aggressiveness in estrogen receptor-positive (ER+) breast cancers (BCa). The novel methodological contribution is in the use of a multi-field-of-view (multi-FOV) framework for integrating image-based information from differently stained histopathology slides. The multi-FOV approach involves a fixed image resolution while simultaneously integrating image descriptors from many FOVs corresponding to different sizes. For each study, the corresponding risk score (high scores reflecting aggressive disease and vice versa), predicted by a molecular assay (Oncotype DX), is available and serves as the surrogate ground truth for long-term patient outcome. Using the risk scores, a trained classifier is used to identify disease aggressiveness for each FOV size. The predictions for each FOV are then combined to yield the final prediction of disease aggressiveness (good, intermediate, or poor outcome). Independent multi-FOV classifiers are constructed for (1) 50 image features describing the spatial arrangement of cancer nuclei (via Voronoi diagram, Delaunay triangulation, and minimum spanning tree graphs) in H and E stained histopathology and (2) one image feature describing the vascular density in CD34 IHC stained histopathology. In a cohort of 29 patients, the multi-FOV classifiers obtained by combining information from the H and E and CD34 IHC stained channels were able to distinguish low- and high-risk patients with an accuracy of 0.91 ± 0.02 and a positive predictive value of 0.94 ± 0.10, suggesting that a purely image-based assay could potentially replace more expensive molecular assays for making disease prognostic predictions.

show abstract

Detecting Prostatic Adenocarcinoma From Digitized Histology Using a Multi-Scale Hierarchical Classification Approach

Cited by 31 publications

References 4 publications

Digital Pathology: A Tool for 21st Century Neuropathology

Digital Pathology: A Tool for 21st Century Neuropathology

Automated labelling of cancer textures in colorectal histopathology slides using quasi-supervised learning

Multi-field-of-view strategy for image-based outcome prediction of multi-parametric estrogen receptor-positive breast cancer histopathology: Comparison to Oncotype DX

Contact Info

Product

Resources

About