scholarly journals Automated Segmentation of Trigeminal Nerve and Cerebrovasculature in MR-Angiography Images by Deep Learning

2021 ◽  
Vol 15 ◽  
Author(s):  
Jinghui Lin ◽  
Lei Mou ◽  
Qifeng Yan ◽  
Shaodong Ma ◽  
Xingyu Yue ◽  
...  

Trigeminal neuralgia caused by paroxysmal and severe pain in the distribution of the trigeminal nerve is a rare chronic pain disorder. It is generally accepted that compression of the trigeminal root entry zone by vascular structures is the major cause of primary trigeminal neuralgia, and vascular decompression is the prior choice in neurosurgical treatment. Therefore, accurate preoperative modeling/segmentation/visualization of trigeminal nerve and its surrounding cerebrovascular is important to surgical planning. In this paper, we propose an automated method to segment trigeminal nerve and its surrounding cerebrovascular in the root entry zone, and to further reconstruct and visual these anatomical structures in three-dimensional (3D) Magnetic Resonance Angiography (MRA). The proposed method contains a two-stage neural network. Firstly, a preliminary confidence map of different anatomical structures is produced by a coarse segmentation stage. Secondly, a refinement segmentation stage is proposed to refine and optimize the coarse segmentation map. To model the spatial and morphological relationship between trigeminal nerve and cerebrovascular structures, the proposed network detects the trigeminal nerve, cerebrovasculature, and brainstem simultaneously. The method has been evaluated on a dataset including 50 MRA volumes, and the experimental results show the state-of-the-art performance of the proposed method with an average Dice similarity coefficient, Hausdorff distance, and average surface distance error of 0.8645, 0.2414, and 0.4296 on multi-tissue segmentation, respectively.

Neurosurgery ◽  
2004 ◽  
Vol 55 (6) ◽  
pp. E1445-E1449 ◽  
Author(s):  
Hiroshi Karibe ◽  
Reizo Shirane ◽  
Hidefumi Jokura ◽  
Takashi Yoshimoto

Abstract OBJECTIVE AND IMPORTANCE: Intrinsic arteriovenous malformation (AVM) of the trigeminal nerve is extremely uncommon and may be associated with trigeminal neuralgia. CLINICAL PRESENTATION: A 55-year-old man experienced severe lightning pain in the second and third divisions of the left trigeminal nerve territory. Vertebral angiography demonstrated an AVM fed by the superior cerebellar artery. Magnetic resonance imaging with three-dimensional spoiled gradient recalled acquisition at steady state revealed an AVM intrinsic to the left trigeminal nerve and a small arterial loop causing compression at the root entry zone of the trigeminal nerve. INTERVENTION: Intraoperative inspection revealed an indentation of the root entry zone caused by a small arterial loop but not by the AVM. The offending artery was displaced to decompress the root entry zone using a prosthesis without resection of the AVM. The patient was relieved of the neuralgia immediately after surgery without further neurological deficit. He has been free of trigeminal neuralgia during a follow-up period of 2 years and is scheduled to undergo stereotactic radiosurgery for the treatment of the AVM. CONCLUSION: Intrinsic AVM of the trigeminal nerve may cause trigeminal neuralgia. However, as in the present case, a coexistent vascular lesion rather than the intrinsic AVM could be a cause of the neuralgia.


Neurocirugía ◽  
2019 ◽  
Vol 30 (3) ◽  
pp. 105-114
Author(s):  
Rafael Medélez-Borbonio ◽  
Alexander Perdomo-Pantoja ◽  
Alejandro Apolinar Serrano-Rubio ◽  
Colson Tomberlin ◽  
Rogelio Revuelta-Gutiérrez ◽  
...  

Neurosurgery ◽  
2006 ◽  
Vol 59 (2) ◽  
pp. 354-359 ◽  
Author(s):  
Selçuk Peker ◽  
Özlem Kurtkaya ◽  
İbrahim Üzün ◽  
M Necmettin Pamir

