Analyzing High-Grade Breast Cancer via Fractal Dimension | InformativeBD

Bonou Malomon Aimé , Hounsossou Cocou Hubert , Ayinon Epiphane Helou Kossi Armel, Dossou Julien, and Biaou Olivier from the different institute of the Benin, wrote a research article about Analyzing High-Grade Breast Cancer via Fractal Dimension, entitled,"High histological grade breast cancer morphological evaluation on mammogram using the box-counting fractal dimension"This research paper published by the International Journal of Biomolecules and Biomedicine | IJBB an open access scholarly research journal on Biomedicine, under the affiliation of the International Network For Natural Sciences | INNSpub, an open access multidisciplinary research journal publisher.

Abstract

To evaluate the high-grade breast cancer morphological complexity on mammogram. We conducted a retrospective study using an open source data got from figshare repository. These anonymized data were collected and used for a study approved by the institutional review board. Cranio-Caudal and Medio-lateral mammograms and their tumor segmented images from 66 patients subdivided in two groups high histological grade (n=23) low-grade (low and intermediate, n=41). From breast cancer image segmentation, we extracted fractal dimension using Fraclac, plugin of ImageJ software based on box-counting method. For our analysis we used comparatively the fractal dimension from cranio-caudal (CC) and medio-lateral (MLO) images. We summarized the fractal dimension of our cohort using boxplot and performed the Wilcoxon non-parametric statistic for fractal dimension comparison of two groups (High-grade and low-grade). There was not difference between CC (mean ± std= 1.1583±0.067) andmLO (mean ± std =1.1551±0.055) breast cancer fractal dimension. For the high-grade differentiation, CC andmLO images fractal dimension were contributed respectively at a little difference but without statistically difference (P value=0.438 and 0.435). High-grade fractal dimensions mean were respectively 1.142±0.044 and 1.144±0.075 for CC andmLO images against 1.166±0.050 and 1.160±0.057 for low-grade. It had been recorded a lower mean value of fractal dimension for high-grade breast cancer without statistically significant. This finding shows that the high-grade breast cancer tends to have a regular shape.

 

Read more : Saharan Flood Risk:Bechar Region Case Study | InformativeBD

Introduction

Breast cancer is the most common cancer in women and a leading cause of cancer death worldwide (Bray et al., 2018). Management of breast cancer relies on the availability of robust clinical and pathological prognostic and predictive factors to guide patient decision making and the selection of treatment. Histological grade is one of important prognostic factor. It is based on the degree of differentiation of the tumor tissue and based on the evaluation of three morphological features: (a) degree of tubule or gland formation, (b) nuclear pleomorphism, and (c) mitotic count. It is used to categorize breast cancer patients in three clinical groups grade I (low), grade II (intermediate) and grade III (high) (Elston and Ellis 1991). High-grade breast cancer is recognized as more aggressive cancer type and is the worst survival prognostic and need a specific treatment (WHO 2006; Rakha et al., 2008b, a).

To date, the histological grading is one of popular method used to categorize breast cancer patients in therapeutic groups (low and high risk). Whereas, this method has been described as subjective method with sometimes inter-observer variability (Gilchrist et al., 1985; Theissig et al., 1990).

In this context, some authors attempted to describe the high-grade breast cancer aspect on medical image in order to allow its a better identification for the clinician. Regarding mammogram, Lamb et al. found that classical appearance of a low or intermediate grade tumor is a speculated mass on mammography (Lamb et al., 2000). SHIN et al. 2011 had also attempted to describe it morphological aspect on mammogram because mammography is one of the primary breast imaging modalities used in breast cancer diagnosis. They found that having Fairly slow developing grade I tumors (low grade) and grade II tumors (intermediate grade) presents a stroma reaction resulting in imaging by spicules while high grade with rapid evolution, do not develop a stroma reaction and has a round shape (Shin et al., 2011). The findings of both previous studies suggested that histological high-grade breast cancer tends to have a particular margin.

Due to development the Computer Aid Diagnosis (CAD) based on mammography several reliable quantitative features had been used to describe breast cancer morphological characteristic. In this context, shape factors such as compactness, fractional concavity, spiculation index, and a Fourier-descriptor-based factor have been proposed for breast lesion classification (Rangayyan et al. 1997, 2000). Latter fractal dimension had been used in the same purpose and it allowed to get a result better than with previous features for the breast cancer differentiation from benign lesion (Rangayyan and Nguyen 2007). Fractal geometry is a powerful tool for describing and modeling natural objects. Most of these applications employ fractal dimension, a measure that captures the so-called complexity of the object, a fundamental descriptor of analyzed objects represented in a digital image. In this context, complexity expresses the level of detail detected at different scales. This measure is immediately related to physical characteristics, which are fundamental to the description and identification of objects, even in our human vision system (texture analysis using fractal). In last decade, following success of CAD, several studies used medical image quantitative features in order to decrypt cancer biology (Sanduleanu et al., 2018). Recently Fan et al. and Huang et al. extracted quantitative features from medical image to find those which are relevant to breast cancer histological grade (Huang et al., 2018; Fan et al., 2019). In these previous studies, fractal dimension was not used, while it showed a better potential for the differentiation of the breast tumors in according to their margin characteristic. Based on hypothesis that the high-grade breast cancer presents a particular margin, we used in this study, the fractal dimension to evaluate its morphological complexity on mammogram and find the importance of this quantitative feature in its differentiation from other grades (low and intermediate).

