Direct Optimization of Signal Detection Metrics in Learning-Based CT Image Restoration

Document Type

Conference Proceeding

Publication Date

2025

Publisher

Society of Photo-optical Instrumentation Engineers (SPIE)

Source Publication

Proceedings, SPIE Medical Imaging Conference

Source ISSN

9781510685963

Original Item ID

DOI: 10.1117/12.3047298

Abstract

Convolutional neural networks (CNNs) used for medical image restoration tasks are typically trained by minimizing pixel-wise error metrics, such as mean-squared error (MSE). However, CNNs trained with these losses are prone to wipe-out small/low-contrast features that can be critical for screening and diagnosis. To address this issue, we introduce a novel training loss designed to preserve weak signals in CNN-processed images. The key idea is to measure model observer performance on a user-specified signal detection task implanted in the training data. The proposed loss improves on the recently introduced Observer Regularizer (ObsReg) loss,1,2 which is not directly interpretable in terms of signal detection theory and requires specialized training. In contrast, the proposed loss function is defined in directly in terms of a classical signal detection metric, and does not require specialized training. Finally, our experiments on synthetic sparse-view breast CT data show that training a CNN with the proposed loss yields improvement in model observer performance on a signal-known-exactly/ background-known-exactly detection task as compared to training with the ObsReg loss.

Comments

Published as part of the proceedings of the SPIE Medical Imaging Conference, 2025. DOI.

Link to Full Text

Share

COinS