Optimization of the automated Sunnybrook Facial Grading System - Improving the reliability of a deep learning network with facial landmarks.

OBJECTIVE: The Sunnybrook Facial Grading System (SFGS) is a well-established grading system to assess the severity and progression of a unilateral facial palsy. The automation of the SFGS makes the SFGS more accessible for researchers, students, clinicians in training, or other untrained co-workers and could be implemented in an eHealth environment. This study investigated the impact on the reliability of the automated SFGS by adding a facial landmark layer in a previously developed convolutional neural network (CNN). METHODS: An existing dataset of 116 patients with a unilateral peripheral facial palsy and 9 healthy subjects performing the SFGS poses was used to train a CNN with a newly added facial landmark layer. A separate model was trained for each of the 13 elements of the SFGS and then used to calculate the SFGS subscores and composite score. The intra-class coefficient of the automated grading system was calculated based on three clinicians experienced in the grading of facial palsy. RESULTS: The inter-rater reliability of the CNN with the additional facial landmarks increased in performance for all composite scores compared to the previous model. The intra-class coefficient for the composite SFGS score increased from 0.87 to 0.91, the resting symmetry subscore increased from 0.45 to 0.62, the symmetry of voluntary movement subscore increased from 0.89 to 0.92, and the synkinesis subscore increased from 0.75 to 0.78. CONCLUSION: The integration of a facial landmark layer into the CNN significantly improved the reliability of the automated SFGS, reaching a performance level comparable to human observers. These results were attained without increasing the dataset underscoring the impact of incorporating facial landmarks into a CNN. These findings indicate that the automated SFGS with facial landmarks is a reliable tool for assessing patients with a unilateral peripheral facial palsy and is applicable in an eHealth environment.

Digital image processing versus visual assessment of chewed two-colour wax in mixing ability tests.

Two-colour chewing gum and wax have been widely used as test foods to evaluate the ability to mix and knead a food bolus. The mixing of the colours has been assessed by computer analysis or by visual inspection. Reports contradict each other about whether computer analysis and visual assessment could equally well discriminate between the masticatory performances of groups of participants with different dental status. This study compares the results of computer analysis of digital images of chewed two-colour wax with the results of visual assessment of these images. Sixty healthy subjects participated and chewed on red-blue wax for 5, 10, 15 and 20 chewing strokes. The subjects were divided into three groups of 20, matched for age and gender, according to their dental status: natural dentition, full dentures and maxillary denture plus implant-supported mandibular overdenture. Mixing of the chewed wax was determined by computer analysis of images of the wax and by visual assessment of the images by five examiners. Both the computer method and the observers were able to distinguish the mixing abilities of the dentate subjects from the two denture wearer groups. Computer analysis could also discriminate the mixing abilities of the two denture groups. However, observers were not able to distinguish the mixing abilities of the two denture groups after 5, 10 and 15 chewing strokes. Only after 20 chewing strokes, they could detect a significant difference in mixing ability.

Immediate implant placement in edentulous oral cancer patients: a long-term retrospective analysis of 207 patients.

Although the functional benefits of implants in the rehabilitation of edentulous cancer patients are well-known, most studies report on postponed implant placement. The outcome of immediate implant placement regarding successful rehabilitation, implant loading and survival is unclear. Two hundred and seven edentulous oral cancer patients that received implants during ablative surgery at the Radboud University Medical Centre between 2000 and 2011 were included. Data regarding the oncological treatment, implant placement, follow-up and prosthodontic rehabilitation were recorded retrospectively with a follow-up period of 5-17 years. Functioning implant-retained dentures were made in 73.9% of the patients. Of the surviving patients, 81.9% had functioning dentures after 2 years and 86.3% after 10 years. Patients with ASA score 1 and younger patients were rehabilitated more frequently. The median time of functioning denture placement was 336 days after surgery, with a negative influence of postoperative radiotherapy. Implant survival was 90.7%, and was lower when the implant was placed in a jaw involved in the tumour. Immediate implant placement during oral cancer surgery led to a high number of edentulous patients rehabilitated with implant-retained dentures, which are placed at an early time.

