Research Article

HMP-MUNet: A Hybrid Deep Learning Framework for Automated Skin Lesion Segmentation in Dermoscopic Images

DOI:

10.3791/69449

March 17th, 2026

* These authors contributed equally

In This Article

Summary

Loading...
$$\rightleftharpoonup{xx}$$ $$\longleftharp{xx}$$, $$\longrightharp{xx}$$,

HMP-MUNet introduces a hybrid deep learning framework for automated skin lesion segmentation. By integrating State-Space Models with multi-scale attention mechanisms, it enhances segmentation accuracy while optimizing computational efficiency, offering a robust solution for skin cancer diagnosis in clinical settings.

Abstract

Loading...
$$\rightleftharpoonup{xx}$$ $$\longleftharp{xx}$$, $$\longrightharp{xx}$$,

Computer-aided diagnosis systems for cutaneous lesions face significant challenges in achieving both high diagnostic accuracy and computational efficiency. Current deep learning approaches often require substantial computational resources while struggling to capture the complex morphological variations inherent in skin lesions across different scales. High-order Multi-scale Parallel Vision Mamba U-Net (HMP-MUNet), a novel deep learning framework that addresses these limitations through an innovative architectural design combining State-Space Models with advanced multi-scale processing capabilities.

The approach described in this study integrates a hybrid U-Net framework that combines a high-order vision state-space module for global context modeling, a multi-scale dilated attention fusion network for hierarchical feature extraction across multiple receptive fields, and a parallel multi-depth flexible network for computational optimization. This architecture uses a modified U-shaped encoder-decoder with increased channel dimensions and advanced attention mechanisms to enhance feature learning.

Comprehensive evaluation on benchmark datasets shows a Dice Similarity Coefficient of 95.85% on PH2 and 90.44% on ISIC2018. The model accomplishes this superior accuracy using only 7.61M parameters, representing a remarkable 72.2% reduction compared to existing Vision Mamba architectures while maintaining high segmentation accuracy. The lightweight design shows potential for deployment across various clinical settings and imaging modalities, pending clinical validation, from specialized dermatology centers to primary care facilities.

HMP-MUNet provides an automated solution for skin lesion segmentation that improves diagnostic consistency and supports clinical workflows, with potential for further validation in clinical use. The integration of high-order modeling capabilities with practical deployment considerations offers a potential solution for improving skin cancer screening protocols and expanding healthcare accessibility in computer-aided diagnosis applications.

Introduction

Loading...
$$\rightleftharpoonup{xx}$$ $$\longleftharp{xx}$$, $$\longrightharp{xx}$$,

Computer-aided diagnosis (CAD) systems aim to improve medical imaging practices across clinical specialties, enhancing disease detection, diagnosis, and treatment planning approaches1. In dermatology, the integration of artificial intelligence (AI) and advanced imaging techniques has emerged as a critical tool for improving diagnostic accuracy and clinical outcomes, particularly in early detection of skin cancer, which accounts for approximately 90% of all skin malignancies2. The development of sophisticated algorithmic approaches for automated cutaneous lesion analysis contributes to the advancement of precision medicin....

Access restricted. Please log in or start a trial to view this content.

Protocol

Loading...
$$\rightleftharpoonup{xx}$$ $$\longleftharp{xx}$$, $$\longrightharp{xx}$$,

This research was performed in compliance with institutional guidelines for computational research and data processing. No human subjects or vertebrate animals were involved in this study.

Dataset preparation and preprocessing

Dataset collection and organization

Dermoscopic images were collected from the PH2, ISIC2018, and ISIC2017 datasets, with specific links provided in the Table of Materials. The PH2 dataset contains 200 high-resolution images (1000 × 1000 pixels), ISIC2018 includes 2,594 images with corresponding ....

Access restricted. Please log in or start a trial to view this content.

