Araştırma Makalesi

From notes to neurons: An open-source AI pipeline for 3D laryngeal modeling in anatomy and music education

Sayı: 81 6 Kasım 2026
PDF İndir
TR EN

From notes to neurons: An open-source AI pipeline for 3D laryngeal modeling in anatomy and music education

Öz

The larynx is a complex anatomical structure central to human voice production, playing a critical role in clinical diagnosis, surgical planning, and rehabilitation. This study aims to develop an open-source, artificial intelligence-based three-dimensional (3D) laryngeal modeling pipeline using medical imaging data. Our approach integrates deep learning-based automatic segmentation (3D U-Net architecture), surface extraction (Marching Cubes), and multi-stage mesh optimization (Laplacian/Taubin smoothing, polygon decimation) within a unified framework, enabling high-accuracy modeling of the larynx's complex anatomy. Segmentation performance achieved a Dice coefficient of 0.87 for vocal folds and 0.90 for the thyroid cartilage, demonstrating comparability with similar studies in the literature. Following 3D reconstruction, mesh optimization reduced the average polygon count by 42% while preserving anatomical integrity. All software components are shared as open source, and the system is designed with a modular architecture adaptable to different anatomical regions. This study provides a reproducible and accessible modeling pipeline in the field of computational anatomy.

Anahtar Kelimeler

Destekleyen Kurum

This study received no institutional or financial support from any organization, funding agency, or academic institution. All work was conducted independently by the authors.

Etik Beyan

Ethics Committee, Data Usage and Open Source Declaration All medical imaging data used in this study consist of fully anonymized datasets obtained from open-access databases (The Cancer Imaging Archive – TCIA). At no stage of the study process were personal data that could reveal individuals' identities used; data security and privacy principles were meticulously observed. The data used were processed in accordance with ethical principles within the framework of the Helsinki Declaration and relevant national legislation. No direct intervention, experimental application, survey, or clinical procedure was performed on human participants in this study. Therefore, the research falls within the scope of retrospective and anonymized data use and is classified among studies that do not require ethics committee approval. The artificial intelligence-based three-dimensional laryngeal modeling pipeline developed within the scope of this study has been shared under the MIT license in line with open science principles. The source code can be accessed at https://github.com/murathan0201-tech/MuratKUS. This study proposes an AI-assisted, open-source, and reproducible three-dimensional laryngeal modeling pipeline based on medical imaging data. This approach, which combines deep learning-based automatic segmentation (3D U-Net), optimized surface reconstruction (Marching Cubes + Laplacian/Taubin smoothing + polygon decimation) stages within a unified framework, fills an important gap in modeling an anatomically complex structure such as the larynx. The findings obtained reveal that the developed models offer high performance in terms of anatomical accuracy (Dice: 0.84-0.90) and visual quality. The success achieved especially in the segmentation of small and complex structures (arytenoid cartilages, vocal folds) demonstrates the effectiveness of the proposed approach. The open-source design of the study increases technical accessibility and supports methodological transparency in the field of computational anatomy. The proposed modeling pipeline offers a flexible structure that can be adapted to different anatomical regions and application scenarios. However, the current study focuses on static anatomical models, and modeling the dynamic physiological behaviors of the larynx (e.g., real-time tissue deformation and vibration simulations) stands out as an important research area for future studies. Furthermore, validation studies to be conducted with larger and more diverse datasets (different age groups, pathological conditions) will further strengthen the generalizability of the model. In conclusion, this study contributes to the field of computational anatomy by bringing together artificial intelligence and three-dimensional modeling techniques.

Teşekkür

The authors would like to thank the editors of Burdur Mehmet Akif Ersoy University Journal of Education Faculty for their constructive feedback and editorial support during the review process.

