Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

P-Mamba: Marrying Perona Malik Diffusion with Mamba for Efficient Pediatric Echocardiographic Left Ventricular Segmentation

Zi Ye, Tianxiang Chen, Fangyijie Wang, Hanwei Zhang, Lijun Zhang

TL;DR

This paper tackles the challenging problem of accurate and efficient left ventricular segmentation in pediatric echocardiography under heavy noise. It introduces P-Mamba, a hybrid architecture that couples a DWT-based Perona–Malik Diffusion Block for noise suppression with a Vision Mamba block for global context, connected via a Mixture of Experts–style gating mechanism. Across pediatric LV datasets and EchoNet-Dynamic, P-Mamba achieves state-of-the-art Dice scores while maintaining superior computational efficiency, outperforming both CNN- and transformer-based baselines. The proposed approach offers a practical and scalable solution for real-time pediatric echocardiography analysis with improved boundary preservation and reduced resource usage.

Abstract

In pediatric cardiology, the accurate and immediate assessment of cardiac function through echocardiography is crucial since it can determine whether urgent intervention is required in many emergencies. However, echocardiography is characterized by ambiguity and heavy background noise interference, causing more difficulty in accurate segmentation. Present methods lack efficiency and are prone to mistakenly segmenting some background noise areas, such as the left ventricular area, due to noise disturbance. To address these issues, we introduce P-Mamba, which integrates the Mixture of Experts (MoE) concept for efficient pediatric echocardiographic left ventricular segmentation. Specifically, we utilize the recently proposed ViM layers from the vision mamba to enhance our model's computational and memory efficiency while modeling global dependencies.In the DWT-based Perona-Malik Diffusion (PMD) Block, we devise a PMD Block for noise suppression while preserving the left ventricle's local shape cues. Consequently, our proposed P-Mamba innovatively combines the PMD's noise suppression and local feature extraction capabilities with Mamba's efficient design for global dependency modeling. We conducted segmentation experiments on two pediatric ultrasound datasets and a general ultrasound dataset, namely Echonet-dynamic, and achieved state-of-the-art (SOTA) results. Leveraging the strengths of the P-Mamba block, our model demonstrates superior accuracy and efficiency compared to established models, including vision transformers with quadratic and linear computational complexity.

P-Mamba: Marrying Perona Malik Diffusion with Mamba for Efficient Pediatric Echocardiographic Left Ventricular Segmentation

TL;DR

This paper tackles the challenging problem of accurate and efficient left ventricular segmentation in pediatric echocardiography under heavy noise. It introduces P-Mamba, a hybrid architecture that couples a DWT-based Perona–Malik Diffusion Block for noise suppression with a Vision Mamba block for global context, connected via a Mixture of Experts–style gating mechanism. Across pediatric LV datasets and EchoNet-Dynamic, P-Mamba achieves state-of-the-art Dice scores while maintaining superior computational efficiency, outperforming both CNN- and transformer-based baselines. The proposed approach offers a practical and scalable solution for real-time pediatric echocardiography analysis with improved boundary preservation and reduced resource usage.

Abstract

In pediatric cardiology, the accurate and immediate assessment of cardiac function through echocardiography is crucial since it can determine whether urgent intervention is required in many emergencies. However, echocardiography is characterized by ambiguity and heavy background noise interference, causing more difficulty in accurate segmentation. Present methods lack efficiency and are prone to mistakenly segmenting some background noise areas, such as the left ventricular area, due to noise disturbance. To address these issues, we introduce P-Mamba, which integrates the Mixture of Experts (MoE) concept for efficient pediatric echocardiographic left ventricular segmentation. Specifically, we utilize the recently proposed ViM layers from the vision mamba to enhance our model's computational and memory efficiency while modeling global dependencies.In the DWT-based Perona-Malik Diffusion (PMD) Block, we devise a PMD Block for noise suppression while preserving the left ventricle's local shape cues. Consequently, our proposed P-Mamba innovatively combines the PMD's noise suppression and local feature extraction capabilities with Mamba's efficient design for global dependency modeling. We conducted segmentation experiments on two pediatric ultrasound datasets and a general ultrasound dataset, namely Echonet-dynamic, and achieved state-of-the-art (SOTA) results. Leveraging the strengths of the P-Mamba block, our model demonstrates superior accuracy and efficiency compared to established models, including vision transformers with quadratic and linear computational complexity.
Paper Structure (22 sections, 12 equations, 5 figures, 5 tables)

This paper contains 22 sections, 12 equations, 5 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. General Deep Learning Segmentation Methods
  4. Medical Image Segmentation Methods
  5. Mamba
  6. Selective State Space Model
  7. Selection Mechanism
  8. Scan
  9. Methodology
  10. DWT-based PMD Block
  11. Vision Mamba Block
  12. Decoder
  13. Experiment
  14. Datasets
  15. Pediatric Dataset
  16. ...and 7 more sections

Figures (5)

  • Figure 1: Visualization of the noise interference challenge among P-Mamba and other models on the pediatric A4C dataset.
  • Figure 2: The efficiency comparisons between P-Mamba and other models on the pediatric PSAX dataset
  • Figure 3: The structure of our P-Mamba.
  • Figure 4: The visual comparison of different methods.
  • Figure 5: The Visualization of the features of TransUnet, P-Mamba w/o PMD, and P-Mamba.