目的 提出基于学习的颅颌面自动修复方法，在自主构建的数据集上进行学习，以自动生成缺损部分的形状，为复杂颅颌面结构的修复提供参考。 方法 基于头颅CT数据重建并标注了125例头骨数据，每一例构建21种缺陷分类，使用图像配准、阈值滤波等技术完成数据预处理，并提出一种新的颅颌面自动修复技术，完成颅颌面缺损部分的形状生成。 结果 提出的方法在CMF Defects数据集上能够重建出兼具美观和保护功能的形状。 结论 颅颌面骨骼形状各异，解剖结构复杂，本研究结合深度学习与数据驱动方法能很好地完成颅颌面骨骼缺损的生成，为颅颌面修复手术的术前规划和术中操作提供可靠的依据。
Abstract
Objective To propose a learning-based automatic restoration method for craniomaxillofacial defects, which learning from a self-constructed dataset to automatically generate the shape of the defective parts, and providing reference for the restoration of complex craniomaxillofacial structures. Methods Based on the head CT data, 125 cases of skull data were reconstructed and annotated. Each case was categorized into 21 defect classes. Various techniques were used for data preprocessing, including image registration and threshold filtering. A novel craniomaxillofacial automatic restoration technique was introduced to generate shapes for the defective portions. Results The proposed method achieves the state-of-the-art results on the CMF Defects dataset, which can reconstruct shapes that combine aesthetics and protective functionality. Conclusions Craniomaxillofacial bone have diverse shapes and complex anatomical structures. This study, combined with deep learning and data-driven methods, can effectively generate the generation of craniomaxillofacial bone defects, providing a reliable foundation for preoperative planning and intraoperative procedures in craniomaxillofacial restoration surgery.
关键词
颅颌面修复 /
图像处理 /
三维重建 /
深度学习
Key words
Craniomaxillofacial restoration; /
Image processing; /
3D reconstruction; Deep learning
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 邱蔚六.口腔颌面部缺损修复重建的现状和展望[J].中国修复重建外科杂志, 2005,19(10):769-772. CNKI:SUN:ZXCW.0.2005-10-000.
[2] Li J, Pepe A, Gsaxner C, et al. An online platform for automatic skull defect restoration and cranial implant design[C]. Medical Imaging 2021: Image-Guided Procedures, Robotic Interventions, and Modeling. SPIE, 2021, 11598: 472-479. DOI: 10.1117/12.2580719.
[3] Oh JH. Recent advances in the reconstruction of cranio-maxillofacial defects using computer-aided design/computer-aided manufacturing[J]. Maxillofac Plast Reconstr Surg, 2018, 40(1):2. DOI:10.1186/s40902-018-0141-9.
[4] Park SH, Han K, Jang HY, et al. Methods for clinical evaluation of artificial intelligence algorithms for medical diagnosis[J]. Radiology, 2023, 306(1): 20-31. DOI: 10.1148/radiol.220182.
[5] Cui Z, Fang Y, Mei L, et al. A fully automatic AI system for tooth and alveolar bone segmentation from cone-beam CT images[J]. Nat Commun, 2022, 13(1):2096. DOI: 10.1038/s41467-022-29637-2.
[6] Li J, Gsaxner C, Pepe A, et al. Synthetic skull bone defects for automatic patient-specific craniofacial implant design[J]. Sci Data, 2021, 8(1):36. DOI: 10.1038/s41597-021-00806-0.
[7] Tingaud-Sequeira A, Trimouille A, Sagardoy T, et al. Oculo-auriculo-vertebral spectrum: new genes and literature review on a complex disease[J]. J Med Genet,2022,59(5):417-427. DOI: 10.1136/jmedgenet- 2021-108219.
[8] Marszałek-Kruk BA, Wójcicki P, Dowgierd K, et al. Treacher Collins syndrome: genetics, clinical features and management[J]. Genes, 2021, 12(9):1392. DOI: 10.3390/genes12091392.
[9] Hegdé J, Tustison N J, Parker W T, et al. An anatomical template for the normalization of medical images of adult human hands[J]. Diagnostics, 2023, 13(12): 2010. DOI:10.3390/diagnostics13122010.
[10]Li J, Von Campe G, Pepe A, et al. Automatic skull defect restoration and cranial implant generation for cranioplasty[J]. Med Image Anal, 2021, 73: 102171. DOI:10.1016/j.media.2021.102171.
[11]Zhang J, Gao Y, Wang L, et al. Automatic craniomaxillofacial landmark digitization via segmentation-guided partially-joint regression forest model and multiscale statistical features[J]. IEEE Trans Biomed Eng, 2015, 63(9): 1820-1829. DOI: 10.1109/TBME.2015.2503421.
[12]Chen X, Lian C, Deng H H, et al. Fast and accurate craniomaxillofacial landmark detection via 3D faster R-CNN[J]. IEEE Trans Med Imaging, 2021, 40(12): 3867-3878. DOI: 10.1109/TMI.2021.3099509.
[13]Silva TP, Hughes MM, Menezes LS, et al. Artificial intelligence-based cephalometric landmark annotation and measurements according to Arnett’s analysis: can we trust a bot to do that [J]? Dentomaxillofac Radiol, 2022, 51(6): 20200548. DOI: 10.1259/dmfr.20200548.
[14]Ma Q, Kobayashi E, Fan B, et al. Machine‐learning‐based approach for predicting postoperative skeletal changes for orthognathic surgical planning[J]. Int J Med Robot, 2022, 18(3): e2379. DOI: 10.1002/rcs.2379.
[15]Tanikawa C, Yamashiro T. Development of novel artificial intelligence systems to predict facial morphology after orthognathic surgery and orthodontic treatment in Japanese patients[J]. Sci Rep, 2021, 11(1): 15853. DOI: 10.1038/s41598-021-95002-w.
[16]Jong L. On the persistence of race: Unique skulls and average tissue depths in the practice of forensic craniofacial depiction[J]. Soc Stud Sci, 2023, 53(6): 891-915. DOI: 10.1177/03063127221112073.
[17]Zheng X, Ding S, Mei Q, et al. A cross-sectional study: correlation of forehead morphology and dentoskeletal malocclusion in Chinese people[J]. BMC Oral Health, 2024, 24(1): 50. DOI: 10.1186/s12903-023-03795-1.
[18]Chen X, Xu L, Li X, et al. Computer-aided implant design for the restoration of cranial defects[J]. Sci Rep, 2017, 7(1): 4199. DOI: 10.1038/s41598-017-04454-6.
PDF(1532 KB)
京ICP备08002354号-3
