Homology-based method for detecting regions of interest in colonic digital images

Abstract

BackgroundA region of interest (ROI) is a part of tissue that contains important information for diagnosis. To use many image analysis methods efficiently, a technique that would allow for ROI identification is required. For the colon, ROIs are characterized by areas of stronger color intensity of hematoxylin. Since malignant tumors grow in the innermost layer, most ROIs will be located in the colonic mucosa and will be an accumulation of tumor cells and/or integrated cells with distorted architecture.MethodsUsing homology theory, our group proposed a method to estimate the contact degree of elements in a unit area of tissue. Homology is a concept that is used in many branches of algebra and topology, and it can quantify the contact degree. Due to the lack of contact inhibition of cancer cells, an area with unusual contact degree is expected to be a potential ROI.ResultsThe current work verifies the accuracy of this method against the results of pathological diagnosis, based on 1825 colonic images provided by the Osaka Medical Center for Cancer and Cardiovascular Diseases. Although we have many false positives and there is a possibility of missing undifferentiated types of cancer, this system is very effective for detecting ROIs.ConclusionsThe mathematical system proposed by our group successfully detects ROIs and is a potentially useful tool for differentiating tumor areas in microscopic examination very quickly. Because we use only the information from low-power field images, there is room for further improvement. This system could be used to screen for not only colon cancer but other cancers as well. More sophisticated and more efficient automated pathological diagnosis systems can be developed by integrating various techniques available today.Virtual SlideThe virtual slide(s) for this article can be found here: http://www.diagnosticpathology.diagnomx.eu/vs/7129390011429407.

Fast and accurate tumor segmentation of histology images using persistent homology and deep convolutional features

“…We compute two relevant homology groups H 0 (X i ) and H 1 (X i ) for 1 ≤ i < k as follows. Instead of using computationally expensive constructs of simplicial topology, as is normal in the literature using persistent homology Nakane et al (2015Nakane et al ( , 2013, we compute H 0 (X i ) by counting the connected components of X i , giving the Betti number β 0 (X i ) and H 1 (X i ) by counting the components of X \ X i , giving the Betti number β 1 (X i ). For our purposes, it is therefore sufficient to calculate, for each i with 1 ≤ i < k, these two numbers, giving a total of 2k − 2 length of feature vector.…”

Homological radiomics analysis for prognostic prediction in lung cancer patients

“…Homology has been successfully utilized in various image-analysis applications, such as the detection and classification of prognostic cancer lesions in pathological or CT images. This was achieved by quantifying the cavitation derived from pixel value heterogeneity in cancerous regions using Betti numbers [15,16], which are mathematically invariant. The zero-and one-dimensional Betti numbers, which can be calculated from two-dimensional images, indicate the number of connected components (b0) and holes (b1) in an object [16].…”

“…This was achieved by quantifying the cavitation derived from pixel value heterogeneity in cancerous regions using Betti numbers [15,16], which are mathematically invariant. The zero-and one-dimensional Betti numbers, which can be calculated from two-dimensional images, indicate the number of connected components (b0) and holes (b1) in an object [16]. The Betti numbers could elucidate the topologically invariant morphological characteristics of cancer, i.e., the intrinsic properties of cancer.…”

Application of the homology method for quantification of low-attenuation lung region in patients with and without COPD

“…Because the homology method calculates the contact degree of tissues (structures), this method has been applied in many fields. 12 – 16 For example, Nakane et al 12 , 13 proposed a new method for evaluating digital pathology images of the colon, in which the Betti numbers were extracted from the region of interest of the pathology images. Their results show that it was possible to use the Betti numbers for screening of colon cancer.…”

“…Notably, the time required to calculate these numbers is very short; using an ordinary computer, calculation of the Betti numbers only requires approximately 3.0 seconds. 12 , 13 …”