Thermography based breast cancer detection using self‐adaptive gray level histogram equalization color enhancement method

Abstract

The early detection of tumor is necessary to save a number of lives. In women, the temperature of the affected area of the tumor is warmer than the unaffected area; therefore the thermography technique can be used to capture the cancerous breast images with a thermal infrared by identifying the temperature difference between them. Color enhancement of the captured breast image is an important consideration for early detection of tumor at this stage. Therefore, in this paper, we propose a self‐adaptive gray level histogram equalization approach to enhance the color of the IR image for early detection of the tumor. This approach does not require any manual feeding of parameters toward images. The final classification of tumorous and non‐tumorous breast images can obtain through certain procedures, which includes, image acquisition, pre‐processing, segmentation, feature extraction and classification. This paper emphasizes the support vector machine (SVM) technique to classify the tumor IR thermography images. The proposed approach is implemented in MATLAB and the experimental results shows an outstanding color enhancement of IR images and better classification compared to other existing methods such as CLAHE, BIi‐histogram equalization and adaptive histogram equalization. The performance was evaluated by using evaluation metrics such as sensitivity, accuracy, and specificity of thermography breast image by the SVM classifier adapted with various color enhancement approaches are found to be 91.6%, 90%, and 87.5%. This approach helps in medical field for early diagnosis with high reliability.

Breast Cancer Classification based on Artificial Intelligence: State of the Art

“…In [29], a new technique called the Self-Adaptive grey level HE Approach (SAHE) was introduced to improve the contrast of thermal infrared breast cancer images. The thermal infrared image of the breast cancer tumour was enhanced in colour using SAHE to aid in its early detection.…”

“…No image-specific parameters need to be inputted by hand into the proposed SAHE. Early and accurate diagnosis in the medical field is aided by SAHE, as shown by research in [29]. In a similar vein, Contrast Limited Adaptive HE (CLAHE) was introduced as a means of enhancing contrast in [30].…”

A Comprehensive Survey on Deep-Learning-Based Breast Cancer Diagnosis

“…The infrared thermal imaging method has gained popularity recently in BrC classification. Only a few studies used this imaging method because the dataset of thermograms is not publicly available [ 148 , 158 ]. Unfortunately, none of the researchers utilized positron-emission tomography (PET) and scintimammography imaging techniques.…”

Fabric yarn detection based on improved fast R-CNN model

“…Finally, the fabric structure is determined by the length and weft of each row, and the fabric structure is determined by scanning the length and weft of each row [2]. Raj et al Reduced the gray image level through histogram equalization, then constructed the gray level co-occurrence matrix according to the pixel spacing and angle changes, calculated its eigenvalue, and obtained the fabric density parameter through its periodic calculation [3]. Used autocorrelation function to determine the position, density, and weave point position of fabric warp and weft yarn.…”