Artificial neural networks distinguish among subtypes of neoplastic colorectal lesions

Selaru, Florin M.; Xu, Yan; Yin, Jing; Zou, Tong; Liu, Thomas C.; Mori, Yuriko; Abraham, John M.; Sato, Fumiaki; Wang, Suna; Twigg, Charlie; Olaru, Andreea; Shustova, Valentina; Leytin, Anatoly; Hytiroglou, Prodromos; Shibata, David; Harpaz, Noam; Meltzer, Stephen J.

doi:10.1053/gast.2002.31904

Cited by 124 publications

(67 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gene expression profiles have been used to classify tumours (Bittner et al, 2000;Ramaswamy et al, 2001;Selaru et al, 2002;Shipp et al, 2002), study the biology of tumour progression and metastasis (Birkenkamp-Demtroder et al, 2002;Ramaswamy et al, 2003), predict clinical outcomes Huang et al, 2003;Iizuka et al, 2003), classify drug resistance (Hofmann et al, 2002;Chang et al, 2003) and identify novel drug targets (Marton et al, 1998). As the technology matures, it is pushing towards mainstream clinical application (Gershon, 2004;Jarvis and Centola, 2005;Cardoso et al, 2008).…”

mentioning

confidence: 99%

Analysis of differential gene expression in colorectal cancer and stroma using fluorescence-activated cell sorting purification

et al. 2009

View full text Add to dashboard Cite

Tumour stroma gene expression in biopsy specimens may obscure the expression of tumour parenchyma, hampering the predictive power of microarrays. We aimed to assess the utility of fluorescence-activated cell sorting (FACS) for generating cell populations for gene expression analysis and to compare the gene expression of FACS-purified tumour parenchyma to that of whole tumour biopsies. Single cell suspensions were generated from colorectal tumour biopsies and tumour parenchyma was separated using FACS. Fluorescence-activated cell sorting allowed reliable estimation and purification of cell populations, generating parenchymal purity above 90%. RNA from FACS-purified and corresponding whole tumour biopsies was hybridised to Affymetrix oligonucleotide microarrays. Whole tumour and parenchymal samples demonstrated differential gene expression, with 289 genes significantly overexpressed in the whole tumour, many of which were consistent with stromal gene expression (e.g., COL6A3, COL1A2, POSTN, TIMP2 ). Genes characteristic of colorectal carcinoma were overexpressed in the FACS-purified cells (e.g., HOX2D and RHOB ). We found FACS to be a robust method for generating samples for gene expression analysis, allowing simultaneous assessment of parenchymal and stromal compartments. Gross stromal contamination may affect the interpretation of cancer gene expression microarray experiments, with implications for hypotheses generation and the stability of expression signatures used for predicting clinical outcomes.

show abstract

mentioning

confidence: 99%

Analysis of differential gene expression in colorectal cancer and stroma using fluorescence-activated cell sorting purification

et al. 2009

View full text Add to dashboard Cite

show abstract

“…Investigating gene expression may help understand the interrelation of genotype and phenotype. DNA microarray methods may be used to detect differences in gene expression in various specimens by parallel analysis on a large scale using just one procedure (7)(8)(9)(10)(11)(12)(13)(14)(15)(16). Therefore, DNA microarray techniques have increasingly been applied to the study of gene expression.…”

Section: Discussionmentioning

confidence: 99%

DNA microarray analysis of the gene expression profile of kidney tissue in a type 2 diabetic rat model

Shen

Zhang²,

Zou

et al. 2010

Mol Med Rep

View full text Add to dashboard Cite

Abstract. The aim of this study was to determine differences in the gene expression profile of kidney tissue from type 2 diabetes mellitus (T2D) and control rats using DNA microarray analysis. Total RNA was extracted from the kidney tissue of the T2D and control rats using the original single step method. cDNA retro-transcribed from an equal quantity of mRNA was labeled with Cy5 and Cy3 fluorescence and served as the probes. The mixed probes were hybridized to a DNA microarray. Fluorescence signals were scanned by an ScanArray 4000 laser scanner and further analyzed by QuantArray software. Apoptotic cells were detected in situ using the Roche TUNEL assay. Serum glucose, ApoAI, ApoB, ApoA1/ApoB, cholesterol and triglyceride levels were significantly higher in the T2D rats than in the controls, but there were no significant differences in serum insulin. When the kidney tissue was screened using the DNA microarray, differential expression was found for 41 genes. Five genes in the T2D rats were upregulated by 2-fold compared to the control rats, while 36 genes were down-regulated by 0.5-fold. Moreover, in the renal tubular epithelial cells, there was a significantly greater number of TUNEL-positive cells in the T2D group than in the control group. A total of 41 genes are associated with the occurrence and development of T2D and diabetic nephropathy. The present study suggests that examining differences in gene expression profiles is of benefit to the diagnosis, treatment and prevention of T2d, diabetic nephropathy and other T2d complications.

show abstract

“…Among them are the training of algorithms, such as artificial neural networks (ANNs), to predict colorectal cancer survival based on a number of variables, or the analysis of the colon from endoscopic images, distinguishing between neoplastic lesions subtypes based on complementary DNA microarray data. [5][6][7] Our focus is on machine learning methods that are related to the endoscopic approach of colorectal cancer management.…”

Section: The Basics Of Machine Learning Algorithmsmentioning

confidence: 99%

Computer-Aided Diagnosis in Colorectal Cancer: Current Concepts and Future Prospects

Ioanovici

Feier

Ţilea

et al. 2017

Journal of Interdisciplinary Medicine

View full text Add to dashboard Cite

Colorectal cancer is an important health issue, both in terms of the number of people affected and the associated costs. Colonoscopy is an important screening method that has a positive impact on the survival of patients with colorectal cancer. The association of colonoscopy with computer-aided diagnostic tools is currently under researchers' focus, as various methods have already been proposed and show great potential for a better management of this disease. We performed a review of the literature and present a series of aspects, such as the basics of machine learning algorithms, different computational models as well as their benchmarks expressed through measurements such as positive prediction value and accuracy of detection, and the classification of colorectal polyps. Introducing computer-aided diagnostic tools can help clinicians obtain results with a high degree of confidence when performing colonoscopies. The growing field of machine learning in medicine will have a big impact on patient management in the future.

show abstract

Artificial neural networks distinguish among subtypes of neoplastic colorectal lesions

Cited by 124 publications

References 55 publications

Analysis of differential gene expression in colorectal cancer and stroma using fluorescence-activated cell sorting purification

Analysis of differential gene expression in colorectal cancer and stroma using fluorescence-activated cell sorting purification

DNA microarray analysis of the gene expression profile of kidney tissue in a type 2 diabetic rat model

Computer-Aided Diagnosis in Colorectal Cancer: Current Concepts and Future Prospects

Contact Info

Product

Resources

About