Residual encoder-decoder based architecture for medical image denoising

• Published in: Multimedia tools and applications Vol. 84; no. 19; pp. 21625 - 21642
• Main Authors: Ferdi, Abdesselam, Benierbah, Said, Nakib, Amir
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.06.2025; Springer Nature B.V
• Subjects: 1239: Emerging Trends and Applications of Deep Learning for Biomedical Data Analysis; Algorithms; Computed tomography; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Datasets; Deep learning; Edge detection; Efficiency; Encoders-Decoders; Image resolution; Medical imaging; Methods; Multimedia Information Systems; Noise reduction; Radiation; Special Purpose and Application-Based Systems; X-rays; Edge detection; Low dose CT; Multi task learning; Image denoising
• ISSN: 1573-7721; 1380-7501; 1573-7721
• DOI: 10.1007/s11042-024-20175-1

High-resolution computed tomography (CT) scans require high doses of X-rays, posing potential health risks to patients, including genetic damage and cancer. Conversely, low doses of X-rays result in noise and artifacts in the reconstructed CT scans. Consequently, the problem of denoising low-dose CT (LDCT) images has become a critical yet challenging issue in the field of CT imaging. However, existing deep learning-based LDCT image denoising methods frequently result in the loss of high-frequency features, such as edges and textures, due to the use of mean squared error loss. To address this issue, we propose a method based on high-frequency feature learning to enhance the denoising performance of existing models. Our method is designed to simultaneously learn the primary task of LDCT image denoising and the auxiliary task of LDCT edge detection, thereby improving the denoising performance without increasing the number of model parameters and the inference time. Our method significantly improves the denoising performance of the RED-CNN model, achieving competitive results compared to state-of-the-art denoising models on the AAPM and Qin-LUNG-CT datasets.