Reference

Abràmoff DMD, Magalhães Dr PJ, Ram Dr SJ. 2004. Image Processing with ImageJ 7.

Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A. 2018. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians 68, 394-424.

Elston CW, Ellis IO. 1991. Pathological prognostic factors in breast cancer. I. The value of histological grade in breast cancer: experience from a large study with long-term follow-up. Histopathology 19, 403-410.

Fan M, Liu Z, Xie S, Xu M, Wang S, Gao X, Li L. 2019. Integration of dynamic contrast-enhanced magnetic resonance imaging and T2-weighted imaging radiomic features by a canonical correlation analysis-based feature fusion method to predict histological grade in ductal breast carcinoma. Physics in Medicine & Biology 64, 215001.

Gilchrist KW, Kalish L, Gould VE, Hirschl S, Imbriglia JE, Levy WM, Patchefsky AS, Penner DW, Pickren J, Roth JA, Schinella RA, Schwartz IS, Wheeler JE. 1985. Interobserver reproducibility of histopathological features in stage II breast cancer. Breast Cancer Research and Treatment 5, 3-10.

Huang S, Franc BL, Harnish RJ, Liu G, Mitra D, Copeland TP, Arasu VA, Kornak J, Jones EF, Behr SC, Hylton NM, Price ER, Esserman L, Seo Y. 2018. Exploration of PET and MRI radiomic features for decoding breast cancer phenotypes and prognosis. NPJ Breast Cancer 4.

Lamb PM, Perry NM, Vinnicombe SJ, Wells CA. 2000. Correlation Between Ultrasound Characteristics, Mammographic Findings and Histological Grade in Patients with Invasive Ductal Carcinoma of the Breast. Clinical Radiology 55, 40-44.

Rakha EA, El-Sayed ME, Lee AHS, Elston CW, Grainge MJ, Hodi Z, Blamey RW, Ellis IO. 2008a. Prognostic significance of Nottingham histologic grade in invasive breast carcinoma. Journal of Clinical Oncology: Official Journal of the American Society of Clinical Oncology 26, 3153-3158.

Rakha EA, El-Sayed ME, Powe DG, Green AR, Habashy H, Grainge MJ, Robertson JFR, Blamey R, Gee J, Nicholson RI, Lee AHS, Ellis IO. 2008b. Invasive lobular carcinoma of the breast: response to hormonal therapy and outcomes. European Journal of Cancer (Oxford, England: 1990) 44. 73-83.

Rangayyan RM, El-Faramawy NM, Desautels JE, Alim OA. 1997. Measures of acutance and shape for classification of breast tumors. IEEE transactions on medical imaging 16, 799-810.

Rangayyan RM, Mudigonda NR, Desautels JEL. 2000. Boundary modelling and shape analysis methods for classification of mammographic masses. Medical and Biological Engineering and Computing 38, 487-496.

Rangayyan RM, Nguyen TM. 2007. Fractal Analysis of Contours of Breast Masses in Mammograms. Journal of Digital Imaging 20, 223-237.

Sanduleanu S, Woodruff HC, Jong EEC, de, Timmeren JE, van, Jochems A, Dubois L, Lambin P. 2018. Tracking tumor biology with radiomics: A systematic review utilizing a radiomics quality score. Radiotherapy and Oncology 127, 349-360.

Schneider CA, Rasband WS, Eliceiri KW. 2012. NIH Image to ImageJ: 25 years of image analysis. Nature Methods 9, 671-675.

Shin HJ, Kim HH, Huh MO, Kim MJ, Yi A, Kim H, Son BH, Ahn SH. 2011. Correlation between mammographic and sonographic findings and prognostic factors in patients with node-negative invasive breast cancer. The British Journal of Radiology 84, 19-30.

Stavros AT. 2004. Breast Ultrasound. Lippincott Williams & Wilkins.

Stavros AT, Thickman D, Rapp CL, Dennis MA, Parker SH,  Sisney GA. 1995. Solid breast nodules: use of sonography to distinguish between benign and malignant lesions. Radiology 196, 123-134.

Tamez-Peña J-G, Rodriguez-Rojas J-A, Gomez-Rueda H, Celaya-Padilla J-M, Rivera-Prieto R-A, Palacios-Corona R, Garza-Montemayor M, Cardona-Huerta S, Treviño V. 2018. Radiogenomics analysis identifies correlations of digital mammography with clinical molecular signatures in breast cancer. PLOS ONE 13, e0193871.

Theissig F, Kunze KD, Haroske G, Meyer W. 1990. Histological Grading of Breast Cancer: Interobserver, Reproducibility and Prognostic Significance. Pathology – Research and Practice 186, 732-736.

Trevino V. 2018. Breast Cancer Images & Segmentation – Correlation of Gene Expression Subtypes and Image Features.

WHO. 2006. Guidelines for management of breast cancer. World Health Organization, Regional Office for the Eastern Mediterranean, Cairo.

Source: High histological gradebreast cancer morphological evaluation on mammogram using the box-countingfractal dimension