RESUMEN
PURPOSE: The purpose of this paper is to construct a 3D tongue model and to generate an animation of tongue movement for speech therapy in patients with lateral articulation (LA). METHODS: The 3D tongue model is generated based on ultrasound (US) images, which are widely used in many clinics. A tongue model is constructed by extracting the tongue surfaces from US images with the help of image processing techniques and a deep learning method. A reference tongue model is generated first using US images of a normal speaker, and a model of an LA patient is then constructed by modifying the reference tongue model. An animation of the tongue movement is generated by deforming the model according to a time sequence. RESULTS: The accuracy of the tongue surfaces estimated by a deep learning method were 22/45 = 49% and 29/45 = 64% for US images of a normal speaker and an LA patient, respectively. In addition, the maximum vertical errors between the ground truth and the estimated spline curves were 1.01 and 1.03 mm for US images of a normal speaker and an LA patient, respectively. CONCLUSION: We have constructed a tongue model and generated a tongue movement animation of an LA patient using US images. The maximum vertical error between the ground truth and the estimated spline curves was only 1.03 mm, and we have confirmed that the generated tongue model is very useful for speech therapy in LA patients.
Asunto(s)
Aprendizaje Profundo , Humanos , Procesamiento de Imagen Asistido por Computador , Lengua/diagnóstico por imagen , UltrasonografíaRESUMEN
PURPOSE: The MERCURY study aimed to evaluate the effects on visual acuity and psychological symptoms, and safety, of ranibizumab and subsequent treatment in patients with diabetic macular oedema (DME) and impaired visual acuity (VA). We report data from the prespecified 12-month interim analysis. METHODS: This was a 24-month, phase 4, open-label, single-arm, prospective, observational study conducted at 20 specialised retinal centres in Japan. Participants were 209 patients with DME and impaired VA, not previously treated with either intravitreal or systemic anti-vascular endothelial growth factor (anti-VEGF) agents, who initiated ranibizumab 0.5 mg per investigator discretion. Following ranibizumab administration, patients were treated per routine clinical practice. Other treatments were allowed. The main outcome measure was the mean change in best-corrected VA (BCVA) in logarithmic minimum angle of resolution (logMAR) from baseline to month 12. An exploratory objective was to assess patients' psychological status using the Hospital Anxiety and Depression Scale (HADS). RESULTS: The mean ± standard deviation BCVA at baseline was 0.43 ± 0.39 logMAR. The mean number of injections of ranibizumab and anti-VEGF agents from baseline to month 11 was 3.2 ± 2.0 and 3.6 ± 2.4, respectively. The BCVA change from baseline to 12 months was - 0.08 ± 0.34 logMAR (p = 0.011), showing a significant improvement; the HADS-anxiety score also decreased significantly (p = 0.001) and the depression score decreased numerically (p = 0.080). CONCLUSION: MERCURY study data confirm the effectiveness of real-world treatment initiated with ranibizumab in Japanese patients with DME. In addition, treatment was able to positively influence anxiety via VA improvement.