比较Mask-RCNN与Mimics在上颌窦建模中的应用

doi:10.13701/j.cnki.kqyxyj.2024.06.014

口腔医学研究 ›› 2024, Vol. 40 ›› Issue (6): 550-554.DOI: 10.13701/j.cnki.kqyxyj.2024.06.014

比较Mask-RCNN与Mimics在上颌窦建模中的应用

王蓉¹, 帕克扎提·色依提², 王铁梅^2*, 张懿³, 钱堃³

1.海军军医大学第一附属医院上海长海医院口腔科上海 200433;
2.南京大学医学院附属口腔医院南京市口腔医院南京大学口腔医学研究所口腔颌面医学影像科江苏南京 2100083.东南大学自动化学院江苏南京 210008

收稿日期:2023-12-20 出版日期:2024-06-28 发布日期:2024-06-19
通讯作者: * 王铁梅,E-mail:tiemei106@263.net
作者简介:王蓉(1992~ ),女,安徽马鞍山人,硕士,医师,研究方向:口腔颌面影像。
基金资助:
江苏省自然科学基金面上项目(编号:BK20150089)

Application of Mask-RCNN and Mimics in Maxillary Sinus Modeling

WANG Rong¹, Pakezhati·SEYITI², WANG Tiemei^2*, ZHANG Yi³, QIAN Kun³

1. Department of Stomatology, The First Affiliated Hospital of Naval Medical University (Second Military Medical University), Shanghai 200433, China;
2. Department of Radiology, Nanjing Stomatological Hospital, Affiliated Hospital of Medical School, Institute of Stomatology Nanjing University, Nanjing 210008, China;
3. Department of Automation, Dongnan University, Nanjing 210008, China

Received:2023-12-20 Online:2024-06-28 Published:2024-06-19

摘要/Abstract

摘要： 目的:比较Mask-RCNN深度学习模型与Mimics三维软件在上颌窦建模中的应用。方法:应用Mask-RCNN及Mimics对纳入的50例患者锥形束CT影像资料进行上颌窦重建并测量上颌窦体积,比较两者重建的效果并对上颌窦体积进行数据分析。结果:在上颌窦建模过程中,应用Mask-RCNN对上颌窦进行图像分割、后处理及重建仅需30余秒,使用Mimics对每例患者上颌窦图像进行手动阈值分割后重建需数十分钟;两者测量的上颌窦体积无显著性差异(P>0.05)。结论:Mask-RCNN深度学习算法优于Mimics,可以更快速准确的重建上颌窦,体现了人工智能在口腔颌面医学影像学领域的辅助诊断价值。

关键词: 人工智能, 实例分割, 锥形束CT, 三维重建, 上颌窦体积

Abstract: Objective: To compare the application of Mask RCNN deep learning model and Mimics 3D software in maxillary sinus modeling. Methods: Mask-RCNN and Mimics were applied to reconstruct the maxillary sinus and measure the volume of maxillary sinus from conical beam CT images in 50 patients included. The reconstruction effects of the two methods were compared, and the volume of the maxillary sinus was analyzed. Results: In the process of modeling the maxillary sinus, using Mask-RCNN for image segmentation, post-processing, and reconstruction only took more than 30 seconds, and using Mimics for manual threshold segmentation and reconstruction of maxillary sinus images for each patient took about tens of minutes. There was no significant difference in the volume of the maxillary sinus measured between two methods (P>0.05). Conclusion: The Mask RCNN deep learning algorithm is superior to Mimics and can reconstruct the maxillary sinus more quickly and accurately, reflecting the auxiliary diagnostic value of artificial intelligence in the field of oral and maxillofacial medical imaging.

Key words: artificial intelligence, image segmentation, cone-beam computed tomography, three-dimensional reconstruction, maxillary sinus volume

王蓉, 帕克扎提·色依提, 王铁梅, 张懿, 钱堃. 比较Mask-RCNN与Mimics在上颌窦建模中的应用[J]. 口腔医学研究, 2024, 40(6): 550-554.

WANG Rong, Pakezhati·SEYITI, WANG Tiemei, ZHANG Yi, QIAN Kun. Application of Mask-RCNN and Mimics in Maxillary Sinus Modeling[J]. Journal of Oral Science Research, 2024, 40(6): 550-554.

