Generating anthropomorphic phantoms using fully unsupervised deformable image registration with convolutional neural networks. Issue 12 (9th November 2020)

• Record Type: Journal Article
• Authors: Chen, Junyu; Li, Ye; Du, Yong; Frey, Eric C.
• Is Part Of: Medical physics. Volume 47:Issue 12(2020)
• Page Start: 6366
• Page End: 6380
• Publication Date: 2020-11-09
• Subjects: computerized Phantom -- convolutional Neural Networks -- deep Neural Networks -- image Registration -- medical Image Simulation; Medical physics -- Periodicals; Medical physics; Geneeskunde; Natuurkunde; Toepassingen; Biophysics; Periodicals; Periodicals; Electronic journals; 610.153
• DOI: 10.1002/mp.14545
• Languages: English
• ISSNs: 0094-2405

Abstract

Abstract : Purpose: Computerized phantoms have been widely used in nuclear medicine imaging for imaging system optimization and validation. Although the existing computerized phantoms can model anatomical variations through organ and phantom scaling, they do not provide a way to fully reproduce the anatomical variations and details seen in humans. In this work, we present a novel registration‐based method for creating highly anatomically detailed computerized phantoms. We experimentally show substantially improved image similarity of the generated phantom to a patient image. Methods: We propose a deep‐learning‐based unsupervised registration method to generate a highly anatomically detailed computerized phantom by warping an XCAT phantom to a patient computed tomography (CT) scan. We implemented and evaluated the proposed method using the NURBS‐based XCAT phantom and a publicly available low‐dose CT dataset from TCIA. A rigorous tradeoff analysis between image similarity and deformation regularization was conducted to select the loss function and regularization term for the proposed method. A novel SSIM‐based unsupervised objective function was proposed. Finally, ablation studies were conducted to evaluate the performance of the proposed method (using the optimal regularization and loss function) and the current state‐of‐the‐art unsupervised registration methods. Results: The proposed method outperformed the state‐of‐the‐art registration methods, such as SyN and VoxelMorph, by more than 8%, measured by the SSIM and less than 30%, by the MSE. The phantom generated by the proposed method was highly detailed and was almost identical in appearance to a patient image. Conclusions: A deep‐learning‐based unsupervised registration method was developed to create anthropomorphic phantoms with anatomies labels that can be used as the basis for modeling organ properties. Experimental results demonstrate the effectiveness of the proposed method. The resulting anthropomorphic phantom is highly realistic. Combined with realistic simulations of the image formation process, the generated phantoms could serve in many applications of medical imaging research. Abstract :