scholarly journals Noninvasive KRAS mutation estimation in colorectal cancer using a deep learning method based on CT imaging

2020 ◽  
Author(s):  
kan He ◽  
Xiaoming Liu ◽  
Mingyang Li ◽  
Xueyan Li ◽  
Hualin Yang ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Deep Learning ◽  
Kras Mutation ◽  
Ct Images ◽  
Ct Imaging ◽  
Kras Mutations ◽  
Training Cohort ◽  
Portal Venous Phase ◽  
Contrast Enhanced Ct ◽  
Pre Treatment

Abstract ABSTRACT Background: The detection of Kirsten rat sarcoma viral oncogene homolog ( KRAS )gene mutations in colorectal cancer (CRC) is key to the optimal design of individualized therapeutic strategies. The noninvasive prediction of the KRAS status in CRC is challenging. Deep learning (DL) in medical imaging has shown its high performance in diagnosis, classification, and prediction in recent years. In this paper, we investigated predictive performance by using a DL method with a residual neural network ( ResNet ) to estimate the KRAS mutation status in CRC patients based on pre-treatment contrast-enhanced CT imaging. Methods: We have collected a dataset consisting of 157 patients with pathology-confirmed CRC who were divided into a training cohort (n = 117) and a testing cohort (n = 40). We developed an ResNet model that used portal venous phase CT images to estimate KRAS mutations in the axial, coronal, and sagittal directions of the training cohort and evaluated the model in the testing cohort. Several groups of expended region of interest （ROI）patches were generated for the ResNet model，to explore whether tissues around the tumor can contribute to cancer assessment. We also explored a radiomics model with the random forest classifier (RFC) to predict KRAS mutations and compared it with the DL model. Results: The ResNet model in the axial direction achieved the higher area under the curve (AUC) value (0.90) in the testing cohort and peaked at 0.93 with an input of “ROI and 20-pixel” surrounding area. AUC of radiomics model in testing cohorts were 0.818. In comparison, the ResNet model showed better predictive ability . Conclusions: Our experiments reveal that the computerized assessment of the pre-treatment CT images of CRC patients using a DL model has the potential to precisely predict KRAS mutations. This new model has the potential to assist in noninvasive KRAS mutation estimation. Keywords: Colorectal Neoplasm, Mutation, Deep Learning

scholarly journals Noninvasive KRAS mutation estimation in colorectal cancer using a deep learning method based on routine CT imaging

2020 ◽  
Author(s):  
kan He ◽  
Xiaoming Liu ◽  
Mingyang Li ◽  
Xueyan Li ◽  
Hualin Yang ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Deep Learning ◽  
Kras Mutation ◽  
Validation Cohort ◽  
Ct Images ◽  
Ct Imaging ◽  
Kras Mutations ◽  
Training Cohort ◽  
Contrast Enhanced Ct ◽  
Pre Treatment

Abstract Background: The detection of KRAS gene mutations in colorectal cancer (CRC) is key to the optimal design of individualized therapeutic strategies. The noninvasive prediction of the KRAS status in CRC is challenging. Deep learning (DL) in medical imaging has shown its high performance in diagnosis, classification, and prediction in recent years. In this paper, we investigated predictive performance by using a DL method with a residual neural network ( ResNet ) to estimate the KRAS mutation status in CRC patients based on routine pre-treatment contrast-enhanced CT imaging. Methods: We have collected a dataset consisting of 157 patients with pathology-confirmed CRC who were randomly divided into a training cohort (n = 117) and a validation cohort (n = 40). We developed an ResNet model that used portal venous phase CT images to estimate KRAS mutations in the axial, coronal, and sagittal directions of the training cohort and validated the model in the validation cohort. Several groups of expended ROI patches were generated for the ResNet model, to explore whether tissues around the tumor can contribute to cancer assessment. We also explored a radiomics model with the random forest classifier (RFC) to predict KRAS mutations and compared it with the DL model. Results: The ResNet model in the axial direction achieved the higher area under the curve (AUC) value (0.90) in the validation cohort and peaked at 0.93 with an input of “ROI and 20-pixel” surrounding area. In the training cohort, the AUC was 0.945 (sensitivity: 0.75; specificity: 0.94), and in the validation cohort, the AUC was0.818 (sensitivity: 0.70; specificity: 0.85). In comparison, the ResNet model showed better predictive ability . Conclusions: Our experiments reveal that the computerized assessment of the pre-treatment CT images of CRC patients using a DL model has the potential to precisely predict KRAS mutations. This new model has the potential to assist in noninvasive KRAS mutation estimation. Keywords: Colorectal Neoplasm, Mutation, Deep Learning

scholarly journals Noninvasive KRAS mutation estimation in colorectal cancer using a deep learning method based on CT imaging

2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Kan He ◽  
Xiaoming Liu ◽  
Mingyang Li ◽  
Xueyan Li ◽  
Hualin Yang ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Deep Learning ◽  
Kras Mutation ◽  
Ct Imaging ◽  
Learning Method

Heterogeneity of acquired KRAS and EGFR mutations in colorectal cancer patients treated with anti-EGFR monoclonal antibodies.

