Computer Techniques for Detection of Breast Cancer and Follow Up Neoadjuvant Treatment: Using Infrared Examinations

Computer Techniques for Detection of Breast Cancer and Follow Up Neoadjuvant Treatment: Using Infrared Examinations

Adriel dos Santos Araujo, Roger Resmini, Maira Beatriz Hernandez Moran, Milena Henriques de Sousa Issa, Aura Conci
Copyright: © 2021 |Pages: 35
DOI: 10.4018/978-1-7998-3456-4.ch005
(Individual Chapters)
No Current Special Offers


This chapter explores several steps of the thermal breast exams analysis process in detecting breast abnormality and evaluating the response of pre-surgical treatment. Topics concerning the process of acquiring, storing, and preprocessing these exams, including a novel segmentation proposal that uses collective intelligence techniques, will be discussed. In addition, various approaches to calculating statistical and geometric descriptors from thermal breast examinations are also considered of this chapter. These descriptors can be used at different stages of the analysis process of these exams. In this sense, two experiments will be presented. The first one explores the use of genetic algorithms in the feature selection process. The second conducts a preliminary study that intends to analyze some descriptors, already used in other works, in the process of evaluating preoperative treatment response. This evaluation is of fundamental importance since the response is directly associated with the prognosis of the disease.
Chapter Preview

Main Focus Of The Chapter

The process of DITE analysis can be divided into several stages. Some of the most common could include activities inherent in exam acquisition, preprocessing, segmentation, the definition of the Region of Interest (ROI), feature computation, feature selection, and classification. In this chapter, several important points that go through all these steps will be discussed.

Some protocols used in the process of acquiring thermographic exams, will be discussed, pointing out the main differences and similarities between them. Moreover, a public dataset with over 7000 DITE and over 2500 users will be presented. The exams in this repository have helped thousands of institutions in their research around the world. Additionally, such a large number of users presents an opportunity for the development of several kinds of research involving the use of collective intelligence in order to assist the process of breast DITE segmentation.

The preprocessing step will also be discussed, in particular, the segmentation approaches, ROI identification, and registration of already segmented breasts will be addressed. Automatic and semi-automatic techniques for preprocessing activities that involve computer vision, crowdsourcing, and machine learning will be discussed (Resmini et al., 2018).

Complete Chapter List

Search this Book: