Peering into the Heart: A Comprehensive Exploration of Semantic Segmentation and Explainable AI on the MnMs-2 Cardiac MRI Dataset

Peering into the Heart: A Comprehensive Exploration of Semantic Segmentation and Explainable AI on the MnMs-2 Cardiac MRI Dataset

Accurate and interpretable segmentation of medical images is crucial for computer-aided diagnosis and image-guided interventions. This study explores the integration of semantic segmentation and explainable AI techniques on the MnMs-2 Cardiac MRI dataset. We propose a segmentation model that achieve...

Full description

Saved in:
Bibliographic Details
Main Authors: Ayoob Mohamed, Nettasinghe Oshan, Sylvester Vithushan, Bowala Helmini, Mohideen Hamdaan
Format: Article
Language:English
Published: Sciendo 2025-01-01
Series:Applied Computer Systems
Subjects:
cardiac magnetic resonance imaging (cmri) semantic segmentation
explainable ai (xai)
residual blocks
vision transformer (vit)
Online Access:https://doi.org/10.2478/acss-2025-0002
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Accurate and interpretable segmentation of medical images is crucial for computer-aided diagnosis and image-guided interventions. This study explores the integration of semantic segmentation and explainable AI techniques on the MnMs-2 Cardiac MRI dataset. We propose a segmentation model that achieves competitive dice scores (nearly 90 %) and Hausdorff distance (less than 70), demonstrating its effectiveness for cardiac MRI analysis. Furthermore, we leverage Grad-CAM, and Feature Ablation, explainable AI techniques, to visualise the regions of interest guiding the model predictions for a target class. This integration enhances interpretability, allowing us to gain insights into the model decision-making process and build trust in its predictions.
ISSN:2255-8691

Similar Items