Assessing the performance of CT image denoisers using Laguerre-Gauss Channelized Hotelling Observer for lesion detection
This work addresses the problem of evaluating diagnostic quality in CT denoising for medical imaging practitioners, highlighting a gap between visual and task-based performance, though it is incremental in applying existing assessment methods.
The study assessed deep learning CT image denoisers for lesion detection, finding they improved visual metrics like PSNR by 2.4-3.8 dB and SSIM by 0.05-0.11 compared to low-dose CT, but detectability with quarter-dose denoised images was inferior to normal-dose CT scans.
The remarkable success of deep learning methods in solving computer vision problems, such as image classification, object detection, scene understanding, image segmentation, etc., has paved the way for their application in biomedical imaging. One such application is in the field of CT image denoising, whereby deep learning methods are proposed to recover denoised images from noisy images acquired at low radiation. Outputs derived from applying deep learning denoising algorithms may appear clean and visually pleasing; however, the underlying diagnostic image quality may not be on par with their normal-dose CT counterparts. In this work, we assessed the image quality of deep learning denoising algorithms by making use of visual perception- and data fidelity-based task-agnostic metrics (like the PSNR and the SSIM) - commonly used in the computer vision - and a task-based detectability assessment (the LCD) - extensively used in the CT imaging. When compared against normal-dose CT images, the deep learning denoisers outperformed low-dose CT based on metrics like the PSNR (by 2.4 to 3.8 dB) and SSIM (by 0.05 to 0.11). However, based on the LCD performance, the detectability using quarter-dose denoised outputs was inferior to that obtained using normal-dose CT scans.