scholarly journals Automated Segmentation of Articular Disc of the Temporomandibular Joint in Magnetic Resonance Images Using Deep Learning: A Proof-of-Concept Study

2021 ◽  
Author(s):  
Shota Ito ◽  
Yuichi Mine ◽  
Yuki Yoshimi ◽  
Saori Takeda ◽  
Akari Tanaka ◽  
...  
Keyword(s):  
Deep Learning ◽  
Magnetic Resonance ◽  
Temporomandibular Joint ◽  
Temporomandibular Disorders ◽  
Temporomandibular Disorder ◽  
Semantic Segmentation ◽  
Magnetic Resonance Images ◽  
Automated Segmentation ◽  
Proof Of Concept ◽  
Articular Disc

Abstract Temporomandibular disorders are typically accompanied by a number of clinical manifestations that involve pain and dysfunction of the masticatory muscles and temporomandibular joint. The most important subgroup of articular abnormalities in patients with temporomandibular disorders includes patients with different forms of articular disc displacement and deformation. Here, we propose a fully automated articular disc detection and segmentation system to support the diagnosis of temporomandibular disorder on magnetic resonance imaging. This system uses deep learning-based semantic segmentation approaches. Two hundred and seventeen magnetic resonance images obtained from patients with normal or displaced articular discs were used to evaluate three deep learning-based semantic segmentation approaches: our proposed encoder-decoder CNN named 3DiscNet (Detection for Displaced articular DISC using convolutional neural NETwork), U-Net, and SegNet-Basic. Of the three algorithms, 3DiscNet and SegNet-Basic showed comparably good metrics (Dice coefficient, sensitivity, and PPV). This study provides a proof-of-concept for a fully automated segmentation methodology of the articular disc on MR images with deep learning, and obtained promising initial results indicating that it could potentially be used in clinical practice for the assessment of temporomandibular disorders.

scholarly journals Automated segmentation of articular disc of the temporomandibular joint on magnetic resonance images using deep learning

2022 ◽  
Vol 12 (1) ◽  
Author(s):  
Shota Ito ◽  
Yuichi Mine ◽  
Yuki Yoshimi ◽  
Saori Takeda ◽  
Akari Tanaka ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Magnetic Resonance ◽  
Convolutional Neural Network ◽  
Temporomandibular Joint ◽  
Temporomandibular Disorders ◽  
Temporomandibular Disorder ◽  
Semantic Segmentation ◽  
Magnetic Resonance Images ◽  
Articular Disc

AbstractTemporomandibular disorders are typically accompanied by a number of clinical manifestations that involve pain and dysfunction of the masticatory muscles and temporomandibular joint. The most important subgroup of articular abnormalities in patients with temporomandibular disorders includes patients with different forms of articular disc displacement and deformation. Here, we propose a fully automated articular disc detection and segmentation system to support the diagnosis of temporomandibular disorder on magnetic resonance imaging. This system uses deep learning-based semantic segmentation approaches. The study included a total of 217 magnetic resonance images from 10 patients with anterior displacement of the articular disc and 10 healthy control subjects with normal articular discs. These images were used to evaluate three deep learning-based semantic segmentation approaches: our proposed convolutional neural network encoder-decoder named 3DiscNet (Detection for Displaced articular DISC using convolutional neural NETwork), U-Net, and SegNet-Basic. Of the three algorithms, 3DiscNet and SegNet-Basic showed comparably good metrics (Dice coefficient, sensitivity, and positive predictive value). This study provides a proof-of-concept for a fully automated deep learning-based segmentation methodology for articular discs on magnetic resonance images, and obtained promising initial results, indicating that the method could potentially be used in clinical practice for the assessment of temporomandibular disorders.

scholarly journals A comparison between two semantic deep learning frameworks for the autosomal dominant polycystic kidney disease segmentation based on magnetic resonance images

2019 ◽  
Vol 19 (S9) ◽  
Author(s):  
Vitoantonio Bevilacqua ◽  
Antonio Brunetti ◽  
Giacomo Donato Cascarano ◽  
Andrea Guerriero ◽  
Francesco Pesce ◽  
...  
Keyword(s):  
Deep Learning ◽  
Magnetic Resonance ◽  
Kidney Disease ◽  
Autosomal Dominant ◽  
Automatic Segmentation ◽  
Semantic Segmentation ◽  
Magnetic Resonance Images ◽  
Polycystic Kidney ◽  
Autosomal Dominant Polycystic Kidney ◽  
Segmentation Of Images

