Creating high-resolution 3D cranial implant geometry using deep learning techniques

Chieh-Tsai Wu; Yao-Hung Yang; Yau-Zen Chang

doi:10.3389/fbioe.2023.1297933

Creating high-resolution 3D cranial implant geometry using deep learning techniques

Front Bioeng Biotechnol. 2023 Dec 11:11:1297933. doi: 10.3389/fbioe.2023.1297933. eCollection 2023.

Authors

Chieh-Tsai Wu^{1

2}, Yao-Hung Yang³, Yau-Zen Chang^{1

4

5}

Affiliations

¹ Department of Neurosurgery, Linkou Chang Gung Memorial Hospital, Taoyuan, Taiwan.
² College of Medicine, Chang Gung University, Taoyuan, Taiwan.
³ ADLINK Technology, Inc, Taoyuan, Taiwan.
⁴ Department of Mechanical Engineering, Chang Gung University, Taoyuan, Taiwan.
⁵ Department of Mechanical Engineering, Ming Chi University of Technology, New Taipei City, Taiwan.

Abstract

Creating a personalized implant for cranioplasty can be costly and aesthetically challenging, particularly for comminuted fractures that affect a wide area. Despite significant advances in deep learning techniques for 2D image completion, generating a 3D shape inpainting remains challenging due to the higher dimensionality and computational demands for 3D skull models. Here, we present a practical deep-learning approach to generate implant geometry from defective 3D skull models created from CT scans. Our proposed 3D reconstruction system comprises two neural networks that produce high-quality implant models suitable for clinical use while reducing training time. The first network repairs low-resolution defective models, while the second network enhances the volumetric resolution of the repaired model. We have tested our method in simulations and real-life surgical practices, producing implants that fit naturally and precisely match defect boundaries, particularly for skull defects above the Frankfort horizontal plane.

Keywords: 3D inpainting; cranial implant; cranioplasty; deep learning; defective skull models; volumetric resolution.

Grants and funding

The author(s) declare financial support was received for the research, authorship, and/or publication of this article. We gratefully acknowledge funding from the National Science and Technology Council, Taiwan, under Grant Nos. NSTC 111-2221-E-182-057, MOST 110-2221-E-182-034, MOST 109-2221-E-182-025, and MOST 108-2221-E-182-061, and Chang Gung Memorial Hospital, Taiwan, under Grant Nos. CMRPG3L1181, CORPD2J0041, and CORPD2J0042.