Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards Multi-modality Fusion and Prototype-based Feature Refinement for Clinically Significant Prostate Cancer Classification in Transrectal Ultrasound

Hong Wu, Juan Fu, Hongsheng Ye, Yuming Zhong, Xuebin Zou, Jianhua Zhou, Yi Wang

TL;DR

A novel learning framework for clinically significant prostate cancer (csPCa) classification using multi-modality TRUS, which generates visual class activation mapping (CAM), which can serve as valuable assistance for localizing csPCa.

Abstract

Prostate cancer is a highly prevalent cancer and ranks as the second leading cause of cancer-related deaths in men globally. Recently, the utilization of multi-modality transrectal ultrasound (TRUS) has gained significant traction as a valuable technique for guiding prostate biopsies. In this study, we propose a novel learning framework for clinically significant prostate cancer (csPCa) classification using multi-modality TRUS. The proposed framework employs two separate 3D ResNet-50 to extract distinctive features from B-mode and shear wave elastography (SWE). Additionally, an attention module is incorporated to effectively refine B-mode features and aggregate the extracted features from both modalities. Furthermore, we utilize few shot segmentation task to enhance the capacity of classification encoder. Due to the limited availability of csPCa masks, a prototype correction module is employed to extract representative prototypes of csPCa. The performance of the framework is assessed on a large-scale dataset consisting of 512 TRUS videos with biopsy-proved prostate cancer. The results demonstrate the strong capability in accurately identifying csPCa, achieving an area under the curve (AUC) of 0.86. Moreover, the framework generates visual class activation mapping (CAM), which can serve as valuable assistance for localizing csPCa. These CAM images may offer valuable guidance during TRUS-guided targeted biopsies, enhancing the efficacy of the biopsy procedure.The code is available at https://github.com/2313595986/SmileCode.

Towards Multi-modality Fusion and Prototype-based Feature Refinement for Clinically Significant Prostate Cancer Classification in Transrectal Ultrasound

TL;DR

A novel learning framework for clinically significant prostate cancer (csPCa) classification using multi-modality TRUS, which generates visual class activation mapping (CAM), which can serve as valuable assistance for localizing csPCa.

Abstract

Prostate cancer is a highly prevalent cancer and ranks as the second leading cause of cancer-related deaths in men globally. Recently, the utilization of multi-modality transrectal ultrasound (TRUS) has gained significant traction as a valuable technique for guiding prostate biopsies. In this study, we propose a novel learning framework for clinically significant prostate cancer (csPCa) classification using multi-modality TRUS. The proposed framework employs two separate 3D ResNet-50 to extract distinctive features from B-mode and shear wave elastography (SWE). Additionally, an attention module is incorporated to effectively refine B-mode features and aggregate the extracted features from both modalities. Furthermore, we utilize few shot segmentation task to enhance the capacity of classification encoder. Due to the limited availability of csPCa masks, a prototype correction module is employed to extract representative prototypes of csPCa. The performance of the framework is assessed on a large-scale dataset consisting of 512 TRUS videos with biopsy-proved prostate cancer. The results demonstrate the strong capability in accurately identifying csPCa, achieving an area under the curve (AUC) of 0.86. Moreover, the framework generates visual class activation mapping (CAM), which can serve as valuable assistance for localizing csPCa. These CAM images may offer valuable guidance during TRUS-guided targeted biopsies, enhancing the efficacy of the biopsy procedure.The code is available at https://github.com/2313595986/SmileCode.
Paper Structure (11 sections, 9 equations, 5 figures, 1 table)

This paper contains 11 sections, 9 equations, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Method
  3. Dimensional Attention Module
  4. Adaptive Spatial Attention Module
  5. Few Shot Segmentation for csPCa
  6. Experiments
  7. Dataset.
  8. Implementation Details.
  9. Quantitative and Qualitative Results.
  10. Conclusion
  11. Acknowledgments.

Figures (5)

  • Figure 1: Visualization of csPCa masks (red) on the specific frames from 4 TRUS videos.
  • Figure 2: Schematic overview of our method for identification of csPCa. Segmentation serves as an auxiliary task for enhancing classification performance.
  • Figure 3: Architecture of the attention module and prototype correction module.
  • Figure 4: Comparison of ROC curves for different methods on the testing set.
  • Figure 5: Nine examples illustrating TRUS frames and their corresponding CAM generated by our network. The ultrasound radiologists verified that the model's predictions of suspicious tumor regions were in agreement with the spatial locations provided by the pathologists.