A New method for promote the performance of deep learning paradigm in diagnosing breast cancer: improving role of fusing multiple views of thermography images

Abstract

Purpose Breast cancer is one of the deadliest cancers among women worldwide which its early detection may significantly reduce its mortality rate. Thermgraphy is a new, non-invasive, non-painful, and low-cost modality that detects abnormalities by detecting heat from the breast surface. Method Recent research has applied deep learning to early breast cancer diagnosis via thermography, using only the frontal view of thermograms. We combine several views of thermal images to improve the performance of pre-trained deep learning architectures in this article. This goal is achieved by combining frontal-45 data with lateral-45 and lateral45 thermograms to construct a detection model that utilizes transfer learning. Result Research in this area uses the Database for Mastology Research (DMR) with infrared images. In this study, transfer based deep learning methods are demonstrated to be effective in fusing several views of thermograms to diagnose breast cancer in a manner that can result in a sensitivity increase of 2-15 percent and a specificity increase of 2-30 percent compared to other deep learning-based or handcrafted schemes. Conclusion Using multiple views of thermograms and transfer learning, this paper proposes a method for improving breast cancer diagnosis. Using methods based on deep learning and methods based on hand-crafted features, we evaluated the performance of the proposed model. Using the obtained results as a basis for future research, the proposed design can be improved and developed as a valid approach in interpreting breast thermography images.

Infrared thermal images using PCSAN‐Net‐DBOA: An approach of breast cancer classification

“…Ensafi et al (2022) have presented a novel strategy for increasing the presentation of a deep learning method to detect breast cancer: the role of combining various thermography picture views. The built‐in deep learning architecture performance was improved by combining several views of thermal pictures.…”

Analytical Optimization of X-ray Mammography for Increased Benefits and Safety; using: Data Analytics, Electronics Engineering and Artificial Intelligence

“…The most common and fatal cancers amongst women is breast cancer. Between 2016 to 2020 alone, official reports from the World Health Organisation(WHO) omdicates aapproximately 7.8 million cases of breast cancer, of which 685,000 of them have died, which makes it a serious killer of an ailment [1]. For easier treatment of breast cancer and also the accompanying reduction of the mortality rate caused by the disease; early detection is pertinent and must be continually optimized to fight the disease effectively and efficiently [2].…”

“…The mostly used two-dimensional mammograms from different projections, takes X-ray images of each breast as a standard procedure. The three primary regions of the female breast are (1) The skin region, (2) the subcutaneous adipose tissue just beneath the skin and (3) the mixed adipose and glandular tissue, of which the average dose absorbed is called the average glandular dose (AGD) [8,9]. To also ensure the safety of X-ray procedures with respect to acceptable radiation levels; agencies like the International Commission on Radiological Protection and the Institute of Medicine have promulgated recommended AGD levels [10].…”