Analysis of KRAS Mutation Status Prediction Model for Colorectal Cancer Based on Medical Imaging

This study retrospectively included some patients with colorectal cancer diagnosed by histopathology, to explore the feasibility of CT medical image texture analysis in predicting KRAS gene mutations in patients with colorectal cancer. Before any surgical procedure, all patients received an enhanced CT scan of the abdomen and pelvis, as well as genetic testing. To define patient groups, divide all patients into test and validation sets based on the order of patient enrollment. A radiologist took a look at the plain axial CT image of the tumor, as well as the portal vein CT image, at the corresponding level. The physician points the computer’s cursor to the relevant area in the image, and TexRAD software programs together texture parameters based on various spatial scale factors, also known as total mean, total variance, statistical entropy, overall total average, mean total, positive mean, skewness value, kurtosis value, and general skewness. Using the same method again two weeks later, the observer and another physician measured the image of each patient again to see if the method was consistent between observers. With regard to clinical information, the KRAS gene mutation group and the wild group of participants in the test set and validation set each had values for the texture parameter. In a study of patients with colorectal cancer, the results demonstrated that CT texture parameters were correlated with the presence of the KRAS gene mutation. The best CT prediction model includes the values of the medium texture image’s slope and the other CT fine texture image’s value of entropy, the medium texture image’s slope and kurtosis, and the medium texture image’s mean and the other CT fine texture image’s value of entropy. Regardless of the training set or the validation set, patients with and without KRAS gene mutations did not differ significantly in clinical characteristics. This method can be used to identify mutations in the KRAS gene in patients with colorectal cancer, making it practical to implement CT medical image texture analysis technology for that purpose.

Download Full-text

Detection of KRAS Gene mutations in paraguayan patients with colorectal cancer

Anales de la Facultad de Ciencias Médicas (Asunción) ◽

10.18004/anales/2021.054.03.33 ◽

2021 ◽

Vol 54 (3) ◽

pp. 33-40

Author(s):

Hugo Torio ◽

Ingrid Rodríguez ◽

Hugo Molina ◽

Blás Antonio Romero ◽

Antonieta Rojas ◽

...

Keyword(s):

Colorectal Cancer ◽

Gene Mutations ◽

Kras Gene

Download Full-text

Novel KRAS Gene Mutations in Sporadic Colorectal Cancer

PLoS ONE ◽

10.1371/journal.pone.0113350 ◽

2014 ◽

Vol 9 (11) ◽

pp. e113350 ◽

Cited By ~ 7

Author(s):

Walid M. Naser ◽

Mohamed A. Shawarby ◽

Dalal M. Al-Tamimi ◽

Arun Seth ◽

Abdulaziz Al-Quorain ◽

...

Keyword(s):

Colorectal Cancer ◽

Gene Mutations ◽

Sporadic Colorectal Cancer ◽

Kras Gene

Download Full-text

Effectiveness of circulating tumor DNA for detection of KRAS gene mutations in colorectal cancer patients: a meta-analysis

OncoTargets and Therapy ◽

10.2147/ott.s123954 ◽

2017 ◽

Vol Volume 10 ◽

pp. 945-953 ◽

Cited By ~ 15

Author(s):

Yi-xin Hao ◽

Qiang Fu ◽

Yan-Yan Guo ◽

Ming Ye ◽

Hui-Xia Zhao ◽

...

Keyword(s):

Colorectal Cancer ◽

Cancer Patients ◽

Meta Analysis ◽

Gene Mutations ◽

Circulating Tumor Dna ◽

Kras Gene ◽

Colorectal Cancer Patients ◽

Tumor Dna

Download Full-text

Application of Neural Networks for the Classification of Diffuse Liver Disease by Quantitative Echography

Ultrasonic Imaging ◽

10.1177/016173469301500302 ◽

1993 ◽

Vol 15 (3) ◽

pp. 205-217 ◽

Cited By ~ 5

Author(s):

M.S. klein Gebbinck ◽

J.T.M. Verhoeven ◽

J.M. Thijssen ◽

T.E. Schouten

Keyword(s):

