Tech ID: L-21-003
Contrast agent (CA) administration to a patient is a frequent prerequisite for medical imaging. For example, in heart imaging, the elimination of gadolinium contrast agent (CA) injections and manual segmentation are crucial for ischemic heart disease (IHD) diagnosis and treatment. In the clinic, CA-based late gadolinium enhancement (LGE) imaging and manual segmentation remain subject to concerns about potential toxicity, inter-observer variability, and ineffectiveness. In cancer diagnosis, contrast-enhanced magnetic resonance imaging (CEMRI) is crucial for the diagnosis of patients with liver tumors, especially for the detection of benign tumors and malignant tumors. While liver CEMRI has high sensitivity for liver tumour diagnosis, it suffers from high-risk, time-consuming, and expensive in current clinical diagnosis due to the use of the gadolinium-based contrast agent (CA) injection. If the CEMRI can be synthesized without CA injection, there is no doubt that it will greatly optimize the diagnosis.
Our researchers have developed a medical imaging technology using Artificial Intelligence (AI), operating on standard non-contrast MR images, to achieve a diagnostic accuracy equivalent to that available with contrast-enhanced images. This method provides for concurrent and simultaneous synthesis of a medical CA-free-AI-enhanced image and medical diagnostic image analysis. For the IHD image study, progressive sequential causal GANs (PSCGAN) are proposed. This is the first one-stop CA-free IHD technology that can simultaneously synthesize an LGE-equivalent image and segment diagnosis-related tissues (i.e., scars, healthy myocardium, blood pools, and other pixels) from cine MR images. The PSCGAN gain unprecedented performance while stably training in both synthesis and segmentation. By training and testing a total of 280 clinical subjects, our PSCGAN yield a synthetic normalization root-mean-squared-error of 0.14 and an overall segmentation accuracy of 97.17%. It also produces a 0.96 correlation coefficient for the scar ratio in a real diagnostic metric evaluation. For diagnosis of liver tumours, a Tripartite Generative Adversarial Network (Tripartite-GAN) was proposed as a non-invasive, time-saving, and inexpensive clinical tool by synthesizing CEMRI to detect tumors without CA injection. This innovative Tripartite-GAN combines three associated-networks (an attention-aware generator, a convolutional neural network-based discriminator, and a region-based convolutional neural network-based detector) for the first time, which achieves CEMRI synthesis and tumor detection promoting each other in an end-to-end framework. This framework is tested on a large corpus of axial T1 FS Pre-Contrast MRI and axial T1 FS Delay MRI of 265 subjects. Experimental results and quantitative evaluation demonstrate that the Tripartite-GAN achieves high-quality CEMRI synthesis that peak signal-to-noise rate of 28.8 and accurate tumor detection that accuracy of 89.4%.
- AI-contrast cardiac image synthesis, validated on the segmentation of ischemic heart diseases(progressive sequential causal GANs) and AI-contrast liver image synthesis, validated on liver tumour detection (Tripartite-GAN)
- Greatly reduces the time of MRI examination, inexpensive and non-invasive, no harm to human body
contrast agent free, medical imaging, artificial intelligence, liver tumour, ischemic heart disease, diagnosis
US Patent Application No. 17/138353, CA Patent Application filed