Image analysis of cardiac hepatopathy secondary to heart failure: Machine learning vs gastroenterologists and
Suguru Miida1, Hiroteru Kamimura2, Shinya Fujiki3
1Division of Gastroenterology and Hepatology, Graduate School of Medical and Dental Sciences, Niigata University, Niigata 951-8520, Japan.
Insights
Machine learning accurately identifies congestive hepatopathy (nutmeg liver) using CT scans by predicting tricuspid regurgitation severity. This aids early liver dysfunction detection in heart failure patients.
Area of Science:
- Radiology
- Cardiology
- Hepatology
- Artificial Intelligence
Background:
- Congestive hepatopathy, or nutmeg liver, is liver damage linked to chronic heart failure (HF).
- Current medical imaging lacks defined characteristics for this condition.
- Early detection of liver dysfunction in HF patients remains a challenge.
Purpose of the Study:
- To utilize machine learning (ML) for identifying congestive hepatopathy imaging features.
- To develop an ML model using incidentally acquired computed tomography (CT) scans.
- To correlate imaging findings with heart failure severity.
Main Methods:
- Retrospective analysis of 179 chronic HF patients with echocardiography and CT data.
- Development of a ResNet-based ML model to predict tricuspid regurgitation (TR) severity from liver CT images.
- Comparison of ML model accuracy against expert clinician performance.
Main Results:
- The ML model demonstrated significantly higher accuracy in predicting TR severity compared to experts.
- The model proved exceptionally reliable in identifying severe TR.
- Analysis included 120 male patients with a mean age of 73.1 years.
Conclusions:
- Deep learning models, specifically ResNet architectures, can detect morphological changes related to TR severity.
- This approach aids in the early identification of liver dysfunction in HF patients.
- Improved early detection may lead to better patient outcomes.
Background:
Congestive hepatopathy, also known as nutmeg liver, is liver damage secondary to chronic heart failure (HF). Its morphological characteristics in terms of medical imaging are not defined and remain unclear.
Aim:
To leverage machine learning to capture imaging features of congestive hepatopathy using incidentally acquired computed tomography (CT) scans.
Methods:
We retrospectively analyzed 179 chronic HF patients who underwent echocardiography and CT within one year. Right HF severity was classified into three grades. Liver CT images at the paraumbilical vein level were used to develop a ResNet-based machine learning model to predict tricuspid regurgitation (TR) severity. Model accuracy was compared with that of six gastroenterology and four radiology experts.
Results:
In the included patients, 120 were male (mean age: 73.1 ± 14.4 years). The accuracy of the results predicting TR severity from a single CT image for the machine learning model was significantly higher than the average accuracy of the experts. The model was found to be exceptionally reliable for predicting severe TR.
Conclusion:
Deep learning models, particularly those using ResNet architectures, can help identify morphological changes associated with TR severity, aiding in early liver dysfunction detection in patients with HF, thereby improving outcomes.
