Automated Colorectal Cancer Diagnosis for Whole-Slice Histopathology

Abstract

Abstract. In this study, we propose a computational diagnosis system for detecting the colorectal cancer from histopathological slices.The computational analysis was usually performed on patch level where only a small part of the slice is covered. However, slice-based classification is more realistic for histopathological diagnosis. The developed method combines both textural and structural features from patch images and proposes a two level classification scheme. In the first level, the patches in slices are classified into possible classes (adenomatous, inflamed, cancer and normal) and the distribution of the patches into these classes is considered as the information representing the slices. Then the slices are classified using a logistic linear classifier. In patch level, we obtain the correct classification accuracies of 94.36% and 96.34% for the cancer and normal classes, respectively. However, in slice level, the accuracies of the 79.17% and 92.68% are achieved for cancer and normal classes, respectively.

Magnetic-Resonance-Imaging Texture Analysis Predicts Early Progression in Rectal Cancer Patients Undergoing Neoadjuvant Chemoradiation

“…An early study by Esgiar et al already showed that entropy texture features extracted from GLCM was capable of differentiating between normal and neoplastic tissue [27]. Additionally, by performing color channel histograms, GLCM, and structural features, Kalkan et al achieved an accuracy of 75.15% in the classification of four types of colon tissues: normal, cancerous, adenomatous, and inflammatory [28]. In our study, a higher GLCM Contrast and a lower GLCM Correlation are also in line with the recent results by Chaddad et al, who report the use of TA extracted from multispectral optical microscopy images for the classification of three types of pathological tissues: benign hyperplasia, intraepithelial neoplasia, and carcinoma [29].…”

Large scale tissue histopathology image classification, segmentation, and visualization via deep convolutional activation features

“…Manually designed features include fractal features [ 29 ], morphometric features [ 30 ], textural features [ 31 ], and object-like features [ 32 ]. Kalkan [ 33 , 34 ] exploits textural and structural features from patch-level images and proposes a two-level classification scheme to distinguish between cancer and non-cancer in colon cancer. Chang [ 35 ] proposes sparse tissue morphometric features at various locations and scales to distinguish tumor, necrosis, and transition to necrosis for the GBM dataset and tumor, normal, and stromal for the KRIC dataset.…”

“…The classifier exploits image-level information and alteration in cell formations under different cancer states. Kalkan [ 33 ] proposes a two-stage classification. The first stage classifies patches into possible categories (adenomatous, inflamed, cancer and normal).…”

On classification with bags, groups and sets

“…While the proposed taxonomy allows for heterogeneity in training and test objects (i.e., SI-MI and MI-SI), it is limited because the training or test objects themselves are homogeneous. It would be interesting to investigate what happens in the case where in the training phase both labeled bags and labeled instances are available, such as in [22]. As we already discussed in Section 3.4, the optimal bag classifier does not necessarily correspond with the optimal instance classifier.…”