Abstract
Recent studies reported that a convolutional neural network (CNN; a deep learning model) can detect elevated pulmonary artery wedge pressure (PAWP) from chest radiographs, the diagnostic images most commonly used for assessing pulmonary congestion in heart failure. However, no method has been published for quantitatively estimating PAWP from such radiographs. We hypothesized that a regression CNN, an alternative type of deep learning, could be a useful tool for quantitatively estimating PAWP in cardiovascular diseases. We retrospectively enrolled 936 patients with cardiovascular diseases who had undergone right heart catheterization (RHC) and chest radiography and estimated PAWP by constructing a regression CNN based on the VGG16 model. We randomly categorized 80% of the data as training data (training group, n = 748) and 20% as test data (test group, n = 188). Moreover, we tuned the learning rate—one of the model parameters—by 5-hold cross-validation of the training group. Correlations between PAWP measured by RHC [ground truth (GT) PAWP] and PAWP derived from the regression CNN (estimated PAWP) were tested. To visualize how the regression CNN assessed the images, we created a regression activation map (RAM), a visualization technique for regression CNN. Estimated PAWP correlated significantly with GT PAWP in both the training (r = 0.76, P < 0.001) and test group (r = 0.62, P < 0.001). Bland–Altman plots found a mean (SEM) difference between GT and estimated PAWP of − 0.23 (0.16) mm Hg in the training and − 0.05 (0.41) mm Hg in the test group. The RAM showed that our regression CNN model estimated high PAWP by focusing on the cardiomegaly and pulmonary congestion. In the test group, the area under the curve (AUC) for detecting elevated PAWP (≥ 18 mm Hg) produced by the regression CNN model was similar to the AUC of an experienced cardiologist (0.86 vs 0.83, respectively; P = 0.24). This proof-of-concept study shows that regression CNN can quantitatively estimate PAWP from standard chest radiographs in cardiovascular diseases.
Highlights
The prevalence of heart failure is increasing, and high rates of mortality and hospital admissions due to heart failure represent a major burden on health care systems [1]
When we compared the area under the curve (AUC) for detecting elevated pulmonary artery wedge pressure (PAWP) produced by the regression Convolutional neural network (CNN) model and the cardiologist in test group, we found that the AUC produced by the regression CNN model was similar to that of the cardiologist (0.86 vs 0.83, respectively; P = 0.24)
This is the first clinical study to propose a method for quantitatively estimating PAWP using a regression CNN with standard chest radiographs in patients with cardiovascular diseases
Summary
The prevalence of heart failure is increasing, and high rates of mortality and hospital admissions due to heart failure represent a major burden on health care systems [1]. In heart failure, elevated left atrial pressure causes pulmonary. Chest radiography is the most common diagnostic imaging tool in medicine and has been used as the first-line test for detecting elevated PAWP [4]. Abnormal signs on chest radiographs, such as increased cardiothoracic ratio, alveolar and interstitial edema, and dilated left atrium, were reported to be associated with elevated PAWP [4]. With the recent development of artificial intelligence (AI), deep learning has become a powerful tool to assist with diagnosis in medicine. Convolutional neural network (CNN) is a traditional type of deep learning model for processing data that have a grid pattern, such as images, and is designed to automatically extract features from low- to high-level patterns [7]. In the field of cardiovascular medicine, recent studies found that CNN was useful for detecting cardiomegaly, heart failure, and elevated PAWP from chest radiographs [11–13].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