Mixing ability test compared with a comminution test in persons with normal and compromised masticatory performance.

A mastication test was needed with a material that forms a bolus and is soft enough to be chewed by persons with compromised oral function, in particular patients confronted with oral cancer. We therefore developed a wax-mixing ability test and compared it with a comminution test using Optocal as test food. We hypothesized that the mixing ability test would be better at differentiating between groups of persons with compromised masticatory performance than the comminution test. Sixty healthy subjects were recruited in three groups of 20, matched for age and gender: a group with natural dentition; a group with full dentures; and a group with maxillary denture and implant-supported mandibular overdenture. The mixing ability test was found to discriminate better between the two full-denture groups than the comminution test.

Masticatory function in subacute TMD patients before and after treatment.

Masticatory function can be impaired in temporomandibular disorders (TMDs) patients. We investigated whether treatment of subacute non-specific TMD patients may influence oral function and clinical outcome measures. Fifteen patients with subacute TMD participated in the study. We quantified masticatory performance, maximum voluntary bite force, muscle activity and chewing cycle duration before and after treatment. Masticatory performance and bite force of patients were compared with the results obtained for an age- and gender-matched group of subjects without TMD complaints. Furthermore, we determined possible changes in anamnestic and clinical scores from questionnaires (mandibular function impairment questionnaire; MFIQ), pain scores and clinical outcome measures. Maximum bite force significantly increased, although the values after treatment were still significantly lower than those of the subjects without TMD complaints. The corresponding electromyography values did not show significant change after treatment. The masticatory performance of the patients remained unaltered; patients chewed significantly less efficient than controls. The average duration of chewing cycles significantly decreased after treatment. We observed a significant improvement in MFIQ scores. During the clenching and chewing tasks, the visual analogue scale scores were significantly higher than before these tasks. We may conclude that subacute temporomandibular joint disorders negatively influence chewing behaviour. Bite force, chewing cycle duration and also perceived mandibular function significantly improved after treatment, although the masticatory performance remained unaltered.

Articular soft tissue injuries associated with mandibular condyle fractures and the effects on oral function.

The majority of studies debating the optimization of treatment for condylar mandibular fractures focus on the bony aspect first. However, fractures of the mandibular condyle may go together with soft tissue injury of the temporomandibular joint. An electronic literature search for this topic was undertaken. Assessment of quality was carried out using the Quality Assessment Tool for Observational Cohort and Cross-Sectional Studies. Sixteen articles were included in this review. The reviewed literature showed that intracapsular fractures and dislocated condylar fractures result in more severe injuries. Serious injury to the disc and capsule of the temporomandibular joint is a contributing factor towards development of complications after closed treatment. The results of this review give an overview of the published studies focusing on articular soft tissue injuries caused by condylar mandibular fractures. Additionally, an overview of the magnetic resonance imaging (MRI) settings used to detect these injuries is provided. Until now, the relation between soft tissue injuries and type of condylar trauma and their influence on clinical outcome has been insufficiently investigated. Before considering reduction of soft tissues next to reduction of the fracture, more research is needed into the impact of soft tissue injuries on oral functioning, in which a uniform classification is used.

Clinical outcomes in the treatment of unilateral condylar fractures: a cross-sectional study.

The treatment of mandibular condyle fractures has been the subject of considerable discussion, especially whether open or closed treatment should be used. There is a need for practical,evidence-based guidelines, and both objective and subjective parameters should be measured. To date, fewstudies have considered clinically relevant subjective parameters. This study was performed to evaluate the outcomes of the treatment of condylar fractures using the Mandibular Function Impairment Questionnaire (MFIQ) and the Diagnostic Criteria for Temporomandibular Disorders (DC/TMD) and to compare the outcomes of open and the closed treatment. Patients with condylar fractures and at least 1year of follow-up were examined. These patients completed the MFIQ and other questionnaires, and were examined according to the DC/TMD. Seventy-four of 171 eligible patients participated in this study. The mean MFIQ score was 10.70 (standard error 2.9) in the open group and 4.96 (standard error 1.3) in the closed group (P=0.023), an outcome in favour of the closed treatment group. Examination according to the DC/TMD did not reveal a significant prevalence of TMD complaints. Closed treatment appears to be a safe and appropriate modality for most unilateral condylar fractures. Although the open group in general showed similar outcomes, this treatment should be reserved for limited indications.