Abstract Background The automatic segmentation of kidneys in medical images is not a trivial task when the subjects undergoing the medical examination are affected by Autosomal Dominant Polycystic Kidney Disease (ADPKD). Several works dealing with the segmentation of Computed Tomography images from pathological subjects were proposed, showing high invasiveness of the examination or requiring interaction by the user for performing the segmentation of the images. In this work, we propose a fully-automated approach for the segmentation of Magnetic Resonance images, both reducing the invasiveness of the acquisition device and not requiring any interaction by the users for the segmentation of the images. Methods Two different approaches are proposed based on Deep Learning architectures using Convolutional Neural Networks (CNN) for the semantic segmentation of images, without needing to extract any hand-crafted features. In details, the first approach performs the automatic segmentation of images without any procedure for pre-processing the input. Conversely, the second approach performs a two-steps classification strategy: a first CNN automatically detects Regions Of Interest (ROIs); a subsequent classifier performs the semantic segmentation on the ROIs previously extracted. Results Results show that even though the detection of ROIs shows an overall high number of false positives, the subsequent semantic segmentation on the extracted ROIs allows achieving high performance in terms of mean Accuracy. However, the segmentation of the entire images input to the network remains the most accurate and reliable approach showing better performance than the previous approach. Conclusion The obtained results show that both the investigated approaches are reliable for the semantic segmentation of polycystic kidneys since both the strategies reach an Accuracy higher than 85%. Also, both the investigated methodologies show performances comparable and consistent with other approaches found in literature working on images from different sources, reducing both the invasiveness of the analyses and the interaction needed by the users for performing the segmentation task.

scholarly journals Evaluation of TMJ articular eminence morphology and disc patterns in patients with disc displacement in MRI

2007 ◽  
Vol 21 (3) ◽  
pp. 265-271 ◽  
Author(s):  
Fabio Henrique Hirata ◽  
Antônio Sérgio Guimarães ◽  
Jefferson Xavier de Oliveira ◽  
Carla Ruffeil Moreira ◽  
Evangelo Tadeu Terra Ferreira ◽  
...  
Keyword(s):  
Magnetic Resonance ◽  
Temporomandibular Joint ◽  
Contralateral Side ◽  
Magnetic Resonance Images ◽  
Disc Displacement ◽  
Articular Disc ◽  
Articular Eminence ◽  
Disc Position ◽  
Disc Configuration ◽  
Disc Displacement With Reduction

The aim of this study was to assess the shape of the temporomandibular joint (TMJ) articular eminence and the articular disc configuration and position in patients with disc displacement. TMJ magnetic resonance images (MRI) of 14 patients with bilateral disc displacement without unilateral reduction were analyzed. Articular eminence morphology was characterized as box, sigmoid, flattened, or deformed. Articular disc configuration was divided into biconcave, biplanar, biconvex, hemiconvex or folded, and its position, as "a" (superior), "b" (anterosuperior), "c" (anterior) or "d" (anteroinferior). The images were divided and the sides with disc displacement with reduction (DDWR) and without reduction (DDWOR) were compared. Regarding articular eminence shape, the sigmoid form presented the greatest incidence, followed by the box form, in the DDWR side, although this was not statistically significant. In the DDWOR side, the flattened shape was the most frequent (p = 0.041). As to disc configuration, the biconcave shape was found in 79% of the DDWR cases (p = 0.001) and the folded type predominated in 43% of the DDWOR cases (p = 0.008). As to disc position, in the DDWR side, "b" (anterosuperior position) was the most frequent (p = 0.001), whereas in the DDWOR side, "d" (anteroinferior position) was the most often observed (p = 0.001). The side of the patient with altered disc configuration and smaller shape of TMJ articular eminence seems to be more likely to develop non-reducing disc displacement as compared to the contralateral side.

