Synthetic skull bone defects for automatic patient-specific craniofacial implant design

Abstract

Patient-specific craniofacial implants are used to repair skull bone defects after trauma or surgery. Currently, cranial implants are designed and produced by third-party suppliers, which is usually time-consuming and expensive. Recent advances in additive manufacturing made the in-hospital or in-operation-room fabrication of personalized implants feasible. However, the implants are still manufactured by external companies. To facilitate an optimized workflow, fast and automatic implant manufacturing is highly desirable. Data-driven approaches, such as deep learning, show currently great potential towards automatic implant design. However, a considerable amount of data is needed to train such algorithms, which is, especially in the medical domain, often a bottleneck. Therefore, we present CT-imaging data of the craniofacial complex from 24 patients, in which we injected various artificial cranial defects, resulting in 240 data pairs and 240 corresponding implants. Based on this work, automatic implant design and manufacturing processes can be trained. Additionally, the data of this work build a solid base for researchers to work on automatic cranial implant designs.

The 3D skull 0–4 years: A validated, generative, statistical shape model

“…Using this normative 3D model, the skull CT data from new patients could be automatically compared to evaluate normal and abnormal skull shape features, for diagnostic purposes and to potentially plan personalised surgical treatments of craniomaxillofacial syndromes when needed ( Farkas et al, 1992 ; Mauler et al, 2017 ; Knoops et al, 2019 ; Staal et al, 2015 ; Fuessinger et al, 2018 ). Craniofacial injuries due to falls, common among young children, and various craniofacial defects could be treated using automatically designed implants, by leveraging synthetic skull data to train the design algorithm, thus making the process less operator dependent and time consuming ( Li et al, 2021 ). To facilitate the development of new model analysis techniques and clinical treatments by research groups without direct access to medical data, the normative 3DMM and synthetically generated new instances could support in silico medicine and clinical trials for the design of surgical devices and implants.…”

MUG500+: Database of 500 high-resolution healthy human skulls and 29 craniotomy skulls and implants

“… The 29 craniotomy skulls together with the corresponding manually designed cranial implants can serve as an evaluation set for automatic cranial implant design algorithms. Researchers can create synthetic cranial defects on the 500 healthy skulls in order to train deep learning algorithms [1] , [5] , [6] , [7] and host challenges [8] . The .stl files included in the MUG500+ dataset are 3D printable and can be used for educational purposes.…”

“…Researchers can create synthetic cranial defects on the 500 healthy skulls in order to train deep learning algorithms [1] , [5] , [6] , [7] and host challenges [8] .…”

The Simplified Tailor-made Workflows for a 3D Slicer-based Craniofacial Implant Design

“…This software allows patients to preview and examine the expected outcome of the implant operation [3]. Several studies have been proposed to design patient-specific craniofacial implant models [10][11][12][13][14][15][16][17][18][19][20] .…”

“…Taper screw holes were made for implant placement and stability. Jianning L. et al 19 proposed an automatic design workflow for cranial implant. The workflow is based on deeplearning networks.…”