Assessment of patch-based mammogram denoising methods using virtual clinical trials and deep learning: trade-off between denoising strength and preservation of structural details
Vincent Dong, Tristan D. Maidment, Lucas Rodrigues Azevedo Pinheiro Borges, Bruno Barufaldi, Susan Ng, Andrew D. A. Maidment · Medical Imaging 2022: Physics of Medical Imaging · 2022
Noiseless digital mammograms (DM) are unobtainable in clinical screening environments, limiting the development of deep learning-based (DL) denoising applications. Virtual clinical trials (VCTs) allow the precise simulation of noise levels in DM images for controlled training of DL models. We evaluated a set of DL denoising models, trained using VCT data, that showcases the trade-offs between denoising strength and fine structure preservation. Our results show that metrics, such as peak signal-to-noise ratio (PSNR), are improved with the use of our trained residual convolutional neural network. This quantifiable improvement indicates that our proposed DL methodology can accurately denoise simulated mammograms.