What type of study is this?

This is a Quantitative Study study.

September 17, 2025

Optimizing Cardiac MR Image Segmentation: Fine-Tuning the Foundational Segment Anything Model (SAM)

Key Points

The fine-tuned model achieved an impressive average Dice Score of 0.951, indicating high accuracy in segmenting cardiac structures.
Using the ACDC cardiac dataset, segmentation techniques were refined for improved identification of the left ventricle, right ventricle, and myocardium.
Fine-tuning the Segment Anything Model's decoder enhances analysis and diagnostic workflows in patients with heart conditions.
This innovation may enable earlier detection and better assessment of heart function and diseases like heart failure and cardiomyopathy.

Abstract

Motivation: Cardiac image segmentation is essential for accurately assessing heart structure in conditions like heart failure. However, general-purpose models lack the specialized focus needed for cardiac MRI. Goal(s): This study fine-tunes the Foundational Segment Anything Model (SAM) to enhance segmentation accuracy on ACDC cardiac dataset, targeting the left ventricle (LV), right ventricle (RV), and myocardium (MYO). Approach: We performed fine-tuning of adapter blocks on SAM's decoder using sam-vit-base model with annotated cine MRI and evaluated segmentation on an unseen test set. Results: The fine-tuned SAM achieved an average Dice Score of 0.951±0.039 and IoU of 0.909±0.065, improving over state-of-the-art models. Impact: Fine-tuning of the foundational model SAM for cardiac MRI offers enhanced segmentation accuracy, enabling precise assessments of heart structure and function. This advancement supports improved diagnostic workflows and potential early detection in conditions like heart failure and cardiomyopathy.

Mark Helpful

Bookmark

Relay