Combining multifractal analyses of digital mammograms and infrared thermograms to assist in early breast cancer diagnosis

Abstract

We used a 1D wavelet transform modulus maxima (WTMM) method to analyze the temporal fluctuations of breast skin temperature recorded with an infrared (IR) camera from a panel of patients with breast cancer. This study shows that the multifractal complexity of temperature fluctuations observed in healthy breasts, is lost in the region of the malignant tumor in cancerous breasts. Then, we applied the 2D WTMM method to analyze the spatial fluctuations of breast density in the X-ray mammograms of the same patients. Compared to the correlated roughness fluctuations observed in the healthy areas, some clear loss of correlations is detected in malignant tumor foci. These physiological and architectural changes in the environment of malignant tumors detected in both thermograms and mammograms open new perspectives in computer-aided multifractal methods to assist in early breast cancer diagnosis.

A Robust Deep Learning-Based Approach for Detection of Breast Cancer from Histopathological Images

“…With classification accuracy scores of 96.77% and 93.41%, the RBF network and J48 algorithms, respectively, came in second and third. Similarly, Gerasimova-Chechkina et al [8] applied the artificial neural network (ANN) with mini-MIAS dataset, and achieved 99.4% accuracy. Likewise, Bhardwaj, A. et al [9] implemented a genetically optimized neural network (GONN) approach to deal with categorization issues, utilized to establish whether a tumor was benign or malignant.…”

Nonlinear Statistical Analysis of Normal and Pathological Infant Cry Signals in Cepstrum Domain by Multifractal Wavelet Leaders

“…Specifically, in recent years, multifractal analysis has received growing attention in biomedical engineering. For example, it was applied in the analysis of various biophysiological signals, including EEG [ 3 , 4 , 5 , 6 , 7 , 8 , 9 , 10 ], ECG [ 11 , 12 , 13 , 14 , 15 ], magnetic resonance images and brainstem volume [ 16 , 17 , 18 ], mammograms [ 19 , 20 ], bone radiographic images [ 21 ], retina digital images [ 22 ], dental implant ultrasonic signal [ 23 ], and liver tissue images [ 24 ], to name few.…”

Loss of Mammographic Tissue Homeostasis in Invasive Lobular and Ductal Breast Carcinomas vs. Benign Lesions

“…On the other hand, microcalcifications can occur in such benign processes as sclerosing adenosis or some fibroadenomas ( Fischmann, 2008 ; Henrot et al, 2014 ). These findings are driving us to “think outside of the tumor” ( Gerasimova-Chechkina et al, 2016 ) and to develop a computational approach to study and quantitatively characterize tissue microenvironment throughout the whole breast ( Marin et al, 2017 ). Indeed, the breast tumor microenvironment plays a key role in early tumorigenesis.…”