Breast cancer intelligent analysis of histopathological data: A systematic review

Felipe André Zeiser, Cristiano André da Costa, Adriana Vial Roehe, Rodrigo da Rosa Righi, Nuno Miguel Cavalheiro Marques

Research output: Contribution to journalReview articlepeer-review

Abstract

For a favorable prognosis of breast cancer, early diagnosis is essential. The histopathological analysis is considered the gold standard to indicate the type of cancer. Histopathology consists of analyzing characteristics of the lesions through tissue sections stained with Hematoxylin and Eosin. During the last years, there is much interest in developing the histopathological slide analysis process. This article aims to explore recent literature related to intelligent analysis of breast cancer histopathological images, defining the taxonomy, identifying challenges, and open questions. The method is based on a systematic literature review, guided by research questions to identify relevant work and identify open problems in the literature. The present study investigates articles published in the last ten years. We are selecting and researching the most significant approaches according to pre-established criteria in the intelligent analysis of breast cancer histopathological images, resulting in a final corpus of 53 articles. As a result, we developed an updated taxonomy, identified the main challenges, public datasets, evaluation metrics, and techniques used in the studies. These results contribute to discussions about the intelligent analysis of breast cancer histopathological images and highlight some research gaps for future studies.

Original languageEnglish
Article number107886
JournalApplied Soft Computing
Volume113
Issue numberPt. A
DOIs
Publication statusPublished - Dec 2021

Keywords

  • Histopathological images
  • Intelligent analysis
  • Machine learning
  • Specialized systems
  • Systematic review

Fingerprint

Dive into the research topics of 'Breast cancer intelligent analysis of histopathological data: A systematic review'. Together they form a unique fingerprint.

Cite this