A Physics-Informed Deep Neural Network for Harmonization of CT Images

• Published in: IEEE transactions on biomedical engineering 2024-12, Vol.71 (12), p.3494-3504
• Main Authors: Zarei, Mojtaba, Sotoudeh-Paima, Saman, McCabe, Cindy, Abadi, Ehsan, Samei, Ehsan
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Biomarkers; Biomedical imaging; Computational modeling; Computed tomography; Datasets; Deep learning; Emphysema; Harmonization; Image acquisition; Image quality; Image reconstruction; Lung diseases; Lung nodules; Lungs; Medical imaging; Neural networks; Nodules; Physics; physics-informed deep learning model; quantification; Radiomics; Signal to noise ratio; Training; Virtual networks
• ISSN: 0018-9294; 1558-2531; 1558-2531
• DOI: 10.1109/TBME.2024.3428399

Objective : Computed Tomography (CT) quantification is affected by the variability in image acquisition and rendition. This paper aimed to reduce this variability by harmonizing the images utilizing physics-based deep neural networks (DNNs). Methods : An adversarial generative network was trained on virtual CT images acquired under various imaging conditions using a virtual imaging platform with 40 computational patient models. These models featured anthropomorphic lungs with different levels of pulmonary diseases, including nodules and emphysema. Imaging was conducted using a validated CT simulator at two dose levels and varying reconstruction kernels. The trained model was tested on an independent virtual test dataset and two clinical datasets. Results : On the virtual test set, the harmonizer improved the structural similarity index from 79.3 \pm 16.4% to 95.8 \pm 1.7%, normalized mean squared error from 16.7 \pm 9.7% to 9.2 \pm 1.7%, and peak signal-to-noise ratio from 27.7 \pm 3.7 dB to 32.2 \pm 1.6 dB. Moreover, the harmonized images yielded more precise quantification of emphysema-based imaging biomarkers for lung attenuation, LAA −950 from 5.6 \pm 8.7% to 0.23 \pm 0.16%, Perc 15 from 43.4 \pm 45.4 HU to 20.0 \pm 7.5 HU, and Lung Mass from 0.3 \pm 0.3 g to 0.1 \pm 0.2 g. In clinical data, the harmonizer reduced biomarker variability by an average of 70%. For lung nodules, harmonized images improved the detectability index by 6.5-fold and DNN-based precision by 6%. Conclusion : The proposed harmonizer significantly enhances image quality and quantification accuracy in CT imaging. Significance: The study demonstrate