Abstract OBJECTIVE: The aim of this study was to evaluate the microanatomy of the central myelin-peripheral myelin transitional zone (TZ) in trigeminal nerves from cadavers. METHODS: One hundred trigeminal nerves from 50 cadaver heads were examined. The cisternal portion of the nerve (from the pons to Meckel's cave) was measured. Horizontal sections were stained and photographed. The photomicrographs were used to measure the extent of central myelin on the medial and lateral aspects of the nerve and to classify TZ shapes. RESULTS: The cisternal portions of the specimens ranged from 8 to 15 mm long (mean, 12.3 mm; median, 11.9 mm). The data from the photomicrographs revealed that the extent of central myelin (distance from pons to TZ) on the medial aspect of the nerve (range, 0.1–2.5 mm; mean, 1.13 mm; median, 1 mm) was shorter than that on the lateral aspect (range, 0.17–6.75 mm; mean, 2.47 mm; median, 2.12 mm). CONCLUSION: The data definitively prove that the root entry zone (REZ, nerve-pons junction) and TZ of the trigeminal nerve are distinct sites and that these terms should never be used interchangeably. The measurements showed that the central myelin occupies only the initial one-fourth of the trigeminal nerve length. If trigeminal neuralgia is caused exclusively by vascular compression of the central myelin, the problem vessel would always have to be located in this region. However, it is well known that pain from trigeminal neuralgia can resolve after vascular decompression at more distal sites. This suggests that the effects of surgical decompression are caused by another mechanism.


1996 ◽  
Vol 84 (5) ◽  
pp. 818-825 ◽  
Author(s):  
Fred G. Barker ◽  
Peter J. Jannetta ◽  
Ramesh P. Babu ◽  
Spiros Pomonis ◽  
David J. Bissonette ◽  
...  

✓ During a 20-year period, 26 patients with typical symptoms of trigeminal neuralgia were found to have posterior fossa tumors at operation. These cases included 14 meningiomas, eight acoustic neurinomas, two epidermoid tumors, one angiolipoma, and one ependymoma. The median patient age was 60 years and 69% of the patients were women. Sixty-five percent of the symptoms were left sided. The median preoperative duration of symptoms was 5 years. The distribution of pain among the three divisions of the trigeminal nerve was similar to that found in patients with trigeminal neuralgia who did not have tumors; however, more divisions tended to be involved in the tumor patients. The mean postoperative follow-up period was 9 years. At operation, the root entry zone of the trigeminal nerve was examined for vascular cross-compression in 21 patients. Vessels compressing the nerve at the root entry zone were observed in all patients examined. Postoperative pain relief was frequent and long lasting. Using Kaplan—Meier methods the authors estimated excellent relief in 81% of the patients 10 years postoperatively, with partial relief in an additional 4%.


Neurosurgery ◽  
2009 ◽  
Vol 65 (5) ◽  
pp. 958-961 ◽  
Author(s):  
Gregory M. Helbig ◽  
James D. Callahan ◽  
Aaron A. Cohen-Gadol

Abstract OBJECTIVE Trigeminal neuralgia is often caused by compression, demyelination, and injury of the trigeminal nerve root entry zone by an adjacent artery and/or vein. Previously described variations of the nerve-vessel relationship note external nerve compression. We offer a detailed classification of intraneural vessels that travel through the trigeminal nerve and safe, effective surgical management. CLINICAL PRESENTATION We report 3 microvascular decompression operations for medically refractory trigeminal neuralgia during which the surgeon encountered a vein crossing through the trigeminal nerve. Two types of intraneural veins are described: type 1, in which the vein travels between the motor and sensory branches of the trigeminal nerve (1 patient), and type 2, in which the vein bisects the sensory branch (portio major) (2 patients). INTERVENTION We recommend sacrificing the intraneural vein between the motor and sensory branches if the vein is small (most likely type 1). If the intraneural vein is large and bisects the sensory branch (most likely type 2), vein mobilization can be achieved, but often requires extensive dissection through the nerve. Because this maneuver may lead to trigeminal nerve injury and result in uncomfortable neuropathy and numbness (including corneal hypoesthesia), we recommend against mobilization of the vein through the nerve, suggesting instead, consideration of a selective trigeminal nerve rhizotomy. CONCLUSION Because aggressive dissection of intraneural vessels can lead to higher than normal complication rates, preoperative knowledge of vein-trigeminal nerve variants is crucial for intraoperative success.


1980 ◽  
Vol 52 (3) ◽  
pp. 381-386 ◽  
Author(s):  
Stephen J. Haines ◽  
Peter J. Jannetta ◽  
David S. Zorub

✓ The vascular relationships of the trigeminal nerve root entry zone were examined bilaterally in 20 cadavers of individuals known to be free of facial pain. Fourteen of 40 nerves made contact with an artery, but only four of these showed evidence of compression or distortion of the nerve. In addition, the vascular relationships of 40 trigeminal nerves exposed surgically for treatment of trigeminal neuralgia were studied, and 31 nerves showed compression by adjacent arteries. Venous compression was seen in four of the cadaver nerves and in eight nerves from patients with trigeminal neuralgia. These data support the hypothesis that arterial compression of the trigeminal nerve is associated with trigeminal neuralgia.


