Toward Better Optimization of Low-Dose CT Enhancement: A Critical Analysis of Loss Functions and Image Quality Assessment Metrics

2025-11-01

AI Summary

Low-dose CT (LDCT) image enhancement suffers from a critical misalignment between conventional loss functions and clinically relevant perceptual quality metrics: standard pixel-wise objectives (e.g., MSE, PSNR, SSIM) fail to ensure diagnostic-level structural fidelity and visual plausibility. This work systematically analyzes the impact of mainstream losses—including MSE, adversarial loss, and task-specific variants—on LDCT reconstruction quality, and for the first time quantifies their substantial deviation from perception-oriented metrics (e.g., LPIPS, NIQE) and expert radiologist assessments. We propose a perception-consistent loss design paradigm integrating structural constraints with semantic-aware regularization. Experiments demonstrate that our method achieves competitive quantitative performance while significantly improving image naturalness and lesion conspicuity (p < 0.01), offering a clinically grounded optimization framework for medical image enhancement.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Security and Privacy: Large-scale security measurements

Abstract

Low-dose CT (LDCT) imaging is widely used to reduce radiation exposure to mitigate high exposure side effects, but often suffers from noise and artifacts that affect diagnostic accuracy. To tackle this issue, deep learning models have been developed to enhance LDCT images. Various loss functions have been employed, including classical approaches such as Mean Square Error and adversarial losses, as well as customized loss functions(LFs) designed for specific architectures. Although these models achieve remarkable performance in terms of PSNR and SSIM, these metrics are limited in their ability to reflect perceptual quality, especially for medical images. In this paper, we focus on one of the most critical elements of DL-based architectures, namely the loss function. We conduct an objective analysis of the relevance of different loss functions for LDCT image quality enhancement and their consistency with image quality metrics. Our findings reveal inconsistencies between LFs and quality metrics, and highlight the need of consideration of image quality metrics when developing a new loss function for image quality enhancement.

Problem

• Analyzing loss functions for low-dose CT image enhancement
• Investigating inconsistencies between loss functions and quality metrics
• Addressing limitations of PSNR and SSIM in medical imaging

Innovation

• Analyzes loss functions for CT enhancement
• Reveals inconsistencies with quality metrics
• Recommends metric-aware loss function design