Direct Dual Energy CT Material Decomposition Using Noise2Noise Prior

Wei Fang; Dufan Wu; Kyungsang Kim; Ramandeep Singh; Mannudeep K. Kalra; Liang Li; Quanzheng Li

doi:10.1109/NSS/MIC42677.2020.9508021

Back

Conference proceeding

Direct Dual Energy CT Material Decomposition Using Noise2Noise Prior

Wei Fang, Dufan Wu, Kyungsang Kim, Ramandeep Singh, Mannudeep K. Kalra, Liang Li and Quanzheng Li

2020 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC), pp.1-3

10/31/2020

DOI: 10.1109/NSS/MIC42677.2020.9508021

View Online

Abstract

Dual energy computed tomography (DECT) can provide material decomposition capability, which can be useful for many clinical diagnosis applications. But the decomposed images can be very noisy due to the dose limit in the scanning and the ill-condition of decomposition process. Recently Noise2Noise framework shows its potential on restoring images by using only noisy data. Inspired by this, we proposed an iterative DECT reconstruction algorithm with a Noise2Noise prior. The algorithm directly estimates material images from projection data and thus can significantly reduce possible bias which may occur in other post-smoothen methods. The Noise2Noise prior was built by a deep neural network, which did NOT need external data for training. The data fidelity term and the Noise2Noise network are alternatively optimized respectively using separable quadratic surrogate (SQS) and Adam algorithm. The method was validated both on simulation data and real clinical data. Quantitative analysis demonstrates the method's promising performance on denoising, bias avoiding and detail reservation.

Computed tomography

Iterative algorithms

Noise reduction

Reconstruction algorithms

Statistical analysis

Training

Training data

Details

Title: Subtitle: Direct Dual Energy CT Material Decomposition Using Noise2Noise Prior
Creators: Wei Fang - Harvard University
Dufan Wu - Massachusetts General Hospital
Kyungsang Kim - Massachusetts General Hospital
Ramandeep Singh - Massachusetts General Hospital
Mannudeep K. Kalra - Massachusetts General Hospital
Liang Li - Tsinghua University
Quanzheng Li - Massachusetts General Hospital
Resource Type: Conference proceeding
Publication Details: 2020 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC), pp.1-3
Publisher: IEEE
DOI: 10.1109/NSS/MIC42677.2020.9508021
eISSN: 2577-0829
Grant note: 11775124 / NSFC (10.13039/501100001809) 2017YFC0109103 / NKRDPC (10.13039/501100012166)
Language: English
Date published: 10/31/2020
Academic Unit: Radiology
Record Identifier: 9984697626002771

Metrics

1 Record Views