MedSegDiffNCA: Diffusion Models With Neural Cellular Automata for Skin Lesion Segmentation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mittal, Avni, Kalkhof, John, Mukhopadhyay, Anirban, Bhavsar, Arnav
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912177655382016
author Mittal, Avni
Kalkhof, John
Mukhopadhyay, Anirban
Bhavsar, Arnav
author_facet Mittal, Avni
Kalkhof, John
Mukhopadhyay, Anirban
Bhavsar, Arnav
contents Denoising Diffusion Models (DDMs) are widely used for high-quality image generation and medical image segmentation but often rely on Unet-based architectures, leading to high computational overhead, especially with high-resolution images. This work proposes three NCA-based improvements for diffusion-based medical image segmentation. First, Multi-MedSegDiffNCA uses a multilevel NCA framework to refine rough noise estimates generated by lower level NCA models. Second, CBAM-MedSegDiffNCA incorporates channel and spatial attention for improved segmentation. Third, MultiCBAM-MedSegDiffNCA combines these methods with a new RGB channel loss for semantic guidance. Evaluations on Lesion segmentation show that MultiCBAM-MedSegDiffNCA matches Unet-based model performance with dice score of 87.84% while using 60-110 times fewer parameters, offering a more efficient solution for low resource medical settings.
format Preprint
id arxiv_https___arxiv_org_abs_2501_02447
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MedSegDiffNCA: Diffusion Models With Neural Cellular Automata for Skin Lesion Segmentation
Mittal, Avni
Kalkhof, John
Mukhopadhyay, Anirban
Bhavsar, Arnav
Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
Denoising Diffusion Models (DDMs) are widely used for high-quality image generation and medical image segmentation but often rely on Unet-based architectures, leading to high computational overhead, especially with high-resolution images. This work proposes three NCA-based improvements for diffusion-based medical image segmentation. First, Multi-MedSegDiffNCA uses a multilevel NCA framework to refine rough noise estimates generated by lower level NCA models. Second, CBAM-MedSegDiffNCA incorporates channel and spatial attention for improved segmentation. Third, MultiCBAM-MedSegDiffNCA combines these methods with a new RGB channel loss for semantic guidance. Evaluations on Lesion segmentation show that MultiCBAM-MedSegDiffNCA matches Unet-based model performance with dice score of 87.84% while using 60-110 times fewer parameters, offering a more efficient solution for low resource medical settings.
title MedSegDiffNCA: Diffusion Models With Neural Cellular Automata for Skin Lesion Segmentation
topic Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2501.02447