Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Narrative Review of Image Processing Techniques Related to Prostate Ultrasound

Haiqiao Wang, Hong Wu, Zhuoyuan Wang, Peiyan Yue, Dong Ni, Pheng-Ann Heng, Yi Wang

TL;DR

This narrative survey maps two decades of image-processing advances for transrectal ultrasound in prostate cancer care, covering segmentation, registration, cancer classification/detection, and needle localization. It traces a shift from traditional, rule-based and hand-crafted feature methods to data-driven deep learning architectures (CNNs, RNNs, and attention models), with growing emphasis on multi-modality data (TRUS, CEUS, SWE, Micro-US, MR-US) and 3D/2.5D representations. Key contributions include a comprehensive taxonomy of modalities, dimensions, and algorithm families, plus standardized evaluation metrics (e.g., DSC, IoU, AUC, TRE, shaft/tip errors) guiding cross-study comparisons. The review highlights persistent challenges—image quality, heterogeneity across scanners, and real-time clinical integration—and outlines future directions toward robust, uncertain-aware, and radiomics-enhanced pipelines that can meaningfully improve diagnostic accuracy and treatment outcomes in PCa care.

Abstract

Prostate cancer (PCa) poses a significant threat to men's health, with early diagnosis being crucial for improving prognosis and reducing mortality rates. Transrectal ultrasound (TRUS) plays a vital role in the diagnosis and image-guided intervention of PCa.To facilitate physicians with more accurate and efficient computer-assisted diagnosis and interventions, many image processing algorithms in TRUS have been proposed and achieved state-of-the-art performance in several tasks, including prostate gland segmentation, prostate image registration, PCa classification and detection, and interventional needle detection. The rapid development of these algorithms over the past two decades necessitates a comprehensive summary. In consequence, this survey provides a \textcolor{blue}{narrative } analysis of this field, outlining the evolution of image processing methods in the context of TRUS image analysis and meanwhile highlighting their relevant contributions. Furthermore, this survey discusses current challenges and suggests future research directions to possibly advance this field further.

A Narrative Review of Image Processing Techniques Related to Prostate Ultrasound

TL;DR

This narrative survey maps two decades of image-processing advances for transrectal ultrasound in prostate cancer care, covering segmentation, registration, cancer classification/detection, and needle localization. It traces a shift from traditional, rule-based and hand-crafted feature methods to data-driven deep learning architectures (CNNs, RNNs, and attention models), with growing emphasis on multi-modality data (TRUS, CEUS, SWE, Micro-US, MR-US) and 3D/2.5D representations. Key contributions include a comprehensive taxonomy of modalities, dimensions, and algorithm families, plus standardized evaluation metrics (e.g., DSC, IoU, AUC, TRE, shaft/tip errors) guiding cross-study comparisons. The review highlights persistent challenges—image quality, heterogeneity across scanners, and real-time clinical integration—and outlines future directions toward robust, uncertain-aware, and radiomics-enhanced pipelines that can meaningfully improve diagnostic accuracy and treatment outcomes in PCa care.

Abstract

Prostate cancer (PCa) poses a significant threat to men's health, with early diagnosis being crucial for improving prognosis and reducing mortality rates. Transrectal ultrasound (TRUS) plays a vital role in the diagnosis and image-guided intervention of PCa.To facilitate physicians with more accurate and efficient computer-assisted diagnosis and interventions, many image processing algorithms in TRUS have been proposed and achieved state-of-the-art performance in several tasks, including prostate gland segmentation, prostate image registration, PCa classification and detection, and interventional needle detection. The rapid development of these algorithms over the past two decades necessitates a comprehensive summary. In consequence, this survey provides a \textcolor{blue}{narrative } analysis of this field, outlining the evolution of image processing methods in the context of TRUS image analysis and meanwhile highlighting their relevant contributions. Furthermore, this survey discusses current challenges and suggests future research directions to possibly advance this field further.
Paper Structure (47 sections, 41 equations, 2 figures, 5 tables)

This paper contains 47 sections, 41 equations, 2 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Task Definition
  3. Prostate Gland Segmentation
  4. Evaluation Metrics
  5. Prostate Image Registration
  6. Evaluation Metrics
  7. Prostate Cancer Classification and Detection
  8. Evaluation Metrics
  9. Needle Detection
  10. Evaluation Metrics
  11. Method Overview
  12. Prostate Gland Segmentation
  13. Modalities
  14. Dimensions
  15. Segmentation Methods
  16. ...and 32 more sections

Figures (2)

  • Figure 1: Classification modalities
  • Figure 2: Application scenarios of needle detection