2013 ◽  
Vol 31 (15_suppl) ◽  
pp. 3512-3512 ◽  
Author(s):  
M. Pia Morelli ◽  
Michael J. Overman ◽  
Arvind Dasari ◽  
Syed Mohammad Ali Kazmi ◽  
Eduardo Vilar Sanchez ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Monoclonal Antibodies ◽  
Kras Mutation ◽  
Egfr Mutation ◽  
Acquired Resistance ◽  
Braf Inhibitor ◽  
Tumor Burden ◽  
Egfr Mutations ◽  
Kras Mutations ◽  
Pre Treatment

3512 Background: Although KRAS and EGFR extracellular domain acquired mutations were detected in two small cohorts and correlated with acquired resistance to anti-EGFR monoclonal antibodies (MAb), the frequency, co-occurrence, and distribution of these acquired mutations is unknown. In this study we evaluated the presence of acquired KRAS and EGFR mutations in cfDNA from CRC patients (pts) treated with anti-EGFR monoclonal antibody. Methods: Plasma was collected from EGFR-MAb refractory mCRC pts as part of the ATTACC (Assessment of Targeted Therapies Against Colorectal Cancer) program. Eligible pts had documentation of pre-treatment KRAS wild type tumor. The cfDNA was extracted from the plasma and analyzed by BEAMing technology for acquired KRAS and EGFR mutation. Results: The plasma from 55 patients was analyzed for EGFR and KRAS mutation. The S492R EGFR mutation was detected in 4 pts (7%) treated with cetuximab. Acquired KRAS mutations were detected in 26 of the 55 KRAS wt samples analyzed (47%). Although codon 61 and 146 mutations are rare in untreated CRCs (2% and 1% of the MDACC population, respectively), these atypical KRAS mutations predominated in acquired resistance (Q61H=33% and A146T=10%). Mutations in more than one KRAS codon are exceedingly rare in the primary tumor. In our study we detected more than one KRAS or EGFR mutation in 30% of the population (p<0.001), suggesting the development of multiple independent clones in individual patients. Compared to 8 patients with known KRAS mutations, the average number of mutant reads in the 26 patients with acquired mutation was substantially lower (p<0.01) despite similar tumor burden. Of note, acquired concomitant KRAS mutations were also found in a BRAF V600 mutant patient previously treated with anti-EGFR MAb and a BRAF inhibitor. Conclusions: KRAS and EGFR acquired mutation are present at low concentrations in cfDNA from mCRC pts refractory to anti-EGFR MAb and they are not mutually exclusive, suggesting heterogeneity of the resistant clones. Anti-EGFR MAb refractory patients showed a higher incidence of atypical KRAS mutation and higher incidence of multiple codon KRAS mutations compared with overall CRC patient.

INVESTIGATION KRAS MUTATION IN CIRCULATION TUMOR DNA IN DIFFERENT STAGES OF COLORECTAL CANCER

2019 ◽  
Vol 65 (5) ◽  
pp. 701-707
Author(s):  
Vitaliy Shubin ◽  
Yuriy Shelygin ◽  
Sergey Achkasov ◽  
Yevgeniy Rybakov ◽  
Aleksey Ponomarenko ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Plasma Volume ◽  
Kras Mutation ◽  
Stage Iv ◽  
Circulating Tumor Dna ◽  
Stage Ii ◽  
Kras Gene ◽  
Kras Mutations ◽  
Droplet Pcr ◽  
Tumor Dna

