DEMIST: A deep-learning-based task-specific denoising approach for myocardial perfusion SPECT
Authors:
- Ashequr RahmanARAshequr Rahman
- Zitong YuZYZitong Yu
- Richard LaforestRLRichard Laforest
- Craig K. AbbeyCACraig K. Abbey
- Barry A. SiegelBSBarry A. Siegel
- Abhinav K. JhaAJAbhinav K. Jha
Preprint
Abstract
There is an important need for methods to process myocardial perfusion imaging (MPI) SPECT images acquired at lower radiation dose and/or acquisition time such that the processed images improve observer performance on the clinical task of detecting perfusion defects. To address this need, we build upon concepts from model-observer theory and our understanding of the human visual system to propose a Detection task-specific deep-learning-based approach for denoising MPI SPECT images (DEMIST). The approach, while performing denoising, is designed to preserve features that influence observer performance on detection tasks. We objectively evaluated DEMIST on the task of detecting perfusion defects using a retrospective study with anonymized clinical data in patients who underwent MPI studies across two scanners (N = 338). The evaluation was performed at low-dose levels of 6.25%, 12.5% and 25% and using an anthropomorphic channelized Hotelling observer. Performance was quantified using area under the receiver operating characteristics curve (AUC). Images denoised with DEMIST yielded significantly higher AUC compared to corresponding low-dose images and images denoised with a commonly used task-agnostic DL-based denoising method. Similar results were observed with stratified analysis based on patient sex and defect type. Additionally, DEMIST improved visual fidelity of the low-dose images as quantified using root mean squared error and structural similarity index metric. A mathematical analysis revealed that DEMIST preserved features that assist in detection tasks while improving the noise properties, resulting in improved observer performance. The results provide strong evidence for further clinical evaluation of DEMIST to denoise low-count images in MPI SPECT.Keywords
All Related Versions
This publication has 41 references indexed in Scilit:
- Observer studies of image quality of denoising reduced-count cardiac single photon emission computed tomography myocardial perfusion imaging by three-dimensional Gaussian post-reconstruction filtering and deep learningJournal of Nuclear Cardiology, 2023
- Need for objective task‐based evaluation of deep learning‐based denoising methods: A study in the context of myocardial perfusion SPECTMedical Physics, 2023
- Deep learning-based denoising in projection-domain and reconstruction-domain for low-dose myocardial perfusion SPECTJournal of Nuclear Cardiology, 2022
- Low‐dose CT denoising via convolutional neural network with an observer loss functionMedical Physics, 2021
- The important role of task-based model observers and related techniques in medical imagingJournal of Nuclear Cardiology, 2019
- Investigation of dose reduction in cardiac perfusion SPECT via optimization and choice of the image reconstruction strategyJournal of Nuclear Cardiology, 2017
- ASNC imaging guidelines for SPECT nuclear cardiology procedures: Stress, protocols, and tracersJournal of Nuclear Cardiology, 2016
- Radiation Reduction: How Low Can YOU go?Journal of Nuclear Cardiology, 2010
- Importance of consideration of radiation doses from cardiac imaging procedures and risks of cancerJournal of Nuclear Cardiology, 2010
- A Monte Carlo program for the simulation of scintillation camera characteristicsComputer Methods and Programs in Biomedicine, 1989