Role of image thermography in early breast cancer detection- Past, present and future

Breast cancer diagnosis using thermography and convolutional neural networks.

A multi-level thresholding method for breast thermograms analysis using Dragonfly algorithm

Developing a breast cancer screening method is very important to facilitate early breast cancer detection and treatment. Building a screening method using medical imaging modality that does not cause body tissue damage (non-invasive) and does not involve physical touch is challenging. Thermography, a non-invasive and non-contact cancer screening method, can detect tumors at an early stage even under precancerous conditions by observing temperature distribution in both breasts. The thermograms obtained on thermography can be interpreted using deep learning models such as convolutional neural networks (CNNs). CNNs can automatically classify breast thermograms into categories such as normal and abnormal. Despite their demostrated utility, CNNs have not been widely used in breast thermogram classification. In this study, we aimed to summarize the current work and progress in breast cancer detection based on thermography and CNNs. We first discuss of breast thermography potential in early breast cancer detection, providing an overview of the availability of breast thermal datasets together with publicly accessible. We also discuss characteristics of breast thermograms and the differences between healthy and cancerous thermographic patterns. Breast thermogram classification using a CNN model is described step by step including a simulation example illustrating feature learning. We cover most research related to the implementation of deep neural networks for breast thermogram classification and propose future research directions for developing representative datasets, feeding the segmented image, assigning a good kernel, and building a lightweight CNN model to improve CNN performance.

/pdf/a-review-on-recent-progress-in-thermal-imaging-and-deep-13iqtxq23g.pdf

A Review on Recent Progress in Thermal Imaging and Deep Learning Approaches for Breast Cancer Detection

Thermography images are a helpful screening tool that can detect breast cancer by showing the body parts that indicate an abnormal change in temperature. Various segmentation methods are proposed to extract regions of interest from breast cancer images to enhance the classification. Many issues were solved using thresholding. In this paper, a new efficient version of the recent chimp optimization algorithm (ChOA), namely opposition-based Levy Flight chimp optimizer (IChOA), was proposed. The original ChOA algorithm can stagnate in local optima and needs varied exploration with an adequate blending of exploitation. Therefore, the convergence is accelerated by improving the initial diversity and good exploitation capability at a later stage of generations. Opposition-based learning (OBL) is applied at the initialization phase of ChOA to boost its population diversity in the search space, and the Levy Flight is used to enhance its exploitation. Moreover, the IChOA is applied to tackle the image segmentation problem using multilevel thresholding. The proposed method tested using Otsu and Kapur methods over a dataset from Mastology Research with Infrared Image (DMR-IR) database during the optimization process. Furthermore, compared against seven other meta-heuristic algorithms, namely Gray wolf optimization (GWO), Moth flame optimization (MFO), Whale optimization algorithm (WOA), Sine–cosine algorithm (SCA), Slap swarm algorithm (SSA), Equilibrium optimization (EO), and original Chimp optimization algorithm (ChOA). Results based on the fitness values of obtained best solutions revealed that the IChOA achieved valuable and accurate results in terms of quality, consistency, accuracy, and the evaluation matrices such as PSNR, SSIM, and FSIM. Eventually, IChOA obtained robustness for the segmentation of various positive and negative cases compared to the methods of its counterparts.

An efficient multilevel thresholding segmentation method for thermography breast cancer imaging based on improved chimp optimization algorithm

In this article, we present a new approach for breast thermogram image analysis by developing a fully automatic segmentation of right and left breast for asymmetry analysis, using shape features of the breast and Polynomial curve fitting. Segmentation results are validated with their respective Ground Truths. Histogram and grey level co-occurrence matrix-based texture features are extracted from the segmented images. Statistical test shows that features are highly significant in detection of breast cancer. We have obtained an accuracy of 90%, sensitivity of 87.5% and specificity of 92.5% for a set of eighty images with forty normal and forty abnormal using SVM RBF classifier.

Roshan Joy Martis

Papers

Asymmetry analysis of breast thermograms using automated segmentation and texture features