To determine mutations in the plasma KRAS gene in patients with colorectal cancer was the aim of this study. The material was obtained from 44 patients with colorectal cancer of different stages (T1-4N0-2bM0-1c). Plasma for the presence of KRAS gene mutation in circulating tumor DNA was investigated using digital droplet polymerase chain reaction (PCR). KRAS mutations in circulating tumor DNA isolated from 1 ml of plasma were detected in 13 (30%) patients with cancer of different stages. Of these, with stage II, there were 3 patients, with III - 5 and with IV - 5. Patients who did not have mutations in 1 ml of plasma were analyzed for mutations of KRAS in circulating tumor DNA isolated from 3 ml of plasma. Five more patients with KRAS mutations were found with II and III stages. The highest concentrations of circulating tumor DNA with KRAS mutation were found in patients with stage IV. The increase in plasma volume to 3 ml did not lead to the identification of mutations in I stage. This study showed that digital droplet PCR allows identification of circulating tumor DNA with the KRAS mutations in patients with stage II-IV of colon cancer. The results can be used to determine the degree of aggressiveness of the tumor at different stages of the disease, but not the 1st, and it is recommended to use a plasma volume of at least 3 ml.

scholarly journals Integrating Machine/Deep Learning Methods and Filtering Techniques for Reliable Mineral Phase Segmentation of 3D X-ray Computed Tomography Images

Energies ◽  
2021 ◽  
Vol 14 (15) ◽  
pp. 4595
Author(s):  
Parisa Asadi ◽  
Lauren E. Beckingham
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Random Forest ◽  
Ct Images ◽  
Ct Imaging ◽  
Learning Method ◽  
Learning Methods ◽  
X Ray ◽  
Machine Learning Methods ◽  
Filtering Techniques

X-ray CT imaging provides a 3D view of a sample and is a powerful tool for investigating the internal features of porous rock. Reliable phase segmentation in these images is highly necessary but, like any other digital rock imaging technique, is time-consuming, labor-intensive, and subjective. Combining 3D X-ray CT imaging with machine learning methods that can simultaneously consider several extracted features in addition to color attenuation, is a promising and powerful method for reliable phase segmentation. Machine learning-based phase segmentation of X-ray CT images enables faster data collection and interpretation than traditional methods. This study investigates the performance of several filtering techniques with three machine learning methods and a deep learning method to assess the potential for reliable feature extraction and pixel-level phase segmentation of X-ray CT images. Features were first extracted from images using well-known filters and from the second convolutional layer of the pre-trained VGG16 architecture. Then, K-means clustering, Random Forest, and Feed Forward Artificial Neural Network methods, as well as the modified U-Net model, were applied to the extracted input features. The models’ performances were then compared and contrasted to determine the influence of the machine learning method and input features on reliable phase segmentation. The results showed considering more dimensionality has promising results and all classification algorithms result in high accuracy ranging from 0.87 to 0.94. Feature-based Random Forest demonstrated the best performance among the machine learning models, with an accuracy of 0.88 for Mancos and 0.94 for Marcellus. The U-Net model with the linear combination of focal and dice loss also performed well with an accuracy of 0.91 and 0.93 for Mancos and Marcellus, respectively. In general, considering more features provided promising and reliable segmentation results that are valuable for analyzing the composition of dense samples, such as shales, which are significant unconventional reservoirs in oil recovery.

scholarly journals Value of contrast-enhanced CT texture analysis in predicting IDH mutation status of intrahepatic cholangiocarcinoma

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Yong Zhu ◽  
Yingfan Mao ◽  
Jun Chen ◽  
Yudong Qiu ◽  
Yue Guan ◽  
...  
Keyword(s):  
Texture Analysis ◽  
Ct Images ◽  
Textural Features ◽  
Mutation Status ◽  
Portal Venous Phase ◽  
Contrast Enhanced Ct ◽  
Contrast Enhanced ◽  
Enhanced Ct ◽  
Venous Phase ◽  
Ct Texture Analysis

AbstractTo explore the value of contrast-enhanced CT texture analysis in predicting isocitrate dehydrogenase (IDH) mutation status of intrahepatic cholangiocarcinomas (ICCs). Institutional review board approved this study. Contrast-enhanced CT images of 138 ICC patients (21 with IDH mutation and 117 without IDH mutation) were retrospectively reviewed. Texture analysis was performed for each lesion and compared between ICCs with and without IDH mutation. All textural features in each phase and combinations of textural features (p < 0.05) by Mann–Whitney U tests were separately used to train multiple support vector machine (SVM) classifiers. The classification generalizability and performance were evaluated using a tenfold cross-validation scheme. Among plain, arterial phase (AP), portal venous phase (VP), equilibrium phase (EP) and Sig classifiers, VP classifier showed the highest accuracy of 0.863 (sensitivity, 0.727; specificity, 0.885), with a mean area under the receiver operating characteristic curve of 0.813 in predicting IDH mutation in validation cohort. Texture features of CT images in portal venous phase could predict IDH mutation status of ICCs with SVM classifier preoperatively.