Automatic detection of anteriorly displaced temporomandibular joint discs on magnetic resonance images using a deep learning algorithm

2021 ◽  
Author(s):  
Bolun Lin ◽  
Mosha Cheng ◽  
Shuze Wang ◽  
Fulong Li ◽  
Qing Zhou
Keyword(s):  
Deep Learning ◽  
Magnetic Resonance ◽  
Temporomandibular Joint ◽  
Diagnostic Criteria ◽  
Orthodontic Treatment ◽  
Data Augmentation ◽  
Learning Algorithm ◽  
Area Under The Curve ◽  
Magnetic Resonance Images ◽  
Learning Models

Objectives: This study aimed to develop models that can automatically detect anterior disc displacement (ADD) of the temporomandibular joint (TMJ) on magnetic resonance images (MRI) before orthodontic treatment to reduce the risk of developing serious complications after treatment. Methods: We used 9009 sagittal MRI of the TMJ as input and constructed three sets of deep learning models to detect ADD automatically. Deep learning models were developed using a convolutional neural network (CNN) based on the ResNet architecture and the “Imagenet” database. Five-fold cross-validation, over sampling, and data augmentation techniques were applied to reduce the risk of overfitting the model. The accuracy and area under the curve (AUC) of the three models were compared. Results: The performance of the maximum open mouth position model was excellent with accuracy and AUC of 0.970 (±0.007) and 0.990 (±0.005), respectively. For closed mouth position models the accuracy and AUC of diagnostic criteria One were 0.863 (±0.008) and 0.922 (±0.009), respectively significantly higher than that of diagnostic criteria two with an 0.839 (±0.013) (p = 0.009) and AUC of 0.885 (±0.018) (p = 0.003). The classification activation heat map also improved our understanding of the models and visually displayed the areas that play a key role in the model recognition process. Conclusion: Our CNN model resulted in high accuracy and AUC in detecting ADD and can therefore potentially be used by clinicians to assess ADD before orthodontic treatment and hence improve treatment outcomes.

Automatic segmentation of the temporomandibular joint disc on magnetic resonance images using a deep learning technique

2021 ◽  
pp. 20210185
Author(s):  
Michihito Nozawa ◽  
Hirokazu Ito ◽  
Yoshiko Ariji ◽  
Motoki Fukuda ◽  
Chinami Igarashi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Magnetic Resonance ◽  
Temporomandibular Joint ◽  
Test Data ◽  
Automatic Segmentation ◽  
Learning Model ◽  
Magnetic Resonance Images ◽  
Mr Images ◽  
Validity Test ◽  
Deep Learning Model

Objectives: The aims of the present study were to construct a deep learning model for automatic segmentation of the temporomandibular joint (TMJ) disc on magnetic resonance (MR) images, and to evaluate the performances using the internal and external test data. Methods: In total, 1200 MR images of closed and open mouth positions in patients with temporomandibular disorder (TMD) were collected from two hospitals (Hospitals A and B). The training and validation data comprised 1000 images from Hospital A, which were used to create a segmentation model. The performance was evaluated using 200 images from Hospital A (internal validity test) and 200 images from Hospital B (external validity test). Results: Although the analysis of performance determined with data from Hospital B showed low recall (sensitivity), compared with the performance determined with data from Hospital A, both performances were above 80%. Precision (positive predictive value) was lower when test data from Hospital A were used for the position of anterior disc displacement. According to the intra-articular TMD classification, the proportions of accurately assigned TMJs were higher when using images from Hospital A than when using images from Hospital B. Conclusion: The segmentation deep learning model created in this study may be useful for identifying disc positions on MR images.

scholarly journals Results of Using Arthrocentesis in the Treatment of Temporomandibular Disorders Associated with Fractures of the Mandibular Condylar Process

2021 ◽  
Vol 6 (6) ◽  
pp. 171-176
Author(s):  
Kh. R. Pohranychna ◽  
◽  
R. Z. Ohonovskyi
Keyword(s):  
Magnetic Resonance ◽  
Temporomandibular Joint ◽  
Computer Tomography ◽  
Temporomandibular Disorders ◽  
Stage Iii ◽  
Articular Disc ◽  
Intermaxillary Fixation ◽  
Disc Protrusion ◽  
Articular Process ◽  
Post Traumatic

