Automatic Masseter Thickness Measurement and Ideal Point Localization for Botulinum Toxin Injection

Xia, Wenjin; Han, Wenqing; Zhang, Yan; Wang, Lisheng; Chai, Gang; Huang, Yalin

doi:10.1109/embc.2019.8856730

Cited by 4 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The intersection of the two diagonal lines was the injection point (Figure 1). This manual localization of BoNT‐A injection point is basically consistent with the automated localization conducted by three‐dimensional computed tomography to localize the maximal bulging point of the masseter muscles 12 . The head was placed in an upright position.…”

Section: Methodssupporting

confidence: 68%

See 1 more Smart Citation

Pivotal role of injection volume on sunken cheek prevention in masseter muscle BoNT‐A injection: A cadaver study

Zhai

et al. 2021

J of Cosmetic Dermatology

View full text Add to dashboard Cite

Background Botulinum neurotoxin A injection is a popular noninvasive alternative for the treatment of masseter hypertrophy. This study was conducted to identify a safe injection volume to avoid sunken lateral cheek after botulinum neurotoxin A injection in the masseter muscle. Methods One milliliter or 0.5 ml of indocyanine green was randomly injected into either side of the masseter muscles of 18 fresh cadaver heads. The bilateral spreads of indocyanine green within the masseter were observed by a fluorescence imager. The masseters were then dissected, and the spreading distance was measured. Results Dye spreading showed an oval shape parallel to the long axis of the masseter muscle. The lower edges of the masseters were all stained with indocyanine green. The upward spreading exceeded the mouth corner‐tragus line in 94.44% (17/18) of the masseters on the 1‐ml side, and 11.11% (2/18) of the masseters on the 0.5‐ml side. The spreading area and upward spreading distance on the 1‐ml side (9.95 ± 0.48 cm2, 3.18 ± 0.31 cm) were significantly larger than the 0.5‐ml side (7.13 ± 0.80 cm2, 2.08 ± 0.32 cm). Conclusions The spread of indocyanine green within the masseter occurs in direct proportion to its volume. A bolus of 1 ml easily exceeded the mouth corner‐tragus line and cause sunken cheek.

show abstract

Section: Methodssupporting

confidence: 68%

“…This manual localization of BoNT-A injection point is basically consistent with the automated localization conducted by three-dimensional computed tomography to localize the maximal bulging point of the masseter muscles. 12 The head was placed in an upright position. A 1-ml syringe with a 27-gauge, 0.5-inch needle was used for injection.…”

Section: Injectionsmentioning

confidence: 99%

Pivotal role of injection volume on sunken cheek prevention in masseter muscle BoNT‐A injection: A cadaver study

Zhai

et al. 2021

J of Cosmetic Dermatology

View full text Add to dashboard Cite

show abstract

“…Moreover, a new loss function combining the Dice score and focal loss is applied in the training process. Xia et al [ 83 ] presented a methodology to automatically measure the masseter thickness and locate the ideal injection point for botulinum toxin into the masseter from a CT scan, in which a 3D UNet with a Resblock is used for the mandible and masseter segmentation. Willems et al [ 84 ] applied the 3D segmentation network from [ 116 ].…”

Section: Resultsmentioning

confidence: 99%

Automatic Segmentation of Mandible from Conventional Methods to Deep Learning—A Review

Qiu

Wel

Kraeima

et al. 2021

JPM

View full text Add to dashboard Cite

Medical imaging techniques, such as (cone beam) computed tomography and magnetic resonance imaging, have proven to be a valuable component for oral and maxillofacial surgery (OMFS). Accurate segmentation of the mandible from head and neck (H&N) scans is an important step in order to build a personalized 3D digital mandible model for 3D printing and treatment planning of OMFS. Segmented mandible structures are used to effectively visualize the mandible volumes and to evaluate particular mandible properties quantitatively. However, mandible segmentation is always challenging for both clinicians and researchers, due to complex structures and higher attenuation materials, such as teeth (filling) or metal implants that easily lead to high noise and strong artifacts during scanning. Moreover, the size and shape of the mandible vary to a large extent between individuals. Therefore, mandible segmentation is a tedious and time-consuming task and requires adequate training to be performed properly. With the advancement of computer vision approaches, researchers have developed several algorithms to automatically segment the mandible during the last two decades. The objective of this review was to present the available fully (semi)automatic segmentation methods of the mandible published in different scientific articles. This review provides a vivid description of the scientific advancements to clinicians and researchers in this field to help develop novel automatic methods for clinical applications.

show abstract

“…To further reduce subjective bias, V-Net with a sliding window strategy has been applied as a automatic segmentation 24. Furthermore, we proposed a U-net maxillofacial segmentation model to improve segmentation accuracy and achieved performance-leading accuracy with a DSC of 0.92 in healthy people 25. However, the algorithm has not yet been applied to disease models.…”

Section: Discussionmentioning

confidence: 99%

“…After adaptive training for the masseter muscle and mandible, we proposed a deep learning model based on U-Net for multiorganization segmentation. The model considers the continuity of section and achieves rapid automatic segmentation and measurement of the masseter muscle in a healthy population in our previous study 17. However, it has not been applied in the HFM with masseter muscle and mandible involvement.…”

mentioning

confidence: 99%

Radiomics and Artificial Intelligence Study of Masseter Muscle Segmentation in Patients With Hemifacial Microsomia

Han

Xia

Zhang

et al. 2023

Journal of Craniofacial Surgery

Self Cite

View full text Add to dashboard Cite

Background: Hemifacial microsomia (HFM) is one of the most common congenital craniofacial condition often accompanied by masseter muscle involvement. U-Net neural convolution network for masseter segmentation is expected to achieve an efficient evaluation of masseter muscle. Methods: A database was established with 108 patients with HFM from June 2012 to June 2019 in our center. Demographic data, OMENS classification, and 1-mm layer thick 3-dimensional computed tomography were included. Two radiologists manually segmented masseter muscles in a consensus reading as the ground truth. A test set of 20 cases was duplicated into 2 groups: an experimental group with the intelligent algorithm and a control group with manual segmentation. The U-net follows the design of 3D RoI-Aware U-Net with overlapping window strategy and references to our previous study of masseter segmentation in a healthy population system. Sorensen dice-similarity coefficient (DSC) muscle volume, average surface distance, recall, and time were used to validate compared with the ground truth. Results:The mean DSC value of 0.794 ± 0.028 for the experiment group was compared with the manual segmentation (0.885 ± 0.118) with α = 0.05 and a noninferiority margin of 15%. In addition, higher DSC was reported in patients with milder mandible deformity (r = 0.824, P < 0.05). Moreover, intelligent automatic segmentation takes only 6.4 seconds showing great efficiency. Conclusions: We first proposed a U-net neural convolutional network and achieved automatic segmentation of masseter muscles in patients with HFM. It is a great attempt at intelligent diagnosis and evaluation of craniofacial diseases.

show abstract

Automatic Masseter Thickness Measurement and Ideal Point Localization for Botulinum Toxin Injection

Cited by 4 publications

References 13 publications

Pivotal role of injection volume on sunken cheek prevention in masseter muscle BoNT‐A injection: A cadaver study

Pivotal role of injection volume on sunken cheek prevention in masseter muscle BoNT‐A injection: A cadaver study

Automatic Segmentation of Mandible from Conventional Methods to Deep Learning—A Review

Radiomics and Artificial Intelligence Study of Masseter Muscle Segmentation in Patients With Hemifacial Microsomia

Contact Info

Product

Resources

About