Thermal-based early breast cancer detection using inception V3, inception V4 and modified inception MV4

Breast cancer is one of the most significant causes of death for women around the world. Breast thermography supported by deep convolutional neural networks is expected to contribute significantly to early detection and facilitate treatment at an early stage. The goal of this study is to investigate the behavior of different recent deep learning methods for identifying breast disorders. To evaluate our proposal, we built classifiers based on deep convolutional neural networks modelling inception V3, inception V4, and a modified version of the latter called inception MV4. MV4 was introduced to maintain the computational cost across all layers by making the resultant number of features and the number of pixel positions equal. DMR database was used for these deep learning models in classifying thermal images of healthy and sick patients. A set of epochs 3–30 were used in conjunction with learning rates 1 × 10–3, 1 × 10–4 and 1 × 10–5, Minibatch 10 and different optimization methods. The training results showed that inception V4 and MV4 with color images, a learning rate of 1 × 10–4, and SGDM optimization method, reached very high accuracy, verified through several experimental repetitions. With grayscale images, inception V3 outperforms V4 and MV4 by a considerable accuracy margin, for any optimization methods. In fact, the inception V3 (grayscale) performance is almost comparable to inception V4 and MV4 (color) performance but only after 20–30 epochs. inception MV4 achieved 7% faster classification response time compared to V4. The use of MV4 model is found to contribute to saving energy consumed and fluidity in arithmetic operations for the graphic processor. The results also indicate that increasing the number of layers may not necessarily be useful in improving the performance.

Enhanced Segmentation of Inflamed ROI to Improve the Accuracy of Identifying Benign and Malignant Cases in Breast Thermogram

Effective analysis of breast thermography needs an accurate segmentation of the inflamed region in Infrared Breast Thermal Images (IBTI) which helps in the diagnosis of breast cancer. However, IBTI suffers from intensity inhomogeneity, overlapping regions of interest, poor contrast, and low signal-to-noise ratio (SNR) due to the imperfect image acquisition process. To mitigate this, this work proposes an enhanced segmentation of the inflamed Region of Interest (ROI) using an active contour method driven by the multiscale local and global fitted image (MLGFI) model. The first phase proposes a bilateral histogram difference-based thresholding (BHDT) method for locating the inflamed ROI. This is then used for automatic initialization of active contours driven by MLGFI to segment the inflamed ROI from IBTI effectively. To prove the effectiveness of this segmentation method, its performance is compared with ground truth image and its accuracy is also evaluated with the state-of-the-art methods (Fuzzy C Means (FCM), Chan-Vese (CV-ACM), and K-means). From the analysis, it is found that the proposed method not only increases the precision and the segmentation accuracy but also reduces the oversegmentation and undersegmentation rate significantly. In the second phase, area-based feature (AF) and average intensity-based feature (AIF) along with the GLCM (gray level cooccurrence matrix) based second-order statistical features are extracted from the inflamed ROI. Based on these features, a system is developed to effectively classify the benign and malignant breast conditions. From the results, it is observed that the proposed model exhibits an improved accuracy of 91.5%, sensitivity of 91%, and specificity of 92% compared to the whole breast thermogram. Hence, it is concluded that the proposed method will improve the efficacy of thermal imaging in the diagnosis of breast cancer.

Thermal Analysis of Realistic Breast Model With Tumor and Validation by Infrared Images

Breast thermography is an emerging adjunct tool to mammography in early breast cancer detection due to its non-invasiveness and safety. Steady-state infrared imaging proves promising in this field as it is not affected by tissue density. The main aim of the present study is to develop a computational thermal model of breast cancer using real breast surface geometry and internal tumor specification. The model depicting the thermal profile of the subject's aggressive ductal carcinoma is calibrated by variation of blood perfusion and metabolic heat generation rate. The subject's IR image is used for validation of the simulated temperature profile. The thermal breast model presented here may prove useful in monitoring the response of tumor post-chemotherapy for female subjects with similar breast cancer characteristics.

The Evolution of New Trends in Breast Thermography

In this chapter, the theoretical foundations of infrared radiation theory and the principles of the infrared imaging technique are presented. The use of infrared (IR) images has increased recently, especially due to the refinement and portability of thermographic cameras. As a result, this type of camera can be used for various medical applications. In this context, the use of IR images is proposed as an auxiliary tool for detecting disease and monitoring, especially for the early detection of breast cancer.

Feature Selection Based on Dialectical Optimization Algorithm for Breast Lesion Classification in Thermographic Images

Breast cancer is the leading cause of death among women worldwide. Early detection and early treatment are critical to minimize the effects of this disease. In this sense, breast thermography has been explored in the process of diagnosing this type of cancer. Furthermore, in an attempt to optimize the diagnosis, intelligent pattern recognition techniques are being used. Features selection performs an essential task in this process to optimize these intelligent techniques. This chapter proposes a features selection method using Dialectical Optimization Method (ODM) associated to a KNN classifier. The authors found that this combination proved to be a good approach showing a low impact on breast lesion classification performance. They obtained around 5% decrease in accuracy, with a reduction of about 46.80% of the features vector. The specificity and sensitivity values they found were competitive to other widely used methods.