Artificial Intelligence Based Semi-automatic Segmentation for Orbital Tumor Preoperative Modeling
Journal of Neurological Surgery Part B: Skull Base · 01.02.2024 · 85 (S 01 S 01) · S1-S398
DOI: 10.1055/s-0044-1779917 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Neurological Surgery Part B: Skull Base, erschienen am 01.02.2024. Verfasst von Margaret B. Mitchell und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Introduction
With the increasing utilization of endoscopic approaches for primary benign orbital tumor (PBOT) surgery, otolaryngologists and ophthalmologists are challenged with determining candidacy for endoscopic resection of benign tumors based on preoperative imaging. Recently, the ORBIT classification system, which characterizes these tumors into one of five classes based on their relationship to key structures such as ophthalmic artery and optic nerve, was shown to correlate with a surgeon’s ability to achieve gross total resection and favorable outcomes via an endoscopic approach. Three-dimensional models of these tumors demonstrating their relationship to these vital structures may be of utility preoperatively, shedding light on potential resectability as well as better informing the operative approach.
Objective
We sought to develop a semi-automatic modality for three-dimensional reconstruction of primary benign orbital tumors, allowing for potential large-scale utilization of this technique.
Methods
A selected case of patients with a tumor of each ORBIT class was identified from the electronic medical record. Patients’ preoperative imaging with computed tomography imaging and magnetic resonance imaging was obtained, and 3D slicer, an open-source software for segmentation of biomedical images, was utilized to segment the tumor as well as key anatomical structures—ophthalmic artery, optic nerve, medial and inferior rectus, globe, and orbital rim—creating a three-dimensional model for each patient.
Results
A model was generated for all five ORBIT classes. These models demonstrated the key findings differentiating classes such as whether a tumor is intraconal vs. extraconal, anterior or posterior to the intersection of the ophthalmic artery and optic nerve, or extends into the pterygopalatine and/or infratemporal fossa through inferior orbital fissure or through the superior orbital fissure. For example, [ Fig. 1 ] demonstrates a class III tumor, which is intraconal and lies posterior to the intersection point of the ophthalmic artery and optic nerve.
Discussion
While the endoscopic approach to resection of PBOT appears to be safe with low rates of adverse events, surgeons are challenged with complex resections due to the oblique and compact anatomy of the orbital cavity and the narrow nasal corridor with multiple surrounding critical structures. Thus, three-dimensional preoperative models may offer valuable insight for both surgical candidacy and surgical approach considerations, and also for demonstration of key relationships between structures. Our study is preliminary in nature and limited to our small sample size, but demonstrates an easily replicable technology with multiple impactful future directions.
Conclusion
Our study utilized 3DSlicer to semi-automatically develop three-dimensional reconstructions of each class of benign orbital tumors as designated by the ORBIT criteria. These reconstructions may provide additional quantitative and qualitative data regarding these tumors, their resectability, and the approaches needed in these surgeries. Fig. 1 Sample 3-Dimensional Reconstruction of Class III ORBIT Tumor. Segmentation of a medial view of the right orbit. The ORBIT class III tumor (green) lies posterior to the intersection of the optic nerve (blue) and the ophthalmic artery (red). The medial rectus muscle (brown) has been made transparent to view the orbit content. The inferior rectus muscle (dark brown), the orbit (white). Publication History Article published online: 05 February 2024 © 2024. Thieme. All rights reserved. Georg Thieme Verlag KG Rüdigerstraße 14, 70469 Stuttgart, Germany
Zitieren
APA
Mitchell, M. B., Bartholonew, R., Zhu, A., Bleier, B., & Ringel, B. (2024). Artificial Intelligence Based Semi-automatic Segmentation for Orbital Tumor Preoperative Modeling. Journal of Neurological Surgery Part B: Skull Base, 85(S 01 S 01), S1-S398. https://doi.org/10.1055/s-0044-1779917
Vancouver
Mitchell MB, Bartholonew R, Zhu A, Bleier B, Ringel B. Artificial Intelligence Based Semi-automatic Segmentation for Orbital Tumor Preoperative Modeling. Journal of Neurological Surgery Part B: Skull Base. 2024;85(S 01 S 01):S1-S398. doi:10.1055/s-0044-1779917
BibTeX
@article{Mitchell2024,
author = {Mitchell, Margaret B. and Bartholonew, Ryan and Zhu, Angela and Bleier, Benjamin and Ringel, Barak},
title = {Artificial Intelligence Based Semi-automatic Segmentation for Orbital Tumor Preoperative Modeling},
journal = {Journal of Neurological Surgery Part B: Skull Base},
year = {2024},
volume = {85},
number = {S 01 S 01},
pages = {S1--S398},
doi = {10.1055/s-0044-1779917}
}
EUVIMED