The purpose of the work was to study the effectiveness of arthrocentesis in the complex treatment of post-traumatic temporomandibular disorders. Materials and methods. The clinical part of the study included 24 patients, who had a history of fractures of the mandibular articular process. Patients underwent radiological examination – orthopantomography, computer tomography, ultrasound and magnetic resonance. Patients with titanium mini-plates after osteosynthesis were subjected to ultrasound, and since the reposition and fixation of fragments was performed using intermaxillary fixation they were subjected to magnetic resonance imaging. Pain assessment was performed according to visual analogue scale. Temporomandibular joint arthrocentesis was performed according to a modified method of D. Nitzan (1991) under local anesthesia. Results and discussion. All patients complained of the temporomandibular joint pain, which was rated from 1 to 6 points. All patients noted pain on palpation of the temporomandibular joint. Limited mouth opening ranging from 30 to 38 mm was found in 11 patients. Lower jaw deviation was observed in 18 patients. All patients had articulatory noises – clicking, and 11 had blocked movement of the joint head. Orthopantomograms or computer tomography revealed satisfactory restoration of the anatomical shape of the mandible after fractures and complete consolidation of the fracture. Ultrasound and magnetic resonance revealed signs of unabsorbed hematoma as consequences of hemarthrosis; in 18 patients – deformity of the capsule, in 17 – a slight thickening of the posterior edge of the articular disc, in 18 patients – disc adhesion, in 13 people – forward disc displacement with reduction, in 11 patients – disc protrusion without reduction. According to clinical and radiological signs after traumatic temporomandibular disorders, patients were divided into two groups according to Wilkes classification: 13 patients with stage II (early-middle) and 11 – with stage III (middle). We also found that after surgical treatment – osteosynthesis, the number of patients with stage III according to Wilkes makes up 58.33% (7 people), while those after splinting – 33.33% (4 people). The control ultrasound and MRI carried out 3-6 months after arthrocentesis showed no signs of hemarthrosis in 11 (84.61%) patients with intra-articular disorders of the second degree, and in 8 (72.72%) patients with internal disorders of the third degree, the position and function of the articular disc were restored. Conclusion. Arthrocentesis with temporomandibular joint lavage is a minimally invasive surgical manipulation that has proven itself in temporomandibular disorders of traumatic origin, in particular after fractures of the articular process of the mandible. Arthrocentesis is recommended to be used after ineffective conservative treatment, as well as to prevent post-traumatic intra-articular disorders in the early post-treatment fractures (intermaxillary fixation or osteosynthesis) with the attenuation of acute post-traumatic events, which is our goal of further work

Asociación entre hábitos parafuncionales de la cavidad bucal y los transtornos temporomandibulares en adolescentes

2018 ◽  
Vol 10 (2) ◽  
Author(s):  
Gabriel Muñoz Quintana
Keyword(s):  
Oral Cavity ◽  
Temporomandibular Joint ◽  
Temporomandibular Disorders ◽  
Temporomandibular Disorder ◽  
Neuromuscular System ◽  
Jaw Movements ◽  
Nail Biting ◽  
Palabras Clave ◽  
Masticatory System ◽  
Objective Being

