🤖 AI Summary
Radiomics feature inconsistency across CT scanners—caused by variations in hardware models and acquisition protocols—hampers clinical reproducibility. To address this, we propose LTDiff++, a multi-scale latent diffusion model that achieves unpaired cross-platform radiomic feature standardization in the latent space. Our method innovatively embeds a conditional denoising diffusion probabilistic model (DDPM) into the bottleneck layer of UNet++, integrating multi-scale feature fusion and latent-space distribution calibration to overcome the generalization limitations of supervised approaches. Evaluated on both patient and phantom CT datasets, LTDiff++ significantly improves radiomic feature consistency: the Concordance Correlation Coefficient (CCC) increases by an average of 32.7% across diverse radiomic features. It outperforms generative adversarial network (GAN)-based and conventional normalization methods, demonstrating superior robustness and enhanced clinical reproducibility.
📝 Abstract
Various imaging modalities are used in patient diagnosis, each offering unique advantages and valuable insights into anatomy and pathology. Computed Tomography (CT) is crucial in diagnostics, providing high-resolution images for precise internal organ visualization. CT's ability to detect subtle tissue variations is vital for diagnosing diseases like lung cancer, enabling early detection and accurate tumor assessment. However, variations in CT scanner models and acquisition protocols introduce significant variability in the extracted radiomic features, even when imaging the same patient. This variability poses considerable challenges for downstream research and clinical analysis, which depend on consistent and reliable feature extraction. Current methods for medical image feature extraction, often based on supervised learning approaches, including GAN-based models, face limitations in generalizing across different imaging environments. In response to these challenges, we propose LTDiff++, a multiscale latent diffusion model designed to enhance feature extraction in medical imaging. The model addresses variability by standardizing non-uniform distributions in the latent space, improving feature consistency. LTDiff++ utilizes a UNet++ encoder-decoder architecture coupled with a conditional Denoising Diffusion Probabilistic Model (DDPM) at the latent bottleneck to achieve robust feature extraction and standardization. Extensive empirical evaluations on both patient and phantom CT datasets demonstrate significant improvements in image standardization, with higher Concordance Correlation Coefficients (CCC) across multiple radiomic feature categories. Through these advancements, LTDiff++ represents a promising solution for overcoming the inherent variability in medical imaging data, offering improved reliability and accuracy in feature extraction processes.