Synthesizing 3D Multi-Contrast Brain Tumor MRIs Using Tumor Mask Conditioning.

Autor:	Truong NCD; Department of Radiology, UT Southwestern Medical Center, Texas, USA., Yogananda CGB; Department of Radiology, UT Southwestern Medical Center, Texas, USA., Wagner BC; Department of Radiology, UT Southwestern Medical Center, Texas, USA., Holcomb JM; Department of Radiology, UT Southwestern Medical Center, Texas, USA., Reddy D; Department of Radiology, UT Southwestern Medical Center, Texas, USA., Saadat N; Department of Radiology, UT Southwestern Medical Center, Texas, USA., Hatanpaa KJ; Department of Pathology, UT Southwestern Medical Center, Texas, USA., Patel TR; Department of Neurological Surgery, UT Southwestern Medical Center, Texas, USA., Fei B; Department of Radiology, UT Southwestern Medical Center, Texas, USA.; Department of Bioengineering, University of Texas at Dallas, Texas, USA., Lee MD; Department of Radiology, NYU Grossman School of Medicine, New York, USA., Jain R; Department of Radiology, NYU Grossman School of Medicine, New York, USA.; Department of Neurosurgery, NYU Grossman School of Medicine, New York, USA., Bruce RJ; Department of Radiology, University of Wisconsin-Madison, Wisconsin, USA., Pinho MC; Department of Radiology, UT Southwestern Medical Center, Texas, USA., Madhuranthakam AJ; Department of Radiology, UT Southwestern Medical Center, Texas, USA., Maldjian JA; Department of Radiology, UT Southwestern Medical Center, Texas, USA.
Jazyk:	angličtina
Zdroj:	Proceedings of SPIE--the International Society for Optical Engineering [Proc SPIE Int Soc Opt Eng] 2024 Feb; Vol. 12931. Date of Electronic Publication: 2024 Apr 02.
DOI:	10.1117/12.3009331
Abstrakt:	Data scarcity and data imbalance are two major challenges in training deep learning models on medical images, such as brain tumor MRI data. The recent advancements in generative artificial intelligence have opened new possibilities for synthetically generating MRI data, including brain tumor MRI scans. This approach can be a potential solution to mitigate the data scarcity problem and enhance training data availability. This work focused on adapting the 2D latent diffusion models to generate 3D multi-contrast brain tumor MRI data with a tumor mask as the condition. The framework comprises two components: a 3D autoencoder model for perceptual compression and a conditional 3D Diffusion Probabilistic Model (DPM) for generating high-quality and diverse multi-contrast brain tumor MRI samples, guided by a conditional tumor mask. Unlike existing works that focused on generating either 2D multi-contrast or 3D single-contrast MRI samples, our models generate multi-contrast 3D MRI samples. We also integrated a conditional module within the UNet backbone of the DPM to capture the semantic class-dependent data distribution driven by the provided tumor mask to generate MRI brain tumor samples based on a specific brain tumor mask. We trained our models using two brain tumor datasets: The Cancer Genome Atlas (TCGA) public dataset and an internal dataset from the University of Texas Southwestern Medical Center (UTSW). The models were able to generate high-quality 3D multi-contrast brain tumor MRI samples with the tumor location aligned by the input condition mask. The quality of the generated images was evaluated using the Fréchet Inception Distance (FID) score. This work has the potential to mitigate the scarcity of brain tumor data and improve the performance of deep learning models involving brain tumor MRI data. Competing Interests: DISCLOSURES The authors declare no conflict of interest.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu