Artificial Intelligence-Driven Video Analysis for Novel Outcome Measures After Smile Reanimation Surgery

Kollar, Branislav; Schneider, Laura; Horner, Verena K.; Zeller, Johannes; Fricke, Mark; Brugger, Zacharias; Gentz, Michael; Kiefer, Jurij; Eisenhardt, Steffen U.

doi:10.1089/fpsam.2020.0556

Cited by 14 publications

(9 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such software has been shown by our and other groups to have a high correlation with layperson assessments. 31,33 In the current study, we show a median happiness intensity score of 0.28 and 0.22 while smiling without and with teeth showing, respectively. In a previous study, we found a median happiness intensity score of 0.55 and 0.84 for GFMT powered by GFNG and MNT, respectively.…”

Section: Discussionsupporting

confidence: 57%

“…In a previous study, we found a median happiness intensity score of 0.55 and 0.84 for GFMT powered by GFNG and MNT, respectively. 31 This comparison suggests that despite an early reinnervation, the elevation of the upper lip and dental show (“full-blown” smile) might be more difficult to achieve in all patients, as compared with patients receiving GFMT. Especially patients with longer denervation times and a strong desire for a bright smile should be preoperatively made aware of this limitation.…”

Section: Discussionmentioning

confidence: 98%

“…The results of such AI software show a high correlation with layperson assessment in evaluating the facial reanimation outcome, which was previously validated by our group and other groups. 31,33…”

Section: Methodsmentioning

confidence: 99%

“…29,30 In addition, the patient photographs and videos were subjected to quantitative analysis by the novel artificial intelligence (AI)-driven software FaceReader (Noldus Information Technology, Wageningen, the Netherlands) that measures automatically and objectively the intensity of emotional expression and facial muscles movement. 31,32 The intensity score (IS) values assigned by the software range between 0 (absent) and 1 (fully present). The results of such AI software show a high correlation with layperson assessment in evaluating the facial reanimation outcome, which was previously validated by our group and other groups.…”

Section: Patients and Functional Outcome Assessmentmentioning

confidence: 99%

See 3 more Smart Citations

Functional Outcome of Dual Reinnervation with Cross-Facial Nerve Graft and Masseteric Nerve Transfer for Facial Paralysis

Kollar

Weiss

Kiefer

et al. 2023

Plastic &Amp; Reconstructive Surgery

Self Cite

View full text Add to dashboard Cite

Background: The combination of cross-facial nerve graft (CFNG) and masseteric nerve transfer (MNT) for reinnervation of facial paralysis may provide advantages of both neural sources. However, quantitative functional outcome reports with a larger number of patients are lacking in the literature. Here we describe our 8-year experience with this surgical technique. Methods: Twenty patients that presented with a complete facial paralysis (duration <12 months) received dual reinnervation with CFNG and MNT. The functional outcome of the procedure was evaluated with the physician-graded outcome metric eFACE. The objective artificial intelligence-driven software Emotrics and FaceReader were used for oral commissure measurements and emotional expression assessment, respectively. Results: The mean follow-up was 31.75±23.32 months. In the eFACE score, the nasolabial fold depth and oral commissure at rest improved significantly (p<0.05) towards a more balanced state after the surgery. Postoperatively, there was a significant decrease in oral commissure asymmetry while smiling (19.22±6.1mm to 12.19±7.52mm). For the emotionality expression, the median intensity score of happiness, as measured by the FaceReader software, increased significantly while smiling (0.28, IQR 0.13-0.64). In 5 (25%) patients, a secondary static midface suspension with fascia lata strip had to be performed due to an unsatisfactory resting symmetry. Older patients and patients with greater preoperative resting asymmetry were more likely to receive static midface suspension. Conclusions: Our results suggest that the combination of MNT and CFNG for reinnervation of facial paralysis provides good voluntary motion and may lessen the use of static midface suspension in the majority of patients.

show abstract

Section: Discussionsupporting

confidence: 57%

Section: Discussionmentioning

confidence: 98%

Section: Methodsmentioning

confidence: 99%

Section: Patients and Functional Outcome Assessmentmentioning

confidence: 99%

See 2 more Smart Citations

Functional Outcome of Dual Reinnervation with Cross-Facial Nerve Graft and Masseteric Nerve Transfer for Facial Paralysis

Kollar

Weiss

Kiefer

et al. 2023

Plastic &Amp; Reconstructive Surgery

Self Cite

View full text Add to dashboard Cite

show abstract

“…Introduction of artificial intelligence (AI)driven facial recognition software into plastic surgery has converted subjective evaluations into objective measurements of outcomes in facial reanimation and cosmetic surgery. [12][13][14][15][16] FaceReader, a commercially available facial recognition software capable of detecting expressions similar to an objective observer, has analyzed consumer facial expressions for market research 17,18 and in social sciences, demonstrating an ability to detect human faces reliably. [19][20][21][22] The same software measured motor function recovery and emotional expression restoration after FT. 23,24 However, these studies are limited by small patient cohorts and lack of external validation.…”

Section: Plastic and Reconstructive Surgery • August 2023 316ementioning

confidence: 99%

“Facial Expression After Face Transplant: The First International Face Transplant Cohort Comparison”

Dorante

Wang

Kollar

et al. 2023

Plastic &Amp; Reconstructive Surgery

Self Cite

View full text Add to dashboard Cite

Background: Assessment of motor function restoration following face transplant (FT) is difficult, as standardized, bilateral tests are lacking. This study aims to bolster support for software-based analysis through international collaboration. Methods: FaceReader (Noldus, Wageningen, The Netherlands), a facial expression analysis software, was used to analyze posttransplant videos of eight FT patients from Boston, Massachusetts (range, 1 to 9 years after transplant), two FT patients from Helsinki, Finland (range, 3 to 4 years after transplant), and three FT patients from Antalya, Turkey (range, 6.5 to 8.5 years after transplant). Age-matched healthy controls from respective countries had no history of prior facial procedures. Videos contained patients and controls performing facial expressions evaluated by software analysis using the Facial Action Coding System. Facial movements were assigned intensity score values between 0 (absent) and 1 (fully present). Maximum values were compared with respective healthy controls to calculate percentage restoration. Results: Of 13 FT patients, eight patients were full FT, five patients were partial FT, and two patients were female patients. Compared with healthy controls, the median restoration of motor function was 36.9% (interquartile range, 28.8% to 52.9%) for all patients with FT (P = 0.151). The median restoration of smile was 37.2% (interquartile range, 31.5% to 52.7%) for all patients with FT (P = 0.065). When facial nerve coaptation was performed at the distal branch level, average motor function restoration was 42.7% ± 3.61% compared with 27.9% ± 6.71% at the proximal trunk coaptation level (P = 0.032). Use of interpositional nerve grafts had no influence on motor outcomes. Conclusions: Software-based analysis is suitable to assess motor function after FT. International collaboration strengthens outcome data for FT. CLINICAL QUESTION/LEVEL OF EVIDENCE: Therapeutic, IV.

show abstract

Changes in Perceived Emotions in Facial Paralysis Patients After Depressor Anguli Oris Excision

O'Rourke,

Stack,

Miller

et al. 2024

The Laryngoscope

View full text Add to dashboard Cite

ObjectivesDepressor anguli oris (DAO) excision can improve clinician‐graded, objective, and patient‐reported smile outcomes in patients with nonflaccid facial paralysis (NFFP). However, no prior research has studied changes in perceived emotions after surgery. This study quantifies changes in perceived emotions with smiling after DAO excision in the largest case series presented to date.MethodsProspectively collected data from patients with NFFP who underwent DAO excision at a tertiary care facial nerve center were reviewed. Patient‐reported, clinician‐graded, and objective smile metrics were compared before and after surgery. Videos of faces at rest and while smiling were analyzed by artificial intelligence‐derived facial expression analysis software to quantify perceived emotions.ResultsSixty‐eight patients underwent isolated DAO excision between August 2021 and August 2023. Patients conveyed significantly more perceived happiness with smile and at rest after surgery (p < 0.001 and p = 0.012, respectively). DAO excision improved oral commissure excursion (p < 0.001), dental show (p < 0.001), and smile angle (p < 0.001) symmetry. Patients reported significant improvements in smiling and social function after surgery.ConclusionsThis study demonstrates DAO excision increases perceived happiness conveyed by patients with NFFP while smiling and at rest. It confirms improved objective, clinician‐graded, and patient‐reported smile outcomes after surgery.Level of EvidenceLevel 4 Laryngoscope, 2024

show abstract

Artificial Intelligence-Driven Video Analysis for Novel Outcome Measures After Smile Reanimation Surgery

Cited by 14 publications

References 30 publications

Functional Outcome of Dual Reinnervation with Cross-Facial Nerve Graft and Masseteric Nerve Transfer for Facial Paralysis

Functional Outcome of Dual Reinnervation with Cross-Facial Nerve Graft and Masseteric Nerve Transfer for Facial Paralysis

“Facial Expression After Face Transplant: The First International Face Transplant Cohort Comparison”

Changes in Perceived Emotions in Facial Paralysis Patients After Depressor Anguli Oris Excision

Contact Info

Product

Resources

About