Denoising transthoracic echocardiographic images in regional wall motion abnormality using deep learning techniques

Image analysis and classification perform well in pre-processed noise-free images than in corrupted images. Synthetic aperture radar (SAR) images, Ultrasound (US) medical images, etc. exhibit speckle noise, which has a multiplicative and granular behavior. In the existing techniques, the autoencoders are used to implement a deep learning-based denoising method specifically for US images. The traditional image denoising techniques as well as deep learning techniques for image denoising. In this paper, we have proposed a deep learning-based model called, Convolutional-based improved despeckling autoencoder (CIDAE) for denoising transthoracic echocardiographic images. The dataset for the network has been collected from patients having Regional Wall Motion Abnormality (RWMA). There were 294 subjects with routine transthoracic examinations, consisting of 151 RWMA and 143 normal hearts (55.7 percent female, ages 20-75 years). The potential of the proposed DL algorithms was evaluated visually and quantitatively using the Structural Similarity Index Measure (SSIM), Peak Signal Noise Ratio (PSNR), and Mean Squared Error (MSE). Our results demonstrate the significance of the proposed CIDAE for denoising echo images of patients with RWMA and structurally normal hearts with a promising p-value < 0.0001.

Automated summary

A deep learning-based denoising model called Convolutional-based improved despeckling autoencoder (CIDAE) is proposed in this paper for denoising transthoracic echocardiographic images. The model is trained with a dataset collected from patients with Regional Wall Motion Abnormality (RWMA). The significance of the proposed CIDAE model for denoising echo images of patients with RWMA and structurally normal hearts is demonstrated through visual and quantitative evaluation.