TY - GEN
T1 - Multi-energy CT material decomposition using Bayesian deep convolutional neural network with explicit penalty of uncertainty and bias
AU - Gong, Hao
AU - Leng, Shuai
AU - Baffour, Francis
AU - Yu, Lifeng
AU - Fletcher, Joel G.
AU - McCollough, Cynthia H.
N1 - Publisher Copyright:
© COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.
PY - 2023
Y1 - 2023
N2 - Convolutional neural network (CNN)-based material decomposition has the potential to improve image quality (visual appearance) and quantitative accuracy of material maps. Most methods use deterministic CNNs with mean-square-error loss to provide point-estimates of mass densities. Point estimates can be over-confident as the reliability of CNNs is frequently compromised by bias and two major uncertainties - data and model uncertainties originating from noise in inputs and train-test data dissimilarity, respectively. Also, mean-square-error lacks explicit control of uncertainty and bias. To tackle these problems, a Bayesian dual-task CNN (BDT-CNN) with explicit penalization of uncertainty and bias was developed. It is a probabilistic CNN that concurrently conducts material classification and quantification and allows for pixel-wise modeling of bias, data uncertainty, and model uncertainty. CNN was trained with images of physical and simulated tissue-mimicking inserts at varying mass densities. Hydroxyapatite (nominal density 400mg/cc) and blood (nominal density 1095mg/cc) inserts were placed in different-sized body phantoms (30 - 45cm) and used to evaluate mean-absolute-bias (MAB) in predicted mass densities across different images at routine- and half-routine-dose. Patient CT exams were collected to assess generalizability of BDT-CNN in the presence of anatomical background. Noise insertion was used to simulate patient exams at half- and quarter-routine-dose. The deterministic dual-task CNN was used as baseline. In phantoms, BDT-CNN improved consistency of insert delineation, especially edges, and reduced overall bias (average MAB for hydroxyapatite: BDT-CNN 5.4mgHA/cc, baseline 11.0mgHA/cc and blood: BDT-CNN 8.9mgBlood/cc, baseline 14.0mgBlood/cc). In patient images, BDT-CNN improved detail preservation, lesion conspicuity, and structural consistency across different dose levels.
AB - Convolutional neural network (CNN)-based material decomposition has the potential to improve image quality (visual appearance) and quantitative accuracy of material maps. Most methods use deterministic CNNs with mean-square-error loss to provide point-estimates of mass densities. Point estimates can be over-confident as the reliability of CNNs is frequently compromised by bias and two major uncertainties - data and model uncertainties originating from noise in inputs and train-test data dissimilarity, respectively. Also, mean-square-error lacks explicit control of uncertainty and bias. To tackle these problems, a Bayesian dual-task CNN (BDT-CNN) with explicit penalization of uncertainty and bias was developed. It is a probabilistic CNN that concurrently conducts material classification and quantification and allows for pixel-wise modeling of bias, data uncertainty, and model uncertainty. CNN was trained with images of physical and simulated tissue-mimicking inserts at varying mass densities. Hydroxyapatite (nominal density 400mg/cc) and blood (nominal density 1095mg/cc) inserts were placed in different-sized body phantoms (30 - 45cm) and used to evaluate mean-absolute-bias (MAB) in predicted mass densities across different images at routine- and half-routine-dose. Patient CT exams were collected to assess generalizability of BDT-CNN in the presence of anatomical background. Noise insertion was used to simulate patient exams at half- and quarter-routine-dose. The deterministic dual-task CNN was used as baseline. In phantoms, BDT-CNN improved consistency of insert delineation, especially edges, and reduced overall bias (average MAB for hydroxyapatite: BDT-CNN 5.4mgHA/cc, baseline 11.0mgHA/cc and blood: BDT-CNN 8.9mgBlood/cc, baseline 14.0mgBlood/cc). In patient images, BDT-CNN improved detail preservation, lesion conspicuity, and structural consistency across different dose levels.
KW - Bayesian neural network
KW - Multi-energy CT
KW - bias
KW - deep learning
KW - material decomposition
KW - uncertainty
UR - http://www.scopus.com/inward/record.url?scp=85160755402&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85160755402&partnerID=8YFLogxK
U2 - 10.1117/12.2654317
DO - 10.1117/12.2654317
M3 - Conference contribution
AN - SCOPUS:85160755402
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - Medical Imaging 2023
A2 - Yu, Lifeng
A2 - Fahrig, Rebecca
A2 - Sabol, John M.
PB - SPIE
T2 - Medical Imaging 2023: Physics of Medical Imaging
Y2 - 19 February 2023 through 23 February 2023
ER -