The effectiveness of graded activity in patients with non-specific low-back pain: a systematic review.

BACKGROUND: Non-specific low-back pain (LBP) is considered a major health and economic problem in Western society. Nowadays a common used intervention on non-specific LBP is graded activity (GA). Graded Activity developed by Lindström et al., consisted of four parts: (i) measurements of functional capacity; (ii) a work-place visit; (iii) back school education and (iv) an individual, sub-maximal, gradually increased exercise program with an operant-conditioning behavioural approach as described by Fordyce et al. OBJECTIVE: To evaluate the effectiveness of GA in adults with non-specific LBP on pain, disabilities and return to work. DATA SOURCES: An extensive literature search of PubMed, Embase, CINAHL and The Cochrane Library was conducted in July 2011. REVIEW METHODS: Randomized controlled trials (RCTs) evaluating the effect of GA in patients with non-specific LBP were eligible. Methodological quality of the studies was assessed according to the PEDro scale. A best-evidence synthesis was conducted according to van Peppen et al. to interpret the outcomes of the included studies. RESULTS: Ten articles were included in this systematic review; these articles described five RCTs (680 patients). The best-evidence synthesis revealed that there was no or insufficient evidence for a positive effect of GA on pain, disabilities and return to work in patients with non-specific LBP. CONCLUSION: Currently there is no or insufficient evidence that GA results in better outcomes of patients with non-specific LBP.

Oral function after maxillectomy and reconstruction with an obturator.

Maxillectomy defects can be reconstructed by a prosthetic obturator or (free) flap transfer, but there is no consensus about the optimal method. This study evaluated 32 maxillectomy patients with prosthetic obturation regarding function (mastication, subjective oral and swallowing complaints and maximal mouth opening). Outcomes were related to the extent of the resection (Brown maxillectomy classification), dentition and history of adjuvant radiotherapy. Maxillectomy defects ranged from 2-1 to 4B on the Brown classification, and most had a defect graded as 2-A or 2-B. Mean mixing ability test after 10 chewing strokes was 24.2 and after 20 chewing strokes 19.7, which compares to edentulous healthy individuals. None of the outcomes was influenced by Brown classification. Radiotherapy negatively influenced mean maximal mouth opening (29.1mm versus 40.9 mm, p=0.017) and subjective outcomes. Edentate obturated patients had worse outcomes than dentate patients, measured by mixing ability test and questionnaire. In conclusion, mastication after obturator reconstruction of a maxillectomy defect is comparable to mastication with full dentures. Size of the maxillectomy defect did not significantly influence functional outcome, but adjuvant radiotherapy resulted in worse mouth opening and self-reported oral and swallowing problems. Residual dentition had a positive influence on mastication and subjective outcomes.

Tongue function in patients treated for malignancies in tongue and/or floor of mouth; a one year prospective study.

Progress in (reconstructive) surgery and radiotherapy tends to improve survival and reduce oral functional deficits. Despite the growing sophistication of cancer treatment, patients still report deterioration in tongue function. Sensory function, mobility, and force of the tongue were determined in 45 patients with a carcinoma of tongue and/or floor of mouth. Measurements were performed before surgery, shortly after surgery, shortly after radiotherapy, 6, and 12 months after surgery. Surgery had a negative impact on tongue sensory function and mobility. Post-surgery radiotherapy did not further deteriorate sensory function, mobility, or force of the tongue. Patients in the surgery-radiotherapy group (SRG) had significantly worse tongue sensory function and mobility than patients in the surgery group (SG), probably caused by more advanced tumour stage and more extensive reconstructions and related scar tissue. The tongue force in patients in both groups significantly increased in the first 6 months after surgery, but this increase disappeared in the next 6 months. The authors conclude that surgery had a significant negative influence on tongue function, especially in the group of patients treated with radiotherapy. No further deterioration of tongue function was observed after post-surgical radiotherapy within the first year after surgery.