2019 ◽  
Vol 19 (1) ◽  
pp. E50-E51 ◽  
Author(s):  
Karl R Abi-Aad ◽  
Evelyn Turcotte ◽  
Devi P Patra ◽  
Matthew E Welz ◽  
Tanmoy Maiti ◽  
...  

Abstract This is the case of an 86-yr-old gentleman who presented with left facial pain exacerbated by eating, drinking, chewing, and shaving (distribution: V2, V3). The patient was diagnosed with trigeminal neuralgia and was refractory to medications. Imaging showed a superior cerebellar artery (SCA) loop adjacent to the trigeminal nerve root entry zone and a decision to perform a microvascular decompression of the fifth nerve was presented to the patient. After patient informed consent was obtained, a standard 3 cm × 3 cm retrosigmoid craniotomy was performed with the patient in a supine head turned position and in reverse Trendelenburg. The arachnoid bands tethering the SCA to the trigeminal nerve were sharply divided. A slit was then made in the tentorium and a 3 mm fenestrated clip was then used to secure the transposed SCA away from the trigeminal nerve. The SCA proximal to this was slightly patulous in its course so a small amount of a fibrin glue was also used to secure the more proximal SCA to the tentorium. The patient was symptom-free postoperatively and no longer required medical therapy. Additionally, imaging was consistent with adequate separation of the nerve from adjacent vessels.1-5


2019 ◽  
Vol 30 (3) ◽  
pp. 105-114
Author(s):  
Rafael Medélez-Borbonio ◽  
Alexander Perdomo-Pantoja ◽  
Alejandro Apolinar Serrano-Rubio ◽  
Colson Tomberlin ◽  
Rogelio Revuelta-Gutiérrez ◽  
...  

Neurosurgery ◽  
2005 ◽  
Vol 56 (3) ◽  
pp. E628-E628 ◽  
Author(s):  
Gabriela-del-Rocío Chávez Chávez ◽  
Antonio A.F. De Salles ◽  
Timothy D. Solberg ◽  
Alessandra Pedroso ◽  
Dulce Espinoza ◽  
...  

Abstract OBJECTIVE: The aim of this study was to demonstrate the use and applications of the three-dimensional fast imaging employing steady-state acquisition (3-D-FIESTA) magnetic resonance imaging sequence in targeting and planning for stereotactic radiosurgery of trigeminal neuralgia. METHODS: A 3-D-FIESTA sequence for visualization of cranial nerves in the cranial base was added to the routine magnetic resonance imaging scan to enhance the treatment planning for trigeminal neuralgia. T1-weighted images, 1 mm thick, were directly compared with the FIESTA sequence for the exact visualization of the trigeminal entry zone and surrounding vasculature. The target accuracy was evaluated by image fusion of computed tomographic and magnetic resonance imaging scans. The anatomy visualized with the FIESTA sequence was validated by direct inspection of the gross anatomic specimens of the trigeminal complex. RESULTS: A total of 15 consecutive patients, 10 women and 5 men, underwent radiosurgery for essential trigeminal neuralgia between April and July, 2003. The mean age of the patients was 65.2 years (range, 24–83 yr). Nine patients had right-sided symptoms. Four patients had had previous surgery (two microvascular decompression, one percutaneous rhizotomy, and one radiofrequency thermocoagulation). The 3-D-FIESTA sequence successfully demonstrated the trigeminal complex (root entry zone, trigeminal ganglion, rootlets, and vasculature) in 14 patients (93.33%). The 3-D-FIESTA sequence also allowed visualization of the branches of the trigeminal nerve inside Meckel's cavity. This exact visualization correlated precisely with the anatomic specimens. In one patient (6.66%), it was not possible to demonstrate the related vasculature. However, the other structures were clearly visualized. CONCLUSION: The 3-D-FIESTA sequence is used in this study for demonstration of the exact anatomy of the trigeminal complex for the purpose of radiosurgical planning and treatment of trigeminal neuralgia. With such imaging techniques, radiosurgical targeting of specific trigeminal nerve branches may be feasible. It has not been possible previously to target individual branches of the trigeminal nerve.


Sign in / Sign up

Export Citation Format

Share Document