La musculatura del sistema masticatorio y la articulación temporomandibular (ATM) están protegidos por reflejos nerviosos básicos y sistema neuromuscular a través de la coordinación de fuerzas musculares, todo lo que produce sobrecarga muscular repetitiva como los hábitos parafuncionales (HPF) pueden ocasionar trastornos temporomandibulares (TTM)1. Los HPF se caracterizan por movimientos anormales a la función mandibular normal sin objetivo funcional, al estar alterados constituyen una fuente productora de fuerzas traumáticas caracterizadas por dirección anormal, intensidad excesiva y repetición frecuente y duradera (Rolando Castillo Hernández, 2001)4. El objetivo del estudio fue identificar la asociación entre la presencia de hábitos parafuncionales de la cavidad bucal y los TTM en adolescentes de la ciudad de Puebla. Estudio observacional descriptivo. Se incluyeron 258 adolescentes, 132 (51.2%) mujeres y 126 (48.8%) hombres, con una edad promedio de 12.5±.73 y quienes fueron diagnosticados con los CDI/TTM y los HPF fueron auto-reportados por los pacientes. Se encontró una prevalencia de los TTM del 39.9% y una prevalencia de HPF del 86%. Los HPF más frecuentemente reportados fueron la succión labial y la onicofagia. Se encontró una asociación significativa (x2=7.31, p=0.007) entre los hábitos parafuncionales y los TTM en adolescentes. Palabras clave: Trastornos temporomandibulares, hábitos parafuncionales, adolescentes, articulación temporomandibular. Abstract The muscles of the masticatory system and temporomandibular joint (TMJ) are protected by basic nerve reflex and neuromuscular system through the coordination of muscle forces, all that repetitive muscle overload occurs as habit parafunctional (HPF) can cause temporomandibular disorder TMD)1. The characteristics of HPF are abnormal jaw movements without a functional objective. Being the jaw movements altered, they constitute a source of traumatic forces with an abnormal direction, excessive intensity and long-lasting and frequent duration. (Rolando Hernandez Castillo 2001)4. Objective: was to identify the association between the presences of parafunctional habits of the oral cavity and TMD in adolescents in the Puebla city in Mexico. Material and methods: Is a observational study, we included 258 adolescents 132 (51%) females and 126 (48.8%) were men, mean age 12.5±.73 and who were diagnosed with CDI/TTM and HPF were self- reported by patients. Results: The prevalence of TMD was 39.9% and a prevalence of 86% HPF. The most frequently reported HPF were lip sucking and nail biting. We found a significant association (x2= 7.31, p = 0,007) between HPF and TMD in adolescents. Key words: Parafunctional habits of oral cavity, temporomandibular disorders, temporomandibular joint. (Odontol Pediatr 2011;10(2): 90-94).

scholarly journals Application of deep learning in detecting neurological disorders from magnetic resonance images: a survey on the detection of Alzheimer’s disease, Parkinson’s disease and schizophrenia

2020 ◽  
Vol 7 (1) ◽  
Author(s):  
Manan Binth Taj Noor ◽  
Nusrat Zerin Zenia ◽  
M Shamim Kaiser ◽  
Shamim Al Mamun ◽  
Mufti Mahmud
Keyword(s):  
Alzheimer’S Disease ◽  
Parkinson’S Disease ◽  
Alzheimer's Disease ◽  
Parkinson's Disease ◽  
Deep Learning ◽  
Magnetic Resonance ◽  
Neurological Disorders ◽  
Magnetic Resonance Images ◽  
Future Research ◽  
Comparative Performance

Abstract Neuroimaging, in particular magnetic resonance imaging (MRI), has been playing an important role in understanding brain functionalities and its disorders during the last couple of decades. These cutting-edge MRI scans, supported by high-performance computational tools and novel ML techniques, have opened up possibilities to unprecedentedly identify neurological disorders. However, similarities in disease phenotypes make it very difficult to detect such disorders accurately from the acquired neuroimaging data. This article critically examines and compares performances of the existing deep learning (DL)-based methods to detect neurological disorders—focusing on Alzheimer’s disease, Parkinson’s disease and schizophrenia—from MRI data acquired using different modalities including functional and structural MRI. The comparative performance analysis of various DL architectures across different disorders and imaging modalities suggests that the Convolutional Neural Network outperforms other methods in detecting neurological disorders. Towards the end, a number of current research challenges are indicated and some possible future research directions are provided.

scholarly journals Temporomandibular Disorders and Bruxism Prevalence in a Portuguese Sample

2021 ◽  
Vol 5 (1) ◽  
pp. 37
Author(s):  
João Belo ◽  
André Almeida ◽  
Paula Moleirinho-Alves ◽  
Catarina Godinho
Keyword(s):  
Temporomandibular Joint ◽  
Temporomandibular Disorders ◽  
Temporomandibular Disorder ◽  
Masticatory Muscles ◽  
Diagnostic Aspects ◽  
Relevant Role

Temporomandibular disorder (TMD) encompasses a set of disorders involving the masticatory muscles, the temporomandibular joint and associated structures. It is a complex biopsychosocial disorder with several triggering, predisposing and perpetuating factors. In the etiology of TMD, oral parafunctions, namely bruxism, play a relevant role. The study of bruxism is complicated by some taxonomic and diagnostic aspects that have prevented achieving an acceptable standardization of diagnosis. The aim of this study was to analyze the prevalence of temporomandibular disorders and bruxism in a Portuguese sample.

Sign in / Sign up

Export Citation Format

Share Document