Breast tumor localization and segmentation using machine learning techniques: Overview of datasets, findings, and methods

• Published in: Computers in biology and medicine Vol. 152; p. 106443
• Main Authors: Ranjbarzadeh, Ramin, Dorosti, Shadi, Jafarzadeh Ghoushchi, Saeid, Caputo, Annalina, Tirkolaee, Erfan Babaee, Ali, Sadia Samar, Arshadi, Zahra, Bendechache, Malika
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.01.2023; Elsevier Limited
• Subjects: Abnormalities; Animals; Artificial intelligence; Breast cancer; Breast Neoplasms - pathology; Computer vision; Deep Learning; Diagnosis; Diagnosis, Computer-Assisted - methods; Female; Fractals; Humans; Image processing; Image Processing, Computer-Assisted - methods; Image segmentation; Imaging techniques; Information technology; Internal Medicine; Learning algorithms; Localization; Machine Learning; Magnetic resonance imaging; Mammary Neoplasms, Animal; Mammography; Mammography - methods; Medical imaging; Other; Task complexity; Tomography; Tumor segmentation; Tumors; Ultrasonic imaging; Deep learning; Image segmentation; Breast cancer; Tumor segmentation
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2022.106443

The Global Cancer Statistics 2020 reported breast cancer (BC) as the most common diagnosis of cancer type. Therefore, early detection of such type of cancer would reduce the risk of death from it. Breast imaging techniques are one of the most frequently used techniques to detect the position of cancerous cells or suspicious lesions. Computer-aided diagnosis (CAD) is a particular generation of computer systems that assist experts in detecting medical image abnormalities. In the last decades, CAD has applied deep learning (DL) and machine learning approaches to perform complex medical tasks in the computer vision area and improve the ability to make decisions for doctors and radiologists. The most popular and widely used technique of image processing in CAD systems is segmentation which consists of extracting the region of interest (ROI) through various techniques. This research provides a detailed description of the main categories of segmentation procedures which are classified into three classes: supervised, unsupervised, and DL. The main aim of this work is to provide an overview of each of these techniques and discuss their pros and cons. This will help researchers better understand these techniques and assist them in choosing the appropriate method for a given use case. •This review aims to discuss about techniques employed to segment breast and tumor.•The approaches about recognizing the breast tumor are presented.•Details of feature extraction algorithms in many papers have been discussed.•Different Datasets related to breast tumor have been proposed and discussed.