Kaynakça

  1. Bruner, J. S. (1966). Toward a theory of instruction. Harvard University Press. Çiçek, Ö., Abdulkadir, A., Lienkamp, S. S., Brox, T., & Ronneberger, O. (2016). 3D U-Net: Learning dense volumetric segmentation from sparse annotation. In Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016 (pp. 424-432). Springer. https://doi.org/10.1007/978-3-319-46723-8_49
  2. Dice, L. R. (1945). Measures of the amount of ecologic association between species. Ecology, 26(3), 297-302. https://doi.org/10.2307/1932409
  3. Fedorov, A., Beichel, R., Kalpathy-Cramer, J., Finet, J., Fillion-Robin, J. C., Pujol, S., ... Kikinis, R. (2012). 3D Slicer as an image computing platform for the Quantitative Imaging Network. Magnetic Resonance Imaging, 30(9), 1323-1341. https://doi.org/10.1016/j.mri.2012.05.001
  4. Fehling, M. K., Grosch, F., Schuster, M. E., Schick, B., & Lohscheller, J. (2020). Fully automatic segmentation of glottis and vocal folds in endoscopic laryngeal high-speed videos using a deep Convolutional LSTM Network. PLoS ONE, 15(2), e0227791. https://doi.org/10.1371/journal.pone.0227791
  5. Kikinis, R., Pieper, S. D., & Vosburgh, K. G. (2014). 3D Slicer: A platform for subject-specific image analysis, visualization, and clinical support. In Intraoperative Imaging and Image-Guided Therapy (pp. 277-289). Springer. https://doi.org/10.1007/978-1-4614-7657-3_19
  6. Lorensen, W. E., & Cline, H. E. (1987). Marching cubes: A high resolution 3D surface construction algorithm. ACM SIGGRAPH Computer Graphics, 21(4), 163-169. https://doi.org/10.1145/37402.37422
  7. Nicholson, D. T., Chalk, C., Funnell, W. R. J., & Daniel, S. J. (2006). Can virtual reality improve anatomy education? A randomised controlled study of a computer-generated three-dimensional anatomical ear model. Medical Education, 40(11), 1081-1087. https://doi.org/10.1111/j.1365-2929.2006.02611.x
  8. Paniagua, M., Hernández, J., & Borda, A. (2019). Three-dimensional visualization as a learning tool in anatomy education: A systematic review. Anatomical Sciences Education, 12(4), 395-404. https://doi.org/10.1002/ase.1870

Ayrıntılar

Birincil Dil

İngilizce

Konular

Öğretim Teknolojileri

Bölüm

Araştırma Makalesi

Yayımlanma Tarihi

6 Kasım 2026

Gönderilme Tarihi

27 Mayıs 2026

Kabul Tarihi

25 Eylül 2026

Yayımlandığı Sayı

Yıl 2026 Sayı: 81

Kaynak Göster

APA
Kuş, M. A., & Gün, E. (2026). From notes to neurons: An open-source AI pipeline for 3D laryngeal modeling in anatomy and music education. Mehmet Akif Ersoy University Journal of Education Faculty, 81, 19-29. https://doi.org/10.21764/maeuefd.1958929
AMA
1.Kuş MA, Gün E. From notes to neurons: An open-source AI pipeline for 3D laryngeal modeling in anatomy and music education. Mehmet Akif Ersoy University Journal of Education Faculty. 2026;(81):19-29. doi:10.21764/maeuefd.1958929
Chicago
Kuş, Murat Abdülgani, ve Elvan Gün. 2026. “From notes to neurons: An open-source AI pipeline for 3D laryngeal modeling in anatomy and music education”. Mehmet Akif Ersoy University Journal of Education Faculty, sy 81: 19-29. https://doi.org/10.21764/maeuefd.1958929.
EndNote
Kuş MA, Gün E (01 Kasım 2026) From notes to neurons: An open-source AI pipeline for 3D laryngeal modeling in anatomy and music education. Mehmet Akif Ersoy University Journal of Education Faculty 81 19–29.
IEEE
[1]M. A. Kuş ve E. Gün, “From notes to neurons: An open-source AI pipeline for 3D laryngeal modeling in anatomy and music education”, Mehmet Akif Ersoy University Journal of Education Faculty, sy 81, ss. 19–29, Kas. 2026, doi: 10.21764/maeuefd.1958929.
ISNAD
Kuş, Murat Abdülgani - Gün, Elvan. “From notes to neurons: An open-source AI pipeline for 3D laryngeal modeling in anatomy and music education”. Mehmet Akif Ersoy University Journal of Education Faculty. 81 (01 Kasım 2026): 19-29. https://doi.org/10.21764/maeuefd.1958929.
JAMA
1.Kuş MA, Gün E. From notes to neurons: An open-source AI pipeline for 3D laryngeal modeling in anatomy and music education. Mehmet Akif Ersoy University Journal of Education Faculty. 2026;:19–29.
MLA
Kuş, Murat Abdülgani, ve Elvan Gün. “From notes to neurons: An open-source AI pipeline for 3D laryngeal modeling in anatomy and music education”. Mehmet Akif Ersoy University Journal of Education Faculty, sy 81, Kasım 2026, ss. 19-29, doi:10.21764/maeuefd.1958929.
Vancouver
1.Murat Abdülgani Kuş, Elvan Gün. From notes to neurons: An open-source AI pipeline for 3D laryngeal modeling in anatomy and music education. Mehmet Akif Ersoy University Journal of Education Faculty. 01 Kasım 2026;(81):19-2. doi:10.21764/maeuefd.1958929

   Mehmet Akif Ersoy Üniversitesi Eğitim Fakültesi Dergisi

33574