Segmentation of prostate ultrasound images: the state of the art and the future directions of segmentation algorithms

Nowadays, prostate cancer has surpassed lung cancer as the most common type of cancer, segmentation of prostate ultrasound images is a critical step in the detection and planning treatment of prostate cancer. However, both ultrasound imaging characteristics and the physiology of the prostate make it...

Full description

Saved in:
Bibliographic Details
Published in:The Artificial intelligence review Vol. 56; no. 1; pp. 615 - 651
Main Authors: Jiang, Jingang, Guo, Yafeng, Bi, Zhuming, Huang, Zhiyuan, Yu, Guang, Wang, Jinke
Format: Journal Article
Language:English
Published: Dordrecht Springer Netherlands 01.01.2023
Springer
Springer Nature B.V
Subjects:
Algorithms
Artificial Intelligence
Cancer
Care and treatment
Classification
Computer Science
Image processing
Image segmentation
Imagery
Lung cancer
Medical treatment
Physiology
Prostate
Prostate cancer
Segmentation
Systematic review
Ultrasonic imaging
Ultrasound imaging
Image segmentation
Diagnosis of prostate cancer
Ultrasound images
Prostate cancer
Segmentation algorithms
Citespace
ISSN:0269-2821, 1573-7462
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Nowadays, prostate cancer has surpassed lung cancer as the most common type of cancer, segmentation of prostate ultrasound images is a critical step in the detection and planning treatment of prostate cancer. However, both ultrasound imaging characteristics and the physiology of the prostate make it difficult to determine the prostate boundaries in ultrasound images. In this paper, we provide a systematic review of advances in the field of ultrasound prostate image segmentation. In particular, three categories of algorithms are reviewed and compared, including edge-based segmentation, region-based segmentation, and those based on specific theoretical models. To understand the state of the art of different segmentations of the prostate ultrasound images, we conduct a literature analysis and a series of comparisons between different algorithms. The features and limitations of each category of segmentation algorithms are further discussed. Finally, we identified promising research directions in advancing the segmentation algorithms for the processing of ultrasound prostate images.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0269-2821
1573-7462
DOI:10.1007/s10462-022-10179-4