Neural Networks ◽

Liver Disease ◽

Image Texture ◽

Attractive Alternative ◽

Diffuse Liver Disease ◽

Texture Parameters ◽

Number Of Patients ◽

Test Sets ◽

Validation Set

Three different methods were investigated to determine their ability to detect and classify various categories of diffuse liver disease. A statistical method, i.e., discriminant analysis, a supervised neural network called backpropagation and a nonsupervised, self-organizing feature map were examined. The investigation was performed on the basis of a previously selected set of acoustic and image texture parameters. The limited number of patients was successfully extended by generating additional but independent data with identical statistical properties. The generated data were used for training and test sets. The final test was made with the original patient data as a validation set. It is concluded that neural networks are an attractive alternative to traditional statistical techniques when dealing with medical detection and classification tasks. Moreover, the use of generated data for training the networks and the discriminant classifier has been shown to be justified and profitable.

Download Full-text

CLINICAL CHARACTERISTICS OF COLORECTAL CANCER IN PATIENTS WITH EGFR-SIGNALING PATHWAY GENE MUTATIONS

Ulyanovsk Medico-biological Journal ◽

10.34014/2227-1848-2019-1-60-67 ◽

2019 ◽

pp. 60-67

Author(s):

I.A. Bogomolova ◽

I.I. Antoneeva ◽

D.R. Dolgova

Keyword(s):

Colorectal Cancer ◽

Adjuvant Chemotherapy ◽

Clinical Characteristics ◽

Gene Mutations ◽

Egfr Signaling ◽

Braf Gene ◽

Braf Mutations ◽

Kras Gene ◽

Egfr Signaling Pathway ◽

Gene Exon

KRAS, NRAS, BRAF mutations are associated with an unfavorable prognosis for colorectal cancer (CRC). At the same time, there is no single point of view on disease development during adjuvant chemotherapy (ACT). Objective. The authors aimed at studying KRAS, NRAS and BRAF mutations in the tumor and their influence on the clinical characteristics of colorectal cancer development. Materials and Methods. Paraffin blocks of the primary CRC tumor (n=37) were used as the material for the study. Using genomic DNA, isolated from the primary tumor, real-time PCR was used to determine the most common mutations in CRC: KRAS gene (exon 2, codon region 12–13), NRAS gene (exon 3, codon region 61), B6F V600E gene. Results. The results of genotyping of DNA samples isolated from the primary CRC tumor paraffin blocks showed that BRAF gene mutations were detected in 8.2 % of cases, NRAS gene mutations were detected in 5.4 % of cases, and KRAS gene mutations were detected in 37.8 % of cases. The authors didn’t reveal any dependencies of the mutation distribution on patients’ gender and age. The examined mutations were more common in adenocarcinomas of high and moderate degrees of differentiation. The relapse-free period after ACT in patients with identified KRAS, NRAS, BRAF gene mutations is significantly less than in those without mutations. Conclusion. The findings suggest that EGFR signaling pathway mutations (KRAS, NRAS and BRAF) increase the risk of disease recurrence and are an unfavorable prognostic factor. Keywords: colorectal cancer, NRAS, KRAS, BRAF mutations, adjuvant chemotherapy.

Download Full-text

KRAS mutation is highly predictive of cetuximab resistance in metastatic colorectal cancer

Journal of Clinical Oncology ◽

10.1200/jco.2007.25.18_suppl.10502 ◽

2007 ◽

Vol 25 (18_suppl) ◽

pp. 10502-10502 ◽

Cited By ~ 7

Author(s):

F. Di Fiore ◽

F. Le Pessot ◽

A. Lamy ◽

F. Charbonnier ◽

J. Sabourin ◽

...

Keyword(s):

