TY - GEN
T1 - Learning efficient channels with a dual loss autoencoder
AU - Granstedt, Jason L.
AU - Zhou, Weimin
AU - Anastasio, Mark A.
N1 - Funding Information:
This research was supported in part by NIH awards EB020604, EB023045, NS102213, EB028652, and NSF award DMS1614305.
Publisher Copyright:
© 2020 SPIE.
PY - 2020
Y1 - 2020
N2 - In medical imaging systems, task-based metrics have been advocated as a means of evaluating image quality. Mathematical observers are one method of computing such metrics. Although the Bayesian Ideal Observer (IO) is optimal by definition, it is frequently intractable and non-linear. Linear approximations to the IO are sometimes employed to obtain task-based statistics when computing the IO is infeasible. The optimal linear observer for maximizing the SNR of the test statistic is the Hotelling Observer (HO). However, the computational cost for computing the HO increases with image size and becomes intractable for larger images. Channelized methods of reducing the dimensionality of the data before computing the HO have become popular, with efficient channels capable of approximating the HO's performance at significantly reduced computational cost. State-of-the-art channels have been learned by using an autoencoder (AE) to encode data by employing a known signal template as the desired reconstruction, but the method is dependant on a high-quality estimate of the signal. An alternative to channels is approximating the test statistic directly using a feed-forward neural network (FFNN). However, this approach can overfit when the amount of training data is limited. In this work, a generalized method for learning channels utilizing an AE with dual losses (AEDL) is proposed. The AEDL framework jointly minimizes both task-specific and reconstruction losses to learn a set of efficient channels, even when the number of training images is relatively small. Preliminary results indicate that the proposed network outperforms state-of-the-art methods on the selected imaging task. Additionally, the AEDL framework suffers from less overfitting than the FFNN.
AB - In medical imaging systems, task-based metrics have been advocated as a means of evaluating image quality. Mathematical observers are one method of computing such metrics. Although the Bayesian Ideal Observer (IO) is optimal by definition, it is frequently intractable and non-linear. Linear approximations to the IO are sometimes employed to obtain task-based statistics when computing the IO is infeasible. The optimal linear observer for maximizing the SNR of the test statistic is the Hotelling Observer (HO). However, the computational cost for computing the HO increases with image size and becomes intractable for larger images. Channelized methods of reducing the dimensionality of the data before computing the HO have become popular, with efficient channels capable of approximating the HO's performance at significantly reduced computational cost. State-of-the-art channels have been learned by using an autoencoder (AE) to encode data by employing a known signal template as the desired reconstruction, but the method is dependant on a high-quality estimate of the signal. An alternative to channels is approximating the test statistic directly using a feed-forward neural network (FFNN). However, this approach can overfit when the amount of training data is limited. In this work, a generalized method for learning channels utilizing an AE with dual losses (AEDL) is proposed. The AEDL framework jointly minimizes both task-specific and reconstruction losses to learn a set of efficient channels, even when the number of training images is relatively small. Preliminary results indicate that the proposed network outperforms state-of-the-art methods on the selected imaging task. Additionally, the AEDL framework suffers from less overfitting than the FFNN.
KW - Autoencoders
KW - Imaging system optimization
KW - Neural networks
KW - Numerical observers
KW - Objective assessment of image quality
UR - http://www.scopus.com/inward/record.url?scp=85085254403&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85085254403&partnerID=8YFLogxK
U2 - 10.1117/12.2549363
DO - 10.1117/12.2549363
M3 - Conference contribution
AN - SCOPUS:85085254403
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - Medical Imaging 2020
A2 - Samuelson, Frank W.
A2 - Taylor-Phillips, Sian
PB - SPIE
T2 - Medical Imaging 2020: Image Perception, Observer Performance, and Technology Assessment
Y2 - 19 February 2020 through 20 February 2020
ER -