参考文献

[1] 帕克扎提·色依提,王铁梅,徐子能,等.基于深度学习在曲面体层图像中人工智能辅助诊断系统初步研究[J].口腔医学研究,2021,37(9):845-849.
[2] Hu JF, Sun J, Lin Z, et al. APANet: Auto-path aggregation for future instance segmentation prediction [J]. IEEE Trans Pattern Anal Mach Intell, 2022, 44(7):3386-3403.
[3] He K, Gkioxari G, Dollar P, et al. Mask R-CNN [J]. IEEE Trans Pattern Anal Mach Intell, 2020, 42(2):386-397.
[4] Yue N, Zhang J, Zhao J, et al. Detection and classification of bronchiectasis based on improved Mask-RCNN [J]. Bioengineering (Basel), 2022, 9(8):359.
[5] Li YZ, Wang Y, Fang KB, et al. Automated meniscus segmentation and tear detection of knee MRI with a 3D mask-RCNN [J]. Eur J Med Res, 2022, 27(1): 247.
[6] 方威扬,林东鑫,寇万福,等.医学图像三维重建系统的研究进展[J].中国医学物理学杂志,2022,39(7): 823-827.
[7] Alqahtani H, Basuhail S, Alsulaimani F, et al. The relationship between maxillary sinus volume and different cephalometric characteristics in orthodontics [J]. Contemp Clin Dent, 2023, 14(3): 191-200.
[8] Aşantoğrol F, Coşgunarslan A. The effect of anatomical variations of the sinonasal region on maxillary sinus volume and dimensions: a three-dimensional study [J]. Braz J Otorhinolaryngol, 2022, 88 Suppl 1(Suppl 1):S118-S127.
[9] Göksel S, Güler AY. Is there a relationship between maxillary sinus’s inferior pneumatisation and sinonasal variations? A retrospective CBCT study [J]. J Oral Maxillofac Res, 2023, 14(3): e3.
[10] Bandong S, Nazaruddin YY, Joelianto E. Faster RCNN mixed-integer optimization with weighted cost function for container detection in port automation [J]. Heliyon, 2023, 9(2):e13213.
[11] Dandekeri SS, Hegde C, Kavassery P, et al. CBCT study of morphologic variations of maxillary sinus septa in relevance to sinus augmentation procedures [J]. Ann Maxillofac Surg, 2020, 10(1): 51-56.
[12] Möhlhenrich SC, Heussen N, Peters F, et al. Is the maxillary sinus really suitable in sex determination? A three-dimensional analysis of maxillary sinus volume and surface depending on sex and dentition [J]. J Craniofac Surg, 2015, 26(8):e723-e726.
[13] Chunduru R, Rachel P, Kailasam V, et al. The evaluation of maxillary sinus dimensions in different craniofacial patterns: A systematic review and meta-analysis [J]. Turk J Orthod, 2023, 36(3):208-215.
[14] Christoloukas N, Mitsea A, Rontogianni A, et al. Gender determination based on CBCT maxillary sinus analysis: A systematic review [J]. Diagnostics (Basel), 2023, 13(23):3536.
[15] Lessa AMG, Oliveira VS, Costa RBA, et al. Anatomical study of the maxillary sinus: which characteristics can influence its volume? [J]. Surg Radiol Anat, 2022, 45(1): 81-87.

比较Mask-RCNN与Mimics在上颌窦建模中的应用

Application of Mask-RCNN and Mimics in Maxillary Sinus Modeling

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	李放, 张锡忠. 不同垂直骨面型下颌第一磨牙横向位置差异的CBCT研究[J]. 口腔医学研究, 2024, 40(6): 544-549.
[2]	葛翘诚, 刘爽, 木合塔尔·霍加. 锥形束CT诊断双侧上下颌第一前磨牙对称性三根三管型1例[J]. 口腔医学研究, 2024, 40(5): 459-460.
[3]	卡地里亚·吐尔逊江, 丁成芳, 王玲. 上颌窦分隔发生率及特征的锥形束CT研究[J]. 口腔医学研究, 2024, 40(3): 259-264.
[4]	苏莉雯, 吴杨. 生成式人工智能在口腔医学的应用潜力与挑战[J]. 口腔医学研究, 2024, 40(1): 11-17.
[5]	古力孜巴·艾海提, 张鹏鑫, 齐佳, 亚尔肯·阿吉, 许辉. 腭裂术后腭咽闭合不全患者面部扭曲行为与腭咽闭合程度的关系[J]. 口腔医学研究, 2023, 39(8): 696-700.
[6]	袁峥鼎, 牟永斌, 李淑媛, 林梓桐. 基于锥形束CT影像的改良三轴旋转法对种植体高度及宽度测量的准确性研究[J]. 口腔医学研究, 2023, 39(6): 496-499.
[7]	陈涛, 马晓威, 姚琴, 史亚伟, 王东苗, 程杰. 儿童和青少年上颌前牙区埋伏多生牙对邻近中切牙发育萌出影响的CBCT影像学分析[J]. 口腔医学研究, 2023, 39(6): 500-504.
[8]	刘亚, 魏路明, 李晓飞, 李晓明, 袁长永, 王鹏来. 探究后牙区拟种植位点牙槽嵴顶CBCT影像的判读误差[J]. 口腔医学研究, 2023, 39(6): 505-509.
[9]	于鸿滨, 钱石兵, 刘超峰, 夏志刚, 高雅格, 张凌鹏. 下颌正中舌侧管、下颌舌侧副管和下颌切牙神经管解剖关系的CBCT影像研究[J]. 口腔医学研究, 2023, 39(5): 440-444.
[10]	王琳琳, 田洪盛, 徐莹, 樊明儒, 秦秀荣. 年轻上颌中切牙根尖区解剖结构的CBCT测量[J]. 口腔医学研究, 2023, 39(5): 445-449.
[11]	李林林, 向国林. 武汉市562名12~16岁青少年下颌第三磨牙生长发育的锥形束CT研究[J]. 口腔医学研究, 2023, 39(3): 217-220.
[12]	石文强, 兰花, 杜兴萍, 张雷. 基于CBCT三维重建的前鼻棘区潜在取骨量研究[J]. 口腔医学研究, 2023, 39(2): 145-150.
[13]	潘逸华, 刘钧. 正畸牙移动相关的神经压迫研究进展[J]. 口腔医学研究, 2023, 39(11): 956-959.
[14]	齐帅, 张旗. 卷积神经网络在牙体牙髓病影像诊断中的研究和应用[J]. 口腔医学研究, 2023, 39(11): 960-964.
[15]	刘鎵仪, 周彦恒. 人工智能在正畸诊疗及疗效预测中的应用进展[J]. 口腔医学研究, 2023, 39(10): 862-865.