This project leverages Artificial Intelligence (AI) to develop a system capable of identifying Cardiac Amyloidosis (CA) in Cardiac Magnetic Resonance (CMR) images. AI has shown remarkable potential in recognizing anatomical structures with higher efficiency than human experts (Falconi et al., n.d.), and machine learning approaches play a pivotal role in many cardiovascular imaging algorithms routinely used for diagnosis and treatment (Henglin et al., 2017).
Cardiac Amyloidosis (CA) is a rare but life-threatening condition caused by the deposition of amyloid proteins in the heart, leading to restrictive cardiomyopathy, heart failure, arrhythmias, and potentially death (Goto et al., 2021). Early diagnosis is critical, as it can significantly improve treatment outcomes (Wechalekar et al., 2016).
The primary goal of this project is to develop an AI-powered system that can identify the presence of CA in CMR scans, improving diagnostic accuracy and reducing time to diagnosis.
CMR is a non-invasive imaging technique that provides detailed insights into the heart's anatomy, function, and tissue characterization. It is particularly effective in diagnosing infiltrative diseases like amyloidosis, where amyloid deposits cause detectable changes in myocardial tissue. Advanced imaging techniques such as T1 mapping and late gadolinium enhancement (LGE) are especially useful for detecting amyloid infiltration with high sensitivity and specificity (Valles, 2019).
The AI system developed in this project analyzes CMR images to identify patterns indicative of CA. This system can be integrated into a Clinical Decision Support System (CDSS), where it would provide healthcare professionals with automated suggestions on whether further tests are needed to confirm or rule out the presence of cardiac amyloidosis, ultimately enhancing diagnostic precision and clinical workflow.
- AI-driven detection of Cardiac Amyloidosis in CMR scans.
- Integration potential with existing medical imaging systems for real-time clinical decision support.
- Early diagnosis of CA to improve patient outcomes and reduce diagnostic delays.
After additional validation and testing, this AI-based solution could be deployed within hospital imaging environments to assist radiologists and cardiologists in making faster, more accurate diagnostic decisions.
-
Clone the repository:
git clone https://github.com/vickyanco/ca-cmr.git
This project is licensed under the MIT License - see the LICENSE file for details.
This project is currently in the development stage. Please refer to the issues for upcoming features and bug fixes.