Classifications of Multispectral Colorectal Cancer Tissues Using Convolution Neural Network

Haj-Hassan, Hawraa; Chaddad, Ahmad; Harkouss, Youssef; Desrosiers, Christian; Toews, Matthew; Tanougast, Camel

doi:10.4103/jpi.jpi_47_16

Cited by 57 publications

(37 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There has been an upsurge in studies related to using image texture features or “radiomics” for computer-assisted diagnosis of digital WSI in the recent years ( 10 , 12 , 21 , 23 , 39 , 40 ). In addition to providing diagnostic information, such analysis may also reveal insights into the underlying biology of cancer, making further investigation into radiomic assessment of CRC a priority.…”

Section: Discussionmentioning

confidence: 99%

“…To our knowledge, this is the first work to investigate the link between scale textures in multispectral images and their association with stages of CRC malignancy. Multiscale texture features derived from multispectral images encode thousands of invisible patterns that are complementary to traditional texture based on GLCM, local binary patterns, Laplacian of Gaussian filter, deep learning ( 10 – 12 , 21 ), or shape measurements ( 22 ). In this context, multiscale texture features measure the heterogeneity in the images of the PT and could be one of the radiomic techniques.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Radiomics Evaluation of Histological Heterogeneity Using Multiscale Textures Derived From 3D Wavelet Transformation of Multispectral Images

2018

Self Cite

View full text Add to dashboard Cite

PurposeColorectal cancer (CRC) is markedly heterogeneous and develops progressively toward malignancy through several stages which include stroma (ST), benign hyperplasia (BH), intraepithelial neoplasia (IN) or precursor cancerous lesion, and carcinoma (CA). Identification of the malignancy stage of CRC pathology tissues (PT) allows the most appropriate therapeutic intervention.MethodsThis study investigates multiscale texture features extracted from CRC pathology sections using 3D wavelet transform (3D-WT) filter. Multiscale features were extracted from digital whole slide images of 39 patients that were segmented in a pre-processing step using an active contour model. The capacity for multiscale texture to compare and classify between PTs was investigated using ANOVA significance test and random forest classifier models, respectively.Results12 significant features derived from the multiscale texture (i.e., variance, entropy, and energy) were found to discriminate between CRC grades at a significance value of p < 0.01 after correction. Combining multiscale texture features lead to a better predictive capacity compared to prediction models based on individual scale features with an average (±SD) classification accuracy of 93.33 (±3.52)%, sensitivity of 88.33 (± 4.12)%, and specificity of 96.89 (± 3.88)%. Entropy was found to be the best classifier feature across all the PT grades with an average of the area under the curve (AUC) value of 91.17, 94.21, 97.70, 100% for ST, BH, IN, and CA, respectively.ConclusionOur results suggest that multiscale texture features based on 3D-WT are sensitive enough to discriminate between CRC grades with the entropy feature, the best predictor of pathology grade.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Radiomics Evaluation of Histological Heterogeneity Using Multiscale Textures Derived From 3D Wavelet Transformation of Multispectral Images

2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…The analysis of multi-textural descriptors and CNN features for medical spectral imaging (prostate and colorectal) has been investigated in previous studies. We have evaluated our multi-textural ensemble based classification approach with some recently published studies [ 6 , 7 , 24 , 26 ] for which the dataset was available to us. This dataset consists of three classes: benign hyperplasia (BH), intraepithelial neoplasia (IN) and carcinoma (CA).…”

Section: Resultsmentioning

confidence: 99%

“…The segmentation was performed using the snake algorithm followed by feature extraction using gray-level co-occurrence matrix (GLCM), the Laplacian of Gaussian (LoG) and discrete wavelet transform. In [ 26 ], convolutional neural network (CNN) was employed to learn the hierarchical features from the gland segmented multispectral colorectal images. In [ 27 ], authors presented a comparison between MSI and RGB images by performing three class classification using a combination of texture and morphological features extracted from the gland nuclei.…”

Section: Related Workmentioning

confidence: 99%

Using spectral imaging for the analysis of abnormalities for colorectal cancer: When is it helpful?

2018

View full text Add to dashboard Cite

The spectral imaging technique has been shown to provide more discriminative information than the RGB images and has been proposed for a range of problems. There are many studies demonstrating its potential for the analysis of histopathology images for abnormality detection but there have been discrepancies among previous studies as well. Many multispectral based methods have been proposed for histopathology images but the significance of the use of whole multispectral cube versus a subset of bands or a single band is still arguable. We performed comprehensive analysis using individual bands and different subsets of bands to determine the effectiveness of spectral information for determining the anomaly in colorectal images. Our multispectral colorectal dataset consists of four classes, each represented by infra-red spectrum bands in addition to the visual spectrum bands. We performed our analysis of spectral imaging by stratifying the abnormalities using both spatial and spectral information. For our experiments, we used a combination of texture descriptors with an ensemble classification approach that performed best on our dataset. We applied our method to another dataset and got comparable results with those obtained using the state-of-the-art method and convolutional neural network based method. Moreover, we explored the relationship of the number of bands with the problem complexity and found that higher number of bands is required for a complex task to achieve improved performance. Our results demonstrate a synergy between infra-red and visual spectrum by improving the classification accuracy (by 6%) on incorporating the infra-red representation. We also highlight the importance of how the dataset should be divided into training and testing set for evaluating the histopathology image-based approaches, which has not been considered in previous studies on multispectral histopathology images.

show abstract

“…ANNs have seen widespread success in predicting and classifying data in multiple cancer subtypes such as early detection [ 11 ], prediction of long term survival [ 12 ] and biomarker discovery in breast cancer [ 10 , 13 ], classifying colorectal cancer tissues [ 14 ] and discriminating between benign and malignant endothelial lesions [ 15 ]. Thus, we are confident that they will see similar success in AD.…”

Section: Introductionmentioning

confidence: 99%

An Artificial Neural Network Integrated Pipeline for Biomarker Discovery Using Alzheimer's Disease as a Case Study

Zafeiris

Rutella

Ball

2018

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

The field of machine learning has allowed researchers to generate and analyse vast amounts of data using a wide variety of methodologies. Artificial Neural Networks (ANN) are some of the most commonly used statistical models and have been successful in biomarker discovery studies in multiple disease types. This review seeks to explore and evaluate an integrated ANN pipeline for biomarker discovery and validation in Alzheimer's disease, the most common form of dementia worldwide with no proven cause and no available cure. The proposed pipeline consists of analysing public data with a categorical and continuous stepwise algorithm and further examination through network inference to predict gene interactions. This methodology can reliably generate novel markers and further examine known ones and can be used to guide future research in Alzheimer's disease.

show abstract

Classifications of Multispectral Colorectal Cancer Tissues Using Convolution Neural Network

Cited by 57 publications

References 28 publications

Radiomics Evaluation of Histological Heterogeneity Using Multiscale Textures Derived From 3D Wavelet Transformation of Multispectral Images

Radiomics Evaluation of Histological Heterogeneity Using Multiscale Textures Derived From 3D Wavelet Transformation of Multispectral Images

Using spectral imaging for the analysis of abnormalities for colorectal cancer: When is it helpful?

An Artificial Neural Network Integrated Pipeline for Biomarker Discovery Using Alzheimer's Disease as a Case Study

Contact Info

Product

Resources

About