scholarly journals Liver fibrosis staging by deep learning: a visual-based explanation of diagnostic decisions of the model

2021 ◽  
Author(s):  
Yunchao Yin ◽  
Derya Yakar ◽  
Rudi A. J. O. Dierckx ◽  
Kim B. Mouridsen ◽  
Thomas C. Kwee ◽  
...  
Keyword(s):  
Deep Learning ◽  
Liver Fibrosis ◽  
Liver Parenchyma ◽  
Ct Images ◽  
Fibrosis Stage ◽  
Contrast Enhanced Ct ◽  
Contrast Enhanced ◽  
Enhanced Ct ◽  
Liver Surface ◽  
Fibrosis Staging

Abstract Objectives Deep learning has been proven to be able to stage liver fibrosis based on contrast-enhanced CT images. However, until now, the algorithm is used as a black box and lacks transparency. This study aimed to provide a visual-based explanation of the diagnostic decisions made by deep learning. Methods The liver fibrosis staging network (LFS network) was developed at contrast-enhanced CT images in the portal venous phase in 252 patients with histologically proven liver fibrosis stage. To give a visual explanation of the diagnostic decisions made by the LFS network, Gradient-weighted Class Activation Mapping (Grad-cam) was used to produce location maps indicating where the LFS network focuses on when predicting liver fibrosis stage. Results The LFS network had areas under the receiver operating characteristic curve of 0.92, 0.89, and 0.88 for staging significant fibrosis (F2–F4), advanced fibrosis (F3–F4), and cirrhosis (F4), respectively, on the test set. The location maps indicated that the LFS network had more focus on the liver surface in patients without liver fibrosis (F0), while it focused more on the parenchyma of the liver and spleen in case of cirrhosis (F4). Conclusions Deep learning methods are able to exploit CT-based information from the liver surface, liver parenchyma, and extrahepatic information to predict liver fibrosis stage. Therefore, we suggest using the entire upper abdomen on CT images when developing deep learning–based liver fibrosis staging algorithms. Key Points • Deep learning algorithms can stage liver fibrosis using contrast-enhanced CT images, but the algorithm is still used as a black box and lacks transparency. • Location maps produced by Gradient-weighted Class Activation Mapping can indicate the focus of the liver fibrosis staging network. • Deep learning methods use CT-based information from the liver surface, liver parenchyma, and extrahepatic information to predict liver fibrosis stage.

scholarly journals IMPACT OF KRAS MUTATIONS IN CLINICAL FEATURES IN COLORECTAL CANCER

2020 ◽  
Vol 33 (3) ◽  
Author(s):  
Renato Morato ZANATTO ◽  
Gianni SANTOS ◽  
Júnea Caris OLIVEIRA ◽  
Eduardo Marcucci PRACUCHO ◽  
Adauto José Ferreira NUNES ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Overall Survival ◽  
Kras Mutation ◽  
Direct Sequencing ◽  
Colorectal Carcinogenesis ◽  
Kras Mutations ◽  
Primary Tumor Site ◽  
Exon 2 ◽  
Metastatic Site ◽  
Colorectal Cancer Patients

ABSTRACT Background: KRAS mutations are important events in colorectal carcinogenesis, as well as negative predictors of response to EGFR inhibitors treatment. Aim: To investigate the association of clinical-pathological features with KRAS mutations in colorectal cancer patients treated. Methods: Data from 69 patients with colorectal cancer either metastatic at diagnosis or later, were retrospectively analyzed. The direct sequencing and pyrosequencing techniques were related to KRAS exon 2. The mutation diagnosis and its type were determined. Results: KRAS mutation was identified in 43.4% of patients. The most common was c.35G>T (p.G12V), c.35G>A (p.G12D) and c.38G>A (p.G13D). No correlation was found between KRAS mutation and age (p=0.646) or gender (p=0.815). However, mutated group had higher CEA levels at admission (p=0.048) and codon 13 mutation was associated with involvement of more than one metastatic site in disease progression (p=0.029). Although there was no association between primary tumor site and mutation diagnosis (p=0.568), primary colon was associated with worse overall survival (p=0.009). Conclusion: The KRAS mutation was identified in almost half of patients. Mutated KRAS group had higher levels of CEA at admission and the mutation at codon 13 was associated with involvement of more than one metastatic site in the course of the disease. Colon disease was associated with the worst overall survival.