Results

Loading...
$$\rightleftharpoonup{xx}$$ $$\longleftharp{xx}$$, $$\longrightharp{xx}$$,

HMP-MUNet architecture design for medical image segmentation

The proposed HMP-MUNet architecture demonstrated exceptional performance in automated cutaneous lesion segmentation tasks. Figure 1 illustrates the complete network architecture, showcasing the hierarchical U-shaped encoder-decoder structure with progressive channel expansion from 8 to 256 channels. The integration of three specialized modules in alternating configuration proved highly e.......

Access restricted. Please log in or start a trial to view this content.

Discussion

Loading...
$$\rightleftharpoonup{xx}$$ $$\longleftharp{xx}$$, $$\longrightharp{xx}$$,

This study presents HMP-MUNet (High-order Multi-scale Parallel Vision Mamba U-Net), a novel deep learning framework that addresses fundamental challenges in computer-aided diagnosis (CAD) for cutaneous lesion segmentation through innovative integration of State-Space Models (SSMs) with advanced architectural components1. The approach described here demonstrates that combining high-order feature interaction mechanisms with multi-scale attention and parallel processing can achieve superior diagnosti.......

Access restricted. Please log in or start a trial to view this content.

Disclosures

Loading...
$$\rightleftharpoonup{xx}$$ $$\longleftharp{xx}$$, $$\longrightharp{xx}$$,

The authors declare that they have no conflicts of interest related to this research. No financial relationships exist between the authors and any commercial entities that could inappropriately influence the work presented in this manuscript. This research was conducted independently, and the findings and conclusions are solely those of the authors. The text of this manuscript was revised and polished with the assistance of ChatGPT, as English is not the authors' native language. The authors confirm that the use of AI assistance was limited to language editing and did not involve any content generation or analysis that would affect the scientific integrity of the work.

Acknowledgements

Loading...
$$\rightleftharpoonup{xx}$$ $$\longleftharp{xx}$$, $$\longrightharp{xx}$$,

The authors gratefully acknowledge the financial support provided by the Scientific Research Project of Liaoning Provincial Department of Education under Grant LJ212510149013 and General Program of National Natural Science Foundation of Liaoning Province 2024-MSLH-377, which made this research possible. We thank the research participants and institutions that contributed to the publicly available datasets used in this study, which enabled comprehensive validation of our proposed methodology.

....

Access restricted. Please log in or start a trial to view this content.

Materials

List of materials used in this article
NameCompanyCatalog NumberComments
CUDA 11.8NVIDIA Corporation, Santa Clara, CA, USASoftware
GPU (32 GB VRAM)NVIDIAOperating system
ISIC2017 DatasetISIC Challengehttps://challenge.isic-archive.com/dataDatasets
ISIC2018 DatasetISIC Challengehttps://challenge.isic-archive.com/dataDatasets
NVIDIA V100 GPUNVIDIA Corporation, Santa Clara, CA, USAHardware
PH2 DatasetUniversidade Do Portohttps://www.fc.up.pt/addi/ph2Datasets
Python 3.8PythonRRID:SCR_018536Software
PyTorch 1.13.0PyTorchRRID:SCR_018536Software
Ubuntu 20.04CanonicalHardware

References

Loading...
$$\rightleftharpoonup{xx}$$ $$\longleftharp{xx}$$, $$\longrightharp{xx}$$,
  1. Maurya, S., et al. A review on recent developments in cancer detection using machine learning and deep learning models. Biomed Signal Process Control. 80 (2), 104398(2023).
  2. Siegel, R. L., Miller, K. D., Wagle, N. S., Jemal, A. Cancer statistics, 2023. CA ....

Access restricted. Please log in or start a trial to view this content.

Reprints and Permissions

Request permission to reuse the text or figures of this JoVE article

Request Permission

Tags

U Net ArchitectureState Space ModelsMulti Scale ProcessingAttention MechanismsComputer Aided DiagnosisFeature ExtractionVision Mamba

Related Articles