Colorectal Cancer ◽

Metastatic Colorectal Cancer ◽

Predictive Factors ◽

Kras Mutation ◽

Copy Number ◽

Gene Copy Number ◽

Gene Mutations ◽

Gene Copy ◽

Kras Gene ◽

Egfr Gene

10502 Background: In metastatic colorectal cancer (MCRC), no molecular predictive markers to cetuximab response have been yet established. The aim was to evaluate whether KRAS gene mutations, EGFR immunochemistery (IHC) and EGFR gene copy number correlate with response to cetuximab. Methods: 59 patients with MCRC treated by cetuximab between July 2004 and December 2005 were retrospectively included. Clinical data were collected and tumour response was evaluated according to RECIST criteria. EGFR IHC was performed using the Dako kit. The EGFR gene copy number was determined by FISH (Fluorescence in-Situ Hybridization). Detection of KRAS gene mutations on exon 2 was performed by sequencing of extracted paraffin-embedded DNA and then by 2 methods, SNaPshot and PCR-LCR, specifically developed to detect small fractions of mutated tumor cells. Response to cetuximab was studied according to clinical data, IHC, FISH and KRAS mutation analysis using the Fischer exact test. Predictive factors of response were determined by logistic regression. Skin reactions were collected but not considered for this analysis as regards the lack of accurate grading in a retrospective study. Times to progression (TTP) were calculated using the Kaplan-Meier method and compared with log-rank test. Results: 12 patients (20.3%) responded to cetuximab (2 patients with complete response and 10 patients with partial response), 19 (32.2%) had stable disease and 28 (47.5%) were in disease progression. A KRAS mutation was detected in 22/59 tumours and, in 6 cases, was missed by sequencing analysis but detected using the SNaPshot and PCR-LCR assays. No KRAS mutation was found in responders patients. KRAS mutation was associated with disease progression (p = 0.0005) and TTP was significantly decreased in mutated KRAS patients (3 vs 5.5 months, p = 0.015). There was no correlation between EGFR IHC and cetuximab response. No EGFR gene copy number increase was detected in responders patients. Predictive factors of cetuximab resistance were KRAS mutation (p=0.003; OR:0.10; 95IC:0.22–0.40) and age<60 (p=0.024; OR:0.13; 95IC:0.02–0.77). Conclusions: KRAS mutation is highly predictive of cetuximab resistance in MCRC. Our study also highlights the need of sensitive methods to ensure an efficient mutation detection. No significant financial relationships to disclose.

Download Full-text

1322 Diagnostic of KRAS gene mutations in colorectal cancer: evaluation of direct sequencing, pyrosequencing and allele specific amplification

European Journal of Cancer Supplements ◽

10.1016/s1359-6349(09)70495-1 ◽

2009 ◽

Vol 7 (2) ◽

pp. 145 ◽

Cited By ~ 1

Author(s):

P.J. Lamy ◽

F. Montels ◽

A.C. Servanton ◽

M. Ychou ◽

E. Crapez

Keyword(s):

Colorectal Cancer ◽

Direct Sequencing ◽

Gene Mutations ◽

Kras Gene ◽

Allele Specific ◽

Specific Amplification

Download Full-text

3014 (Presidential session, Tue 25 Sep 12.30–14.30) ORAL Association of somatic KRAS gene mutations and clinical outcome in patients (pts) with metastatic colorectal cancer (mCRC) receiving panitumumab monotherapy

European Journal of Cancer Supplements ◽

10.1016/s1359-6349(07)70942-4 ◽

2007 ◽

Vol 5 (4) ◽

pp. 239 ◽

Cited By ~ 11

Author(s):

D. Freeman ◽

T. Juan ◽

N.J. Meropol ◽

J.R. Hecht ◽

J. Berlin ◽

...

Keyword(s):

Colorectal Cancer ◽

Clinical Outcome ◽

Metastatic Colorectal Cancer ◽

Gene Mutations ◽

Kras Gene ◽

Presidential Session

Download Full-text

Application of image texture analysis for varietal classification of barley

International Agrophysics ◽

10.2478/v10247-012-0012-z ◽

2012 ◽

Vol 26 (1) ◽

pp. 81-90 ◽

Cited By ~ 8

Author(s):

P. Zapotoczny

Keyword(s):

Discriminant Analysis ◽

Texture Analysis ◽

Classification Accuracy ◽

Image Texture ◽

Image Texture Analysis ◽

Texture Parameters ◽

Varietal Classification ◽

Variable Reduction ◽

Barley Kernel

Application of image texture analysis for varietal classification of barleyThis paper presents the results of a study into the use of the texture parameters of barley kernel images in varietal classification. A total of more than 270 textures have been calculated from the surface of single kernels and bulk grain. The measurements were performed in four channels from a 24 bit image. The results were processed statistically by variable reduction and general discriminant analysis. Classification accuracy was more than 99%.

Download Full-text