scholarly journals No Duplicate KRAS Mutation is Identified on the Same Allele in Gastric or Colorectal Cancer Cells with Multiple KRAS Mutations

2007 ◽  
Vol 35 (4) ◽  
pp. 450-457 ◽  
Author(s):  
K Kimura ◽  
T Nagasaka ◽  
N Hoshizima ◽  
H Sasamoto ◽  
K Notohara ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Gastric Cancer ◽  
Cancer Cells ◽  
Kras Mutation ◽  
Direct Sequencing ◽  
Gastric Cancer Cells ◽  
Kras Mutations ◽  
Colorectal Cancer Cells ◽  
Pcr Products ◽  
Codon 12 And 13

Codon 12 and 13 mutations in 170 colorectal cancer (CRC) and 66 gastric cancer (GC) specimens were analysed by an ‘enriched’ polymerase chain reaction–restriction fragment length polymorphism (PCR–RFLP) method. All identified mutations were verified by direct sequencing of the second PCR products. Among the 170 CRC specimens, mutations were identified in 47 (28%) and 13 (7.6%) cases in codons 12 and 13, respectively. In the 66 GC specimens examined, however, mutations in codons 12 and 13 were only detected in two (3.0%) and one (1.5%) cases, respectively. Mutations in both codon 12 and 13 were found in 3/170 (1.8%) CRCs and 1/66 (1.5%) GCs. Duplicate mutations were never identified in the same allele, which was confirmed by direct sequencing of the second amplified products. The majority of colorectal and gastric cancer cells with KRAS mutations are homogeneous because they have the same KRAS mutation. A few colorectal or gastric cancers, however, showed heterogeneity, as verified by the fact that single mutations were identified in the same allele.

BRAF and KRAS mutations as additional risk factors in the context of clinical parameters of patients with colorectal cancer.

2013 ◽  
Vol 31 (15_suppl) ◽  
pp. 3522-3522
Author(s):  
Vlad Calin Popovici ◽  
Eva Budinska ◽  
Arnaud Roth ◽  
Fred Bosman ◽  
Sabine Tejpar ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Overall Survival ◽  
Braf Mutation ◽  
Kras Mutation ◽  
Prognostic Value ◽  
Tumor Site ◽  
Kras Mutations ◽  
P Values ◽  
Significance Level ◽  
Survival After Relapse

3522 Background: The BRAF and KRAS mutations have been proposed as prognostic markers in colorectal cancer (CRC). Of them, only the BRAF V600E mutation has been validated as prognostic for overall survival and survival after relapse, while the value of KRAS mutation is still unclear. Methods: In a cohort of 1423 stage II-III patients from the PETACC-3 clinical trial, the prognostic value of the BRAF and KRAS mutations was retrospectively assessed in all possible stratifications defined by the 5 factors (T and N stage, tumor site and grade, and microsatellite instability status), by log rank test for overall survival (OS), relapse-free survival (RFS), and survival after relapse (SAR). The presence of interactions was tested by Wald test. The significance level was set to 0.01 for Bonferroni-adjusted p-values (P*), and a second level for a trend towards statistical significance was set at 0.05 for unadjusted p-values (P). Results: BRAF mutation was a marker of poor OS only in microsatellite stable (MSS) and left-sided tumors, with no prognostic value in microsatellite instable (MSI-H) or right-sided tumors. In MSS/left-sided tumors, BRAF mutation represents a marker of higher risk than previously reported: OS HR=6.4 [95% CI: 3.6-11.5], P* < 0.0001. For SAR, BRAF was prognostic in more stratifications, with higher risk in MSS/left-sided tumors (HR=3.9 [95% CI: 2.1-7.2], P* = 0.0002) than in MSS/right-sided (HR=2.3 [95% CI: 1.2-4.4], P=0.01). A novel observation was that BRAF mutation was prognostic also for RFS, but only in MSS/left-sided tumors (HR=3.6 [95% CI:2-6.3], P*=0.0005]). Additionally, heterogeneity in OS and RFS among BRAF mutants was observed. In general, KRAS mutation did not reach the significance level required, but showed a trend to become a prognostic marker for RFS in MSS tumors with early lymph node involvement (N1) (HR=1.6 [95% CI:1.1-2.2], P=0.01). Conclusions: The prognostic utility of the BRAF and KRAS mutations has to be interpreted in the context of other factors. For the BRAF mutation, a clear interaction with MSI status and tumor site was observed, with BRAF mutation indicating a much higher risk in MSS/left-sided tumors than previously considered.

Sign in / Sign up

Export Citation Format

Share Document